Delete release-drafter.yml

fix: #8450

1. Add a new function check_rwlock to check and autocorrect rwlock info.
2. Add related tests for it.

.dvcignore

@@ -0,0 +1,4 @@
+/tests
+/dvc
+/.github
+/bin

.git_archival.txt

@@ -0,0 +1,4 @@
+node: $Format:%H$
+node-date: $Format:%cI$
+describe-name: $Format:%(describe:tags=true)$
+ref-names: $Format:%D$

.gitattributes

@@ -0,0 +1 @@
+.git_archival.txt  export-subst

.github/CODEOWNERS

@@ -1 +0,0 @@
-*       @iterative/dvc

.github/FUNDING.yml

@@ -1,3 +0,0 @@
-# These are supported funding model platforms
-
-patreon: DVCorg

.github/mergify.yml

@@ -1,9 +0,0 @@
-pull_request_rules:
-  - name: backport patches to 1.11
-    conditions:
-      - base=master
-      - label=backport-1.11
-    actions:
-      backport:
-        branches:
-          - "1.11"

.github/release-drafter.yml

@@ -1,49 +0,0 @@
-# Config for https://github.com/apps/release-drafter
-name-template: "$RESOLVED_VERSION 🦉 "
-tag-template: "$RESOLVED_VERSION"
-categories:
-  - title: "🚀 New Features and Enhancements "
-    labels:
-      - "feature"
-      - "enhancement"
-      - "ui"
-  - title: "💣 Breaking Changes "
-    labels:
-      - "breaking-change"
-  - title: "🏇 Optimizations "
-    labels:
-      - "optimize"
-      - "performance"
-  - title: "🐛 Bug Fixes "
-    labels:
-      - "bugfix"
-      - "bug"
-  - title: "🔨 Maintenance "
-    labels:
-      - "maintenance"
-      - "refactoring"
-      - "chore"
-      - "build"
-      - "ci"
-change-template: "- $TITLE (#$NUMBER) @$AUTHOR"
-version-resolver:
-  major:
-    labels:
-      - "major"
-  minor:
-    labels:
-      - "minor"
-  patch:
-    labels:
-      - "patch"
-  default: patch
-exclude-labels:
-  - "skip-changelog"
-template: |
-  > Refer to https://dvc.org/doc/install for installation instructions.
-
-  ## Changes
-
-  $CHANGES
-
-  Thanks again to $CONTRIBUTORS for the contributions! 🎉

.github/workflows/benchmarks.yaml

@@ -1,23 +1,18 @@
 name: benchmarks
 on: [pull_request, workflow_dispatch]
 
+concurrency:
+  group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
+  cancel-in-progress: true
+
 jobs:
   bench:
     name: run benchmarks
-    runs-on: ${{ matrix.os }}
-    strategy:
-      fail-fast: false
-      matrix:
-        os: [ubuntu-18.04]
+    runs-on: ubuntu-latest
     steps:
-      - name: Cancel Previous Runs
-        uses: styfle/[email protected]
+      - uses: actions/setup-python@v4
         with:
-          access_token: ${{ github.token }}
-      - uses: actions/setup-python@v2
-        with:
-            python-version: 3.7
-      - uses: iterative/dvc-bench@master
+            python-version: "3.10"
+      - uses: iterative/dvc-bench@main
         with:
             pytest_options: "-k 'test_init or test_help'"
-

.github/workflows/packages.yaml

@@ -2,156 +2,96 @@ name: Build packages
 on:
   push:
     branches:
-    - master
+    - main
   release:
     types: [released, prereleased]
   workflow_dispatch:
+
 jobs:
-  deb:
-    runs-on: ubuntu-18.04
+  binary:
+    strategy:
+      matrix:
+        include:
+         - {pkg: "deb",  os: "ubuntu-18.04", asset: "dvc_${{ github.event.release.tag_name }}_amd64.deb"}
+         - {pkg: "rpm", os: "ubuntu-18.04", asset: "dvc-${{ github.event.release.tag_name }}-1.x86_64.rpm"}
+         - {pkg: "osxpkg", os: "macos-10.15", asset: "dvc-${{ github.event.release.tag_name }}.pkg"}
+         - {pkg: "exe",  os: "windows-2019", asset: "dvc-${{ github.event.release.tag_name }}.exe"}
+
+    name: ${{ matrix.pkg }}
+    runs-on: ${{ matrix.os }}
     steps:
-    - uses: actions/checkout@v2.4.0
+    - uses: actions/checkout@v3
       with:
           fetch-depth: 0
+
     - name: Set up Python 3.9
-      uses: actions/setup-python@v2.2.2
+      uses: actions/setup-python@v4
       with:
         python-version: 3.9
-    - name: Set up Ruby 2.4
-      uses: actions/[email protected]
+        cache: pip
+        cache-dependency-path: |
+          setup.cfg
+          scripts/build-requirements.txt
+
+    - name: Set up Ruby 2.6
+      uses: ruby/setup-ruby@v1
+      if: matrix.pkg != 'exe'
       with:
-        ruby-version: 2.4
-    - name: Install deps
-      run: |
-        pip install .[all]
-        pip install -r scripts/build-requirements.txt
-        gem install --no-document fpm
-    - name: Build deb
-      run: python scripts/build.py deb
-    - name: Publish deb
-      if: github.event_name == 'release'
-      uses: actions/[email protected]
-      env:
-        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-      with:
-        upload_url: ${{ github.event.release.upload_url }}
-        asset_path: scripts/fpm/dvc_${{ github.event.release.tag_name }}_amd64.deb
-        asset_name: dvc_${{ github.event.release.tag_name }}_amd64.deb
-        asset_content_type: binary/octet-stream
-  rpm:
-    runs-on: ubuntu-18.04
-    steps:
-    - uses: actions/[email protected]
-      with:
-        fetch-depth: 0
-    - name: Set up Python 3.9
-      uses: actions/[email protected]
-      with:
-        python-version: 3.9
-    - name: Set up Ruby 2.4
-      uses: actions/[email protected]
-      with:
-        ruby-version: 2.4
-    - name: Install deps
-      run: |
-        pip install .[all]
-        pip install -r scripts/build-requirements.txt
-        gem install --no-document fpm
-    - name: Build rpm
-      run: python scripts/build.py rpm
-    - name: Publish rpm
-      if: github.event_name == 'release'
-      uses: actions/[email protected]
-      env:
-        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-      with:
-        upload_url: ${{ github.event.release.upload_url }}
-        asset_path: scripts/fpm/dvc-${{ github.event.release.tag_name }}-1.x86_64.rpm
-        asset_name: dvc-${{ github.event.release.tag_name }}-1.x86_64.rpm
-        asset_content_type: binary/octet-stream
-  osxpkg:
-    runs-on: macos-10.15
-    steps:
-    - uses: actions/[email protected]
-      with:
-        fetch-depth: 0
-    - name: Set up Python 3.9
-      uses: actions/[email protected]
-      with:
-        python-version: 3.9
-    - name: Set up Ruby 2.4
-      uses: actions/[email protected]
-      with:
-        ruby-version: 2.4
-    - name: Install deps
-      run: |
-        # available lxml (webdav dependency) wheels are built with an old
-        # SDK, which breaks osxpkg notarization. Building from scratch
-        # instead.
-        pip install .[all] --no-binary lxml
-        pip install -r scripts/build-requirements.txt
-        gem install --no-document fpm
-    - name: Build
-      run: python scripts/build.py osxpkg
-    - name: Publish
-      if: github.event_name == 'release'
-      uses: actions/[email protected]
-      env:
-        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-      with:
-        upload_url: ${{ github.event.release.upload_url }}
-        asset_path: scripts/fpm/dvc-${{ github.event.release.tag_name }}.pkg
-        asset_name: dvc-${{ github.event.release.tag_name }}.pkg
-        asset_content_type: binary/octet-stream
-  exe:
-    runs-on: windows-2019
-    steps:
-    - uses: actions/[email protected]
-      with:
-        fetch-depth: 0
-    - name: Set up Python 3.9
-      uses: actions/[email protected]
-      with:
-        python-version: 3.9
+        ruby-version: '2.6'
+
+    - name: Install fpm
+      if: matrix.pkg != 'exe'
+      run: gem install --no-document fpm
+
     - name: Install deps
       run: |
+        pip install -U wheel pip setuptools
         pip install .[all]
         pip install -r scripts/build-requirements.txt
+
     - name: Pull images
-      run: |
-        dvc pull
-    - name: Build
-      run: python scripts\build.py exe
-      shell: cmd
-    - name: Publish
+      run: dvc pull
+
+    - name: Build ${{ matrix.pkg }}
+      run: python scripts/build.py ${{ matrix.pkg }}
+
+    - name: Publish ${{ matrix.pkg }}
       if: github.event_name == 'release'
+      uses: actions/[email protected]
       env:
         GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-      uses: actions/[email protected]
       with:
         upload_url: ${{ github.event.release.upload_url }}
-        asset_path: scripts/innosetup/dvc-${{ github.event.release.tag_name }}.exe
-        asset_name: dvc-${{ github.event.release.tag_name }}.exe
+        asset_path: scripts/${{ matrix.pkg == 'exe' && 'innosetup' || 'fpm' }}/${{ matrix.asset }}
+        asset_name: ${{ matrix.asset }}
         asset_content_type: binary/octet-stream
+
   pip:
-    runs-on: ubuntu-18.04
+    runs-on: ubuntu-20.04
     steps:
-    - uses: actions/checkout@v2.4.0
+    - uses: actions/checkout@v3
       with:
         fetch-depth: 0
-    - name: Set up Python 3.7
-      uses: actions/setup-python@v2.2.2
+
+    - name: Set up Python 3.8
+      uses: actions/setup-python@v4
       with:
-        python-version: 3.7
+        python-version: 3.8
+        cache: pip
+        cache-dependency-path: setup.cfg
+
     - name: Install
-      run: pip install ".[all,tests]"
+      run: |
+        pip install -U wheel pip build setuptools
+        pip install ".[all,tests]"
+
     - name: Build packages
       run: |
         pip install -U pip
         ./scripts/build_package.sh
+
     - name: Publish packages to PyPI
       if: github.event_name == 'release'
-      uses: pypa/gh-action-pypi-publish@master
+      uses: pypa/gh-action-pypi-publish@release/v1
       with:
-        user: __token__
         password: ${{ secrets.PYPI_TOKEN }}

.github/workflows/tests.yaml

@@ -1,39 +1,42 @@
 name: Tests
 
 on:
-  pull_request: {}
-  push: {}
+  push:
+    branches: [main]
+  pull_request:
   schedule:
     - cron: '5 1 * * *'  # every day at 01:05
+  workflow_dispatch:
 
 env:
   DVC_TEST: "true"
   HOMEBREW_NO_AUTO_UPDATE: 1
   SHELL: /bin/bash
 
+concurrency:
+  group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
+  cancel-in-progress: true
+
 jobs:
   lint:
     timeout-minutes: 10
     runs-on: ubuntu-latest
     steps:
-    - name: Cancel Previous Runs
-      uses: styfle/[email protected]
-      with:
-        access_token: ${{ github.token }}
-    - uses: actions/[email protected]
+    - uses: actions/checkout@v3
       with:
         fetch-depth: 0
     - name: Set up Python 3.8
-      uses: actions/setup-python@v2.2.2
+      uses: actions/setup-python@v4
       with:
         python-version: 3.8
     - name: Install requirements
       run: |
         pip install --upgrade pip setuptools wheel
-        pip install ".[dev]" pre-commit
+        pip install collective.checkdocs==0.2
+        pip install ".[dev]"
     - name: Check README
       run: python setup.py checkdocs
-    - uses: pre-commit/action@v2.0.3
+    - uses: pre-commit/action@v3.0.0
   tests:
     timeout-minutes: 45
     runs-on: ${{ matrix.os }}
@@ -41,49 +44,38 @@ jobs:
       fail-fast: false
       matrix:
         os: [ubuntu-20.04, windows-latest, macos-latest]
-        pyv: ["3.7", "3.8", "3.9", "3.10"]
+        pyv: ["3.8", "3.9", "3.10"]
+        pytest-filter: 
+        - "import or plot or live or experiment"
+        - "not (import or plot or live or experiment)"
+        include:
+        - {os: ubuntu-latest, pyv: "3.11-dev"}
+
     steps:
-    - uses: actions/checkout@v2.4.0
+    - uses: actions/checkout@v3
       with:
         fetch-depth: 0
     - name: Set up Python
-      uses: actions/setup-python@v2.2.2
+      uses: actions/setup-python@v4
       with:
         python-version: ${{ matrix.pyv }}
-    - name: get pip cache dir
-      id: pip-cache-dir
-      run: |
-        echo "::set-output name=dir::$(pip cache dir)"
-    - name: set pip cache
-      id: pip-cache
-      uses: actions/[email protected]
-      with:
-        path: ${{ steps.pip-cache-dir.outputs.dir }}
-        key: ${{ runner.os }}-pip-${{ hashFiles('setup.cfg') }}
-        restore-keys: |
-          ${{ runner.os }}-pip-
+        cache: pip
+        cache-dependency-path: setup.cfg
     - name: install
       if: steps.cache.pip-cache-dir.cache-hit != 'true'
       run: |
         pip install --upgrade pip setuptools wheel
         pip install -e ".[dev]"
-    - name: setup git
-      run: |
-        git config --global user.email "[email protected]"
-        git config --global user.name "DVC Tester"
     - name: run tests
       timeout-minutes: 40
-      run: >-
-        python -m tests -n=auto
-        --cov-report=xml --cov-report=term
-        ${{ env.extra_test_args }}
+      run: pytest -nauto -ra --durations 100 --cov=dvc --cov-report=xml --cov-report=term -k "${{ matrix.pytest-filter }}"
     - name: upload coverage report
-      uses: codecov/codecov-action@v2.1.0
+      uses: codecov/codecov-action@v3
       with:
         file: ./coverage.xml
         fail_ci_if_error: false
   notify:
-    if: github.ref == 'refs/heads/master' && failure()
+    if: github.ref == 'refs/heads/main' && failure()
     needs:
       - lint
       - tests
@@ -94,6 +86,6 @@ jobs:
       env:
         SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
         SLACK_COLOR: ${{ job.status }}
-        SLACK_MESSAGE: 'CI Failed on master :boom:'
+        SLACK_MESSAGE: 'CI Failed on main :boom:'
         SLACK_TITLE: CI Status
         SLACK_USERNAME: DVC-CI

.gitignore

@@ -1,10 +1,13 @@
+__pycache__/
 neatlynx.conf
-neatlynx/__pycache__
 .idea
 /cache
 *.pyc
-.env/
-.env2.7/
+
+.env*/
+.venv
+env/
+venv/
 .python-version
 
 .dvc.conf.lock
@@ -26,6 +29,7 @@ innosetup/config.ini
 
 .coverage
 .coverage.*
+coverage.xml
 
 *.sw?
 
@@ -40,3 +44,9 @@ scripts/ci/gcp-creds.json
 
 *~
 /dvc/_dvc_version.py
+
+.mypy_cache/
+.pytest_cache/
+.nox/
+.tox/
+htmlcov/

.pre-commit-config.yaml

@@ -6,9 +6,9 @@ repos:
       - id: black
         language_version: python3
     repo: https://github.com/ambv/black
-    rev: 21.12b0
+    rev: 22.10.0
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.0.1
+    rev: v4.3.0
     hooks:
       - id: check-toml
       - id: check-yaml
@@ -16,9 +16,9 @@ repos:
       - id: codespell
         args: 
           - --ignore-words-list
-          - ba,datas,fo,uptodate,cachable
+          - ba,datas,fo,uptodate,cachable,falsy
     repo: https://github.com/codespell-project/codespell
-    rev: v2.1.0
+    rev: v2.2.2
   - hooks:
       - id: isort
         language_version: python3

README.rst

@@ -3,97 +3,114 @@
 `Website <https://dvc.org>`_
 • `Docs <https://dvc.org/doc>`_
 • `Blog <http://blog.dataversioncontrol.com>`_
-• `Twitter <https://twitter.com/DVCorg>`_
-• `Chat (Community & Support) <https://dvc.org/chat>`_
 • `Tutorial <https://dvc.org/doc/get-started>`_
-• `Mailing List <https://sweedom.us10.list-manage.com/subscribe/post?u=a08bf93caae4063c4e6a351f6&id=24c0ecc49a>`_
+• `Related Technologies <https://dvc.org/doc/user-guide/related-technologies>`_
+• `How DVC works`_
+• `VS Code Extension`_
+• `Installation`_
+• `Contributing`_
+• `Community and Support`_
 
-|CI| |Maintainability| |Coverage| |Donate| |DOI|
+|CI| |Python Version| |Coverage| |VS Code| |DOI|
 
 |PyPI| |Packages| |Brew| |Conda| |Choco| |Snap|
 
 |
 
-**Data Version Control** or **DVC** is an **open-source** tool for data science and machine
-learning projects. Key features:
+**Data Version Control** or **DVC** is a command line tool and `VS Code Extension`_ to help you develop reproducible machine learning projects:
 
-#. Simple **command line** Git-like experience. Does not require installing and maintaining
-   any databases. Does not depend on any proprietary online services.
+#. **Version** your data and models.
+   Store them in your cloud storage but keep their version info in your Git repo.
 
-#. Management and versioning of **datasets** and **machine learning
-   models**. Data can be saved in S3, Google cloud, Azure, Alibaba 
-   cloud, SSH server, HDFS, or even local HDD RAID.
+#. **Iterate** fast with lightweight pipelines.
+   When you make changes, only run the steps impacted by those changes.
 
-#. Makes projects **reproducible** and **shareable**; helping to answer questions about how
-   a model was built.
+#. **Track** experiments in your local Git repo (no servers needed).
 
-#. Helps manage experiments with Git tags/branches and **metrics** tracking.
+#. **Compare** any data, code, parameters, model, or performance plots.
 
-**DVC** aims to replace spreadsheet and document sharing tools (such as Excel or Google Docs)
-frequently used as both knowledge repositories and team ledgers.
-DVC also replaces both ad-hoc scripts to track, move, and deploy different model versions
-and ad-hoc data file suffixes and prefixes.
-
-.. contents:: **Contents**
-  :backlinks: none
-
-How DVC works
-=============
-
-We encourage you to read our `Get Started <https://dvc.org/doc/get-started>`_ guide to better understand what DVC
-is and how it can fit your scenarios.
-
-The easiest (but not perfect!) *analogy* to describe it: DVC is Git (or Git-LFS to be precise) & Makefiles
-made right and tailored specifically for ML and Data Science scenarios.
-
-#. ``Git/Git-LFS`` part - DVC helps store and share data artifacts and models, connecting them with a Git repository.
-#. ``Makefile``\ s part - DVC describes how one data or model artifact was built from other data and code.
-
-DVC usually runs along with Git. Git is used as usual to store and version code (including DVC meta-files). DVC helps
-to store data and model files seamlessly out of Git, while preserving almost the same user experience as if they
-were stored in Git itself. To store and share the data cache, DVC supports multiple remotes - any cloud (S3, Azure,
-Google Cloud, etc) or any on-premise network storage (via SSH, for example).
-
-|Flowchart|
-
-The DVC pipelines (computational graph) feature connects code and data together. It is possible to explicitly
-specify all steps required to produce a model: input dependencies including data, commands to run,
-and output information to be saved. See the quick start section below or
-the `Get Started <https://dvc.org/doc/get-started>`_ tutorial to learn more.
+#. **Share** experiments and automatically reproduce anyone's experiment.
 
 Quick start
 ===========
 
-Please read `Get Started <https://dvc.org/doc/get-started>`_ guide for a full version. Common workflow commands include:
+    Please read our `Command Reference <https://dvc.org/doc/command-reference>`_ for a complete list.
 
-+-----------------------------------+----------------------------------------------------------------------------+
-| Step                              | Command                                                                    |
-+===================================+============================================================================+
-| Track data                        | | ``$ git add train.py``                                                   |
-|                                   | | ``$ dvc add images.zip``                                                 |
-+-----------------------------------+----------------------------------------------------------------------------+
-| Connect code and data by commands | | ``$ dvc run -n prepare -d images.zip -o images/ unzip -q images.zip``    |
-|                                   | | ``$ dvc run -n train -d images/ -d train.py -o model.p python train.py`` |
-+-----------------------------------+----------------------------------------------------------------------------+
-| Make changes and reproduce        | | ``$ vi train.py``                                                        |
-|                                   | | ``$ dvc repro model.p.dvc``                                              |
-+-----------------------------------+----------------------------------------------------------------------------+
-| Share code                        | | ``$ git add .``                                                          |
-|                                   | | ``$ git commit -m 'The baseline model'``                                 |
-|                                   | | ``$ git push``                                                           |
-+-----------------------------------+----------------------------------------------------------------------------+
-| Share data and ML models          | | ``$ dvc remote add myremote -d s3://mybucket/image_cnn``                 |
-|                                   | | ``$ dvc push``                                                           |
-+-----------------------------------+----------------------------------------------------------------------------+
+A common CLI workflow includes:
+
+
++-----------------------------------+----------------------------------------------------------------------------------------------------+
+| Task                              | Terminal                                                                                           |
++===================================+====================================================================================================+
+| Track data                        | | ``$ git add train.py params.yaml``                                                               |
+|                                   | | ``$ dvc add images/``                                                                            |
++-----------------------------------+----------------------------------------------------------------------------------------------------+
+| Connect code and data             | | ``$ dvc stage add -n featurize -d images/ -o features/ python featurize.py``                     |
+|                                   | | ``$ dvc stage add -n train -d features/ -d train.py -o model.p -M metrics.json python train.py`` |
++-----------------------------------+----------------------------------------------------------------------------------------------------+
+| Make changes and experiment       | | ``$ dvc exp run -n exp-baseline``                                                                |
+|                                   | | ``$ vi train.py``                                                                                |
+|                                   | | ``$ dvc exp run -n exp-code-change``                                                             |
++-----------------------------------+----------------------------------------------------------------------------------------------------+
+| Compare and select experiments    | | ``$ dvc exp show``                                                                               |
+|                                   | | ``$ dvc exp apply exp-baseline``                                                                 |
++-----------------------------------+----------------------------------------------------------------------------------------------------+
+| Share code                        | | ``$ git add .``                                                                                  |
+|                                   | | ``$ git commit -m 'The baseline model'``                                                         |
+|                                   | | ``$ git push``                                                                                   |
++-----------------------------------+----------------------------------------------------------------------------------------------------+
+| Share data and ML models          | | ``$ dvc remote add myremote -d s3://mybucket/image_cnn``                                         |
+|                                   | | ``$ dvc push``                                                                                   |
++-----------------------------------+----------------------------------------------------------------------------------------------------+
+
+How DVC works
+=============
+
+    We encourage you to read our `Get Started
+    <https://dvc.org/doc/get-started>`_ docs to better understand what DVC
+    does and how it can fit your scenarios.
+
+The closest *analogies* to describe the main DVC features are these:
+
+#. **Git for data**: Store and share data artifacts (like Git-LFS but without a server) and models, connecting them with a Git repository. Data management meets GitOps!
+#. **Makefiles** for ML: Describes how data or model artifacts are built from other data and code in a standard format. Now you can version your data pipelines with Git.
+#. Local **experiment tracking**: Turn your machine into an ML experiment management platform, and collaborate with others using existing Git hosting (Github, Gitlab, etc.).
+
+Git is employed as usual to store and version code (including DVC meta-files as placeholders for data).
+DVC `stores data and model files <https://dvc.org/doc/start/data-management>`_ seamlessly in a cache outside of Git, while preserving almost the same user experience as if they were in the repo.
+To share and back up the *data cache*, DVC supports multiple remote storage platforms - any cloud (S3, Azure, Google Cloud, etc.) or on-premise network storage (via SSH, for example).
+
+|Flowchart|
+
+`DVC pipelines <https://dvc.org/doc/start/data-management/data-pipelines>`_ (computational graphs) connect code and data together.
+They specify all steps required to produce a model: input dependencies including code, data, commands to run; and output information to be saved.
+
+Last but not least, `DVC Experiment Versioning <https://dvc.org/doc/start/experiments>`_ lets you prepare and run a large number of experiments.
+Their results can be filtered and compared based on hyperparameters and metrics, and visualized with multiple plots.
+
+.. _`VS Code Extension`:
+
+Visual Studio Code Extension
+============================
+
+|VS Code|
+
+To use DVC as a GUI right from your VS Code IDE, install the `DVC Extension <https://marketplace.visualstudio.com/items?itemName=Iterative.dvc>`_ from the Marketplace.
+It currently features experiment tracking and data management, and more features (data pipeline support, etc.) are coming soon!
+
+|VS Code Extension Overview|
+
+    Note: You'll have to install core DVC on your system separately (as detailed
+    below). The Extension will guide you if needed.
 
 Installation
 ============
 
-There are four options to install DVC: ``pip``, Homebrew, Conda (Anaconda) or an OS-specific package.
+There are several ways to install DVC: in VS Code; using ``snap``, ``choco``, ``brew``, ``conda``, ``pip``; or with an OS-specific package.
 Full instructions are `available here <https://dvc.org/doc/get-started/install>`_.
 
-Snap (Snapcraft/Linux)
-----------------------
+Snapcraft (Linux)
+-----------------
 
 |Snap|
 
@@ -102,11 +119,10 @@ Snap (Snapcraft/Linux)
    snap install dvc --classic
 
 This corresponds to the latest tagged release.
-Add ``--beta`` for the latest tagged release candidate,
-or ``--edge`` for the latest ``master`` version.
+Add ``--beta`` for the latest tagged release candidate, or ``--edge`` for the latest ``main`` version.
 
-Choco (Chocolatey/Windows)
---------------------------
+Chocolatey (Windows)
+--------------------
 
 |Choco|
 
@@ -114,8 +130,8 @@ Choco (Chocolatey/Windows)
 
    choco install dvc
 
-Brew (Homebrew/Mac OS)
-----------------------
+Brew (mac OS)
+-------------
 
 |Brew|
 
@@ -123,8 +139,8 @@ Brew (Homebrew/Mac OS)
 
    brew install dvc
 
-Conda (Anaconda)
-----------------
+Anaconda (Any platform)
+-----------------------
 
 |Conda|
 
@@ -133,11 +149,10 @@ Conda (Anaconda)
    conda install -c conda-forge mamba # installs much faster than conda
    mamba install -c conda-forge dvc
 
-Depending on the remote storage type you plan to use to keep and share your data, you might need to
-install optional dependencies: `dvc-s3`, `dvc-azure`, `dvc-gdrive`, `dvc-gs`, `dvc-oss`, `dvc-ssh`.
+Depending on the remote storage type you plan to use to keep and share your data, you might need to install optional dependencies: `dvc-s3`, `dvc-azure`, `dvc-gdrive`, `dvc-gs`, `dvc-oss`, `dvc-ssh`.
 
-pip (PyPI)
-----------
+PyPI (Python)
+-------------
 
 |PyPI|
 
@@ -145,10 +160,8 @@ pip (PyPI)
 
    pip install dvc
 
-Depending on the remote storage type you plan to use to keep and share your data, you might need to specify
-one of the optional dependencies: ``s3``, ``gs``, ``azure``, ``oss``, ``ssh``. Or ``all`` to include them all.
-The command should look like this: ``pip install dvc[s3]`` (in this case AWS S3 dependencies such as ``boto3``
-will be installed automatically).
+Depending on the remote storage type you plan to use to keep and share your data, you might need to specify one of the optional dependencies: ``s3``, ``gs``, ``azure``, ``oss``, ``ssh``. Or ``all`` to include them all.
+The command should look like this: ``pip install 'dvc[s3]'`` (in this case AWS S3 dependencies such as ``boto3`` will be installed automatically).
 
 To install the development version, run:
 
@@ -156,88 +169,58 @@ To install the development version, run:
 
    pip install git+git://github.com/iterative/dvc
 
-Package
--------
+Package (Platform-specific)
+---------------------------
 
 |Packages|
 
-Self-contained packages for Linux, Windows, and Mac are available. The latest version of the packages
-can be found on the GitHub `releases page <https://github.com/iterative/dvc/releases>`_.
+Self-contained packages for Linux, Windows, and Mac are available.
+The latest version of the packages can be found on the GitHub `releases page <https://github.com/iterative/dvc/releases>`_.
 
 Ubuntu / Debian (deb)
 ^^^^^^^^^^^^^^^^^^^^^
 .. code-block:: bash
 
    sudo wget https://dvc.org/deb/dvc.list -O /etc/apt/sources.list.d/dvc.list
-   sudo apt-get update
-   sudo apt-get install dvc
+   wget -qO - https://dvc.org/deb/iterative.asc | sudo apt-key add -
+   sudo apt update
+   sudo apt install dvc
 
 Fedora / CentOS (rpm)
 ^^^^^^^^^^^^^^^^^^^^^
 .. code-block:: bash
 
    sudo wget https://dvc.org/rpm/dvc.repo -O /etc/yum.repos.d/dvc.repo
+   sudo rpm --import https://dvc.org/rpm/iterative.asc
    sudo yum update
    sudo yum install dvc
 
-Comparison to related technologies
-==================================
-
-#. Data Engineering tools such as `AirFlow <https://airflow.apache.org/>`,
-   `Luigi <https://github.com/spotify/luigi>`, and others - in DVC data,
-   model and ML pipelines represent a single ML project focused on data
-   scientists' experience.  Data engineering tools orchestrate multiple data
-   projects and focus on efficient execution. A DVC project can be used from
-   existing data pipelines as a single execution step.
-
-#. `Git-annex <https://git-annex.branchable.com/>`_ - DVC uses the idea of storing the content of large files (which should
-   not be in a Git repository) in a local key-value store, and uses file hardlinks/symlinks instead of
-   copying/duplicating files.
-
-#. `Git-LFS <https://git-lfs.github.com/>`_ - DVC is compatible with many
-   remote storage services (S3, Google Cloud, Azure, SSH, etc). DVC also
-   uses reflinks or hardlinks to avoid copy operations on checkouts; thus
-   handling large data files much more efficiently.
-
-#. Makefile (and analogues including ad-hoc scripts) - DVC tracks
-   dependencies (in a directed acyclic graph).
-
-#. `Workflow Management Systems <https://en.wikipedia.org/wiki/Workflow_management_system>`_ - DVC is a workflow
-   management system designed specifically to manage machine learning experiments. DVC is built on top of Git.
-
-#. `DAGsHub <https://dagshub.com/>`_ - online service to host DVC
-   projects.  It provides a useful UI around DVC repositories and integrates
-   other tools.
-
-#. `DVC Studio <https://studio.iterative.ai/>`_ - official online
-   platform for DVC projects.  It can be used to manage data and models, run
-   and track experiments, and visualize and share results.  Also, it
-   integrates with `CML (CI/CD for ML) <https://cml.dev/>` for training
-   models in the cloud or Kubernetes.
-
-
 Contributing
 ============
 
-|Maintainability| |Donate|
+|Maintainability|
 
-Contributions are welcome! Please see our `Contributing Guide <https://dvc.org/doc/user-guide/contributing/core>`_ for more
-details. Thanks to all our contributors!
+Contributions are welcome!
+Please see our `Contributing Guide <https://dvc.org/doc/user-guide/contributing/core>`_ for more details.
+Thanks to all our contributors!
 
 |Contribs|
 
-Mailing List
-============
+Community and Support
+=====================
 
-Want to stay up to date? Want to help improve DVC by participating in our occasional polls? Subscribe to our `mailing list <https://sweedom.us10.list-manage.com/subscribe/post?u=a08bf93caae4063c4e6a351f6&id=24c0ecc49a>`_. No spam, really low traffic.
+* `Twitter <https://twitter.com/DVCorg>`_
+* `Forum <https://discuss.dvc.org/>`_
+* `Discord Chat <https://dvc.org/chat>`_
+* `Email <mailto:[email protected]>`_
+* `Mailing List <https://sweedom.us10.list-manage.com/subscribe/post?u=a08bf93caae4063c4e6a351f6&id=24c0ecc49a>`_
 
 Copyright
 =========
 
 This project is distributed under the Apache license version 2.0 (see the LICENSE file in the project root).
 
-By submitting a pull request to this project, you agree to license your contribution under the Apache license version
-2.0 to this project.
+By submitting a pull request to this project, you agree to license your contribution under the Apache license version 2.0 to this project.
 
 Citation
 ========
@@ -254,7 +237,10 @@ Barrak, A., Eghan, E.E. and Adams, B. `On the Co-evolution of ML Pipelines and S
    :target: https://dvc.org
    :alt: DVC logo
 
-.. |CI| image:: https://github.com/iterative/dvc/workflows/Tests/badge.svg?branch=master
+.. |VS Code Extension Overview| image:: https://raw.githubusercontent.com/iterative/vscode-dvc/main/extension/docs/overview.gif
+   :alt: DVC Extension for VS Code
+
+.. |CI| image:: https://github.com/iterative/dvc/workflows/Tests/badge.svg?branch=main
    :target: https://github.com/iterative/dvc/actions
    :alt: GHA Tests
 
@@ -262,14 +248,14 @@ Barrak, A., Eghan, E.E. and Adams, B. `On the Co-evolution of ML Pipelines and S
    :target: https://codeclimate.com/github/iterative/dvc
    :alt: Code Climate
 
-.. |Coverage| image:: https://codecov.io/gh/iterative/dvc/branch/master/graph/badge.svg
+.. |Python Version| image:: https://img.shields.io/pypi/pyversions/dvc
+   :target: https://pypi.org/project/dvc
+   :alt: Python Version
+
+.. |Coverage| image:: https://codecov.io/gh/iterative/dvc/branch/main/graph/badge.svg
    :target: https://codecov.io/gh/iterative/dvc
    :alt: Codecov
 
-.. |Donate| image:: https://img.shields.io/badge/patreon-donate-green.svg?logo=patreon
-   :target: https://www.patreon.com/DVCorg/overview
-   :alt: Donate
-
 .. |Snap| image:: https://img.shields.io/badge/snap-install-82BEA0.svg?logo=snapcraft
    :target: https://snapcraft.io/dvc
    :alt: Snapcraft
@@ -305,3 +291,7 @@ Barrak, A., Eghan, E.E. and Adams, B. `On the Co-evolution of ML Pipelines and S
 .. |Contribs| image:: https://contrib.rocks/image?repo=iterative/dvc
    :target: https://github.com/iterative/dvc/graphs/contributors
    :alt: Contributors
+
+.. |VS Code| image:: https://vsmarketplacebadge.apphb.com/version/Iterative.dvc.svg
+   :target: https://marketplace.visualstudio.com/items?itemName=Iterative.dvc
+   :alt: VS Code Extension

dvc/__main__.py

@@ -1,7 +1,7 @@
 """Main entry point for DVC command line tool."""
 import sys
 
-from dvc.main import main
+from dvc.cli import main
 
 if __name__ == "__main__":
     sys.exit(main(sys.argv[1:]))

dvc/_debug.py

@@ -1,8 +1,28 @@
 from contextlib import ExitStack, contextmanager
-from typing import TYPE_CHECKING, Callable, Union
+from datetime import datetime
+from typing import TYPE_CHECKING, Callable, Optional, Union
 
 if TYPE_CHECKING:
     from argparse import Namespace
+    from types import FrameType
+
+
+@contextmanager
+def viztracer_profile(path: Union[Callable[[], str], str], depth: int = -1):
+    try:
+        import viztracer  # pylint: disable=import-error
+    except ImportError:
+        print("Failed to run profiler, viztracer is not installed")
+        yield
+        return
+
+    tracer = viztracer.VizTracer(max_stack_depth=depth)
+
+    tracer.start()
+    yield
+    tracer.stop()
+
+    tracer.save(path() if callable(path) else path)
 
 
 @contextmanager
@@ -87,6 +107,38 @@ def debug():
         raise  # prevent from jumping ahead
 
 
+def _sigshow(_, frame: Optional["FrameType"]) -> None:
+    from shutil import get_terminal_size
+    from traceback import format_stack
+
+    from dvc.ui import ui
+
+    lines = "\u2015" * get_terminal_size().columns
+    ui.error_write(lines, "\n", *format_stack(frame), lines, sep="")
+
+
+@contextmanager
+def show_stack():
+    r"""Show stack trace on SIGQUIT (Ctrl-\) or SIGINFO (Ctrl-T on macOS)."""
+    import signal
+
+    signal.signal(signal.SIGQUIT, _sigshow)
+    try:
+        signal.signal(signal.SIGINFO, _sigshow)  # only available on macOS
+    except AttributeError:
+        pass
+    yield
+
+
+def _get_path_func(tool: str, ext: str):
+    fmt = f"{tool}.dvc-{{now:%Y%m%d}}_{{now:%H%M%S}}.{ext}"
+
+    def func(now: Optional["datetime"] = None) -> str:
+        return fmt.format(now=now or datetime.now())
+
+    return func
+
+
 @contextmanager
 def debugtools(args: "Namespace" = None, **kwargs):
     kw = vars(args) if args else {}
@@ -99,13 +151,16 @@ def debugtools(args: "Namespace" = None, **kwargs):
             stack.enter_context(profile(kw.get("cprofile_dump")))
         if kw.get("instrument") or kw.get("instrument_open"):
             stack.enter_context(instrument(kw.get("instrument_open", False)))
+        if kw.get("show_stack", False):
+            stack.enter_context(show_stack())
         if kw.get("yappi"):
-            from datetime import datetime
-
-            output = "callgrind.dvc-{0:%Y%m%d}_{0:%H%M%S}.out"
-            stack.enter_context(
-                yappi_profile(path=lambda: output.format(datetime.now()))
-            )
+            path_func = _get_path_func("callgrind", "out")
+            stack.enter_context(yappi_profile(path=path_func))
+        if kw.get("viztracer") or kw.get("viztracer_depth"):
+            path_func = _get_path_func("viztracer", "json")
+            depth = kw.get("viztracer_depth") or -1
+            prof = viztracer_profile(path=path_func, depth=depth)
+            stack.enter_context(prof)
         yield
 
 
@@ -118,6 +173,10 @@ def add_debugging_flags(parser):
     parser.add_argument(
         "--yappi", action="store_true", default=False, help=SUPPRESS
     )
+    parser.add_argument(
+        "--viztracer", action="store_true", default=False, help=SUPPRESS
+    )
+    parser.add_argument("--viztracer-depth", type=int, help=SUPPRESS)
     parser.add_argument("--cprofile-dump", help=SUPPRESS)
     parser.add_argument(
         "--pdb", action="store_true", default=False, help=SUPPRESS
@@ -128,3 +187,10 @@ def add_debugging_flags(parser):
     parser.add_argument(
         "--instrument-open", action="store_true", default=False, help=SUPPRESS
     )
+    parser.add_argument(
+        "--show-stack",
+        "--ss",
+        action="store_true",
+        default=False,
+        help=SUPPRESS,
+    )

dvc/analytics.py

@@ -50,7 +50,7 @@ def is_enabled():
             Config(validate=False).get("core", {}).get("analytics", "true")
         )
 
-    logger.debug("Analytics is {}abled.".format("en" if enabled else "dis"))
+    logger.debug("Analytics is %sabled.", "en" if enabled else "dis")
 
     return enabled
 
@@ -102,6 +102,8 @@ def _runtime_info():
     """
     Gather information from the environment where DVC runs to fill a report.
     """
+    from iterative_telemetry import find_or_create_user_id
+
     from dvc import __version__
     from dvc.utils import is_binary
 
@@ -110,7 +112,7 @@ def _runtime_info():
         "is_binary": is_binary(),
         "scm_class": _scm_in_use(),
         "system_info": _system_info(),
-        "user_id": _find_or_create_user_id(),
+        "user_id": find_or_create_user_id(),
     }
 
 
@@ -146,45 +148,3 @@ def _system_info():
 
     # We don't collect data for any other system.
     raise NotImplementedError
-
-
-def _find_or_create_user_id():
-    """
-    The user's ID is stored on a file under the global config directory.
-
-    The file should contain a JSON with a "user_id" key:
-
-        {"user_id": "16fd2706-8baf-433b-82eb-8c7fada847da"}
-
-    IDs are generated randomly with UUID.
-    """
-    import uuid
-
-    from dvc.config import Config
-    from dvc.lock import Lock, LockError
-    from dvc.utils.fs import makedirs
-
-    config_dir = Config.get_dir("global")
-    fname = os.path.join(config_dir, "user_id")
-    lockfile = os.path.join(config_dir, "user_id.lock")
-
-    # Since the `fname` and `lockfile` are under the global config,
-    # we need to make sure such directory exist already.
-    makedirs(config_dir, exist_ok=True)
-
-    try:
-        with Lock(lockfile):
-            try:
-                with open(fname, encoding="utf-8") as fobj:
-                    user_id = json.load(fobj)["user_id"]
-
-            except (FileNotFoundError, ValueError, KeyError):
-                user_id = str(uuid.uuid4())
-
-                with open(fname, "w", encoding="utf-8") as fobj:
-                    json.dump({"user_id": user_id}, fobj)
-
-            return user_id
-
-    except LockError:
-        logger.debug(f"Failed to acquire '{lockfile}'")

dvc/annotations.py

@@ -0,0 +1,35 @@
+from dataclasses import asdict, dataclass, field, fields
+from typing import Any, ClassVar, Dict, List, Optional
+
+from funcy import compact
+
+
+@dataclass
+class Annotation:
+    PARAM_DESC: ClassVar[str] = "desc"
+    PARAM_TYPE: ClassVar[str] = "type"
+    PARAM_LABELS: ClassVar[str] = "labels"
+    PARAM_META: ClassVar[str] = "meta"
+
+    desc: Optional[str] = None
+    type: Optional[str] = None
+    labels: List[str] = field(default_factory=list)
+    meta: Dict[str, Any] = field(default_factory=dict)
+
+    def update(self, **kwargs) -> "Annotation":
+        for attr, value in kwargs.items():
+            if value and hasattr(self, attr):
+                setattr(self, attr, value)
+        return self
+
+    def to_dict(self) -> Dict[str, str]:
+        return compact(asdict(self))
+
+
+ANNOTATION_FIELDS = [field.name for field in fields(Annotation)]
+ANNOTATION_SCHEMA = {
+    Annotation.PARAM_DESC: str,
+    Annotation.PARAM_TYPE: str,
+    Annotation.PARAM_LABELS: [str],
+    Annotation.PARAM_META: object,
+}

dvc/api.py

@@ -1,122 +0,0 @@
-import os
-from contextlib import _GeneratorContextManager as GCM
-
-from funcy import reraise
-
-from dvc.exceptions import OutputNotFoundError, PathMissingError
-from dvc.repo import Repo
-
-
-def get_url(path, repo=None, rev=None, remote=None):
-    """
-    Returns the URL to the storage location of a data file or directory tracked
-    in a DVC repo. For Git repos, HEAD is used unless a rev argument is
-    supplied. The default remote is tried unless a remote argument is supplied.
-
-    Raises OutputNotFoundError if the file is not tracked by DVC.
-
-    NOTE: This function does not check for the actual existence of the file or
-    directory in the remote storage.
-    """
-    with Repo.open(repo, rev=rev, subrepos=True, uninitialized=True) as _repo:
-        fs_path = _repo.fs.path.join(_repo.root_dir, path)
-        with reraise(FileNotFoundError, PathMissingError(path, repo)):
-            metadata = _repo.repo_fs.metadata(fs_path)
-
-        if not metadata.is_dvc:
-            raise OutputNotFoundError(path, repo)
-
-        cloud = metadata.repo.cloud
-        md5 = metadata.repo.dvcfs.info(fs_path)["md5"]
-        return cloud.get_url_for(remote, checksum=md5)
-
-
-def open(  # noqa, pylint: disable=redefined-builtin
-    path, repo=None, rev=None, remote=None, mode="r", encoding=None
-):
-    """
-    Open file in the supplied path tracked in a repo (both DVC projects and
-    plain Git repos are supported). For Git repos, HEAD is used unless a rev
-    argument is supplied. The default remote is tried unless a remote argument
-    is supplied. It may only be used as a context manager:
-
-        with dvc.api.open(
-                'path/to/file',
-                repo='https://example.com/url/to/repo'
-                ) as fd:
-            # ... Handle file object fd
-    """
-    args = (path,)
-    kwargs = {
-        "repo": repo,
-        "remote": remote,
-        "rev": rev,
-        "mode": mode,
-        "encoding": encoding,
-    }
-    return _OpenContextManager(_open, args, kwargs)
-
-
-class _OpenContextManager(GCM):
-    def __init__(
-        self, func, args, kwds
-    ):  # pylint: disable=super-init-not-called
-        self.gen = func(*args, **kwds)
-        self.func, self.args, self.kwds = func, args, kwds
-
-    def __getattr__(self, name):
-        raise AttributeError(
-            "dvc.api.open() should be used in a with statement."
-        )
-
-
-def _open(path, repo=None, rev=None, remote=None, mode="r", encoding=None):
-    with Repo.open(repo, rev=rev, subrepos=True, uninitialized=True) as _repo:
-        with _repo.open_by_relpath(
-            path, remote=remote, mode=mode, encoding=encoding
-        ) as fd:
-            yield fd
-
-
-def read(path, repo=None, rev=None, remote=None, mode="r", encoding=None):
-    """
-    Returns the contents of a tracked file (by DVC or Git). For Git repos, HEAD
-    is used unless a rev argument is supplied. The default remote is tried
-    unless a remote argument is supplied.
-    """
-    with open(
-        path, repo=repo, rev=rev, remote=remote, mode=mode, encoding=encoding
-    ) as fd:
-        return fd.read()
-
-
-def make_checkpoint():
-    """
-    Signal DVC to create a checkpoint experiment.
-
-    If the current process is being run from DVC, this function will block
-    until DVC has finished creating the checkpoint. Otherwise, this function
-    will return immediately.
-    """
-    import builtins
-    from time import sleep
-
-    from dvc.env import DVC_CHECKPOINT, DVC_ROOT
-    from dvc.stage.monitor import CheckpointTask
-
-    if os.getenv(DVC_CHECKPOINT) is None:
-        return
-
-    root_dir = os.getenv(DVC_ROOT, Repo.find_root())
-    signal_file = os.path.join(
-        root_dir, Repo.DVC_DIR, "tmp", CheckpointTask.SIGNAL_FILE
-    )
-
-    with builtins.open(signal_file, "w", encoding="utf-8") as fobj:
-        # NOTE: force flushing/writing empty file to disk, otherwise when
-        # run in certain contexts (pytest) file may not actually be written
-        fobj.write("")
-        fobj.flush()
-        os.fsync(fobj.fileno())
-    while os.path.exists(signal_file):
-        sleep(0.1)

dvc/api/__init__.py

@@ -0,0 +1,15 @@
+from dvc.fs.dvc import _DVCFileSystem as DVCFileSystem
+
+from .data import open  # pylint: disable=redefined-builtin
+from .data import get_url, read
+from .experiments import make_checkpoint
+from .params import params_show
+
+__all__ = [
+    "get_url",
+    "make_checkpoint",
+    "open",
+    "params_show",
+    "read",
+    "DVCFileSystem",
+]

dvc/api/data.py

@@ -0,0 +1,213 @@
+from contextlib import _GeneratorContextManager as GCM
+from typing import Optional
+
+from funcy import reraise
+
+from dvc.exceptions import OutputNotFoundError, PathMissingError
+from dvc.repo import Repo
+
+
+def get_url(path, repo=None, rev=None, remote=None):
+    """
+    Returns the URL to the storage location of a data file or directory tracked
+    in a DVC repo. For Git repos, HEAD is used unless a rev argument is
+    supplied. The default remote is tried unless a remote argument is supplied.
+
+    Raises OutputNotFoundError if the file is not tracked by DVC.
+
+    NOTE: This function does not check for the actual existence of the file or
+    directory in the remote storage.
+    """
+    with Repo.open(repo, rev=rev, subrepos=True, uninitialized=True) as _repo:
+        fs_path = _repo.dvcfs.from_os_path(path)
+        with reraise(FileNotFoundError, PathMissingError(path, repo)):
+            info = _repo.dvcfs.info(fs_path)
+
+        dvc_info = info.get("dvc_info")
+        if not dvc_info:
+            raise OutputNotFoundError(path, repo)
+
+        dvc_repo = info["repo"]
+        md5 = dvc_info["md5"]
+
+        return dvc_repo.cloud.get_url_for(remote, checksum=md5)
+
+
+class _OpenContextManager(GCM):
+    def __init__(
+        self, func, args, kwds
+    ):  # pylint: disable=super-init-not-called
+        self.gen = func(*args, **kwds)
+        self.func, self.args, self.kwds = func, args, kwds
+
+    def __getattr__(self, name):
+        raise AttributeError(
+            "dvc.api.open() should be used in a with statement."
+        )
+
+
+def open(  # noqa, pylint: disable=redefined-builtin
+    path: str,
+    repo: Optional[str] = None,
+    rev: Optional[str] = None,
+    remote: Optional[str] = None,
+    mode: str = "r",
+    encoding: Optional[str] = None,
+):
+    """
+    Opens a file tracked in a DVC project.
+
+    This function may only be used as a context manager (using the `with`
+    keyword, as shown in the examples).
+
+    This function makes a direct connection to the remote storage, so the file
+    contents can be streamed. Your code can process the data buffer as it's
+    streamed, which optimizes memory usage.
+
+    Note:
+        Use dvc.api.read() to load the complete file contents
+        in a single function call, no context manager involved.
+        Neither function utilizes disc space.
+
+    Args:
+        path (str): location and file name of the target to open,
+        relative to the root of `repo`.
+        repo (str, optional): location of the DVC project or Git Repo.
+            Defaults to the current DVC project (found by walking up from the
+            current working directory tree).
+            It can be a URL or a file system path.
+            Both HTTP and SSH protocols are supported for online Git repos
+            (e.g. [user@]server:project.git).
+        rev (str, optional): Any `Git revision`_ such as a branch or tag name,
+            a commit hash or a dvc experiment name.
+            Defaults to HEAD.
+            If `repo` is not a Git repo, this option is ignored.
+        remote (str, optional): Name of the `DVC remote`_ used to form the
+            returned URL string.
+            Defaults to the `default remote`_ of `repo`.
+            For local projects, the cache is tried before the default remote.
+        mode (str, optional): Specifies the mode in which the file is opened.
+            Defaults to "r" (read).
+            Mirrors the namesake parameter in builtin `open()`_.
+            Only reading `mode` is supported.
+        encoding(str, optional): `Codec`_ used to decode the file contents.
+            Defaults to None.
+            This should only be used in text mode.
+            Mirrors the namesake parameter in builtin `open()`_.
+
+    Returns:
+        _OpenContextManager: A context manager that generatse a corresponding
+            `file object`_.
+            The exact type of file object depends on the mode used.
+            For more details, please refer to Python's `open()`_ built-in,
+            which is used under the hood.
+
+    Raises:
+        AttributeError: If this method is not used as a context manager.
+        ValueError: If non-read `mode` is used.
+
+    Examples:
+
+        - Use data or models from a DVC repository.
+
+        Any file tracked in a DVC project (and stored remotely) can be
+        processed directly in your Python code with this API.
+        For example, an XML file tracked in a public DVC repo on GitHub can be
+        processed like this:
+
+        >>> from xml.sax import parse
+        >>> import dvc.api
+        >>> from mymodule import mySAXHandler
+
+        >>> with dvc.api.open(
+        ...     'get-started/data.xml',
+        ...     repo='https://github.com/iterative/dataset-registry'
+        ... ) as fd:
+        ...     parse(fd, mySAXHandler)
+
+        We use a SAX XML parser here because dvc.api.open() is able to stream
+        the data from remote storage.
+        The mySAXHandler object should handle the event-driven parsing of the
+        document in this case.
+        This increases the performance of the code (minimizing memory usage),
+        and is typically faster than loading the whole data into memory.
+
+        - Accessing private repos
+
+        This is just a matter of using the right repo argument, for example an
+        SSH URL (requires that the credentials are configured locally):
+
+        >>> import dvc.api
+
+        >>> with dvc.api.open(
+        ...     'features.dat',
+        ...     repo='[email protected]:path/to/repo.git'
+        ... ) as fd:
+        ...     # ... Process 'features'
+        ...     pass
+
+        - Use different versions of data
+
+        Any git revision (see `rev`) can be accessed programmatically.
+        For example, if your DVC repo has tagged releases of a CSV dataset:
+
+        >>> import csv
+        >>> import dvc.api
+        >>> with dvc.api.open(
+        ...     'clean.csv',
+        ...     rev='v1.1.0'
+        ... ) as fd:
+        ...     reader = csv.reader(fd)
+        ...     # ... Process 'clean' data from version 1.1.0
+
+    .. _Git revision:
+        https://git-scm.com/docs/revisions
+
+    .. _DVC remote:
+        https://dvc.org/doc/command-reference/remote
+
+    .. _default remote:
+        https://dvc.org/doc/command-reference/remote/default
+
+    .. _open():
+        https://docs.python.org/3/library/functions.html#open
+
+    .. _Codec:
+        https://docs.python.org/3/library/codecs.html#standard-encodings
+
+    .. _file object:
+        https://docs.python.org/3/glossary.html#term-file-object
+
+    """
+    if "r" not in mode:
+        raise ValueError("Only reading `mode` is supported.")
+
+    args = (path,)
+    kwargs = {
+        "repo": repo,
+        "remote": remote,
+        "rev": rev,
+        "mode": mode,
+        "encoding": encoding,
+    }
+    return _OpenContextManager(_open, args, kwargs)
+
+
+def _open(path, repo=None, rev=None, remote=None, mode="r", encoding=None):
+    with Repo.open(repo, rev=rev, subrepos=True, uninitialized=True) as _repo:
+        with _repo.open_by_relpath(
+            path, remote=remote, mode=mode, encoding=encoding
+        ) as fd:
+            yield fd
+
+
+def read(path, repo=None, rev=None, remote=None, mode="r", encoding=None):
+    """
+    Returns the contents of a tracked file (by DVC or Git). For Git repos, HEAD
+    is used unless a rev argument is supplied. The default remote is tried
+    unless a remote argument is supplied.
+    """
+    with open(
+        path, repo=repo, rev=rev, remote=remote, mode=mode, encoding=encoding
+    ) as fd:
+        return fd.read()

dvc/api/experiments.py

@@ -0,0 +1,33 @@
+import builtins
+import os
+from time import sleep
+
+from dvc.env import DVC_CHECKPOINT, DVC_ROOT
+from dvc.repo import Repo
+from dvc.stage.monitor import CheckpointTask
+
+
+def make_checkpoint():
+    """
+    Signal DVC to create a checkpoint experiment.
+
+    If the current process is being run from DVC, this function will block
+    until DVC has finished creating the checkpoint. Otherwise, this function
+    will return immediately.
+    """
+    if os.getenv(DVC_CHECKPOINT) is None:
+        return
+
+    root_dir = os.getenv(DVC_ROOT, Repo.find_root())
+    signal_file = os.path.join(
+        root_dir, Repo.DVC_DIR, "tmp", CheckpointTask.SIGNAL_FILE
+    )
+
+    with builtins.open(signal_file, "w", encoding="utf-8") as fobj:
+        # NOTE: force flushing/writing empty file to disk, otherwise when
+        # run in certain contexts (pytest) file may not actually be written
+        fobj.write("")
+        fobj.flush()
+        os.fsync(fobj.fileno())
+    while os.path.exists(signal_file):
+        sleep(0.1)

dvc/api/params.py

@@ -0,0 +1,278 @@
+from collections import Counter
+from typing import Dict, Iterable, Optional, Union
+
+from funcy import first
+
+from dvc.exceptions import DvcException
+from dvc.repo import Repo
+
+
+def params_show(
+    *targets: str,
+    repo: Optional[str] = None,
+    stages: Optional[Union[str, Iterable[str]]] = None,
+    rev: Optional[str] = None,
+    deps: bool = False,
+) -> Dict:
+    """Get parameters tracked in `repo`.
+
+    Without arguments, this function will retrieve all params from all tracked
+    parameter files, for the current working tree.
+
+    See the options below to restrict the parameters retrieved.
+
+    Args:
+        *targets (str, optional): Names of the parameter files to retrieve
+        params from. For example, "params.py, myparams.toml".
+        If no `targets` are provided, all parameter files tracked in `dvc.yaml`
+        will be used.
+        Note that targets don't necessarily have to be defined in `dvc.yaml`.
+        repo (str, optional): location of the DVC repository.
+            Defaults to the current project (found by walking up from the
+            current working directory tree).
+            It can be a URL or a file system path.
+            Both HTTP and SSH protocols are supported for online Git repos
+            (e.g. [user@]server:project.git).
+        stages (Union[str, Iterable[str]], optional): Name or names of the
+            stages to retrieve parameters from.
+            Defaults to `None`.
+            If `None`, all parameters from all stages will be retrieved.
+            If this method is called from a different location to the one where
+            the `dvc.yaml` is found, the relative path to the `dvc.yaml` must
+            be provided as a prefix with the syntax `{relpath}:{stage}`.
+            For example: `subdir/dvc.yaml:stage-0` or `../dvc.yaml:stage-1`.
+        rev (str, optional): Name of the `Git revision`_ to retrieve parameters
+            from.
+            Defaults to `None`.
+            An example of git revision can be a branch or tag name, a commit
+            hash or a dvc experiment name.
+            If `repo` is not a Git repo, this option is ignored.
+            If `None`, the current working tree will be used.
+        deps (bool, optional): Whether to retrieve only parameters that are
+            stage dependencies or not.
+            Defaults to `False`.
+
+    Returns:
+        Dict: See Examples below.
+
+    Raises:
+        DvcException: If no params are found in `repo`.
+
+    Examples:
+
+        - No arguments.
+
+        Working on https://github.com/iterative/example-get-started
+
+        >>> import json
+        >>> import dvc.api
+        >>> params = dvc.api.params_show()
+        >>> print(json.dumps(params, indent=4))
+        {
+            "prepare": {
+                "split": 0.2,
+                "seed": 20170428
+            },
+            "featurize": {
+                "max_features": 200,
+                "ngrams": 2
+            },
+            "train": {
+                "seed": 20170428,
+                "n_est": 50,
+                "min_split": 0.01
+            }
+        }
+
+        ---
+
+        - Filtering with `stages`.
+
+        Working on https://github.com/iterative/example-get-started
+
+        `stages` can a single string:
+
+        >>> import json
+        >>> import dvc.api
+        >>> params = dvc.api.params_show(stages="prepare")
+        >>> print(json.dumps(params, indent=4))
+        {
+            "prepare": {
+                "split": 0.2,
+                "seed": 20170428
+            }
+        }
+
+        Or an iterable of strings:
+
+        >>> import json
+        >>> import dvc.api
+        >>> params = dvc.api.params_show(stages=["prepare", "train"])
+        >>> print(json.dumps(params, indent=4))
+        {
+            "prepare": {
+                "split": 0.2,
+                "seed": 20170428
+            },
+            "train": {
+                "seed": 20170428,
+                "n_est": 50,
+                "min_split": 0.01
+            }
+        }
+
+        ---
+
+        - Using `rev`.
+
+        Working on https://github.com/iterative/example-get-started
+
+        >>> import json
+        >>> import dvc.api
+        >>> params = dvc.api.params_show(rev="tune-hyperparams")
+        >>> print(json.dumps(params, indent=4))
+        {
+            "prepare": {
+                "split": 0.2,
+                "seed": 20170428
+            },
+            "featurize": {
+                "max_features": 200,
+                "ngrams": 2
+            },
+            "train": {
+                "seed": 20170428,
+                "n_est": 100,
+                "min_split": 8
+            }
+        }
+
+        ---
+
+        - Using `targets`.
+
+        Working on `multi-params-files` folder of
+        https://github.com/iterative/pipeline-conifguration
+
+        You can pass a single target:
+
+        >>> import json
+        >>> import dvc.api
+        >>> params = dvc.api.params_show("params.yaml")
+        >>> print(json.dumps(params, indent=4))
+        {
+            "run_mode": "prod",
+            "configs": {
+                "dev": "configs/params_dev.yaml",
+                "test": "configs/params_test.yaml",
+                "prod": "configs/params_prod.yaml"
+            },
+            "evaluate": {
+                "dataset": "micro",
+                "size": 5000,
+                "metrics": ["f1", "roc-auc"],
+                "metrics_file": "reports/metrics.json",
+                "plots_cm": "reports/plot_confusion_matrix.png"
+            }
+        }
+
+
+        Or multiple targets:
+
+        >>> import json
+        >>> import dvc.api
+        >>> params = dvc.api.params_show(
+        ...     "configs/params_dev.yaml", "configs/params_prod.yaml")
+        >>> print(json.dumps(params, indent=4))
+        {
+            "configs/params_prod.yaml:run_mode": "prod",
+            "configs/params_prod.yaml:config_file": "configs/params_prod.yaml",
+            "configs/params_prod.yaml:data_load": {
+                "dataset": "large",
+                "sampling": {
+                "enable": true,
+                "size": 50000
+                }
+            },
+            "configs/params_prod.yaml:train": {
+                "epochs": 1000
+            },
+            "configs/params_dev.yaml:run_mode": "dev",
+            "configs/params_dev.yaml:config_file": "configs/params_dev.yaml",
+            "configs/params_dev.yaml:data_load": {
+                "dataset": "development",
+                "sampling": {
+                "enable": true,
+                "size": 1000
+                }
+            },
+            "configs/params_dev.yaml:train": {
+                "epochs": 10
+            }
+        }
+
+        ---
+
+        - Git URL as `repo`.
+
+        >>> import json
+        >>> import dvc.api
+        >>> params = dvc.api.params_show(
+        ...     repo="https://github.com/iterative/demo-fashion-mnist")
+        {
+            "train": {
+                "batch_size": 128,
+                "hidden_units": 64,
+                "dropout": 0.4,
+                "num_epochs": 10,
+                "lr": 0.001,
+                "conv_activation": "relu"
+            }
+        }
+
+
+    .. _Git revision:
+        https://git-scm.com/docs/revisions
+
+    """
+    if isinstance(stages, str):
+        stages = [stages]
+
+    def _onerror_raise(result: Dict, exception: Exception, *args, **kwargs):
+        raise exception
+
+    def _postprocess(params):
+        processed = {}
+        for rev, rev_data in params.items():
+            processed[rev] = {}
+
+            counts = Counter()
+            for file_data in rev_data["data"].values():
+                for k in file_data["data"]:
+                    counts[k] += 1
+
+            for file_name, file_data in rev_data["data"].items():
+                to_merge = {
+                    (k if counts[k] == 1 else f"{file_name}:{k}"): v
+                    for k, v in file_data["data"].items()
+                }
+                processed[rev] = {**processed[rev], **to_merge}
+
+        if "workspace" in processed:
+            del processed["workspace"]
+
+        if not processed:
+            raise DvcException("No params found")
+
+        return processed[first(processed)]
+
+    with Repo.open(repo) as _repo:
+        params = _repo.params.show(
+            revs=rev if rev is None else [rev],
+            targets=targets,
+            deps=deps,
+            onerror=_onerror_raise,
+            stages=stages,
+        )
+
+    return _postprocess(params)

dvc/cli/__init__.py

@@ -0,0 +1,227 @@
+"""This module provides an entrypoint to the dvc cli and parsing utils."""
+
+import logging
+import sys
+
+# Workaround for CPython bug. See [1] and [2] for more info.
+# [1] https://github.com/aws/aws-cli/blob/1.16.277/awscli/clidriver.py#L55
+# [2] https://bugs.python.org/issue29288
+from typing import Optional
+
+"".encode("idna")
+
+logger = logging.getLogger("dvc")
+
+
+class DvcParserError(Exception):
+    """Base class for CLI parser errors."""
+
+    def __init__(self):
+        super().__init__("parser error")
+
+
+def parse_args(argv=None):
+    """Parses CLI arguments.
+
+    Args:
+        argv: optional list of arguments to parse. sys.argv is used by default.
+
+    Raises:
+        DvcParserError: raised for argument parsing errors.
+    """
+    from .parser import get_main_parser
+
+    parser = get_main_parser()
+    args = parser.parse_args(argv)
+    args.parser = parser
+    return args
+
+
+def _log_unknown_exceptions() -> None:
+    from dvc.info import get_dvc_info
+    from dvc.logger import FOOTER
+
+    logger.exception("unexpected error")
+    if logger.isEnabledFor(logging.DEBUG):
+        logger.debug("Version info for developers:\n%s", get_dvc_info())
+    logger.info(FOOTER)
+    return None
+
+
+def _log_exceptions(exc: Exception) -> Optional[int]:
+    """Try to log some known exceptions, that are not DVCExceptions."""
+    from dvc.utils import error_link, format_link
+
+    if isinstance(exc, OSError):
+        import errno
+
+        if exc.errno == errno.EMFILE:
+            logger.exception(
+                "too many open files, please visit "
+                "{} to see how to handle this "
+                "problem".format(error_link("many-files")),
+                extra={"tb_only": True},
+            )
+        else:
+            _log_unknown_exceptions()
+        return None
+
+    from dvc.fs import AuthError, ConfigError, RemoteMissingDepsError
+
+    if isinstance(exc, RemoteMissingDepsError):
+        from dvc.utils.pkg import PKG
+
+        proto = exc.protocol
+        by_pkg = {
+            "pip": f"pip install 'dvc[{proto}]'",
+            "conda": f"conda install -c conda-forge dvc-{proto}",
+        }
+
+        cmd = by_pkg.get(PKG)
+        if cmd:
+            link = format_link("https://dvc.org/doc/install")
+            hint = (
+                f"To install dvc with those dependencies, run:\n"
+                "\n"
+                f"\t{cmd}\n"
+                "\n"
+                f"See {link} for more info."
+            )
+        else:
+            link = format_link("https://github.com/iterative/dvc/issues")
+            hint = f"\nPlease report this bug to {link}. Thank you!"
+
+        logger.exception(
+            f"URL '{exc.url}' is supported but requires these missing "
+            f"dependencies: {exc.missing_deps}. {hint}",
+            extra={"tb_only": True},
+        )
+        return None
+
+    if isinstance(exc, (AuthError, ConfigError)):
+        link = format_link("https://man.dvc.org/remote/modify")
+        logger.exception("configuration error")
+        logger.exception(
+            f"{exc!s}\nLearn more about configuration settings at {link}.",
+            extra={"tb_only": True},
+        )
+        return 251
+
+    from dvc_data.hashfile.cache import DiskError
+
+    if isinstance(exc, DiskError):
+        from dvc.utils import relpath
+
+        directory = relpath(exc.directory)
+        logger.exception(
+            f"Could not open pickled '{exc.type}' cache.\n"
+            f"Remove the '{directory}' directory and then retry this command."
+            f"\nSee {error_link('pickle')} for more information.",
+            extra={"tb_only": True},
+        )
+        return None
+
+    from dvc_data.hashfile.build import IgnoreInCollectedDirError
+
+    if isinstance(exc, IgnoreInCollectedDirError):
+        logger.exception("")
+        return None
+
+    _log_unknown_exceptions()
+    return None
+
+
+def main(argv=None):  # noqa: C901
+    """Main entry point for dvc CLI.
+
+    Args:
+        argv: optional list of arguments to parse. sys.argv is used by default.
+
+    Returns:
+        int: command's return code.
+    """
+    from dvc._debug import debugtools
+    from dvc.config import ConfigError
+    from dvc.exceptions import DvcException, NotDvcRepoError
+    from dvc.logger import disable_other_loggers, set_loggers_level
+
+    # NOTE: stderr/stdout may be closed if we are running from dvc.daemon.
+    # On Linux we directly call cli.main after double forking and closing
+    # the copied parent's standard file descriptors. If we make any logging
+    # calls in this state it will cause an exception due to writing to a closed
+    # file descriptor.
+    if sys.stderr.closed:  # pylint: disable=using-constant-test
+        logging.disable()
+    elif sys.stdout.closed:  # pylint: disable=using-constant-test
+        logging.disable(logging.INFO)
+
+    args = None
+    disable_other_loggers()
+
+    outerLogLevel = logger.level
+    try:
+        args = parse_args(argv)
+
+        level = None
+        if args.quiet:
+            level = logging.CRITICAL
+        elif args.verbose == 1:
+            level = logging.DEBUG
+        elif args.verbose > 1:
+            level = logging.TRACE
+
+        if level is not None:
+            set_loggers_level(level)
+
+        logger.trace(args)
+
+        if not sys.stdout.closed and not args.quiet:
+            from dvc.ui import ui
+
+            ui.enable()
+
+        with debugtools(args):
+            cmd = args.func(args)
+            ret = cmd.do_run()
+    except ConfigError:
+        logger.exception("configuration error")
+        ret = 251
+    except KeyboardInterrupt:
+        logger.exception("interrupted by the user")
+        ret = 252
+    except BrokenPipeError:
+        import os
+
+        # Python flushes standard streams on exit; redirect remaining output
+        # to devnull to avoid another BrokenPipeError at shutdown
+        # See: https://docs.python.org/3/library/signal.html#note-on-sigpipe
+        devnull = os.open(os.devnull, os.O_WRONLY)
+        os.dup2(devnull, sys.stdout.fileno())
+        ret = 141  # 128 + 13 (SIGPIPE)
+    except NotDvcRepoError:
+        logger.exception("")
+        ret = 253
+    except DvcException:
+        ret = 255
+        logger.exception("")
+    except DvcParserError:
+        ret = 254
+    except Exception as exc:  # noqa, pylint: disable=broad-except
+        # pylint: disable=no-member
+        ret = _log_exceptions(exc) or 255
+
+    try:
+        from dvc import analytics
+
+        if analytics.is_enabled():
+            analytics.collect_and_send_report(args, ret)
+
+        return ret
+    finally:
+        logger.setLevel(outerLogLevel)
+
+        from dvc.external_repo import clean_repos
+
+        # Remove cached repos in the end of the call, these are anonymous
+        # so won't be reused by any other subsequent run anyway.
+        clean_repos()

dvc/cli/actions.py

@@ -0,0 +1,20 @@
+from argparse import _AppendAction
+
+
+class CommaSeparatedArgs(_AppendAction):  # pylint: disable=protected-access
+    def __call__(self, parser, namespace, values, option_string=None):
+        from funcy import ldistinct
+
+        items = getattr(namespace, self.dest) or []
+        items.extend(map(str.strip, values.split(",")))
+        setattr(namespace, self.dest, ldistinct(items))
+
+
+class KeyValueArgs(_AppendAction):
+    def __call__(self, parser, namespace, values, option_string=None):
+        items = getattr(namespace, self.dest) or {}
+        for value in filter(bool, values):
+            key, _, value = value.partition("=")
+            items[key.strip()] = value
+
+        setattr(namespace, self.dest, items)

dvc/cli/command.py

@@ -0,0 +1,36 @@
+import logging
+import os
+from abc import ABC, abstractmethod
+
+logger = logging.getLogger(__name__)
+
+
+class CmdBase(ABC):
+    UNINITIALIZED = False
+
+    def __init__(self, args):
+        from dvc.repo import Repo
+
+        os.chdir(args.cd)
+
+        self.repo: "Repo" = Repo(uninitialized=self.UNINITIALIZED)
+        self.config = self.repo.config
+        self.args = args
+
+    def do_run(self):
+        with self.repo:
+            return self.run()
+
+    @abstractmethod
+    def run(self):
+        pass
+
+
+class CmdBaseNoRepo(CmdBase):
+    def __init__(self, args):  # pylint: disable=super-init-not-called
+        self.args = args
+
+        os.chdir(args.cd)
+
+    def do_run(self):
+        return self.run()

dvc/cli/completion.py

@@ -1,17 +1,6 @@
-import argparse
-import logging
-
 import shtab
 
-from dvc.command.base import CmdBaseNoRepo, append_doc_link
-from dvc.ui import ui
-
-logger = logging.getLogger(__name__)
-FILE = shtab.FILE
-DIR = shtab.DIRECTORY
-
-PREAMBLE = {
-    "bash": """
+BASH_PREAMBLE = """
 # $1=COMP_WORDS[1]
 _dvc_compgen_DVCFiles() {
   compgen -d -S '/' -- $1  # recurse into subdirs
@@ -30,11 +19,12 @@ _dvc_compgen_stages_and_files() {
 }
 
 _dvc_compgen_exps() {
-    local _dvc_exps=($(dvc exp list -q --all --names-only))
+    local _dvc_exps=($(dvc exp list -q --all-commits --names-only))
     compgen -W "${_dvc_exps[*]}" -- $1
 }
-    """,
-    "zsh": """
+"""
+
+ZSH_PREAMBLE = """
 _dvc_compadd_DVCFiles() {
     _files -g '(*?.dvc|Dvcfile|dvc.yaml)'
 }
@@ -63,49 +53,21 @@ _dvc_compadd_stages_and_files() {
 }
 
 _dvc_compadd_exps() {
-    _describe 'experiments' "($(dvc exp list -q -a --names-only))"
+    _describe 'experiments' "($(dvc exp list -q --all-commits --names-only))"
 }
-    """,
+"""
+
+PREAMBLE = {
+    "bash": BASH_PREAMBLE,
+    "zsh": ZSH_PREAMBLE,
 }
 
+FILE = shtab.FILE
+DIR = shtab.DIRECTORY
 DVC_FILE = {"bash": "_dvc_compgen_DVCFiles", "zsh": "_dvc_compadd_DVCFiles"}
-
 STAGE = {"bash": "_dvc_compgen_stages", "zsh": "_dvc_compadd_stages"}
-
 DVCFILES_AND_STAGE = {
     "bash": "_dvc_compgen_stages_and_files",
     "zsh": "_dvc_compadd_stages_and_files",
 }
-
 EXPERIMENT = {"bash": "_dvc_compgen_exps", "zsh": "_dvc_compadd_exps"}
-
-
-class CmdCompletion(CmdBaseNoRepo):
-    def run(self):
-        from dvc.cli import get_main_parser
-
-        parser = get_main_parser()
-        shell = self.args.shell
-        script = shtab.complete(parser, shell=shell, preamble=PREAMBLE)
-        ui.write(script, force=True)
-        return 0
-
-
-def add_parser(subparsers, parent_parser):
-    COMPLETION_HELP = "Generate shell tab completion."
-    COMPLETION_DESCRIPTION = "Prints out shell tab completion scripts."
-    completion_parser = subparsers.add_parser(
-        "completion",
-        parents=[parent_parser],
-        description=append_doc_link(COMPLETION_DESCRIPTION, "completion"),
-        help=COMPLETION_HELP,
-        formatter_class=argparse.RawDescriptionHelpFormatter,
-    )
-    completion_parser.add_argument(
-        "-s",
-        "--shell",
-        help="Shell syntax for completions.",
-        default="bash",
-        choices=["bash", "zsh"],
-    )
-    completion_parser.set_defaults(func=CmdCompletion)

dvc/cli/parser.py

@@ -1,11 +1,10 @@
-"""DVC command line interface"""
+"""Main parser for the dvc cli."""
 import argparse
 import logging
 import os
 import sys
 
-from ._debug import add_debugging_flags
-from .command import (
+from dvc.commands import (
     add,
     cache,
     check_ignore,
@@ -15,6 +14,7 @@ from .command import (
     config,
     daemon,
     dag,
+    data,
     data_sync,
     destroy,
     diff,
@@ -28,13 +28,14 @@ from .command import (
     imp_url,
     init,
     install,
-    live,
     ls,
+    ls_url,
     machine,
     metrics,
     move,
     params,
     plots,
+    queue,
     remote,
     remove,
     repro,
@@ -45,13 +46,14 @@ from .command import (
     update,
     version,
 )
-from .command.base import fix_subparsers
-from .exceptions import DvcParserError
+
+from . import DvcParserError
 
 logger = logging.getLogger(__name__)
 
 COMMANDS = [
     init,
+    queue,
     get,
     get_url,
     destroy,
@@ -74,6 +76,7 @@ COMMANDS = [
     install,
     root,
     ls,
+    ls_url,
     freeze,
     dag,
     daemon,
@@ -87,8 +90,8 @@ COMMANDS = [
     stage,
     experiments,
     check_ignore,
-    live,
     machine,
+    data,
 ]
 
 
@@ -96,7 +99,7 @@ def _find_parser(parser, cmd_cls):
     defaults = parser._defaults  # pylint: disable=protected-access
     if not cmd_cls or cmd_cls == defaults.get("func"):
         parser.print_help()
-        raise DvcParserError()
+        raise DvcParserError
 
     actions = parser._actions  # pylint: disable=protected-access
     for action in actions:
@@ -143,6 +146,8 @@ def get_parent_parser():
     When overwriting `-q` or `-v`, you need to instantiate a new object
     in order to prevent some weird behavior.
     """
+    from dvc._debug import add_debugging_flags
+
     parent_parser = argparse.ArgumentParser(add_help=False)
     add_debugging_flags(parent_parser)
     log_level_group = parent_parser.add_mutually_exclusive_group()
@@ -207,23 +212,11 @@ def get_main_parser():
         help="Use `dvc COMMAND --help` for command-specific help.",
     )
 
+    from .utils import fix_subparsers
+
     fix_subparsers(subparsers)
 
     for cmd in COMMANDS:
         cmd.add_parser(subparsers, parent_parser)
 
     return parser
-
-
-def parse_args(argv=None):
-    """Parses CLI arguments.
-
-    Args:
-        argv: optional list of arguments to parse. sys.argv is used by default.
-
-    Raises:
-        dvc.exceptions.DvcParserError: raised for argument parsing errors.
-    """
-    parser = get_main_parser()
-    args = parser.parse_args(argv)
-    return args

dvc/cli/utils.py

@@ -0,0 +1,34 @@
+def fix_subparsers(subparsers):
+    """Workaround for bug in Python 3. See more info at:
+    https://bugs.python.org/issue16308
+    https://github.com/iterative/dvc/issues/769
+
+    Args:
+        subparsers: subparsers to fix.
+    """
+    subparsers.required = True
+    subparsers.dest = "cmd"
+
+
+def append_doc_link(help_message, path):
+    from dvc.utils import format_link
+
+    if not path:
+        return help_message
+    doc_base = "https://man.dvc.org/"
+    return "{message}\nDocumentation: {link}".format(
+        message=help_message, link=format_link(doc_base + path)
+    )
+
+
+def hide_subparsers_from_help(subparsers):
+    # metavar needs to be explicitly set in order to hide subcommands
+    # from the 'positional arguments' choices list
+    # see: https://bugs.python.org/issue22848
+    # Need to set `add_help=False`, but avoid setting `help`
+    # (not even to `argparse.SUPPPRESS`).
+    # NOTE: The argument is the parent subparser, not the subcommand parser.
+    cmds = [
+        cmd for cmd, parser in subparsers.choices.items() if parser.add_help
+    ]
+    subparsers.metavar = "{{{}}}".format(",".join(cmds))

dvc/command/base.py

@@ -1,59 +0,0 @@
-import logging
-import os
-from abc import ABC, abstractmethod
-
-logger = logging.getLogger(__name__)
-
-
-def fix_subparsers(subparsers):
-    """Workaround for bug in Python 3. See more info at:
-    https://bugs.python.org/issue16308
-    https://github.com/iterative/dvc/issues/769
-
-    Args:
-        subparsers: subparsers to fix.
-    """
-    subparsers.required = True
-    subparsers.dest = "cmd"
-
-
-def append_doc_link(help_message, path):
-    from dvc.utils import format_link
-
-    if not path:
-        return help_message
-    doc_base = "https://man.dvc.org/"
-    return "{message}\nDocumentation: {link}".format(
-        message=help_message, link=format_link(doc_base + path)
-    )
-
-
-class CmdBase(ABC):
-    UNINITIALIZED = False
-
-    def __init__(self, args):
-        from dvc.repo import Repo
-
-        os.chdir(args.cd)
-
-        self.repo = Repo(uninitialized=self.UNINITIALIZED)
-        self.config = self.repo.config
-        self.args = args
-
-    def do_run(self):
-        with self.repo:
-            return self.run()
-
-    @abstractmethod
-    def run(self):
-        pass
-
-
-class CmdBaseNoRepo(CmdBase):
-    def __init__(self, args):  # pylint: disable=super-init-not-called
-        self.args = args
-
-        os.chdir(args.cd)
-
-    def do_run(self):
-        return self.run()

dvc/command/live.py

@@ -1,93 +0,0 @@
-import argparse
-from pathlib import Path
-
-from dvc.command import completion
-from dvc.command.base import CmdBase, fix_subparsers
-from dvc.ui import ui
-
-
-class CmdLive(CmdBase):
-    UNINITIALIZED = True
-
-    def _run(self, target, revs=None):
-        metrics, plots = self.repo.live.show(target=target, revs=revs)
-
-        if plots:
-            html_path = Path.cwd() / (self.args.target + "_html")
-            from dvc.render.utils import render
-
-            index_path = render(self.repo, plots, metrics, html_path)
-            ui.write(index_path.as_uri())
-            return 0
-        return 1
-
-
-class CmdLiveShow(CmdLive):
-    def run(self):
-        return self._run(self.args.target)
-
-
-class CmdLiveDiff(CmdLive):
-    def run(self):
-        return self._run(self.args.target, self.args.revs)
-
-
-def shared_parent_parser():
-    parent_parser = argparse.ArgumentParser(add_help=False)
-    parent_parser.add_argument(
-        "target", help="Logs dir to produce summary from"
-    ).complete = completion.DIR
-    parent_parser.add_argument(
-        "-o",
-        "--out",
-        default=None,
-        help="Destination path to save plots to",
-        metavar="<path>",
-    ).complete = completion.DIR
-    return parent_parser
-
-
-def add_parser(subparsers, parent_parser):
-    LIVE_DESCRIPTION = (
-        "Commands to visualize and compare dvclive-produced logs."
-    )
-    live_parser = subparsers.add_parser(
-        "live",
-        parents=[parent_parser],
-        formatter_class=argparse.RawDescriptionHelpFormatter,
-        description=LIVE_DESCRIPTION,
-    )
-    live_subparsers = live_parser.add_subparsers(
-        dest="cmd",
-        help="Use `dvc live CMD --help` to display command-specific help.",
-    )
-
-    fix_subparsers(live_subparsers)
-
-    SHOW_HELP = "Visualize dvclive directory content."
-    live_show_parser = live_subparsers.add_parser(
-        "show",
-        parents=[parent_parser, shared_parent_parser()],
-        help=SHOW_HELP,
-        formatter_class=argparse.RawDescriptionHelpFormatter,
-    )
-    live_show_parser.set_defaults(func=CmdLiveShow)
-
-    DIFF_HELP = (
-        "Show multiple versions of dvclive data, "
-        "by plotting it in single view."
-    )
-    live_diff_parser = live_subparsers.add_parser(
-        "diff",
-        parents=[parent_parser, shared_parent_parser()],
-        help=DIFF_HELP,
-        formatter_class=argparse.RawDescriptionHelpFormatter,
-    )
-    live_diff_parser.add_argument(
-        "--revs",
-        nargs="*",
-        default=None,
-        help="Git revision (e.g. SHA, branch, tag)",
-        metavar="<commit>",
-    )
-    live_diff_parser.set_defaults(func=CmdLiveDiff)

dvc/command/plots.py

@@ -1,265 +0,0 @@
-import argparse
-import logging
-
-from dvc.command import completion
-from dvc.command.base import CmdBase, append_doc_link, fix_subparsers
-from dvc.exceptions import DvcException
-from dvc.render.utils import find_vega, render
-from dvc.ui import ui
-from dvc.utils import format_link
-
-logger = logging.getLogger(__name__)
-
-
-class CmdPlots(CmdBase):
-    def _func(self, *args, **kwargs):
-        raise NotImplementedError
-
-    def _props(self):
-        from dvc.schema import PLOT_PROPS
-
-        # Pass only props specified by user, to not shadow ones from plot def
-        props = {p: getattr(self.args, p) for p in PLOT_PROPS}
-        return {k: v for k, v in props.items() if v is not None}
-
-    def run(self):
-        from pathlib import Path
-
-        if self.args.show_vega:
-            if not self.args.targets:
-                logger.error("please specify a target for `--show-vega`")
-                return 1
-            if len(self.args.targets) > 1:
-                logger.error(
-                    "you can only specify one target for `--show-vega`"
-                )
-                return 1
-
-        try:
-            plots_data = self._func(
-                targets=self.args.targets, props=self._props()
-            )
-
-            if not plots_data:
-                ui.error_write(
-                    "No plots were loaded, "
-                    "visualization file will not be created."
-                )
-
-            if self.args.show_vega:
-                target = self.args.targets[0]
-                plot_json = find_vega(self.repo, plots_data, target)
-                if plot_json:
-                    ui.write(plot_json)
-                return 0
-
-            rel: str = self.args.out or "dvc_plots"
-            path: Path = (Path.cwd() / rel).resolve()
-            index_path = render(
-                self.repo,
-                plots_data,
-                path=path,
-                html_template_path=self.args.html_template,
-            )
-
-            ui.write(index_path.as_uri())
-
-            if self.args.open:
-                return ui.open_browser(index_path)
-
-            return 0
-
-        except DvcException:
-            logger.exception("")
-            return 1
-
-
-class CmdPlotsShow(CmdPlots):
-    UNINITIALIZED = True
-
-    def _func(self, *args, **kwargs):
-        return self.repo.plots.show(*args, **kwargs)
-
-
-class CmdPlotsDiff(CmdPlots):
-    UNINITIALIZED = True
-
-    def _func(self, *args, **kwargs):
-        return self.repo.plots.diff(
-            *args,
-            revs=self.args.revisions,
-            experiment=self.args.experiment,
-            **kwargs,
-        )
-
-
-class CmdPlotsModify(CmdPlots):
-    def run(self):
-        self.repo.plots.modify(
-            self.args.target, props=self._props(), unset=self.args.unset
-        )
-        return 0
-
-
-def add_parser(subparsers, parent_parser):
-    PLOTS_HELP = (
-        "Commands to visualize and compare plot metrics in structured files "
-        "(JSON, YAML, CSV, TSV)."
-    )
-
-    plots_parser = subparsers.add_parser(
-        "plots",
-        parents=[parent_parser],
-        description=append_doc_link(PLOTS_HELP, "plots"),
-        help=PLOTS_HELP,
-        formatter_class=argparse.RawDescriptionHelpFormatter,
-    )
-    plots_subparsers = plots_parser.add_subparsers(
-        dest="cmd",
-        help="Use `dvc plots CMD --help` to display command-specific help.",
-    )
-
-    fix_subparsers(plots_subparsers)
-
-    SHOW_HELP = "Generate plots from metrics files."
-    plots_show_parser = plots_subparsers.add_parser(
-        "show",
-        parents=[parent_parser],
-        description=append_doc_link(SHOW_HELP, "plots/show"),
-        help=SHOW_HELP,
-        formatter_class=argparse.RawDescriptionHelpFormatter,
-    )
-    plots_show_parser.add_argument(
-        "targets",
-        nargs="*",
-        help="Files to visualize (supports any file, "
-        "even when not found as `plots` in `dvc.yaml`). "
-        "Shows all plots by default.",
-    ).complete = completion.FILE
-    _add_props_arguments(plots_show_parser)
-    _add_output_arguments(plots_show_parser)
-    plots_show_parser.set_defaults(func=CmdPlotsShow)
-
-    PLOTS_DIFF_HELP = (
-        "Show multiple versions of plot metrics "
-        "by plotting them in a single image."
-    )
-    plots_diff_parser = plots_subparsers.add_parser(
-        "diff",
-        parents=[parent_parser],
-        description=append_doc_link(PLOTS_DIFF_HELP, "plots/diff"),
-        help=PLOTS_DIFF_HELP,
-        formatter_class=argparse.RawDescriptionHelpFormatter,
-    )
-    plots_diff_parser.add_argument(
-        "--targets",
-        nargs="*",
-        help=(
-            "Specific plots file(s) to visualize "
-            "(even if not found as `plots` in `dvc.yaml`). "
-            "Shows all tracked plots by default."
-        ),
-        metavar="<paths>",
-    ).complete = completion.FILE
-    plots_diff_parser.add_argument(
-        "-e",
-        "--experiment",
-        action="store_true",
-        default=False,
-        help=argparse.SUPPRESS,
-    )
-    plots_diff_parser.add_argument(
-        "revisions", nargs="*", default=None, help="Git commits to plot from"
-    )
-    _add_props_arguments(plots_diff_parser)
-    _add_output_arguments(plots_diff_parser)
-    plots_diff_parser.set_defaults(func=CmdPlotsDiff)
-
-    PLOTS_MODIFY_HELP = (
-        "Modify display properties of data-series plots "
-        "(has no effect on image-type plots)."
-    )
-    plots_modify_parser = plots_subparsers.add_parser(
-        "modify",
-        parents=[parent_parser],
-        description=append_doc_link(PLOTS_MODIFY_HELP, "plots/modify"),
-        help=PLOTS_MODIFY_HELP,
-        formatter_class=argparse.RawDescriptionHelpFormatter,
-    )
-    plots_modify_parser.add_argument(
-        "target", help="Metric file to set properties to"
-    ).complete = completion.FILE
-    _add_props_arguments(plots_modify_parser)
-    plots_modify_parser.add_argument(
-        "--unset",
-        nargs="*",
-        metavar="<property>",
-        help="Unset one or more display properties.",
-    )
-    plots_modify_parser.set_defaults(func=CmdPlotsModify)
-
-
-def _add_props_arguments(parser):
-    parser.add_argument(
-        "-t",
-        "--template",
-        nargs="?",
-        default=None,
-        help=(
-            "Special JSON or HTML schema file to inject with the data. "
-            "See {}".format(
-                format_link("https://man.dvc.org/plots#plot-templates")
-            )
-        ),
-        metavar="<path>",
-    ).complete = completion.FILE
-    parser.add_argument(
-        "-x", default=None, help="Field name for X axis.", metavar="<field>"
-    )
-    parser.add_argument(
-        "-y", default=None, help="Field name for Y axis.", metavar="<field>"
-    )
-    parser.add_argument(
-        "--no-header",
-        action="store_false",
-        dest="header",
-        default=None,  # Use default None to distinguish when it's not used
-        help="Provided CSV or TSV datafile does not have a header.",
-    )
-    parser.add_argument(
-        "--title", default=None, metavar="<text>", help="Plot title."
-    )
-    parser.add_argument(
-        "--x-label", default=None, help="X axis label", metavar="<text>"
-    )
-    parser.add_argument(
-        "--y-label", default=None, help="Y axis label", metavar="<text>"
-    )
-
-
-def _add_output_arguments(parser):
-    parser.add_argument(
-        "-o",
-        "--out",
-        default=None,
-        help="Destination path to save plots to",
-        metavar="<path>",
-    ).complete = completion.DIR
-    parser.add_argument(
-        "--show-vega",
-        action="store_true",
-        default=False,
-        help="Show output in Vega format.",
-    )
-    parser.add_argument(
-        "--open",
-        action="store_true",
-        default=False,
-        help="Open plot file directly in the browser.",
-    )
-    parser.add_argument(
-        "--html-template",
-        default=None,
-        help="Custom HTML template for VEGA visualization.",
-        metavar="<path>",
-    )

dvc/commands/add.py

@@ -1,12 +1,44 @@
 import argparse
 import logging
 
-from dvc.command import completion
-from dvc.command.base import CmdBase, append_doc_link
+from dvc.cli import completion
+from dvc.cli.actions import KeyValueArgs
+from dvc.cli.command import CmdBase
+from dvc.cli.utils import append_doc_link
 
 logger = logging.getLogger(__name__)
 
 
+def _add_annotating_args(parser: argparse.ArgumentParser) -> None:
+    parser.add_argument(
+        "--desc",
+        type=str,
+        metavar="<text>",
+        help="User description of the data.",
+    )
+    parser.add_argument(
+        "--meta",
+        metavar="key=value",
+        nargs=1,
+        action=KeyValueArgs,
+        help="Custom metadata to add to the data.",
+    )
+    parser.add_argument(
+        "--label",
+        dest="labels",
+        type=str,
+        action="append",
+        metavar="<str>",
+        help="Label for the data.",
+    )
+    parser.add_argument(
+        "--type",
+        type=str,
+        metavar="<str>",
+        help="Type of the data.",
+    )
+
+
 class CmdAdd(CmdBase):
     def run(self):
         from dvc.exceptions import (
@@ -27,6 +59,9 @@ class CmdAdd(CmdBase):
                 glob=self.args.glob,
                 desc=self.args.desc,
                 out=self.args.out,
+                type=self.args.type,
+                labels=self.args.labels,
+                meta=self.args.meta,
                 remote=self.args.remote,
                 to_remote=self.args.to_remote,
                 jobs=self.args.jobs,
@@ -101,21 +136,15 @@ def add_parser(subparsers, parent_parser):
         "--jobs",
         type=int,
         help=(
-            "Number of jobs to run simultaneously. "
+            "Only used along with '--to-remote'. "
+            "Number of jobs to run simultaneously "
+            "when pushing data to remote."
             "The default value is 4 * cpu_count(). "
-            "For SSH remotes, the default is 4. "
         ),
         metavar="<number>",
     )
-    parser.add_argument(
-        "--desc",
-        type=str,
-        metavar="<text>",
-        help=(
-            "User description of the data (optional). "
-            "This doesn't affect any DVC operations."
-        ),
-    )
+
+    _add_annotating_args(parser)
     parser.add_argument(
         "targets", nargs="+", help="Input files/directories to add."
     ).complete = completion.FILE

dvc/commands/cache.py

@@ -1,8 +1,8 @@
 import argparse
 
-from dvc.command import completion
-from dvc.command.base import append_doc_link, fix_subparsers
-from dvc.command.config import CmdConfig
+from dvc.cli import completion
+from dvc.cli.utils import append_doc_link, fix_subparsers
+from dvc.commands.config import CmdConfig
 from dvc.ui import ui
 
 
@@ -28,7 +28,7 @@ class CmdCacheDir(CmdConfig):
 
 
 def add_parser(subparsers, parent_parser):
-    from dvc.command.config import parent_config_parser
+    from dvc.commands.config import parent_config_parser
 
     CACHE_HELP = "Manage cache settings."
 

dvc/commands/check_ignore.py

@@ -1,7 +1,8 @@
 import argparse
 
-from dvc.command import completion
-from dvc.command.base import CmdBase, append_doc_link
+from dvc.cli import completion
+from dvc.cli.command import CmdBase
+from dvc.cli.utils import append_doc_link
 from dvc.ui import ui
 
 

dvc/commands/checkout.py

@@ -1,8 +1,9 @@
 import argparse
 import operator
 
-from dvc.command import completion
-from dvc.command.base import CmdBase, append_doc_link
+from dvc.cli import completion
+from dvc.cli.command import CmdBase
+from dvc.cli.utils import append_doc_link
 from dvc.exceptions import CheckoutError
 from dvc.ui import ui
 
@@ -54,6 +55,10 @@ class CmdCheckout(CmdBase):
 
         if exc:
             raise exc
+
+        if self.args.relink:
+            msg = "Relinked successfully"
+            ui.write(msg)
         return 0
 
 
@@ -105,7 +110,7 @@ def add_parser(subparsers, parent_parser):
         nargs="*",
         help=(
             "Limit command scope to these tracked files/directories, "
-            ".dvc files, or stage names."
+            ".dvc files and stage names."
         ),
     ).complete = completion.DVC_FILE
     checkout_parser.set_defaults(func=CmdCheckout)

dvc/commands/commit.py

@@ -1,8 +1,9 @@
 import argparse
 import logging
 
-from dvc.command import completion
-from dvc.command.base import CmdBase, append_doc_link
+from dvc.cli import completion
+from dvc.cli.command import CmdBase
+from dvc.cli.utils import append_doc_link
 
 logger = logging.getLogger(__name__)
 
@@ -69,7 +70,9 @@ def add_parser(subparsers, parent_parser):
     commit_parser.add_argument(
         "targets",
         nargs="*",
-        help="stages or .dvc files to commit. Optional. "
-        "(Finds all DVC files in the workspace by default.)",
+        help=(
+            "Limit command scope to these tracked files/directories, "
+            ".dvc files and stage names."
+        ),
     ).complete = completion.DVCFILES_AND_STAGE
     commit_parser.set_defaults(func=CmdCommit)

dvc/commands/completion.py

@@ -0,0 +1,40 @@
+import argparse
+import logging
+
+from dvc.cli.command import CmdBaseNoRepo
+from dvc.cli.completion import PREAMBLE
+from dvc.cli.utils import append_doc_link
+from dvc.ui import ui
+
+logger = logging.getLogger(__name__)
+
+
+class CmdCompletion(CmdBaseNoRepo):
+    def run(self):
+        import shtab
+
+        shell = self.args.shell
+        parser = self.args.parser
+        script = shtab.complete(parser, shell=shell, preamble=PREAMBLE)
+        ui.write(script, force=True)
+        return 0
+
+
+def add_parser(subparsers, parent_parser):
+    COMPLETION_HELP = "Generate shell tab completion."
+    COMPLETION_DESCRIPTION = "Prints out shell tab completion scripts."
+    completion_parser = subparsers.add_parser(
+        "completion",
+        parents=[parent_parser],
+        description=append_doc_link(COMPLETION_DESCRIPTION, "completion"),
+        help=COMPLETION_HELP,
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+    )
+    completion_parser.add_argument(
+        "-s",
+        "--shell",
+        help="Shell syntax for completions.",
+        default="bash",
+        choices=["bash", "zsh"],
+    )
+    completion_parser.set_defaults(func=CmdCompletion)

dvc/commands/config.py

@@ -2,7 +2,8 @@ import argparse
 import logging
 import os
 
-from dvc.command.base import CmdBaseNoRepo, append_doc_link
+from dvc.cli.command import CmdBaseNoRepo
+from dvc.cli.utils import append_doc_link
 from dvc.ui import ui
 
 logger = logging.getLogger(__name__)

dvc/commands/daemon.py

@@ -1,5 +1,6 @@
-from dvc.command import completion
-from dvc.command.base import CmdBaseNoRepo, fix_subparsers
+from dvc.cli import completion
+from dvc.cli.command import CmdBaseNoRepo
+from dvc.cli.utils import fix_subparsers
 
 
 class CmdDaemonBase(CmdBaseNoRepo):

dvc/commands/dag.py

@@ -1,10 +1,15 @@
 import argparse
+from typing import TYPE_CHECKING
 
-from dvc.command.base import CmdBase, append_doc_link
+from dvc.cli.command import CmdBase
+from dvc.cli.utils import append_doc_link
 from dvc.ui import ui
 
+if TYPE_CHECKING:
+    from networkx import DiGraph
 
-def _show_ascii(G):
+
+def _show_ascii(G: "DiGraph"):
     from dvc.dagascii import draw
     from dvc.repo.graph import get_pipelines
 
@@ -17,16 +22,54 @@ def _show_ascii(G):
     return "\n".join(ret)
 
 
-def _show_dot(G):
+def _quote_label(node):
+    label = str(node)
+    # Node names should not contain ":" unless they are quoted with "".
+    # See: https://github.com/pydot/pydot/issues/258.
+    if label[0] != '"' and label[-1] != '"':
+        return f'"{label}"'
+    return label
+
+
+def _show_dot(G: "DiGraph"):
     import io
 
+    import networkx as nx
     from networkx.drawing.nx_pydot import write_dot
 
     dot_file = io.StringIO()
-    write_dot(G, dot_file)
+
+    nx.relabel_nodes(G, _quote_label, copy=False)
+    write_dot(G.reverse(), dot_file)
     return dot_file.getvalue()
 
 
+def _show_mermaid(G, markdown: bool = False):
+    from dvc.repo.graph import get_pipelines
+
+    pipelines = get_pipelines(G)
+
+    graph = "flowchart TD"
+
+    total_nodes = 0
+    for pipeline in pipelines:
+        node_ids = {}
+        nodes = sorted(str(x) for x in pipeline.nodes)
+        for node in nodes:
+            total_nodes += 1
+            node_id = f"node{total_nodes}"
+            graph += f'\n\t{node_id}["{node}"]'
+            node_ids[node] = node_id
+        edges = sorted((str(a), str(b)) for b, a in pipeline.edges)
+        for a, b in edges:
+            graph += f"\n\t{node_ids[str(a)]}-->{node_ids[str(b)]}"
+
+    if markdown:
+        return f"```mermaid\n{graph}\n```"
+
+    return graph
+
+
 def _collect_targets(repo, target, outs):
     if not target:
         return []
@@ -43,9 +86,9 @@ def _collect_targets(repo, target, outs):
             targets.extend([str(out) for out in stage.outs])
             continue
 
-        for out in outs_trie.itervalues(
+        for out in outs_trie.itervalues(  # noqa: B301
             prefix=repo.fs.path.parts(path)
-        ):  # noqa: B301
+        ):
             targets.extend(str(out))
 
     return targets
@@ -104,6 +147,8 @@ class CmdDAG(CmdBase):
 
         if self.args.dot:
             ui.write(_show_dot(G))
+        elif self.args.mermaid or self.args.markdown:
+            ui.write(_show_mermaid(G, self.args.markdown))
         else:
             with ui.pager():
                 ui.write(_show_ascii(G))
@@ -126,6 +171,20 @@ def add_parser(subparsers, parent_parser):
         default=False,
         help="Print DAG with .dot format.",
     )
+    dag_parser.add_argument(
+        "--mermaid",
+        action="store_true",
+        default=False,
+        help="Print DAG with mermaid format.",
+    )
+    dag_parser.add_argument(
+        "--md",
+        "--show-md",
+        action="store_true",
+        default=False,
+        dest="markdown",
+        help="Print DAG with mermaid format wrapped in Markdown block.",
+    )
     dag_parser.add_argument(
         "--full",
         action="store_true",
@@ -145,7 +204,7 @@ def add_parser(subparsers, parent_parser):
     dag_parser.add_argument(
         "target",
         nargs="?",
-        help="Stage or output to show pipeline for (optional). "
+        help="Stage name or output to show pipeline for. "
         "Finds all stages in the workspace by default.",
     )
     dag_parser.set_defaults(func=CmdDAG)

dvc/commands/data.py

@@ -0,0 +1,297 @@
+import argparse
+import logging
+from operator import itemgetter
+from typing import TYPE_CHECKING, Any, Dict, Iterable, Set
+
+from funcy import chunks, compact, log_durations
+
+from dvc.cli import completion
+from dvc.cli.actions import CommaSeparatedArgs
+from dvc.cli.command import CmdBase
+from dvc.cli.utils import (
+    append_doc_link,
+    fix_subparsers,
+    hide_subparsers_from_help,
+)
+from dvc.ui import ui
+from dvc.utils import colorize
+
+if TYPE_CHECKING:
+    from dvc.repo.data import Status as DataStatus
+
+
+logger = logging.getLogger(__name__)
+
+
+class CmdDataStatus(CmdBase):
+    COLORS = {
+        "not_in_cache": "red",
+        "committed": "green",
+        "uncommitted": "yellow",
+        "untracked": "cyan",
+    }
+    LABELS = {
+        "not_in_cache": "Not in cache",
+        "committed": "DVC committed changes",
+        "uncommitted": "DVC uncommitted changes",
+        "untracked": "Untracked files",
+        "unchanged": "DVC unchanged files",
+    }
+    HINTS = {
+        "not_in_cache": ('use "dvc fetch <file>..." to download files',),
+        "committed": (
+            "git commit the corresponding dvc files to update the repo",
+        ),
+        "uncommitted": (
+            'use "dvc commit <file>..." to track changes',
+            'use "dvc checkout <file>..." to discard changes',
+        ),
+        "untracked": (
+            'use "git add <file> ..." or '
+            '"dvc add <file>..." to commit to git or to dvc',
+        ),
+        "git_dirty": (
+            "there are {}changes not tracked by dvc, "
+            'use "git status" to see',
+        ),
+    }
+
+    @staticmethod
+    def _process_status(status: "DataStatus"):
+        """Flatten stage status, and filter empty stage status contents."""
+        for stage, stage_status in status.items():
+            items = stage_status
+            if isinstance(stage_status, dict):
+                items = {
+                    file: state
+                    for state, files in stage_status.items()
+                    for file in files
+                }
+            if not items:
+                continue
+            yield stage, items
+
+    @classmethod
+    def _show_status(cls, status: "DataStatus") -> int:
+        git_info = status.pop("git")  # type: ignore[misc]
+        result = dict(cls._process_status(status))
+        if not result:
+            no_changes = "No changes"
+            if git_info.get("is_empty", False):
+                no_changes += " in an empty git repo"
+            ui.write(f"{no_changes}.")
+
+        for idx, (stage, stage_status) in enumerate(result.items()):
+            if idx:
+                ui.write()
+
+            label = cls.LABELS.get(stage, stage.capitalize() + " files")
+            header = f"{label}:"
+            color = cls.COLORS.get(stage, None)
+
+            ui.write(header)
+            if hints := cls.HINTS.get(stage):
+                for hint in hints:
+                    ui.write(f"  ({hint})")
+
+            if isinstance(stage_status, dict):
+                items = [
+                    ": ".join([state, file])
+                    for file, state in stage_status.items()
+                ]
+            else:
+                items = stage_status
+
+            tabs = "\t".expandtabs(8)
+            for chunk in chunks(1000, items):
+                out = "\n".join(tabs + item for item in chunk)
+                ui.write(colorize(out, color))
+
+        if (hints := cls.HINTS.get("git_dirty")) and git_info.get("is_dirty"):
+            for hint in hints:
+                message = hint.format("other " if result else "")
+                ui.write(f"[blue]({message})[/]", styled=True)
+        return 0
+
+    def run(self) -> int:
+        with log_durations(logger.trace, "in data_status"):  # type: ignore
+            status = self.repo.data_status(
+                granular=self.args.granular,
+                untracked_files=self.args.untracked_files,
+            )
+
+        if not self.args.unchanged:
+            status.pop("unchanged")  # type: ignore[misc]
+        if self.args.untracked_files == "no":
+            status.pop("untracked")
+        if self.args.json:
+            status.pop("git")  # type: ignore[misc]
+            ui.write_json(compact(status))
+            return 0
+        return self._show_status(status)
+
+
+class CmdDataLs(CmdBase):
+    @staticmethod
+    def _show_table(
+        d: Iterable[Dict[str, Any]],
+        filter_types: Set[str],
+        filter_labels: Set[str],
+        markdown: bool = False,
+    ) -> None:
+        from rich.style import Style
+
+        from dvc.compare import TabularData
+
+        td = TabularData(
+            columns=["Path", "Type", "Labels", "Description"], fill_value="-"
+        )
+        for entry in sorted(d, key=itemgetter("path")):
+            typ = entry.get("type", "")
+            desc = entry.get("desc", "-")
+            labels = entry.get("labels", [])
+
+            if filter_types and typ not in filter_types:
+                continue
+            if filter_labels and filter_labels.isdisjoint(labels):
+                continue
+
+            rich_label = ui.rich_text()
+            for index, label in enumerate(labels):
+                if index:
+                    rich_label.append(",")
+                style = Style(bold=label in filter_labels, color="green")
+                rich_label.append(label, style=style)
+
+            if markdown and desc:
+                desc = desc.partition("\n")[0]
+
+            path = ui.rich_text(entry["path"], style="cyan")
+            type_style = Style(bold=typ in filter_types, color="yellow")
+            typ = ui.rich_text(entry.get("type", ""), style=type_style)
+            td.append([path, typ or "-", rich_label or "-", desc])
+
+        td.render(markdown=markdown, rich_table=True)
+
+    def run(self):
+        from dvc.repo.data import ls
+
+        filter_labels = set(self.args.labels)
+        filter_types = set(self.args.type)
+        d = ls(
+            self.repo, targets=self.args.targets, recursive=self.args.recursive
+        )
+        self._show_table(
+            d,
+            filter_labels=filter_labels,
+            filter_types=filter_types,
+            markdown=self.args.markdown,
+        )
+        return 0
+
+
+def add_parser(subparsers, parent_parser):
+    data_parser = subparsers.add_parser(
+        "data",
+        parents=[parent_parser],
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+    )
+    data_subparsers = data_parser.add_subparsers(
+        dest="cmd",
+        help="Use `dvc data CMD --help` to display command-specific help.",
+    )
+    fix_subparsers(data_subparsers)
+
+    DATA_STATUS_HELP = (
+        "Show changes between the last git commit, "
+        "the dvcfiles and the workspace."
+    )
+    data_status_parser = data_subparsers.add_parser(
+        "status",
+        parents=[parent_parser],
+        description=append_doc_link(DATA_STATUS_HELP, "data/status"),
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+        help=DATA_STATUS_HELP,
+    )
+    data_status_parser.add_argument(
+        "--json",
+        action="store_true",
+        default=False,
+        help="Show output in JSON format.",
+    )
+    data_status_parser.add_argument(
+        "--show-json",
+        action="store_true",
+        default=False,
+        dest="json",
+        help=argparse.SUPPRESS,
+    )
+    data_status_parser.add_argument(
+        "--granular",
+        action="store_true",
+        default=False,
+        help="Show granular file-level info for DVC-tracked directories.",
+    )
+    data_status_parser.add_argument(
+        "--unchanged",
+        action="store_true",
+        default=False,
+        help="Show unmodified DVC-tracked files.",
+    )
+    data_status_parser.add_argument(
+        "--untracked-files",
+        choices=["no", "all"],
+        default="no",
+        const="all",
+        nargs="?",
+        help="Show untracked files.",
+    )
+    data_status_parser.set_defaults(func=CmdDataStatus)
+
+    DATA_LS_HELP = "List data tracked by DVC with its metadata."
+    data_ls_parser = data_subparsers.add_parser(
+        "ls",
+        aliases=["list"],
+        parents=[parent_parser],
+        description=append_doc_link(DATA_LS_HELP, "data/ls"),
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+        add_help=False,
+    )
+    data_ls_parser.add_argument(
+        "--md",
+        "--show-md",
+        dest="markdown",
+        action="store_true",
+        default=False,
+        help="Show tabulated output in the Markdown format (GFM).",
+    )
+    data_ls_parser.add_argument(
+        "--type",
+        action=CommaSeparatedArgs,
+        default=[],
+        help="Comma-separated list of type to filter.",
+    )
+    data_ls_parser.add_argument(
+        "--labels",
+        action=CommaSeparatedArgs,
+        default=[],
+        help="Comma-separated list of labels to filter.",
+    )
+    data_ls_parser.add_argument(
+        "-R",
+        "--recursive",
+        action="store_true",
+        default=False,
+        help="Recursively list from the specified directories.",
+    )
+    data_ls_parser.add_argument(
+        "targets",
+        default=None,
+        nargs="*",
+        help=(
+            "Limit command scope to these tracked files/directories, "
+            ".dvc files, or stage names."
+        ),
+    ).complete = completion.DVCFILES_AND_STAGE
+    data_ls_parser.set_defaults(func=CmdDataLs)
+    hide_subparsers_from_help(data_subparsers)

dvc/commands/data_sync.py

@@ -1,8 +1,9 @@
 import argparse
 import logging
 
-from dvc.command import completion
-from dvc.command.base import CmdBase, append_doc_link
+from dvc.cli import completion
+from dvc.cli.command import CmdBase
+from dvc.cli.utils import append_doc_link
 
 logger = logging.getLogger(__name__)
 
@@ -18,7 +19,7 @@ class CmdDataBase(CmdBase):
 
 class CmdDataPull(CmdDataBase):
     def log_summary(self, stats):
-        from dvc.command.checkout import log_changes
+        from dvc.commands.checkout import log_changes
 
         log_changes(stats)
         super().log_summary(stats)
@@ -42,7 +43,8 @@ class CmdDataPull(CmdDataBase):
             )
             self.log_summary(stats)
         except (CheckoutError, DvcException) as exc:
-            self.log_summary(getattr(exc, "stats", {}))
+            if stats := getattr(exc, "stats", {}):
+                self.log_summary(stats)
             logger.exception("failed to pull data from the cloud")
             return 1
 
@@ -97,7 +99,7 @@ class CmdDataFetch(CmdDataBase):
 
 
 def shared_parent_parser():
-    from dvc.cli import get_parent_parser
+    from dvc.cli.parser import get_parent_parser
 
     # Parent parser used in pull/push/status
     parent_parser = argparse.ArgumentParser(
@@ -110,7 +112,6 @@ def shared_parent_parser():
         help=(
             "Number of jobs to run simultaneously. "
             "The default value is 4 * cpu_count(). "
-            "For SSH remotes, the default is 4. "
         ),
         metavar="<number>",
     )
@@ -119,7 +120,7 @@ def shared_parent_parser():
         nargs="*",
         help=(
             "Limit command scope to these tracked files/directories, "
-            ".dvc files, or stage names."
+            ".dvc files and stage names."
         ),
     ).complete = completion.DVC_FILE
 
@@ -127,7 +128,7 @@ def shared_parent_parser():
 
 
 def add_parser(subparsers, _parent_parser):
-    from dvc.command.status import CmdDataStatus
+    from dvc.commands.status import CmdDataStatus
 
     # Pull
     PULL_HELP = "Download tracked files or directories from remote storage."
@@ -194,7 +195,7 @@ def add_parser(subparsers, _parent_parser):
         "--glob",
         action="store_true",
         default=False,
-        help="Pull cache for targets matching shell-style wildcards.",
+        help=argparse.SUPPRESS,
     )
     pull_parser.set_defaults(func=CmdDataPull)
 

dvc/commands/destroy.py

@@ -1,7 +1,8 @@
 import argparse
 import logging
 
-from dvc.command.base import CmdBase, append_doc_link
+from dvc.cli.command import CmdBase
+from dvc.cli.utils import append_doc_link
 
 logger = logging.getLogger(__name__)
 

dvc/commands/diff.py

@@ -2,8 +2,9 @@ import argparse
 import logging
 import os
 
-from dvc.command import completion
-from dvc.command.base import CmdBase, append_doc_link
+from dvc.cli import completion
+from dvc.cli.command import CmdBase
+from dvc.cli.utils import append_doc_link
 from dvc.ui import ui
 
 logger = logging.getLogger(__name__)
@@ -127,7 +128,7 @@ class CmdDiff(CmdBase):
             show_hash = self.args.show_hash
             hide_missing = self.args.b_rev or self.args.hide_missing
             if hide_missing:
-                del diff["not in cache"]
+                diff.pop("not in cache", None)
 
             for key, entries in diff.items():
                 entries = sorted(

dvc/commands/experiments/__init__.py

@@ -0,0 +1,103 @@
+import argparse
+
+from dvc.cli.utils import (
+    append_doc_link,
+    fix_subparsers,
+    hide_subparsers_from_help,
+)
+from dvc.commands.experiments import (
+    apply,
+    branch,
+    diff,
+    exec_run,
+    gc,
+    init,
+    ls,
+    pull,
+    push,
+    queue_worker,
+    remove,
+    run,
+    show,
+)
+
+SUB_COMMANDS = [
+    apply,
+    branch,
+    diff,
+    exec_run,
+    gc,
+    init,
+    ls,
+    pull,
+    push,
+    queue_worker,
+    remove,
+    run,
+    show,
+]
+
+
+def add_parser(subparsers, parent_parser):
+    EXPERIMENTS_HELP = "Commands to run and compare experiments."
+
+    experiments_parser = subparsers.add_parser(
+        "experiments",
+        parents=[parent_parser],
+        aliases=["exp"],
+        description=append_doc_link(EXPERIMENTS_HELP, "exp"),
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+        help=EXPERIMENTS_HELP,
+    )
+
+    experiments_subparsers = experiments_parser.add_subparsers(
+        dest="cmd",
+        help="Use `dvc experiments CMD --help` to display "
+        "command-specific help.",
+    )
+
+    fix_subparsers(experiments_subparsers)
+    for cmd in SUB_COMMANDS:
+        cmd.add_parser(experiments_subparsers, parent_parser)
+    hide_subparsers_from_help(experiments_subparsers)
+
+
+def add_rev_selection_flags(
+    experiments_subcmd_parser, command: str, default: bool = True
+):
+    experiments_subcmd_parser.add_argument(
+        "-A",
+        "--all-commits",
+        action="store_true",
+        default=False,
+        help=(
+            f"{command} all experiments in the repository "
+            "(overrides `--rev` and `--num`)."
+        ),
+    )
+    default_msg = " (HEAD by default)" if default else ""
+    msg = (
+        f"{command} experiments derived from the specified `<commit>` as "
+        f"baseline{default_msg}."
+    )
+    experiments_subcmd_parser.add_argument(
+        "--rev",
+        type=str,
+        default=None,
+        help=msg,
+        metavar="<commit>",
+    )
+    experiments_subcmd_parser.add_argument(
+        "-n",
+        "--num",
+        type=int,
+        default=1,
+        dest="num",
+        metavar="<num>",
+        help=(
+            f"{command} experiments from the last `num` commits "
+            "(first parents) starting from the `--rev` baseline. "
+            "Give a negative value to include all first-parent commits "
+            "(similar to `git log -n`)."
+        ),
+    )

dvc/commands/experiments/apply.py

@@ -0,0 +1,42 @@
+import argparse
+import logging
+
+from dvc.cli import completion
+from dvc.cli.command import CmdBase
+from dvc.cli.utils import append_doc_link
+
+logger = logging.getLogger(__name__)
+
+
+class CmdExperimentsApply(CmdBase):
+    def run(self):
+
+        self.repo.experiments.apply(
+            self.args.experiment, force=self.args.force
+        )
+
+        return 0
+
+
+def add_parser(experiments_subparsers, parent_parser):
+
+    EXPERIMENTS_APPLY_HELP = (
+        "Apply the changes from an experiment to your workspace."
+    )
+    experiments_apply_parser = experiments_subparsers.add_parser(
+        "apply",
+        parents=[parent_parser],
+        description=append_doc_link(EXPERIMENTS_APPLY_HELP, "exp/apply"),
+        help=EXPERIMENTS_APPLY_HELP,
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+    )
+    experiments_apply_parser.add_argument(
+        "--no-force",
+        action="store_false",
+        dest="force",
+        help="Fail if this command would overwrite conflicting changes.",
+    )
+    experiments_apply_parser.add_argument(
+        "experiment", help="Experiment to be applied."
+    ).complete = completion.EXPERIMENT
+    experiments_apply_parser.set_defaults(func=CmdExperimentsApply)

dvc/commands/experiments/branch.py

@@ -0,0 +1,34 @@
+import argparse
+import logging
+
+from dvc.cli.command import CmdBase
+from dvc.cli.utils import append_doc_link
+
+logger = logging.getLogger(__name__)
+
+
+class CmdExperimentsBranch(CmdBase):
+    def run(self):
+
+        self.repo.experiments.branch(self.args.experiment, self.args.branch)
+
+        return 0
+
+
+def add_parser(experiments_subparsers, parent_parser):
+
+    EXPERIMENTS_BRANCH_HELP = "Promote an experiment to a Git branch."
+    experiments_branch_parser = experiments_subparsers.add_parser(
+        "branch",
+        parents=[parent_parser],
+        description=append_doc_link(EXPERIMENTS_BRANCH_HELP, "exp/branch"),
+        help=EXPERIMENTS_BRANCH_HELP,
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+    )
+    experiments_branch_parser.add_argument(
+        "experiment", help="Experiment to be promoted."
+    )
+    experiments_branch_parser.add_argument(
+        "branch", help="Name for the new Git branch"
+    )
+    experiments_branch_parser.set_defaults(func=CmdExperimentsBranch)

dvc/commands/experiments/diff.py

@@ -0,0 +1,118 @@
+import argparse
+import logging
+
+from dvc.cli import completion
+from dvc.cli.command import CmdBase
+from dvc.cli.utils import append_doc_link
+from dvc.commands.metrics import DEFAULT_PRECISION
+from dvc.exceptions import DvcException
+from dvc.ui import ui
+
+logger = logging.getLogger(__name__)
+
+
+class CmdExperimentsDiff(CmdBase):
+    def run(self):
+
+        try:
+            diff = self.repo.experiments.diff(
+                a_rev=self.args.a_rev,
+                b_rev=self.args.b_rev,
+                all=self.args.all,
+                param_deps=self.args.param_deps,
+            )
+        except DvcException:
+            logger.exception("failed to show experiments diff")
+            return 1
+
+        if self.args.json:
+            ui.write_json(diff)
+        elif diff:
+            from dvc.compare import show_diff
+
+            precision = self.args.precision or DEFAULT_PRECISION
+            diffs = [("metrics", "Metric"), ("params", "Param")]
+            for idx, (key, title) in enumerate(diffs):
+                if idx:
+                    # we are printing tables even in `--quiet` mode
+                    # so we should also be printing the "table" separator
+                    ui.write(force=True)
+
+                show_diff(
+                    diff[key],
+                    title=title,
+                    markdown=self.args.markdown,
+                    no_path=self.args.no_path,
+                    on_empty_diff="diff not supported",
+                    precision=precision if key == "metrics" else None,
+                    a_rev=self.args.a_rev,
+                    b_rev=self.args.b_rev,
+                )
+
+        return 0
+
+
+def add_parser(experiments_subparsers, parent_parser):
+
+    EXPERIMENTS_DIFF_HELP = (
+        "Show changes between experiments in the DVC repository."
+    )
+
+    experiments_diff_parser = experiments_subparsers.add_parser(
+        "diff",
+        parents=[parent_parser],
+        description=append_doc_link(EXPERIMENTS_DIFF_HELP, "exp/diff"),
+        help=EXPERIMENTS_DIFF_HELP,
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+    )
+    experiments_diff_parser.add_argument(
+        "a_rev", nargs="?", help="Old experiment to compare (defaults to HEAD)"
+    ).complete = completion.EXPERIMENT
+    experiments_diff_parser.add_argument(
+        "b_rev",
+        nargs="?",
+        help="New experiment to compare (defaults to the current workspace)",
+    ).complete = completion.EXPERIMENT
+    experiments_diff_parser.add_argument(
+        "--all",
+        action="store_true",
+        default=False,
+        help="Show unchanged metrics/params as well.",
+    )
+    experiments_diff_parser.add_argument(
+        "--param-deps",
+        action="store_true",
+        default=False,
+        help="Show only params that are stage dependencies.",
+    )
+    experiments_diff_parser.add_argument(
+        "--json",
+        "--show-json",
+        action="store_true",
+        default=False,
+        help="Show output in JSON format.",
+    )
+    experiments_diff_parser.add_argument(
+        "--md",
+        "--show-md",
+        action="store_true",
+        default=False,
+        dest="markdown",
+        help="Show tabulated output in the Markdown format (GFM).",
+    )
+    experiments_diff_parser.add_argument(
+        "--no-path",
+        action="store_true",
+        default=False,
+        help="Don't show metric/param path.",
+    )
+    experiments_diff_parser.add_argument(
+        "--precision",
+        type=int,
+        help=(
+            "Round metrics/params to `n` digits precision after the decimal "
+            f"point. Rounds to {DEFAULT_PRECISION} digits by default."
+        ),
+        metavar="<n>",
+    )
+    experiments_diff_parser.set_defaults(func=CmdExperimentsDiff)

dvc/commands/experiments/exec_run.py

@@ -0,0 +1,42 @@
+import logging
+
+from dvc.cli.command import CmdBaseNoRepo
+
+logger = logging.getLogger(__name__)
+
+
+class CmdExecutorRun(CmdBaseNoRepo):
+    """Run an experiment executor."""
+
+    def run(self):
+        from dvc.repo.experiments.executor.base import (
+            BaseExecutor,
+            ExecutorInfo,
+        )
+        from dvc.utils.serialize import load_json
+
+        info = ExecutorInfo.from_dict(load_json(self.args.infofile))
+        BaseExecutor.reproduce(
+            info=info,
+            rev="",
+            queue=None,
+            log_level=logger.getEffectiveLevel(),
+            infofile=self.args.infofile,
+        )
+        return 0
+
+
+def add_parser(experiments_subparsers, parent_parser):
+    EXEC_RUN_HELP = "Run an experiment executor."
+    exec_run_parser = experiments_subparsers.add_parser(
+        "exec-run",
+        parents=[parent_parser],
+        description=EXEC_RUN_HELP,
+        add_help=False,
+    )
+    exec_run_parser.add_argument(
+        "--infofile",
+        help="Path to executor info file",
+        default=None,
+    )
+    exec_run_parser.set_defaults(func=CmdExecutorRun)

dvc/commands/experiments/gc.py

@@ -0,0 +1,150 @@
+import argparse
+import logging
+
+from dvc.cli.command import CmdBase
+from dvc.cli.utils import append_doc_link
+from dvc.exceptions import InvalidArgumentError
+from dvc.ui import ui
+
+logger = logging.getLogger(__name__)
+
+
+def _raise_error_if_all_disabled(**kwargs):
+    if not any(kwargs.values()):
+        raise InvalidArgumentError(
+            "Either of `-w|--workspace`, `-a|--all-branches`, `-T|--all-tags`,"
+            " `--all-commits` or `--date` needs to be set."
+        )
+
+
+class CmdExperimentsGC(CmdBase):
+    def run(self):
+        _raise_error_if_all_disabled(
+            all_branches=self.args.all_branches,
+            all_tags=self.args.all_tags,
+            all_commits=self.args.all_commits,
+            commit_date=self.args.commit_date,
+            workspace=self.args.workspace,
+        )
+
+        msg = "This will remove all experiments except those derived from "
+
+        msg += "the workspace"
+        if self.args.all_commits:
+            msg += " and all git commits"
+        else:
+            if self.args.all_branches and self.args.all_tags:
+                msg += " and all git branches and tags"
+            elif self.args.all_branches:
+                msg += " and all git branches"
+            elif self.args.all_tags:
+                msg += " and all git tags"
+
+            if self.args.commit_date:
+                msg += (
+                    " and all git commits before date "
+                    f"{self.args.commit_date}"
+                )
+        msg += " of the current repo."
+
+        if self.args.queued:
+            msg += " Run queued experiments will be preserved."
+        else:
+            msg += " Run queued experiments will be removed."
+
+        logger.warning(msg)
+
+        msg = "Are you sure you want to proceed?"
+        if not self.args.force and not ui.confirm(msg):
+            return 1
+
+        removed = self.repo.experiments.gc(
+            all_branches=self.args.all_branches,
+            all_tags=self.args.all_tags,
+            all_commits=self.args.all_commits,
+            workspace=self.args.workspace,
+            commit_date=self.args.commit_date,
+            queued=self.args.queued,
+        )
+
+        if removed:
+            ui.write(
+                f"Removed {removed} experiments.",
+                "To remove unused cache files",
+                "use 'dvc gc'.",
+            )
+        else:
+            ui.write("No experiments to remove.")
+        return 0
+
+
+def add_parser(experiments_subparsers, parent_parser):
+
+    EXPERIMENTS_GC_HELP = "Garbage collect unneeded experiments."
+    EXPERIMENTS_GC_DESCRIPTION = (
+        "Removes all experiments which are not derived from the specified"
+        "Git revisions."
+    )
+    experiments_gc_parser = experiments_subparsers.add_parser(
+        "gc",
+        parents=[parent_parser],
+        description=append_doc_link(EXPERIMENTS_GC_DESCRIPTION, "exp/gc"),
+        help=EXPERIMENTS_GC_HELP,
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+    )
+    experiments_gc_parser.add_argument(
+        "-w",
+        "--workspace",
+        action="store_true",
+        default=False,
+        help="Keep experiments derived from the current workspace.",
+    )
+    experiments_gc_parser.add_argument(
+        "-a",
+        "--all-branches",
+        action="store_true",
+        default=False,
+        help="Keep experiments derived from the tips of all Git branches.",
+    )
+    experiments_gc_parser.add_argument(
+        "-T",
+        "--all-tags",
+        action="store_true",
+        default=False,
+        help="Keep experiments derived from all Git tags.",
+    )
+    experiments_gc_parser.add_argument(
+        "-A",
+        "--all-commits",
+        action="store_true",
+        default=False,
+        help="Keep experiments derived from all Git commits.",
+    )
+    experiments_gc_parser.add_argument(
+        "--date",
+        type=str,
+        dest="commit_date",
+        metavar="<YYYY-MM-DD>",
+        default=None,
+        help=(
+            "Keep experiments from the commits after (inclusive) a certain "
+            "date. Date must match the extended ISO 8601 format (YYYY-MM-DD)."
+        ),
+    )
+    experiments_gc_parser.add_argument(
+        "--queued",
+        action="store_true",
+        default=False,
+        help=(
+            "Keep queued experiments (experiments run queue will be cleared "
+            "by default)."
+        ),
+    )
+    experiments_gc_parser.add_argument(
+        "-f",
+        "--force",
+        action="store_true",
+        default=False,
+        help="Force garbage collection - automatically agree to all prompts.",
+    )
+    experiments_gc_parser.set_defaults(func=CmdExperimentsGC)

dvc/commands/experiments/init.py

@@ -0,0 +1,210 @@
+import argparse
+import logging
+from typing import TYPE_CHECKING, List
+
+from funcy import compact
+
+from dvc.cli.command import CmdBase
+from dvc.cli.utils import append_doc_link
+from dvc.exceptions import InvalidArgumentError
+from dvc.ui import ui
+
+if TYPE_CHECKING:
+    from dvc.dependency import Dependency
+    from dvc.stage import PipelineStage
+
+
+logger = logging.getLogger(__name__)
+
+
+class CmdExperimentsInit(CmdBase):
+    DEFAULT_NAME = "train"
+    CODE = "src"
+    DATA = "data"
+    MODELS = "models"
+    DEFAULT_METRICS = "metrics.json"
+    DEFAULT_PARAMS = "params.yaml"
+    PLOTS = "plots"
+    DEFAULTS = {
+        "code": CODE,
+        "data": DATA,
+        "models": MODELS,
+        "metrics": DEFAULT_METRICS,
+        "params": DEFAULT_PARAMS,
+        "plots": PLOTS,
+    }
+
+    def run(self):
+        from dvc.commands.stage import parse_cmd
+
+        cmd = parse_cmd(self.args.command)
+        if not self.args.interactive and not cmd:
+            raise InvalidArgumentError("command is not specified")
+
+        from dvc.repo.experiments.init import init
+
+        defaults = {}
+        if not self.args.explicit:
+            config = self.repo.config["exp"]
+            defaults.update({**self.DEFAULTS, **config})
+
+        cli_args = compact(
+            {
+                "cmd": cmd,
+                "code": self.args.code,
+                "data": self.args.data,
+                "models": self.args.models,
+                "metrics": self.args.metrics,
+                "params": self.args.params,
+                "plots": self.args.plots,
+                "live": self.args.live,
+            }
+        )
+
+        initialized_stage, initialized_deps, initialized_out_dirs = init(
+            self.repo,
+            name=self.args.name,
+            type=self.args.type,
+            defaults=defaults,
+            overrides=cli_args,
+            interactive=self.args.interactive,
+            force=self.args.force,
+        )
+        self._post_init_display(
+            initialized_stage, initialized_deps, initialized_out_dirs
+        )
+        if self.args.run:
+            self.repo.experiments.run(targets=[initialized_stage.addressing])
+        return 0
+
+    def _post_init_display(
+        self,
+        stage: "PipelineStage",
+        new_deps: List["Dependency"],
+        new_out_dirs: List[str],
+    ) -> None:
+        from dvc.utils import humanize
+
+        path_fmt = "[green]{}[/green]".format
+        if new_deps:
+            deps_paths = humanize.join(map(path_fmt, new_deps))
+            ui.write(f"Creating dependencies: {deps_paths}", styled=True)
+
+        if new_out_dirs:
+            out_dirs_paths = humanize.join(map(path_fmt, new_out_dirs))
+            ui.write(
+                f"Creating output directories: {out_dirs_paths}", styled=True
+            )
+
+        ui.write(
+            f"Creating [b]{self.args.name}[/b] stage in [green]dvc.yaml[/]",
+            styled=True,
+        )
+        if stage.outs or not self.args.run:
+            # separate the above status-like messages with help/tips section
+            ui.write(styled=True)
+
+        if stage.outs:
+            outs_paths = humanize.join(map(path_fmt, stage.outs))
+            tips = f"Ensure your experiment command creates {outs_paths}."
+            ui.write(tips, styled=True)
+
+        if not self.args.run:
+            ui.write(
+                'You can now run your experiment using [b]"dvc exp run"[/].',
+                styled=True,
+            )
+        else:
+            # separate between `exp.run` output and `dvc exp init` output
+            ui.write(styled=True)
+
+
+def add_parser(experiments_subparsers, parent_parser):
+
+    EXPERIMENTS_INIT_HELP = "Quickly setup any project to use experiments."
+    experiments_init_parser = experiments_subparsers.add_parser(
+        "init",
+        parents=[parent_parser],
+        description=append_doc_link(EXPERIMENTS_INIT_HELP, "exp/init"),
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+        help=EXPERIMENTS_INIT_HELP,
+    )
+    experiments_init_parser.add_argument(
+        "command",
+        nargs=argparse.REMAINDER,
+        help="Command to execute.",
+        metavar="command",
+    )
+    experiments_init_parser.add_argument(
+        "--run",
+        action="store_true",
+        help="Run the experiment after initializing it",
+    )
+    experiments_init_parser.add_argument(
+        "--interactive",
+        "-i",
+        action="store_true",
+        help="Prompt for values that are not provided",
+    )
+    experiments_init_parser.add_argument(
+        "-f",
+        "--force",
+        action="store_true",
+        default=False,
+        help="Overwrite existing stage",
+    )
+    experiments_init_parser.add_argument(
+        "--explicit",
+        action="store_true",
+        default=False,
+        help="Only use the path values explicitly provided",
+    )
+    experiments_init_parser.add_argument(
+        "--name",
+        "-n",
+        help="Name of the stage to create (default: %(default)s)",
+        default=CmdExperimentsInit.DEFAULT_NAME,
+    )
+    experiments_init_parser.add_argument(
+        "--code",
+        help="Path to the source file or directory "
+        "which your experiments depend"
+        f" (default: {CmdExperimentsInit.CODE})",
+    )
+    experiments_init_parser.add_argument(
+        "--data",
+        help="Path to the data file or directory "
+        "which your experiments depend"
+        f" (default: {CmdExperimentsInit.DATA})",
+    )
+    experiments_init_parser.add_argument(
+        "--models",
+        help="Path to the model file or directory for your experiments"
+        f" (default: {CmdExperimentsInit.MODELS})",
+    )
+    experiments_init_parser.add_argument(
+        "--params",
+        help="Path to the parameters file for your experiments"
+        f" (default: {CmdExperimentsInit.DEFAULT_PARAMS})",
+    )
+    experiments_init_parser.add_argument(
+        "--metrics",
+        help="Path to the metrics file for your experiments"
+        f" (default: {CmdExperimentsInit.DEFAULT_METRICS})",
+    )
+    experiments_init_parser.add_argument(
+        "--plots",
+        help="Path to the plots file or directory for your experiments"
+        f" (default: {CmdExperimentsInit.PLOTS})",
+    )
+    experiments_init_parser.add_argument(
+        "--live",
+        help="Path to log dvclive outputs for your experiments",
+    )
+    experiments_init_parser.add_argument(
+        "--type",
+        choices=["default", "checkpoint"],
+        default="default",
+        help="Select type of stage to create (default: %(default)s)",
+    )
+    experiments_init_parser.set_defaults(func=CmdExperimentsInit)

dvc/commands/experiments/ls.py

@@ -0,0 +1,68 @@
+import argparse
+import logging
+
+from dvc.cli.command import CmdBase
+from dvc.cli.utils import append_doc_link
+
+logger = logging.getLogger(__name__)
+
+
+class CmdExperimentsList(CmdBase):
+    def run(self):
+        name_only = self.args.name_only
+        exps = self.repo.experiments.ls(
+            all_commits=self.args.all_commits,
+            rev=self.args.rev,
+            num=self.args.num,
+            git_remote=self.args.git_remote,
+        )
+        tags = self.repo.scm.describe(exps)
+        remained = {baseline for baseline, tag in tags.items() if tag is None}
+        base = "refs/heads/"
+        ref_heads = self.repo.scm.describe(remained, base=base)
+
+        for baseline in exps:
+            name = (
+                tags[baseline]
+                or ref_heads[baseline][len(base) :]
+                or baseline[:7]
+            )
+            if not name_only:
+                print(f"{name}:")
+            for exp_name in exps[baseline]:
+                indent = "" if name_only else "\t"
+                print(f"{indent}{exp_name}")
+
+        return 0
+
+
+def add_parser(experiments_subparsers, parent_parser):
+    from . import add_rev_selection_flags
+
+    EXPERIMENTS_LIST_HELP = "List local and remote experiments."
+    experiments_list_parser = experiments_subparsers.add_parser(
+        "list",
+        parents=[parent_parser],
+        description=append_doc_link(EXPERIMENTS_LIST_HELP, "exp/list"),
+        help=EXPERIMENTS_LIST_HELP,
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+    )
+    add_rev_selection_flags(experiments_list_parser, "List")
+    experiments_list_parser.add_argument(
+        "--name-only",
+        "--names-only",
+        action="store_true",
+        help="Only output experiment names (without parent commits).",
+    )
+    experiments_list_parser.add_argument(
+        "git_remote",
+        nargs="?",
+        default=None,
+        help=(
+            "Optional Git remote name or Git URL. "
+            "If provided, experiments from the specified Git repository "
+            " will be listed instead of local ones."
+        ),
+        metavar="<git_remote>",
+    )
+    experiments_list_parser.set_defaults(func=CmdExperimentsList)

dvc/commands/experiments/pull.py

@@ -0,0 +1,117 @@
+import argparse
+import logging
+
+from dvc.cli.command import CmdBase
+from dvc.cli.utils import append_doc_link
+from dvc.exceptions import InvalidArgumentError
+from dvc.ui import ui
+
+logger = logging.getLogger(__name__)
+
+
+class CmdExperimentsPull(CmdBase):
+    def raise_error_if_all_disabled(self):
+        if not any(
+            [self.args.experiment, self.args.all_commits, self.args.rev]
+        ):
+            raise InvalidArgumentError(
+                "Either provide an `experiment` argument, or use the "
+                "`--rev` or `--all-commits` flag."
+            )
+
+    def run(self):
+        self.raise_error_if_all_disabled()
+
+        pulled_exps = self.repo.experiments.pull(
+            self.args.git_remote,
+            self.args.experiment,
+            all_commits=self.args.all_commits,
+            rev=self.args.rev,
+            num=self.args.num,
+            force=self.args.force,
+            pull_cache=self.args.pull_cache,
+            dvc_remote=self.args.dvc_remote,
+            jobs=self.args.jobs,
+            run_cache=self.args.run_cache,
+        )
+
+        if pulled_exps:
+            ui.write(
+                f"Pulled experiment '{pulled_exps}'",
+                f"from Git remote '{self.args.git_remote}'.",
+            )
+        else:
+            ui.write("No experiments to pull.")
+        if not self.args.pull_cache:
+            ui.write(
+                "To pull cached outputs for this experiment"
+                "from DVC remote storage,"
+                "re-run this command without '--no-cache'."
+            )
+
+        return 0
+
+
+def add_parser(experiments_subparsers, parent_parser):
+    from . import add_rev_selection_flags
+
+    EXPERIMENTS_PULL_HELP = "Pull an experiment from a Git remote."
+    experiments_pull_parser = experiments_subparsers.add_parser(
+        "pull",
+        parents=[parent_parser],
+        description=append_doc_link(EXPERIMENTS_PULL_HELP, "exp/pull"),
+        help=EXPERIMENTS_PULL_HELP,
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+    )
+    add_rev_selection_flags(experiments_pull_parser, "Pull", False)
+    experiments_pull_parser.add_argument(
+        "-f",
+        "--force",
+        action="store_true",
+        help="Replace local experiment already exists.",
+    )
+    experiments_pull_parser.add_argument(
+        "--no-cache",
+        action="store_false",
+        dest="pull_cache",
+        help=(
+            "Do not pull cached outputs for this experiment from DVC remote "
+            "storage."
+        ),
+    )
+    experiments_pull_parser.add_argument(
+        "-r",
+        "--remote",
+        dest="dvc_remote",
+        metavar="<name>",
+        help="Name of the DVC remote to use when pulling cached outputs.",
+    )
+    experiments_pull_parser.add_argument(
+        "-j",
+        "--jobs",
+        type=int,
+        metavar="<number>",
+        help=(
+            "Number of jobs to run simultaneously when pulling from DVC "
+            "remote storage."
+        ),
+    )
+    experiments_pull_parser.add_argument(
+        "--run-cache",
+        action="store_true",
+        default=False,
+        help="Pull run history for all stages.",
+    )
+    experiments_pull_parser.add_argument(
+        "git_remote",
+        help="Git remote name or Git URL.",
+        metavar="<git_remote>",
+    )
+    experiments_pull_parser.add_argument(
+        "experiment",
+        nargs="*",
+        default=None,
+        help="Experiments to pull.",
+        metavar="<experiment>",
+    )
+    experiments_pull_parser.set_defaults(func=CmdExperimentsPull)

dvc/commands/experiments/push.py

@@ -0,0 +1,119 @@
+import argparse
+import logging
+
+from dvc.cli import completion
+from dvc.cli.command import CmdBase
+from dvc.cli.utils import append_doc_link
+from dvc.exceptions import InvalidArgumentError
+from dvc.ui import ui
+
+logger = logging.getLogger(__name__)
+
+
+class CmdExperimentsPush(CmdBase):
+    def raise_error_if_all_disabled(self):
+        if not any(
+            [self.args.experiment, self.args.all_commits, self.args.rev]
+        ):
+            raise InvalidArgumentError(
+                "Either provide an `experiment` argument, or use the "
+                "`--rev` or `--all-commits` flag."
+            )
+
+    def run(self):
+
+        self.raise_error_if_all_disabled()
+
+        pushed_exps = self.repo.experiments.push(
+            self.args.git_remote,
+            self.args.experiment,
+            all_commits=self.args.all_commits,
+            rev=self.args.rev,
+            num=self.args.num,
+            force=self.args.force,
+            push_cache=self.args.push_cache,
+            dvc_remote=self.args.dvc_remote,
+            jobs=self.args.jobs,
+            run_cache=self.args.run_cache,
+        )
+
+        if pushed_exps:
+            ui.write(
+                f"Pushed experiment '{pushed_exps}'"
+                f"to Git remote '{self.args.git_remote}'."
+            )
+        else:
+            ui.write("No experiments to push.")
+        if not self.args.push_cache:
+            ui.write(
+                "To push cached outputs",
+                "for this experiment to DVC remote storage,"
+                "re-run this command without '--no-cache'.",
+            )
+
+        return 0
+
+
+def add_parser(experiments_subparsers, parent_parser):
+    from . import add_rev_selection_flags
+
+    EXPERIMENTS_PUSH_HELP = "Push a local experiment to a Git remote."
+    experiments_push_parser = experiments_subparsers.add_parser(
+        "push",
+        parents=[parent_parser],
+        description=append_doc_link(EXPERIMENTS_PUSH_HELP, "exp/push"),
+        help=EXPERIMENTS_PUSH_HELP,
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+    )
+    add_rev_selection_flags(experiments_push_parser, "Push", False)
+    experiments_push_parser.add_argument(
+        "-f",
+        "--force",
+        action="store_true",
+        help="Replace experiment in the Git remote if it already exists.",
+    )
+    experiments_push_parser.add_argument(
+        "--no-cache",
+        action="store_false",
+        dest="push_cache",
+        help=(
+            "Do not push cached outputs for this experiment to DVC remote "
+            "storage."
+        ),
+    )
+    experiments_push_parser.add_argument(
+        "-r",
+        "--remote",
+        dest="dvc_remote",
+        metavar="<name>",
+        help="Name of the DVC remote to use when pushing cached outputs.",
+    )
+    experiments_push_parser.add_argument(
+        "-j",
+        "--jobs",
+        type=int,
+        metavar="<number>",
+        help=(
+            "Number of jobs to run simultaneously when pushing to DVC remote "
+            "storage."
+        ),
+    )
+    experiments_push_parser.add_argument(
+        "--run-cache",
+        action="store_true",
+        default=False,
+        help="Push run history for all stages.",
+    )
+    experiments_push_parser.add_argument(
+        "git_remote",
+        help="Git remote name or Git URL.",
+        metavar="<git_remote>",
+    )
+    experiments_push_parser.add_argument(
+        "experiment",
+        nargs="*",
+        default=None,
+        help="Experiments to push.",
+        metavar="<experiment>",
+    ).complete = completion.EXPERIMENT
+    experiments_push_parser.set_defaults(func=CmdExperimentsPush)

dvc/commands/experiments/queue_worker.py

@@ -0,0 +1,25 @@
+import logging
+
+from dvc.cli.command import CmdBase
+
+logger = logging.getLogger(__name__)
+
+
+class CmdQueueWorker(CmdBase):
+    """Run the exp queue worker."""
+
+    def run(self):
+        self.repo.experiments.celery_queue.worker.start(self.args.name)
+        return 0
+
+
+def add_parser(experiments_subparsers, parent_parser):
+    QUEUE_WORKER_HELP = "Run the exp queue worker."
+    parser = experiments_subparsers.add_parser(
+        "queue-worker",
+        parents=[parent_parser],
+        description=QUEUE_WORKER_HELP,
+        add_help=False,
+    )
+    parser.add_argument("name", help="Celery worker name.")
+    parser.set_defaults(func=CmdQueueWorker)

dvc/commands/experiments/remove.py

@@ -0,0 +1,72 @@
+import argparse
+import logging
+
+from dvc.cli.command import CmdBase
+from dvc.cli.utils import append_doc_link
+from dvc.exceptions import InvalidArgumentError
+from dvc.ui import ui
+
+logger = logging.getLogger(__name__)
+
+
+class CmdExperimentsRemove(CmdBase):
+    def check_arguments(self):
+        if not any(
+            [
+                self.args.all_commits,
+                self.args.rev,
+                self.args.queue,
+            ]
+        ) ^ bool(self.args.experiment):
+            raise InvalidArgumentError(
+                "Either provide an `experiment` argument, or use the "
+                "`--rev` or `--all-commits` or `--queue` flag."
+            )
+
+    def run(self):
+
+        self.check_arguments()
+
+        removed_list = self.repo.experiments.remove(
+            exp_names=self.args.experiment,
+            all_commits=self.args.all_commits,
+            rev=self.args.rev,
+            num=self.args.num,
+            queue=self.args.queue,
+            git_remote=self.args.git_remote,
+        )
+        removed = ",".join(removed_list)
+        ui.write(f"Removed experiments: {removed}")
+
+        return 0
+
+
+def add_parser(experiments_subparsers, parent_parser):
+    from . import add_rev_selection_flags
+
+    EXPERIMENTS_REMOVE_HELP = "Remove experiments."
+    experiments_remove_parser = experiments_subparsers.add_parser(
+        "remove",
+        parents=[parent_parser],
+        description=append_doc_link(EXPERIMENTS_REMOVE_HELP, "exp/remove"),
+        help=EXPERIMENTS_REMOVE_HELP,
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+    )
+    remove_group = experiments_remove_parser.add_mutually_exclusive_group()
+    add_rev_selection_flags(experiments_remove_parser, "Remove", False)
+    remove_group.add_argument(
+        "--queue", action="store_true", help="Remove all queued experiments."
+    )
+    remove_group.add_argument(
+        "-g",
+        "--git-remote",
+        metavar="<git_remote>",
+        help="Name or URL of the Git remote to remove the experiment from",
+    )
+    experiments_remove_parser.add_argument(
+        "experiment",
+        nargs="*",
+        help="Experiments to remove.",
+        metavar="<experiment>",
+    )
+    experiments_remove_parser.set_defaults(func=CmdExperimentsRemove)

dvc/commands/experiments/run.py

@@ -0,0 +1,142 @@
+import argparse
+import logging
+
+from dvc.cli import completion
+from dvc.cli.utils import append_doc_link
+from dvc.commands.repro import CmdRepro
+from dvc.commands.repro import add_arguments as add_repro_arguments
+from dvc.exceptions import InvalidArgumentError
+from dvc.ui import ui
+
+logger = logging.getLogger(__name__)
+
+
+class CmdExperimentsRun(CmdRepro):
+    def run(self):
+        from dvc.compare import show_metrics
+
+        if self.args.checkpoint_resume:
+            if self.args.reset:
+                raise InvalidArgumentError(
+                    "--reset and --rev are mutually exclusive."
+                )
+            if not (self.args.queue or self.args.tmp_dir):
+                raise InvalidArgumentError(
+                    "--rev can only be used in conjunction with "
+                    "--queue or --temp."
+                )
+
+        if self.args.reset:
+            ui.write("Any existing checkpoints will be reset and re-run.")
+
+        results = self.repo.experiments.run(
+            name=self.args.name,
+            queue=self.args.queue,
+            run_all=self.args.run_all,
+            jobs=self.args.jobs,
+            params=self.args.set_param,
+            checkpoint_resume=self.args.checkpoint_resume,
+            reset=self.args.reset,
+            tmp_dir=self.args.tmp_dir,
+            machine=self.args.machine,
+            **self._common_kwargs,
+        )
+
+        if self.args.metrics and results:
+            metrics = self.repo.metrics.show(revs=list(results))
+            metrics.pop("workspace", None)
+            show_metrics(metrics)
+
+        return 0
+
+
+def add_parser(experiments_subparsers, parent_parser):
+
+    EXPERIMENTS_RUN_HELP = "Run or resume an experiment."
+    experiments_run_parser = experiments_subparsers.add_parser(
+        "run",
+        parents=[parent_parser],
+        description=append_doc_link(EXPERIMENTS_RUN_HELP, "exp/run"),
+        help=EXPERIMENTS_RUN_HELP,
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+    )
+    _add_run_common(experiments_run_parser)
+    experiments_run_parser.add_argument(
+        "-r",
+        "--rev",
+        type=str,
+        dest="checkpoint_resume",
+        help=(
+            "Continue the specified checkpoint experiment. Can only be used "
+            "in conjunction with --queue or --temp."
+        ),
+        metavar="<experiment_rev>",
+    ).complete = completion.EXPERIMENT
+    experiments_run_parser.add_argument(
+        "--reset",
+        action="store_true",
+        help="Reset existing checkpoints and restart the experiment.",
+    )
+    experiments_run_parser.set_defaults(func=CmdExperimentsRun)
+
+
+def _add_run_common(parser):
+    """Add common args for 'exp run'."""
+    # inherit arguments from `dvc repro`
+    add_repro_arguments(parser)
+    parser.add_argument(
+        "-n",
+        "--name",
+        default=None,
+        help=(
+            "Human-readable experiment name. If not specified, a name will "
+            "be auto-generated."
+        ),
+        metavar="<name>",
+    )
+    parser.add_argument(
+        "-S",
+        "--set-param",
+        action="append",
+        default=[],
+        help="Use the specified param value when reproducing pipelines.",
+        metavar="[<filename>:]<param_name>=<param_value>",
+    )
+    parser.add_argument(
+        "--queue",
+        action="store_true",
+        default=False,
+        help="Stage this experiment in the run queue for future execution.",
+    )
+    parser.add_argument(
+        "--run-all",
+        action="store_true",
+        default=False,
+        help="Execute all experiments in the run queue. Implies --temp.",
+    )
+    parser.add_argument(
+        "-j",
+        "--jobs",
+        type=int,
+        default=1,
+        help="Run the specified number of experiments at a time in parallel.",
+        metavar="<number>",
+    )
+    parser.add_argument(
+        "--temp",
+        action="store_true",
+        dest="tmp_dir",
+        help=(
+            "Run this experiment in a separate temporary directory instead of "
+            "your workspace."
+        ),
+    )
+    parser.add_argument(
+        "--machine",
+        default=None,
+        help=argparse.SUPPRESS,
+        # help=(
+        #     "Run this experiment on the specified 'dvc machine' instance."
+        # )
+        # metavar="<name>",
+    )

dvc/commands/experiments/show.py

@@ -0,0 +1,666 @@
+import argparse
+import logging
+import os
+import re
+from collections import Counter, OrderedDict, defaultdict
+from datetime import date, datetime
+from typing import TYPE_CHECKING
+
+from funcy import lmap
+
+from dvc.cli import completion
+from dvc.cli.command import CmdBase
+from dvc.cli.utils import append_doc_link
+from dvc.commands.metrics import DEFAULT_PRECISION
+from dvc.exceptions import DvcException, InvalidArgumentError
+from dvc.ui import ui
+from dvc.utils.flatten import flatten
+from dvc.utils.serialize import encode_exception
+
+if TYPE_CHECKING:
+    from dvc.compare import TabularData
+    from dvc.ui import RichText
+
+FILL_VALUE = "-"
+FILL_VALUE_ERRORED = "!"
+
+
+logger = logging.getLogger(__name__)
+
+
+def _update_names(names, items):
+    for name, item in items:
+        item = item.get("data", {})
+        if isinstance(item, dict):
+            item = flatten(item)
+            names[name].update({key: None for key in item})
+
+
+def _collect_names(all_experiments, **kwargs):
+    metric_names = defaultdict(dict)
+    param_names = defaultdict(dict)
+    deps_names = set()
+
+    for _, experiments in all_experiments.items():
+        for exp_data in experiments.values():
+            exp = exp_data.get("data", {})
+            _update_names(metric_names, exp.get("metrics", {}).items())
+            _update_names(param_names, exp.get("params", {}).items())
+            for dep_name in exp.get("deps", {}):
+                deps_names.add(dep_name)
+
+    return metric_names, param_names, sorted(deps_names)
+
+
+experiment_types = {
+    "checkpoint_tip": "│ ╓",
+    "checkpoint_commit": "│ ╟",
+    "checkpoint_base": "├─╨",
+    "branch_commit": "├──",
+    "branch_base": "└──",
+    "baseline": "",
+}
+
+
+def _collect_rows(
+    base_rev,
+    experiments,
+    all_headers,
+    metric_headers,
+    param_headers,
+    metric_names,
+    param_names,
+    deps_names,
+    precision=DEFAULT_PRECISION,
+    sort_by=None,
+    sort_order=None,
+    fill_value=FILL_VALUE,
+    iso=False,
+):
+    from scmrepo.git import Git
+
+    if sort_by:
+        sort_path, sort_name, sort_type = _sort_column(
+            sort_by, metric_names, param_names
+        )
+        reverse = sort_order == "desc"
+        experiments = _sort_exp(
+            experiments, sort_path, sort_name, sort_type, reverse
+        )
+
+    new_checkpoint = True
+    for i, (rev, results) in enumerate(experiments.items()):
+        fill_value = FILL_VALUE_ERRORED if results.get("error") else fill_value
+        row_dict = {k: fill_value for k in all_headers}
+
+        exp = results.get("data", {})
+
+        state = exp.get("status")
+        if state == "Success":
+            state = fill_value
+
+        is_baseline = rev == "baseline"
+
+        if is_baseline:
+            name_rev = base_rev[:7] if Git.is_sha(base_rev) else base_rev
+        else:
+            name_rev = rev[:7]
+
+        tip = exp.get("checkpoint_tip")
+        parent_rev = exp.get("checkpoint_parent", "")
+        parent_exp = experiments.get(parent_rev, {}).get("data", {})
+        parent_tip = parent_exp.get("checkpoint_tip")
+
+        parent = ""
+        if is_baseline:
+            typ = "baseline"
+        elif tip:
+            if tip == parent_tip:
+                typ = (
+                    "checkpoint_tip" if new_checkpoint else "checkpoint_commit"
+                )
+            elif parent_rev == base_rev:
+                typ = "checkpoint_base"
+            else:
+                typ = "checkpoint_commit"
+                parent = parent_rev[:7]
+        elif i < len(experiments) - 1:
+            typ = "branch_commit"
+        else:
+            typ = "branch_base"
+
+        if not is_baseline:
+            new_checkpoint = not (tip and tip == parent_tip)
+
+        row_dict["Experiment"] = exp.get("name", "")
+        row_dict["rev"] = name_rev
+        row_dict["typ"] = typ
+        row_dict["Created"] = format_time(
+            exp.get("timestamp"), fill_value, iso
+        )
+        row_dict["parent"] = parent
+        row_dict["State"] = state
+        row_dict["Executor"] = exp.get("executor", fill_value)
+
+        _extend_row(
+            row_dict,
+            metric_names,
+            metric_headers,
+            exp.get("metrics", {}).items(),
+            precision,
+            fill_value=fill_value,
+        )
+        _extend_row(
+            row_dict,
+            param_names,
+            param_headers,
+            exp.get("params", {}).items(),
+            precision,
+            fill_value=fill_value,
+        )
+        for dep in deps_names:
+            hash_info = exp.get("deps", {}).get(dep, {}).get("hash")
+            if hash_info is not None:
+                hash_info = hash_info[:7]
+            row_dict[dep] = hash_info
+        yield list(row_dict.values())
+
+
+def _sort_column(sort_by, metric_names, param_names):
+    path, _, sort_name = sort_by.rpartition(":")
+    matches = set()
+
+    if path:
+        if path in metric_names and sort_name in metric_names[path]:
+            matches.add((path, sort_name, "metrics"))
+        if path in param_names and sort_name in param_names[path]:
+            matches.add((path, sort_name, "params"))
+    else:
+        for path in metric_names:
+            if sort_name in metric_names[path]:
+                matches.add((path, sort_name, "metrics"))
+        for path in param_names:
+            if sort_name in param_names[path]:
+                matches.add((path, sort_name, "params"))
+
+    if len(matches) == 1:
+        return matches.pop()
+    if len(matches) > 1:
+        raise InvalidArgumentError(
+            "Ambiguous sort column '{}' matched '{}'".format(
+                sort_by,
+                ", ".join([f"{path}:{name}" for path, name, _ in matches]),
+            )
+        )
+    raise InvalidArgumentError(f"Unknown sort column '{sort_by}'")
+
+
+def _sort_exp(experiments, sort_path, sort_name, typ, reverse):
+    def _sort(item):
+        rev, exp = item
+        exp_data = exp.get("data", {})
+        tip = exp_data.get("checkpoint_tip")
+        if tip and tip != rev:
+            # Sort checkpoint experiments by tip commit
+            return _sort((tip, experiments[tip]))
+        data = exp_data.get(typ, {}).get(sort_path, {}).get("data", {})
+        val = flatten(data).get(sort_name)
+        return val is None, val
+
+    ret = OrderedDict()
+    if "baseline" in experiments:
+        ret["baseline"] = experiments.pop("baseline")
+
+    ret.update(sorted(experiments.items(), key=_sort, reverse=reverse))
+    return ret
+
+
+def format_time(datetime_obj, fill_value=FILL_VALUE, iso=False):
+    if datetime_obj is None:
+        return fill_value
+
+    if iso:
+        return datetime_obj.isoformat()
+
+    if datetime_obj.date() == date.today():
+        fmt = "%I:%M %p"
+    else:
+        fmt = "%b %d, %Y"
+    return datetime_obj.strftime(fmt)
+
+
+def _extend_row(row, names, headers, items, precision, fill_value=FILL_VALUE):
+    from dvc.compare import _format_field, with_value
+
+    for fname, data in items:
+        item = data.get("data", {})
+        item = flatten(item) if isinstance(item, dict) else {fname: item}
+        for name in names[fname]:
+            value = with_value(
+                item.get(name),
+                FILL_VALUE_ERRORED if data.get("error", None) else fill_value,
+            )
+            # wrap field data in ui.rich_text, otherwise rich may
+            # interpret unescaped braces from list/dict types as rich
+            # markup tags
+            value = ui.rich_text(str(_format_field(value, precision)))
+            if name in headers:
+                row[name] = value
+            else:
+                row[f"{fname}:{name}"] = value
+
+
+def experiments_table(
+    all_experiments,
+    headers,
+    metric_headers,
+    metric_names,
+    param_headers,
+    param_names,
+    deps_names,
+    sort_by=None,
+    sort_order=None,
+    precision=DEFAULT_PRECISION,
+    fill_value=FILL_VALUE,
+    iso=False,
+) -> "TabularData":
+    from funcy import lconcat
+
+    from dvc.compare import TabularData
+
+    all_headers = lconcat(headers, metric_headers, param_headers, deps_names)
+    td = TabularData(all_headers, fill_value=fill_value)
+    for base_rev, experiments in all_experiments.items():
+        rows = _collect_rows(
+            base_rev,
+            experiments,
+            all_headers,
+            metric_headers,
+            param_headers,
+            metric_names,
+            param_names,
+            deps_names,
+            sort_by=sort_by,
+            sort_order=sort_order,
+            precision=precision,
+            fill_value=fill_value,
+            iso=iso,
+        )
+        td.extend(rows)
+
+    return td
+
+
+def prepare_exp_id(kwargs) -> "RichText":
+    exp_name = kwargs["Experiment"]
+    rev = kwargs["rev"]
+    typ = kwargs.get("typ", "baseline")
+
+    if typ == "baseline" or not exp_name:
+        text = ui.rich_text(exp_name or rev)
+    else:
+        text = ui.rich_text.assemble(rev, " [", (exp_name, "bold"), "]")
+
+    parent = kwargs.get("parent")
+    suff = f" ({parent})" if parent else ""
+    text.append(suff)
+
+    tree = experiment_types[typ]
+    pref = f"{tree} " if tree else ""
+    return ui.rich_text(pref) + text
+
+
+def baseline_styler(typ):
+    return {"style": "bold"} if typ == "baseline" else {}
+
+
+def show_experiments(
+    all_experiments,
+    keep=None,
+    drop=None,
+    pager=True,
+    csv=False,
+    markdown=False,
+    pcp=False,
+    **kwargs,
+):
+    from funcy.seqs import flatten as flatten_list
+
+    metric_names, param_names, deps_names = _collect_names(all_experiments)
+
+    headers = [
+        "Experiment",
+        "rev",
+        "typ",
+        "Created",
+        "parent",
+        "State",
+        "Executor",
+    ]
+
+    names = {**metric_names, **param_names}
+    counter = Counter(flatten_list([list(a.keys()) for a in names.values()]))
+    counter.update(headers)
+    metric_headers = _normalize_headers(metric_names, counter)
+    param_headers = _normalize_headers(param_names, counter)
+
+    td = experiments_table(
+        all_experiments,
+        headers,
+        metric_headers,
+        metric_names,
+        param_headers,
+        param_names,
+        deps_names,
+        kwargs.get("sort_by"),
+        kwargs.get("sort_order"),
+        kwargs.get("precision"),
+        kwargs.get("fill_value"),
+        kwargs.get("iso"),
+    )
+    if keep:
+        for col in td.keys():
+            if re.match(keep, col):
+                td.protect(col)
+
+    for col in ("State", "Executor"):
+        if td.is_empty(col):
+            td.drop(col)
+
+    row_styles = lmap(baseline_styler, td.column("typ"))
+
+    if not csv:
+        merge_headers = ["Experiment", "rev", "typ", "parent"]
+        td.column("Experiment")[:] = map(
+            prepare_exp_id, td.as_dict(merge_headers)
+        )
+        td.drop(*merge_headers[1:])
+
+    headers = {
+        "metrics": metric_headers,
+        "params": param_headers,
+        "deps": deps_names,
+    }
+    styles = {
+        "Experiment": {"no_wrap": True, "header_style": "black on grey93"},
+        "Created": {"header_style": "black on grey93"},
+        "State": {"header_style": "black on grey93"},
+        "Executor": {"header_style": "black on grey93"},
+    }
+    header_bg_colors = {
+        "metrics": "cornsilk1",
+        "params": "light_cyan1",
+        "deps": "plum2",
+    }
+    styles.update(
+        {
+            header: {
+                "justify": "right" if typ == "metrics" else "left",
+                "header_style": f"black on {header_bg_colors[typ]}",
+                "collapse": idx != 0,
+                "no_wrap": typ == "metrics",
+            }
+            for typ, hs in headers.items()
+            for idx, header in enumerate(hs)
+        }
+    )
+
+    if kwargs.get("only_changed", False) or pcp:
+        td.drop_duplicates("cols", ignore_empty=False)
+
+    cols_to_drop = set()
+    if drop is not None:
+        cols_to_drop = {col for col in td.keys() if re.match(drop, col)}
+    if pcp:
+        cols_to_drop.add("Created")
+    td.drop(*cols_to_drop)
+
+    if pcp:
+        subset = {x for x in td.keys() if x != "Experiment"}
+        td.dropna(
+            "rows",
+            how="all",
+            subset=subset,
+        )
+        td.drop_duplicates("rows", subset=subset)
+        if "Experiment" in td:
+            td.column("Experiment")[:] = [
+                # remove tree characters
+                str(x).encode("ascii", "ignore").strip().decode()
+                for x in td.column("Experiment")
+            ]
+        out = kwargs.get("out") or "dvc_plots"
+        output_file = os.path.join(out, "index.html")
+        ui.write(
+            td.to_parallel_coordinates(
+                output_path=os.path.abspath(output_file),
+                color_by=kwargs.get("sort_by") or "Experiment",
+            )
+        )
+        if kwargs.get("open"):
+            return ui.open_browser(output_file)
+
+    else:
+        td.render(
+            pager=pager,
+            borders="horizontals",
+            rich_table=True,
+            header_styles=styles,
+            row_styles=row_styles,
+            csv=csv,
+            markdown=markdown,
+        )
+
+
+def _normalize_headers(names, count):
+    return [
+        name if count[name] == 1 else f"{path}:{name}"
+        for path in names
+        for name in names[path]
+    ]
+
+
+def _format_json(item):
+    if isinstance(item, (date, datetime)):
+        return item.isoformat()
+    return encode_exception(item)
+
+
+class CmdExperimentsShow(CmdBase):
+    def run(self):
+        try:
+            all_experiments = self.repo.experiments.show(
+                all_branches=self.args.all_branches,
+                all_tags=self.args.all_tags,
+                all_commits=self.args.all_commits,
+                hide_queued=self.args.hide_queued,
+                hide_failed=self.args.hide_failed,
+                revs=self.args.rev,
+                num=self.args.num,
+                sha_only=self.args.sha,
+                param_deps=self.args.param_deps,
+                fetch_running=self.args.fetch_running,
+            )
+        except DvcException:
+            logger.exception("failed to show experiments")
+            return 1
+
+        if self.args.json:
+            ui.write_json(all_experiments, default=_format_json)
+        else:
+            precision = (
+                self.args.precision or None
+                if self.args.csv
+                else DEFAULT_PRECISION
+            )
+            fill_value = "" if self.args.csv else FILL_VALUE
+            iso = True if self.args.csv else False
+
+            show_experiments(
+                all_experiments,
+                keep=self.args.keep,
+                drop=self.args.drop,
+                sort_by=self.args.sort_by,
+                sort_order=self.args.sort_order,
+                precision=precision,
+                fill_value=fill_value,
+                iso=iso,
+                pager=not self.args.no_pager,
+                csv=self.args.csv,
+                markdown=self.args.markdown,
+                only_changed=self.args.only_changed,
+                pcp=self.args.pcp,
+                out=self.args.out,
+                open=self.args.open,
+            )
+        return 0
+
+
+def add_parser(experiments_subparsers, parent_parser):
+    from . import add_rev_selection_flags
+
+    EXPERIMENTS_SHOW_HELP = "Print experiments."
+    experiments_show_parser = experiments_subparsers.add_parser(
+        "show",
+        parents=[parent_parser],
+        description=append_doc_link(EXPERIMENTS_SHOW_HELP, "exp/show"),
+        help=EXPERIMENTS_SHOW_HELP,
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+    )
+    add_rev_selection_flags(experiments_show_parser, "Show")
+    experiments_show_parser.add_argument(
+        "-a",
+        "--all-branches",
+        action="store_true",
+        default=False,
+        help="Show experiments derived from the tip of all Git branches.",
+    )
+    experiments_show_parser.add_argument(
+        "-T",
+        "--all-tags",
+        action="store_true",
+        default=False,
+        help="Show experiments derived from all Git tags.",
+    )
+    experiments_show_parser.add_argument(
+        "--no-pager",
+        action="store_true",
+        default=False,
+        help="Do not pipe output into a pager.",
+    )
+    experiments_show_parser.add_argument(
+        "--only-changed",
+        action="store_true",
+        default=False,
+        help=(
+            "Only show metrics/params with values varying "
+            "across the selected experiments."
+        ),
+    )
+    experiments_show_parser.add_argument(
+        "--drop",
+        help="Remove the columns matching the specified regex pattern.",
+        metavar="<regex_pattern>",
+    )
+    experiments_show_parser.add_argument(
+        "--keep",
+        help="Preserve the columns matching the specified regex pattern.",
+        metavar="<regex_pattern>",
+    )
+    experiments_show_parser.add_argument(
+        "--param-deps",
+        action="store_true",
+        default=False,
+        help="Show only params that are stage dependencies.",
+    )
+    experiments_show_parser.add_argument(
+        "--sort-by",
+        help="Sort related experiments by the specified metric or param.",
+        metavar="<metric/param>",
+    )
+    experiments_show_parser.add_argument(
+        "--sort-order",
+        help=(
+            "Sort order to use with --sort-by."
+            " Defaults to ascending ('asc')."
+        ),
+        choices=("asc", "desc"),
+        default="asc",
+    )
+    experiments_show_parser.add_argument(
+        "--sha",
+        action="store_true",
+        default=False,
+        help="Always show git commit SHAs instead of branch/tag names.",
+    )
+    experiments_show_parser.add_argument(
+        "--hide-failed",
+        action="store_true",
+        default=False,
+        help="Hide failed experiments in the table.",
+    )
+    experiments_show_parser.add_argument(
+        "--hide-queued",
+        action="store_true",
+        default=False,
+        help="Hide queued experiments in the table.",
+    )
+    experiments_show_parser.add_argument(
+        "--json",
+        "--show-json",
+        action="store_true",
+        default=False,
+        help="Print output in JSON format instead of a human-readable table.",
+    )
+    experiments_show_parser.add_argument(
+        "--csv",
+        "--show-csv",
+        action="store_true",
+        default=False,
+        help="Print output in csv format instead of a human-readable table.",
+    )
+    experiments_show_parser.add_argument(
+        "--md",
+        "--show-md",
+        action="store_true",
+        default=False,
+        dest="markdown",
+        help="Show tabulated output in the Markdown format (GFM).",
+    )
+    experiments_show_parser.add_argument(
+        "--precision",
+        type=int,
+        help=(
+            "Round metrics/params to `n` digits precision after the decimal "
+            f"point. Rounds to {DEFAULT_PRECISION} digits by default."
+        ),
+        metavar="<n>",
+    )
+    experiments_show_parser.add_argument(
+        "--parallel-coordinates-plot",
+        "--pcp",
+        dest="pcp",
+        action="store_true",
+        default=False,
+        help="Generate a Parallel Coordinates Plot from the tabulated output.",
+    )
+    experiments_show_parser.add_argument(
+        "-o",
+        "--out",
+        default=None,
+        help="Destination folder to save the Parallel Coordinates Plot to",
+        metavar="<path>",
+    ).complete = completion.DIR
+    experiments_show_parser.add_argument(
+        "--open",
+        action="store_true",
+        default=False,
+        help="Open the Parallel Coordinates Plot directly in the browser.",
+    )
+    experiments_show_parser.add_argument(
+        "--no-fetch",
+        dest="fetch_running",
+        action="store_false",
+        help=argparse.SUPPRESS,
+    )
+    experiments_show_parser.set_defaults(func=CmdExperimentsShow)

dvc/commands/freeze.py

@@ -1,8 +1,9 @@
 import argparse
 import logging
 
-from dvc.command import completion
-from dvc.command.base import CmdBase, append_doc_link
+from dvc.cli import completion
+from dvc.cli.command import CmdBase
+from dvc.cli.utils import append_doc_link
 from dvc.exceptions import DvcException
 
 logger = logging.getLogger(__name__)
@@ -15,7 +16,7 @@ class CmdFreezeBase(CmdBase):
             try:
                 func(target)
             except DvcException:
-                logger.exception(f"failed to {name} '{target}'")
+                logger.exception("failed to %s '%s'", name, target)
                 ret = 1
         return ret
 

dvc/commands/gc.py

@@ -2,7 +2,8 @@ import argparse
 import logging
 import os
 
-from dvc.command.base import CmdBase, append_doc_link
+from dvc.cli.command import CmdBase
+from dvc.cli.utils import append_doc_link
 from dvc.ui import ui
 
 logger = logging.getLogger(__name__)
@@ -10,29 +11,46 @@ logger = logging.getLogger(__name__)
 
 class CmdGC(CmdBase):
     def run(self):
-        from dvc.repo.gc import _raise_error_if_all_disabled
+        from dvc.repo.gc import _validate_args
 
-        _raise_error_if_all_disabled(
+        _validate_args(
             all_branches=self.args.all_branches,
             all_tags=self.args.all_tags,
             all_commits=self.args.all_commits,
+            all_experiments=self.args.all_experiments,
+            commit_date=self.args.commit_date,
             workspace=self.args.workspace,
+            rev=self.args.rev,
+            num=self.args.num,
         )
 
+        if self.args.rev:
+            self.args.num = self.args.num or 1
+
         msg = "This will remove all cache except items used in "
 
         msg += "the workspace"
         if self.args.all_commits:
             msg += " and all git commits"
-        elif self.args.all_branches and self.args.all_tags:
-            msg += " and all git branches and tags"
-        elif self.args.all_branches:
-            msg += " and all git branches"
-        elif self.args.all_tags:
-            msg += " and all git tags"
-        elif self.args.all_experiments:
-            msg += " and all experiments"
+        else:
+            if self.args.all_branches and self.args.all_tags:
+                msg += " and all git branches and tags"
+            elif self.args.all_branches:
+                msg += " and all git branches"
+            elif self.args.all_tags:
+                msg += " and all git tags"
+            if self.args.commit_date:
+                msg += (
+                    " and all git commits before date "
+                    f"{self.args.commit_date}"
+                )
+            if self.args.rev:
+                msg += (
+                    f" and last {self.args.num} commits from {self.args.rev}"
+                )
 
+        if self.args.all_experiments:
+            msg += " and all experiments"
         if self.args.repos:
             msg += " of the current and the following repos:"
 
@@ -52,12 +70,15 @@ class CmdGC(CmdBase):
             all_tags=self.args.all_tags,
             all_commits=self.args.all_commits,
             all_experiments=self.args.all_experiments,
+            commit_date=self.args.commit_date,
             cloud=self.args.cloud,
             remote=self.args.remote,
             force=self.args.force,
             jobs=self.args.jobs,
             repos=self.args.repos,
             workspace=self.args.workspace,
+            rev=self.args.rev,
+            num=self.args.num,
         )
         return 0
 
@@ -82,6 +103,26 @@ def add_parser(subparsers, parent_parser):
         default=False,
         help="Keep data files used in the current workspace.",
     )
+    gc_parser.add_argument(
+        "--rev",
+        type=str,
+        default=None,
+        help="Keep data files used in the specified <commit>.",
+        metavar="<commit>",
+    )
+    gc_parser.add_argument(
+        "-n",
+        "--num",
+        type=int,
+        dest="num",
+        metavar="<num>",
+        help=(
+            "Keep data files used in the last `num` commits "
+            "starting from the `--rev` <commit>. "
+            "Only used if `--rev` is also provided. "
+            "Defaults to `1`."
+        ),
+    )
     gc_parser.add_argument(
         "-a",
         "--all-branches",
@@ -103,6 +144,18 @@ def add_parser(subparsers, parent_parser):
         default=False,
         help="Keep data files for all Git commits.",
     )
+    gc_parser.add_argument(
+        "--date",
+        type=str,
+        dest="commit_date",
+        metavar="<YYYY-MM-DD>",
+        default=None,
+        help=(
+            "Keep cached data referenced in the commits after ( inclusive )"
+            " a certain time. Date must match the extended ISO 8601 format "
+            "(YYYY-MM-DD)."
+        ),
+    )
     gc_parser.add_argument(
         "--all-experiments",
         action="store_true",
@@ -136,7 +189,6 @@ def add_parser(subparsers, parent_parser):
         help=(
             "Number of jobs to run simultaneously. "
             "The default value is 4 * cpu_count(). "
-            "For SSH remotes, the default is 4. "
         ),
         metavar="<number>",
     )

dvc/commands/get.py

@@ -1,10 +1,11 @@
 import argparse
 import logging
 
+from dvc.cli import completion
+from dvc.cli.command import CmdBaseNoRepo
 from dvc.exceptions import DvcException
 
-from . import completion
-from .base import CmdBaseNoRepo, append_doc_link
+from ..cli.utils import append_doc_link
 
 logger = logging.getLogger(__name__)
 
@@ -93,7 +94,6 @@ def add_parser(subparsers, parent_parser):
         help=(
             "Number of jobs to run simultaneously. "
             "The default value is 4 * cpu_count(). "
-            "For SSH remotes, the default is 4. "
         ),
         metavar="<number>",
     )

dvc/commands/get_url.py

@@ -1,10 +1,11 @@
 import argparse
 import logging
 
+from dvc.cli import completion
+from dvc.cli.command import CmdBaseNoRepo
 from dvc.exceptions import DvcException
 
-from . import completion
-from .base import CmdBaseNoRepo, append_doc_link
+from ..cli.utils import append_doc_link
 
 logger = logging.getLogger(__name__)
 
@@ -17,7 +18,7 @@ class CmdGetUrl(CmdBaseNoRepo):
             Repo.get_url(self.args.url, out=self.args.out, jobs=self.args.jobs)
             return 0
         except DvcException:
-            logger.exception(f"failed to get '{self.args.url}'")
+            logger.exception("failed to get '%s'", self.args.url)
             return 1
 
 
@@ -43,7 +44,6 @@ def add_parser(subparsers, parent_parser):
         help=(
             "Number of jobs to run simultaneously. "
             "The default value is 4 * cpu_count(). "
-            "For SSH remotes, the default is 4. "
         ),
         metavar="<number>",
     )

dvc/commands/git_hook.py

@@ -1,7 +1,8 @@
 import logging
 import os
 
-from dvc.command.base import CmdBaseNoRepo, fix_subparsers
+from dvc.cli.command import CmdBaseNoRepo
+from dvc.cli.utils import fix_subparsers
 from dvc.exceptions import NotDvcRepoError
 
 logger = logging.getLogger(__name__)
@@ -25,7 +26,7 @@ class CmdHookBase(CmdBaseNoRepo):
 
 class CmdPreCommit(CmdHookBase):
     def _run(self):
-        from dvc.main import main
+        from dvc.cli import main
 
         return main(["status"])
 
@@ -49,14 +50,14 @@ class CmdPostCheckout(CmdHookBase):
         if os.path.isdir(os.path.join(".git", "rebase-merge")):
             return 0
 
-        from dvc.main import main
+        from dvc.cli import main
 
         return main(["checkout"])
 
 
 class CmdPrePush(CmdHookBase):
     def _run(self):
-        from dvc.main import main
+        from dvc.cli import main
 
         return main(["push"])
 
@@ -73,7 +74,7 @@ class CmdMergeDriver(CmdHookBase):
             our = Dvcfile(dvc, self.args.our, verify=False)
             their = Dvcfile(dvc, self.args.their, verify=False)
 
-            our.merge(ancestor, their)
+            our.merge(ancestor, their, allowed=["add", "remove", "change"])
 
             return 0
         finally:

dvc/commands/imp.py

@@ -1,8 +1,9 @@
 import argparse
 import logging
 
-from dvc.command import completion
-from dvc.command.base import CmdBase, append_doc_link
+from dvc.cli import completion
+from dvc.cli.command import CmdBase
+from dvc.cli.utils import append_doc_link
 from dvc.exceptions import DvcException
 
 logger = logging.getLogger(__name__)
@@ -18,7 +19,11 @@ class CmdImport(CmdBase):
                 fname=self.args.file,
                 rev=self.args.rev,
                 no_exec=self.args.no_exec,
+                no_download=self.args.no_download,
                 desc=self.args.desc,
+                type=self.args.type,
+                labels=self.args.labels,
+                meta=self.args.meta,
                 jobs=self.args.jobs,
             )
         except DvcException:
@@ -32,6 +37,8 @@ class CmdImport(CmdBase):
 
 
 def add_parser(subparsers, parent_parser):
+    from .add import _add_annotating_args
+
     IMPORT_HELP = (
         "Download file or directory tracked by DVC or by Git "
         "into the workspace, and track it."
@@ -68,20 +75,19 @@ def add_parser(subparsers, parent_parser):
         help="Specify name of the .dvc file this command will generate.",
         metavar="<filename>",
     )
-    import_parser.add_argument(
+    no_download_exec_group = import_parser.add_mutually_exclusive_group()
+    no_download_exec_group.add_argument(
         "--no-exec",
         action="store_true",
         default=False,
-        help="Only create .dvc file without actually downloading it.",
+        help="Only create .dvc file without actually importing target data.",
     )
-    import_parser.add_argument(
-        "--desc",
-        type=str,
-        metavar="<text>",
-        help=(
-            "User description of the data (optional). "
-            "This doesn't affect any DVC operations."
-        ),
+    no_download_exec_group.add_argument(
+        "--no-download",
+        action="store_true",
+        default=False,
+        help="Create .dvc file including target data hash value(s)"
+        " but do not actually download the file(s).",
     )
     import_parser.add_argument(
         "-j",
@@ -90,8 +96,9 @@ def add_parser(subparsers, parent_parser):
         help=(
             "Number of jobs to run simultaneously. "
             "The default value is 4 * cpu_count(). "
-            "For SSH remotes, the default is 4. "
         ),
         metavar="<number>",
     )
+
+    _add_annotating_args(import_parser)
     import_parser.set_defaults(func=CmdImport)

dvc/commands/imp_url.py

@@ -1,8 +1,9 @@
 import argparse
 import logging
 
-from dvc.command import completion
-from dvc.command.base import CmdBase, append_doc_link
+from dvc.cli import completion
+from dvc.cli.command import CmdBase
+from dvc.cli.utils import append_doc_link
 from dvc.exceptions import DvcException
 
 logger = logging.getLogger(__name__)
@@ -16,10 +17,15 @@ class CmdImportUrl(CmdBase):
                 out=self.args.out,
                 fname=self.args.file,
                 no_exec=self.args.no_exec,
+                no_download=self.args.no_download,
                 remote=self.args.remote,
                 to_remote=self.args.to_remote,
                 desc=self.args.desc,
+                type=self.args.type,
+                labels=self.args.labels,
+                meta=self.args.meta,
                 jobs=self.args.jobs,
+                version_aware=self.args.version_aware,
             )
         except DvcException:
             logger.exception(
@@ -33,6 +39,8 @@ class CmdImportUrl(CmdBase):
 
 
 def add_parser(subparsers, parent_parser):
+    from .add import _add_annotating_args
+
     IMPORT_HELP = (
         "Download or copy file from URL and take it under DVC control."
     )
@@ -65,11 +73,19 @@ def add_parser(subparsers, parent_parser):
         help="Specify name of the .dvc file this command will generate.",
         metavar="<filename>",
     ).complete = completion.DIR
-    import_parser.add_argument(
+    no_download_exec_group = import_parser.add_mutually_exclusive_group()
+    no_download_exec_group.add_argument(
         "--no-exec",
         action="store_true",
         default=False,
-        help="Only create .dvc file without actually downloading it.",
+        help="Only create .dvc file without actually importing target data.",
+    )
+    no_download_exec_group.add_argument(
+        "--no-download",
+        action="store_true",
+        default=False,
+        help="Create .dvc file including target data hash value(s)"
+        " but do not actually download the file(s).",
     )
     import_parser.add_argument(
         "--to-remote",
@@ -90,17 +106,17 @@ def add_parser(subparsers, parent_parser):
         help=(
             "Number of jobs to run simultaneously. "
             "The default value is 4 * cpu_count(). "
-            "For SSH remotes, the default is 4. "
         ),
         metavar="<number>",
     )
     import_parser.add_argument(
-        "--desc",
-        type=str,
-        metavar="<text>",
+        "--version-aware",
+        action="store_true",
+        default=False,
         help=(
-            "User description of the data (optional). "
-            "This doesn't affect any DVC operations."
+            "Import using cloud versioning. Implied if the URL contains a "
+            "version ID."
         ),
     )
+    _add_annotating_args(import_parser)
     import_parser.set_defaults(func=CmdImportUrl)

dvc/commands/init.py

@@ -4,7 +4,8 @@ import logging
 import colorama
 
 from dvc import analytics
-from dvc.command.base import CmdBaseNoRepo, append_doc_link
+from dvc.cli.command import CmdBaseNoRepo
+from dvc.cli.utils import append_doc_link
 from dvc.utils import boxify
 from dvc.utils import format_link as fmt_link
 

dvc/commands/install.py

@@ -1,7 +1,8 @@
 import argparse
 import logging
 
-from dvc.command.base import CmdBase, append_doc_link
+from dvc.cli.command import CmdBase
+from dvc.cli.utils import append_doc_link
 from dvc.exceptions import DvcException
 
 logger = logging.getLogger(__name__)

dvc/commands/ls/__init__.py

@@ -1,9 +1,10 @@
 import argparse
 import logging
 
-from dvc.command import completion
-from dvc.command.base import CmdBaseNoRepo, append_doc_link
-from dvc.command.ls.ls_colors import LsColors
+from dvc.cli import completion
+from dvc.cli.command import CmdBaseNoRepo
+from dvc.cli.utils import append_doc_link
+from dvc.commands.ls.ls_colors import LsColors
 from dvc.exceptions import DvcException
 from dvc.ui import ui
 
@@ -41,7 +42,7 @@ class CmdList(CmdBaseNoRepo):
                 ui.write("\n".join(entries))
             return 0
         except DvcException:
-            logger.exception(f"failed to list '{self.args.url}'")
+            logger.exception("failed to list '%s'", self.args.url)
             return 1
 
 

dvc/commands/ls_url.py

@@ -0,0 +1,43 @@
+import argparse
+import logging
+
+from dvc.cli.command import CmdBaseNoRepo
+from dvc.cli.utils import append_doc_link
+from dvc.ui import ui
+
+from .ls import _prettify
+
+logger = logging.getLogger(__name__)
+
+
+class CmdListUrl(CmdBaseNoRepo):
+    def run(self):
+        from dvc.repo import Repo
+
+        entries = Repo.ls_url(self.args.url, recursive=self.args.recursive)
+        if entries:
+            entries = _prettify(entries, with_color=True)
+            ui.write("\n".join(entries))
+        return 0
+
+
+def add_parser(subparsers, parent_parser):
+    LS_HELP = "List directory contents from URL."
+    lsurl_parser = subparsers.add_parser(
+        "list-url",
+        aliases=["ls-url"],
+        parents=[parent_parser],
+        description=append_doc_link(LS_HELP, "list-url"),
+        help=LS_HELP,
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+    )
+    lsurl_parser.add_argument(
+        "url", help="See `dvc import-url -h` for full list of supported URLs."
+    )
+    lsurl_parser.add_argument(
+        "-R",
+        "--recursive",
+        action="store_true",
+        help="Recursively list files.",
+    )
+    lsurl_parser.set_defaults(func=CmdListUrl)

dvc/commands/machine.py

@@ -1,7 +1,8 @@
 import argparse
 
-from dvc.command.base import CmdBase, append_doc_link, fix_subparsers
-from dvc.command.config import CmdConfig
+from dvc.cli.command import CmdBase
+from dvc.cli.utils import append_doc_link, fix_subparsers
+from dvc.commands.config import CmdConfig
 from dvc.compare import TabularData
 from dvc.config import ConfigError
 from dvc.exceptions import DvcException
@@ -241,6 +242,7 @@ class CmdMachineStatus(CmdBase):
         "instance_hdd_size",
         "instance_gpu",
     ]
+    FILL_VALUE = "-"
 
     def _add_row(
         self,
@@ -250,7 +252,11 @@ class CmdMachineStatus(CmdBase):
     ):
 
         if not all_status:
-            row = [name, None, "offline"]
+            row = [
+                name,
+                self.FILL_VALUE,
+                "offline",
+            ]  # back to `None` after #7167
             td.append(row)
         for i, status in enumerate(all_status, start=1):
             row = [name, f"num_{i}", "running" if status else "offline"]
@@ -264,7 +270,7 @@ class CmdMachineStatus(CmdBase):
             raise MachineDisabledError
 
         td = TabularData(
-            self.INSTANCE_FIELD + self.SHOWN_FIELD, fill_value="-"
+            self.INSTANCE_FIELD + self.SHOWN_FIELD, fill_value=self.FILL_VALUE
         )
 
         if self.args.name:
@@ -304,7 +310,7 @@ class CmdMachineSsh(CmdBase):
 
 
 def add_parser(subparsers, parent_parser):
-    from dvc.command.config import parent_config_parser
+    from dvc.commands.config import parent_config_parser
 
     machine_HELP = "Set up and manage cloud machines."
     machine_parser = subparsers.add_parser(

dvc/commands/metrics.py

@@ -1,8 +1,9 @@
 import argparse
 import logging
 
-from dvc.command import completion
-from dvc.command.base import CmdBase, append_doc_link, fix_subparsers
+from dvc.cli import completion
+from dvc.cli.command import CmdBase
+from dvc.cli.utils import append_doc_link, fix_subparsers
 from dvc.exceptions import DvcException
 from dvc.ui import ui
 from dvc.utils.serialize import encode_exception

dvc/commands/move.py

@@ -1,8 +1,9 @@
 import argparse
 import logging
 
-from dvc.command import completion
-from dvc.command.base import CmdBase, append_doc_link
+from dvc.cli import completion
+from dvc.cli.command import CmdBase
+from dvc.cli.utils import append_doc_link
 from dvc.exceptions import DvcException
 
 logger = logging.getLogger(__name__)

dvc/commands/params.py

@@ -1,8 +1,9 @@
 import argparse
 import logging
 
-from dvc.command import completion
-from dvc.command.base import CmdBase, append_doc_link, fix_subparsers
+from dvc.cli import completion
+from dvc.cli.command import CmdBase
+from dvc.cli.utils import append_doc_link, fix_subparsers
 from dvc.exceptions import DvcException
 from dvc.ui import ui
 

dvc/commands/plots.py

@@ -0,0 +1,441 @@
+import argparse
+import json
+import logging
+import os
+
+from funcy import first
+
+from dvc.cli import completion
+from dvc.cli.command import CmdBase
+from dvc.cli.utils import append_doc_link, fix_subparsers
+from dvc.exceptions import DvcException
+from dvc.ui import ui
+from dvc.utils import format_link
+
+logger = logging.getLogger(__name__)
+
+
+def _show_json(renderers, split=False):
+    from dvc.render.convert import to_json
+
+    result = {
+        renderer.name: to_json(renderer, split) for renderer in renderers
+    }
+    ui.write_json(result)
+
+
+def _adjust_vega_renderers(renderers):
+    from dvc.render import REVISION_FIELD, VERSION_FIELD
+    from dvc_render import VegaRenderer
+
+    for r in renderers:
+        if isinstance(r, VegaRenderer):
+            if _data_versions_count(r) > 1:
+                summary = _summarize_version_infos(r)
+                for dp in r.datapoints:
+                    vi = dp.pop(VERSION_FIELD, {})
+                    keys = list(vi.keys())
+                    for key in keys:
+                        if not (len(summary.get(key, set())) > 1):
+                            vi.pop(key)
+                    if vi:
+                        dp["rev"] = "::".join(vi.values())
+            else:
+                for dp in r.datapoints:
+                    dp[REVISION_FIELD] = dp[VERSION_FIELD]["revision"]
+                    dp.pop(VERSION_FIELD, {})
+
+
+def _summarize_version_infos(renderer):
+    from collections import defaultdict
+
+    from dvc.render import VERSION_FIELD
+
+    result = defaultdict(set)
+
+    for dp in renderer.datapoints:
+        for key, value in dp.get(VERSION_FIELD, {}).items():
+            result[key].add(value)
+    return dict(result)
+
+
+def _data_versions_count(renderer):
+    from itertools import product
+
+    summary = _summarize_version_infos(renderer)
+    x = product(summary.get("filename", {None}), summary.get("field", {None}))
+    return len(set(x))
+
+
+class CmdPlots(CmdBase):
+    def _func(self, *args, **kwargs):
+        raise NotImplementedError
+
+    def _props(self):
+        from dvc.schema import PLOT_PROPS
+
+        # Pass only props specified by user, to not shadow ones from plot def
+        props = {p: getattr(self.args, p) for p in PLOT_PROPS}
+        return {k: v for k, v in props.items() if v is not None}
+
+    def _config_files(self):
+        config_files = None
+        if self.args.from_config:
+            config_files = {self.args.from_config}
+        return config_files
+
+    def _html_template_path(self):
+        html_template_path = self.args.html_template
+        if not html_template_path:
+            html_template_path = self.repo.config.get("plots", {}).get(
+                "html_template", None
+            )
+            if html_template_path and not os.path.isabs(html_template_path):
+                html_template_path = os.path.join(
+                    self.repo.dvc_dir, html_template_path
+                )
+        return html_template_path
+
+    def run(self):
+        from pathlib import Path
+
+        from dvc.render.match import match_defs_renderers
+        from dvc_render import render_html
+
+        if self.args.show_vega:
+            if not self.args.targets:
+                logger.error("please specify a target for `--show-vega`")
+                return 1
+            if len(self.args.targets) > 1:
+                logger.error(
+                    "you can only specify one target for `--show-vega`"
+                )
+                return 1
+            if self.args.json:
+                logger.error(
+                    "'--show-vega' and '--json' are mutually exclusive "
+                    "options."
+                )
+                return 1
+
+        try:
+            plots_data = self._func(
+                targets=self.args.targets,
+                props=self._props(),
+                config_files=self._config_files(),
+            )
+
+            if not plots_data:
+                ui.error_write(
+                    "No plots were loaded, "
+                    "visualization file will not be created."
+                )
+
+            out: str = self.args.out or self.repo.config.get("plots", {}).get(
+                "out_dir", "dvc_plots"
+            )
+
+            renderers_out = (
+                out if self.args.json else os.path.join(out, "static")
+            )
+
+            renderers = match_defs_renderers(
+                data=plots_data,
+                out=renderers_out,
+                templates_dir=self.repo.plots.templates_dir,
+            )
+            if self.args.json:
+                _show_json(renderers, self.args.split)
+                return 0
+
+            _adjust_vega_renderers(renderers)
+            if self.args.show_vega:
+                renderer = first(filter(lambda r: r.TYPE == "vega", renderers))
+                if renderer:
+                    ui.write_json(json.loads(renderer.get_filled_template()))
+                return 0
+
+            output_file: Path = (Path.cwd() / out).resolve() / "index.html"
+
+            if renderers:
+                render_html(
+                    renderers=renderers,
+                    output_file=output_file,
+                    template_path=self._html_template_path(),
+                )
+
+                ui.write(output_file.as_uri())
+                auto_open = self.repo.config["plots"].get("auto_open", False)
+                if self.args.open or auto_open:
+                    if not auto_open:
+                        ui.write(
+                            "To enable auto opening, you can run:\n"
+                            "\n"
+                            "\tdvc config plots.auto_open true"
+                        )
+                    return ui.open_browser(output_file)
+
+            return 0
+
+        except DvcException:
+            logger.exception("")
+            return 1
+
+
+class CmdPlotsShow(CmdPlots):
+    UNINITIALIZED = True
+
+    def _func(self, *args, **kwargs):
+        return self.repo.plots.show(*args, **kwargs)
+
+
+class CmdPlotsDiff(CmdPlots):
+    UNINITIALIZED = True
+
+    def _func(self, *args, **kwargs):
+        return self.repo.plots.diff(
+            *args,
+            revs=self.args.revisions,
+            experiment=self.args.experiment,
+            **kwargs,
+        )
+
+
+class CmdPlotsModify(CmdPlots):
+    def run(self):
+        self.repo.plots.modify(
+            self.args.target, props=self._props(), unset=self.args.unset
+        )
+        return 0
+
+
+class CmdPlotsTemplates(CmdBase):
+    def run(self):
+        from dvc.exceptions import InvalidArgumentError
+        from dvc_render.vega_templates import TEMPLATES
+
+        try:
+            target = self.args.template
+            if target:
+                for template in TEMPLATES:
+                    if target == template.DEFAULT_NAME:
+                        ui.write_json(template.DEFAULT_CONTENT)
+                        return 0
+                raise InvalidArgumentError(f"Unexpected template: {target}.")
+
+            else:
+                for template in TEMPLATES:
+                    ui.write(template.DEFAULT_NAME)
+
+            return 0
+        except DvcException:
+            logger.exception("")
+            return 1
+
+
+def add_parser(subparsers, parent_parser):
+    PLOTS_HELP = "Commands to visualize and compare plot data."
+
+    plots_parser = subparsers.add_parser(
+        "plots",
+        parents=[parent_parser],
+        description=append_doc_link(PLOTS_HELP, "plots"),
+        help=PLOTS_HELP,
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+    )
+    plots_subparsers = plots_parser.add_subparsers(
+        dest="cmd",
+        help="Use `dvc plots CMD --help` to display command-specific help.",
+    )
+
+    fix_subparsers(plots_subparsers)
+
+    SHOW_HELP = (
+        "Generate plots from target files or from `plots`"
+        " definitions in `dvc.yaml`."
+    )
+    plots_show_parser = plots_subparsers.add_parser(
+        "show",
+        parents=[parent_parser],
+        description=append_doc_link(SHOW_HELP, "plots/show"),
+        help=SHOW_HELP,
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+    )
+    plots_show_parser.add_argument(
+        "targets",
+        nargs="*",
+        help=(
+            "Plots files or plot IDs from `dvc.yaml` to visualize. "
+            "Shows all plots by default."
+        ),
+    ).complete = completion.FILE
+    _add_props_arguments(plots_show_parser)
+    _add_output_argument(plots_show_parser)
+    _add_ui_arguments(plots_show_parser)
+    plots_show_parser.set_defaults(func=CmdPlotsShow)
+
+    PLOTS_DIFF_HELP = (
+        "Show multiple versions of a plot by overlaying them "
+        "in a single image."
+    )
+    plots_diff_parser = plots_subparsers.add_parser(
+        "diff",
+        parents=[parent_parser],
+        description=append_doc_link(PLOTS_DIFF_HELP, "plots/diff"),
+        help=PLOTS_DIFF_HELP,
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+    )
+    plots_diff_parser.add_argument(
+        "--targets",
+        nargs="*",
+        help=(
+            "Specific plots to visualize. "
+            "Accepts any file path or plot name from `dvc.yaml` file. "
+            "Shows all tracked plots by default."
+        ),
+        metavar="<paths>",
+    ).complete = completion.FILE
+    plots_diff_parser.add_argument(
+        "-e",
+        "--experiment",
+        action="store_true",
+        default=False,
+        help=argparse.SUPPRESS,
+    )
+    plots_diff_parser.add_argument(
+        "revisions", nargs="*", default=None, help="Git commits to plot from"
+    )
+    _add_props_arguments(plots_diff_parser)
+    _add_output_argument(plots_diff_parser)
+    _add_ui_arguments(plots_diff_parser)
+    plots_diff_parser.set_defaults(func=CmdPlotsDiff)
+
+    PLOTS_MODIFY_HELP = (
+        "Modify display properties of data-series plots "
+        "defined in stages (has no effect on image plots)."
+    )
+    plots_modify_parser = plots_subparsers.add_parser(
+        "modify",
+        parents=[parent_parser],
+        description=append_doc_link(PLOTS_MODIFY_HELP, "plots/modify"),
+        help=PLOTS_MODIFY_HELP,
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+    )
+    plots_modify_parser.add_argument(
+        "target",
+        help="Plots file to set properties for (defined at the stage level).",
+    ).complete = completion.FILE
+    _add_props_arguments(plots_modify_parser)
+    plots_modify_parser.add_argument(
+        "--unset",
+        nargs="*",
+        metavar="<property>",
+        help="Unset one or more display properties.",
+    )
+    plots_modify_parser.set_defaults(func=CmdPlotsModify)
+
+    TEMPLATES_HELP = (
+        "List built-in plots templates or show JSON specification for one."
+    )
+    plots_templates_parser = plots_subparsers.add_parser(
+        "templates",
+        parents=[parent_parser],
+        description=append_doc_link(TEMPLATES_HELP, "plots/templates"),
+        help=TEMPLATES_HELP,
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+    )
+    plots_templates_parser.add_argument(
+        "template",
+        default=None,
+        nargs="?",
+        help=(
+            "Template for which to show JSON specification. "
+            "List all template names by default."
+        ),
+    )
+    plots_templates_parser.set_defaults(func=CmdPlotsTemplates)
+
+
+def _add_props_arguments(parser):
+    parser.add_argument(
+        "-t",
+        "--template",
+        nargs="?",
+        default=None,
+        help=(
+            "Special JSON or HTML schema file to inject with the data. "
+            "See {}".format(
+                format_link("https://man.dvc.org/plots#plot-templates")
+            )
+        ),
+        metavar="<path>",
+    ).complete = completion.FILE
+    parser.add_argument(
+        "-x", default=None, help="Field name for X axis.", metavar="<field>"
+    )
+    parser.add_argument(
+        "-y", default=None, help="Field name for Y axis.", metavar="<field>"
+    )
+    parser.add_argument(
+        "--no-header",
+        action="store_false",
+        dest="header",
+        default=None,  # Use default None to distinguish when it's not used
+        help="Provided CSV or TSV datafile does not have a header.",
+    )
+    parser.add_argument(
+        "--title", default=None, metavar="<text>", help="Plot title."
+    )
+    parser.add_argument(
+        "--x-label", default=None, help="X axis label", metavar="<text>"
+    )
+    parser.add_argument(
+        "--y-label", default=None, help="Y axis label", metavar="<text>"
+    )
+
+
+def _add_output_argument(parser, typ="plots"):
+    parser.add_argument(
+        "-o",
+        "--out",
+        default=None,
+        help=f"Directory to save {typ} to.",
+        metavar="<path>",
+    ).complete = completion.DIR
+
+
+def _add_ui_arguments(parser):
+    parser.add_argument(
+        "--show-vega",
+        action="store_true",
+        default=False,
+        help="Show output in Vega format.",
+    )
+    parser.add_argument(
+        "--json",
+        "--show-json",
+        action="store_true",
+        default=False,
+        help=argparse.SUPPRESS,
+    )
+    parser.add_argument(
+        "--split", action="store_true", default=False, help=argparse.SUPPRESS
+    )
+    parser.add_argument(
+        "--open",
+        action="store_true",
+        default=False,
+        help="Open plot file directly in the browser.",
+    )
+    parser.add_argument(
+        "--html-template",
+        default=None,
+        help="Custom HTML template for VEGA visualization.",
+        metavar="<path>",
+    )
+    parser.add_argument(
+        "--from-config",
+        default=None,
+        metavar="<path>",
+        help=argparse.SUPPRESS,
+    )

dvc/commands/queue/__init__.py

@@ -0,0 +1,34 @@
+import argparse
+
+from dvc.cli.utils import append_doc_link, fix_subparsers
+from dvc.commands.queue import kill, logs, remove, start, status, stop
+
+SUB_COMMANDS = [
+    start,
+    stop,
+    status,
+    logs,
+    remove,
+    kill,
+]
+
+
+def add_parser(subparsers, parent_parser):
+    QUEUE_HELP = "Commands to manage experiments queue."
+
+    queue_parser = subparsers.add_parser(
+        "queue",
+        parents=[parent_parser],
+        description=append_doc_link(QUEUE_HELP, "queue"),
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+        help=QUEUE_HELP,
+    )
+
+    queue_subparsers = queue_parser.add_subparsers(
+        dest="cmd",
+        help="Use `dvc queue CMD --help` to display " "command-specific help.",
+    )
+
+    fix_subparsers(queue_subparsers)
+    for cmd in SUB_COMMANDS:
+        cmd.add_parser(queue_subparsers, parent_parser)

dvc/commands/queue/kill.py

@@ -0,0 +1,34 @@
+import argparse
+import logging
+
+from dvc.cli.command import CmdBase
+from dvc.cli.utils import append_doc_link
+
+logger = logging.getLogger(__name__)
+
+
+class CmdQueueKill(CmdBase):
+    """Kill exp task in queue."""
+
+    def run(self):
+        self.repo.experiments.celery_queue.kill(revs=self.args.task)
+
+        return 0
+
+
+def add_parser(queue_subparsers, parent_parser):
+    QUEUE_KILL_HELP = "Kill actively running experiment queue tasks."
+    queue_kill_parser = queue_subparsers.add_parser(
+        "kill",
+        parents=[parent_parser],
+        description=append_doc_link(QUEUE_KILL_HELP, "queue/kill"),
+        help=QUEUE_KILL_HELP,
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+    )
+    queue_kill_parser.add_argument(
+        "task",
+        nargs="*",
+        help="Tasks in queue to kill.",
+        metavar="<task>",
+    )
+    queue_kill_parser.set_defaults(func=CmdQueueKill)

dvc/commands/queue/logs.py

@@ -0,0 +1,56 @@
+import argparse
+import logging
+
+from dvc.cli.command import CmdBase
+from dvc.cli.utils import append_doc_link
+
+logger = logging.getLogger(__name__)
+
+
+class CmdQueueLogs(CmdBase):
+    """Show output logs for a queued experiment."""
+
+    def run(self):
+        self.repo.experiments.celery_queue.logs(
+            rev=self.args.task,
+            encoding=self.args.encoding,
+            follow=self.args.follow,
+        )
+
+        return 0
+
+
+def add_parser(queue_subparsers, parent_parser):
+    QUEUE_LOGS_HELP = (
+        "Show output logs for running and completed experiment queue tasks."
+    )
+    queue_logs_parser = queue_subparsers.add_parser(
+        "logs",
+        parents=[parent_parser],
+        description=append_doc_link(QUEUE_LOGS_HELP, "queue/logs"),
+        help=QUEUE_LOGS_HELP,
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+    )
+    queue_logs_parser.add_argument(
+        "-e",
+        "--encoding",
+        help=(
+            "Text encoding for log output. Defaults to system locale encoding."
+        ),
+        metavar="<encoding>",
+    )
+    queue_logs_parser.add_argument(
+        "-f",
+        "--follow",
+        help=(
+            "Attach to task and follow additional live output. Only "
+            "applicable if the task is still running."
+        ),
+        action="store_true",
+    )
+    queue_logs_parser.add_argument(
+        "task",
+        help="Task to show.",
+        metavar="<task>",
+    )
+    queue_logs_parser.set_defaults(func=CmdQueueLogs)

dvc/commands/queue/remove.py

@@ -0,0 +1,95 @@
+import argparse
+import logging
+
+from dvc.cli.command import CmdBase
+from dvc.cli.utils import append_doc_link
+from dvc.exceptions import InvalidArgumentError
+from dvc.ui import ui
+
+logger = logging.getLogger(__name__)
+
+
+class CmdQueueRemove(CmdBase):
+    """Remove exp in queue."""
+
+    def check_arguments(self):
+        clear_flag = any(
+            [
+                self.args.all,
+                self.args.queued,
+                self.args.failed,
+                self.args.success,
+            ]
+        )
+        if not (clear_flag ^ bool(self.args.task)):
+            raise InvalidArgumentError(
+                "Either provide an `tasks` argument, or use the "
+                "`--all`, `--queued`, `--failed`, `--success` flag."
+            )
+
+    def run(self):
+
+        self.check_arguments()
+
+        if self.args.all:
+            self.args.queued = True
+            self.args.failed = True
+            self.args.success = True
+
+        if self.args.queued or self.args.failed or self.args.success:
+            removed_list = self.repo.experiments.celery_queue.clear(
+                success=self.args.success,
+                queued=self.args.queued,
+                failed=self.args.failed,
+            )
+        else:
+            removed_list = self.repo.experiments.celery_queue.remove(
+                revs=self.args.task,
+            )
+
+        if removed_list:
+            removed = ", ".join(removed_list)
+            ui.write(f"Removed tasks in queue: {removed}")
+        else:
+            ui.write(f"No tasks found named {self.args.task}")
+
+        return 0
+
+
+def add_parser(queue_subparsers, parent_parser):
+
+    QUEUE_REMOVE_HELP = "Remove queued and completed tasks from the queue."
+    queue_remove_parser = queue_subparsers.add_parser(
+        "remove",
+        parents=[parent_parser],
+        description=append_doc_link(QUEUE_REMOVE_HELP, "queue/remove"),
+        help=QUEUE_REMOVE_HELP,
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+    )
+    queue_remove_parser.add_argument(
+        "--all",
+        action="store_true",
+        help="Remove all queued and completed tasks from the queue.",
+    )
+    queue_remove_parser.add_argument(
+        "--queued",
+        action="store_true",
+        help="Remove all queued tasks from the queue.",
+    )
+    queue_remove_parser.add_argument(
+        "--success",
+        action="store_true",
+        help="Remove all successful tasks from the queue.",
+    )
+    queue_remove_parser.add_argument(
+        "--failed",
+        action="store_true",
+        help="Remove all failed tasks from the queue.",
+    )
+    queue_remove_parser.add_argument(
+        "task",
+        nargs="*",
+        help="Tasks to remove.",
+        metavar="<task>",
+    )
+    queue_remove_parser.set_defaults(func=CmdQueueRemove)

dvc/commands/queue/start.py

@@ -0,0 +1,48 @@
+import argparse
+import logging
+
+from dvc.cli.command import CmdBase
+from dvc.cli.utils import append_doc_link
+from dvc.ui import ui
+
+logger = logging.getLogger(__name__)
+
+
+class CmdQueueStart(CmdBase):
+    """Start exp queue workers."""
+
+    def run(self):
+        started = self.repo.experiments.celery_queue.start_workers(
+            self.args.jobs
+        )
+
+        suffix = "s" if started > 1 else ""
+        ui.write(
+            f"Started '{started}' new experiments task queue worker{suffix}."
+        )
+
+        return 0
+
+
+def add_parser(queue_subparsers, parent_parser):
+
+    QUEUE_START_HELP = "Start the experiments task queue worker."
+    queue_start_parser = queue_subparsers.add_parser(
+        "start",
+        parents=[parent_parser],
+        description=append_doc_link(QUEUE_START_HELP, "queue/start"),
+        help=QUEUE_START_HELP,
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+    )
+    queue_start_parser.add_argument(
+        "-j",
+        "--jobs",
+        type=int,
+        default=1,
+        help=(
+            "Maximum number of concurrent queue workers to start. "
+            "Defaults to 1."
+        ),
+        metavar="<number>",
+    )
+    queue_start_parser.set_defaults(func=CmdQueueStart)

dvc/commands/queue/status.py

@@ -0,0 +1,62 @@
+import argparse
+import logging
+from typing import List, Mapping, Optional
+
+from dvc.cli.command import CmdBase
+from dvc.cli.utils import append_doc_link
+from dvc.compare import TabularData
+from dvc.ui import ui
+
+from ..experiments.show import format_time
+
+logger = logging.getLogger(__name__)
+
+
+class CmdQueueStatus(CmdBase):
+    """Show queue task and worker status."""
+
+    def run(self):
+        result: List[
+            Mapping[str, Optional[str]]
+        ] = self.repo.experiments.celery_queue.status()
+        if result:
+            all_headers = ["Task", "Name", "Created", "Status"]
+            td = TabularData(all_headers)
+            for exp in result:
+                created = format_time(exp.get("timestamp"))
+                td.append(
+                    [
+                        exp["rev"][:7],
+                        exp.get("name", ""),
+                        created,
+                        exp["status"],
+                    ]
+                )
+            td.render()
+        else:
+            ui.write("No experiment tasks in the queue.")
+        ui.write()
+
+        worker_status = self.repo.experiments.celery_queue.worker_status()
+        active_count = len(
+            [name for name, task in worker_status.items() if task]
+        )
+        idle_count = len(worker_status) - active_count
+
+        ui.write(f"Worker status: {active_count} active, {idle_count} idle")
+
+        return 0
+
+
+def add_parser(queue_subparsers, parent_parser):
+    QUEUE_STATUS_HELP = (
+        "Show the status of experiments queue tasks and workers."
+    )
+    queue_status_parser = queue_subparsers.add_parser(
+        "status",
+        parents=[parent_parser],
+        description=append_doc_link(QUEUE_STATUS_HELP, "queue/status"),
+        help=QUEUE_STATUS_HELP,
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+    )
+    queue_status_parser.set_defaults(func=CmdQueueStatus)

dvc/commands/queue/stop.py

@@ -0,0 +1,43 @@
+import argparse
+import logging
+
+from dvc.cli.command import CmdBase
+from dvc.cli.utils import append_doc_link
+from dvc.ui import ui
+
+logger = logging.getLogger(__name__)
+
+
+class CmdQueueStop(CmdBase):
+    """Stop exp queue workers."""
+
+    def run(self):
+        self.repo.experiments.celery_queue.shutdown(kill=self.args.kill)
+
+        if self.args.kill:
+            ui.write(
+                "All running tasks in the queue have been killed."
+                "Queue workers are stopping."
+            )
+        else:
+            ui.write("Queue workers will stop after running tasks finish.")
+
+        return 0
+
+
+def add_parser(queue_subparsers, parent_parser):
+
+    QUEUE_STOP_HELP = "Stop all experiments task queue workers."
+    queue_stop_parser = queue_subparsers.add_parser(
+        "stop",
+        parents=[parent_parser],
+        description=append_doc_link(QUEUE_STOP_HELP, "queue/stop"),
+        help=QUEUE_STOP_HELP,
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+    )
+    queue_stop_parser.add_argument(
+        "--kill",
+        action="store_true",
+        help="Kill all running tasks before stopping the queue workers.",
+    )
+    queue_stop_parser.set_defaults(func=CmdQueueStop)

dvc/commands/remote.py

@@ -1,7 +1,7 @@
 import argparse
 
-from dvc.command.base import append_doc_link, fix_subparsers
-from dvc.command.config import CmdConfig
+from dvc.cli.utils import append_doc_link, fix_subparsers
+from dvc.commands.config import CmdConfig
 from dvc.ui import ui
 from dvc.utils import format_link
 
@@ -113,8 +113,8 @@ class CmdRemoteDefault(CmdRemote):
 class CmdRemoteList(CmdRemote):
     def run(self):
         conf = self.config.read(self.args.level)
-        for name, conf in conf["remote"].items():
-            ui.write(name, conf["url"], sep="\t")
+        for name, remote_conf in conf["remote"].items():
+            ui.write(name, remote_conf["url"], sep="\t")
         return 0
 
 
@@ -151,7 +151,7 @@ class CmdRemoteRename(CmdRemote):
 
 
 def add_parser(subparsers, parent_parser):
-    from dvc.command.config import parent_config_parser
+    from dvc.commands.config import parent_config_parser
 
     REMOTE_HELP = "Set up and manage data remotes."
     remote_parser = subparsers.add_parser(

dvc/commands/remove.py

@@ -1,8 +1,9 @@
 import argparse
 import logging
 
-from dvc.command import completion
-from dvc.command.base import CmdBase, append_doc_link
+from dvc.cli import completion
+from dvc.cli.command import CmdBase
+from dvc.cli.utils import append_doc_link
 from dvc.exceptions import DvcException
 
 logger = logging.getLogger(__name__)

dvc/commands/repro.py

@@ -1,21 +1,22 @@
 import argparse
 
-from dvc.command import completion
-from dvc.command.base import CmdBase, append_doc_link
-from dvc.command.status import CmdDataStatus
+from dvc.cli import completion
+from dvc.cli.command import CmdBase
+from dvc.cli.utils import append_doc_link
+from dvc.commands.status import CmdDataStatus
 
 
 class CmdRepro(CmdBase):
     def run(self):
         from dvc.ui import ui
 
-        stages = self.repo.reproduce(**self._repro_kwargs)
+        stages = self.repo.reproduce(
+            **self._common_kwargs, **self._repro_kwargs
+        )
         if len(stages) == 0:
             ui.write(CmdDataStatus.UP_TO_DATE_MSG)
         else:
-            ui.write(
-                "Use `dvc push` to send your updates to " "remote storage."
-            )
+            ui.write("Use `dvc push` to send your updates to remote storage.")
 
         if self.args.metrics:
             from dvc.compare import show_metrics
@@ -26,7 +27,7 @@ class CmdRepro(CmdBase):
         return 0
 
     @property
-    def _repro_kwargs(self):
+    def _common_kwargs(self):
         return {
             "targets": self.args.targets,
             "single_item": self.args.single_item,
@@ -35,12 +36,17 @@ class CmdRepro(CmdBase):
             "interactive": self.args.interactive,
             "pipeline": self.args.pipeline,
             "all_pipelines": self.args.all_pipelines,
-            "run_cache": not self.args.no_run_cache,
-            "no_commit": self.args.no_commit,
             "downstream": self.args.downstream,
             "recursive": self.args.recursive,
             "force_downstream": self.args.force_downstream,
             "pull": self.args.pull,
+        }
+
+    @property
+    def _repro_kwargs(self):
+        return {
+            "run_cache": not self.args.no_run_cache,
+            "no_commit": self.args.no_commit,
             "glob": self.args.glob,
         }
 
@@ -49,7 +55,16 @@ def add_arguments(repro_parser):
     repro_parser.add_argument(
         "targets",
         nargs="*",
-        help="Stages to reproduce. 'dvc.yaml' by default.",
+        help=(
+            """\
+Stages to reproduce. 'dvc.yaml' by default.
+The targets can be path to a dvc.yaml file or `.dvc` file,
+or a stage name from dvc.yaml file from
+current working directory. To run a stage from dvc.yaml
+from other directories, the target must be a path followed by colon `:`
+and then the stage name name.
+"""
+        ),
     ).complete = completion.DVCFILES_AND_STAGE
     repro_parser.add_argument(
         "-f",
@@ -58,6 +73,13 @@ def add_arguments(repro_parser):
         default=False,
         help="Reproduce even if dependencies were not changed.",
     )
+    repro_parser.add_argument(
+        "-i",
+        "--interactive",
+        action="store_true",
+        default=False,
+        help="Ask for confirmation before reproducing each stage.",
+    )
     repro_parser.add_argument(
         "-s",
         "--single-item",
@@ -66,27 +88,6 @@ def add_arguments(repro_parser):
         help="Reproduce only single data item without recursive dependencies "
         "check.",
     )
-    repro_parser.add_argument(
-        "-m",
-        "--metrics",
-        action="store_true",
-        default=False,
-        help="Show metrics after reproduction.",
-    )
-    repro_parser.add_argument(
-        "--dry",
-        action="store_true",
-        default=False,
-        help="Only print the commands that would be executed without "
-        "actually executing.",
-    )
-    repro_parser.add_argument(
-        "-i",
-        "--interactive",
-        action="store_true",
-        default=False,
-        help="Ask for confirmation before reproducing each stage.",
-    )
     repro_parser.add_argument(
         "-p",
         "--pipeline",
@@ -110,13 +111,17 @@ def add_arguments(repro_parser):
         help="Reproduce all stages in the specified directory.",
     )
     repro_parser.add_argument(
-        "--no-run-cache",
+        "-m",
+        "--metrics",
         action="store_true",
         default=False,
-        help=(
-            "Execute stage commands even if they have already been run with "
-            "the same command/dependencies/outputs/etc before."
-        ),
+        help="Show metrics after reproduction.",
+    )
+    repro_parser.add_argument(
+        "--downstream",
+        action="store_true",
+        default=False,
+        help="Start from the specified stages when reproducing pipelines.",
     )
     repro_parser.add_argument(
         "--force-downstream",
@@ -125,18 +130,6 @@ def add_arguments(repro_parser):
         help="Reproduce all descendants of a changed stage even if their "
         "direct dependencies didn't change.",
     )
-    repro_parser.add_argument(
-        "--no-commit",
-        action="store_true",
-        default=False,
-        help="Don't put files/directories into cache.",
-    )
-    repro_parser.add_argument(
-        "--downstream",
-        action="store_true",
-        default=False,
-        help="Start from the specified stages when reproducing pipelines.",
-    )
     repro_parser.add_argument(
         "--pull",
         action="store_true",
@@ -147,10 +140,11 @@ def add_arguments(repro_parser):
         ),
     )
     repro_parser.add_argument(
-        "--glob",
+        "--dry",
         action="store_true",
         default=False,
-        help="Allows targets containing shell-style wildcards.",
+        help="Only print the commands that would be executed without "
+        "actually executing.",
     )
 
 
@@ -165,5 +159,28 @@ def add_parser(subparsers, parent_parser):
         help=REPRO_HELP,
         formatter_class=argparse.RawDescriptionHelpFormatter,
     )
+    # repro/exp run shared args
     add_arguments(repro_parser)
+    # repro only args
+    repro_parser.add_argument(
+        "--glob",
+        action="store_true",
+        default=False,
+        help="Allows targets containing shell-style wildcards.",
+    )
+    repro_parser.add_argument(
+        "--no-commit",
+        action="store_true",
+        default=False,
+        help="Don't put files/directories into cache.",
+    )
+    repro_parser.add_argument(
+        "--no-run-cache",
+        action="store_true",
+        default=False,
+        help=(
+            "Execute stage commands even if they have already been run with "
+            "the same command/dependencies/outputs/etc before."
+        ),
+    )
     repro_parser.set_defaults(func=CmdRepro)

dvc/commands/root.py

@@ -1,7 +1,8 @@
 import argparse
 import logging
 
-from dvc.command.base import CmdBaseNoRepo, append_doc_link
+from dvc.cli.command import CmdBaseNoRepo
+from dvc.cli.utils import append_doc_link
 from dvc.utils import relpath
 
 logger = logging.getLogger(__name__)

dvc/commands/run.py

@@ -1,8 +1,9 @@
 import argparse
 import logging
 
-from dvc.command.base import CmdBase, append_doc_link
-from dvc.command.stage import parse_cmd
+from dvc.cli.command import CmdBase
+from dvc.cli.utils import append_doc_link
+from dvc.commands.stage import parse_cmd
 from dvc.exceptions import DvcException
 
 logger = logging.getLogger(__name__)
@@ -52,7 +53,7 @@ class CmdRun(CmdBase):
 
 
 def add_parser(subparsers, parent_parser):
-    from dvc.command.stage import _add_common_args
+    from dvc.commands.stage import _add_common_args
 
     RUN_HELP = (
         "Generate a dvc.yaml file from a command and execute the command."
@@ -68,12 +69,25 @@ def add_parser(subparsers, parent_parser):
     run_parser.add_argument(
         "--file", metavar="<filename>", help=argparse.SUPPRESS
     )
+    run_parser.add_argument(
+        "--single-stage",
+        action="store_true",
+        default=False,
+        help=argparse.SUPPRESS,
+    )
+    _add_common_args(run_parser)
     run_parser.add_argument(
         "--no-exec",
         action="store_true",
         default=False,
         help="Only create dvc.yaml without actually running it.",
     )
+    run_parser.add_argument(
+        "--no-commit",
+        action="store_true",
+        default=False,
+        help="Don't put files/directories into cache.",
+    )
     run_parser.add_argument(
         "--no-run-cache",
         action="store_true",
@@ -83,17 +97,4 @@ def add_parser(subparsers, parent_parser):
             "with the same command/dependencies/outputs/etc before."
         ),
     )
-    run_parser.add_argument(
-        "--no-commit",
-        action="store_true",
-        default=False,
-        help="Don't put files/directories into cache.",
-    )
-    run_parser.add_argument(
-        "--single-stage",
-        action="store_true",
-        default=False,
-        help=argparse.SUPPRESS,
-    )
-    _add_common_args(run_parser)
     run_parser.set_defaults(func=CmdRun)

dvc/commands/stage.py

@@ -3,8 +3,9 @@ import logging
 from itertools import chain, filterfalse
 from typing import TYPE_CHECKING, Dict, Iterable, List
 
-from dvc.command import completion
-from dvc.command.base import CmdBase, append_doc_link, fix_subparsers
+from dvc.cli import completion
+from dvc.cli.command import CmdBase
+from dvc.cli.utils import append_doc_link, fix_subparsers
 from dvc.utils.cli_parse import parse_params
 from dvc.utils.humanize import truncate_text
 
@@ -75,7 +76,7 @@ class CmdStageList(CmdBase):
         # removing duplicates while maintaining order
         collected = chain.from_iterable(
             self.repo.stage.collect(
-                target=target, recursive=self.args.recursive, accept_group=True
+                target=target, recursive=self.args.recursive
             )
             for target in self.args.targets
         )
@@ -93,9 +94,7 @@ class CmdStageList(CmdBase):
         self.repo.stage_collection_error_handler = log_error
 
         stages = self._get_stages()
-        names_only = self.args.names_only
-
-        data = prepare_stages_data(stages, description=not names_only)
+        data = prepare_stages_data(stages, description=not self.args.name_only)
         ui.table(data.items())
 
         return 0
@@ -138,6 +137,13 @@ class CmdStageAdd(CmdBase):
 
 
 def _add_common_args(parser):
+    parser.add_argument(
+        "-f",
+        "--force",
+        action="store_true",
+        default=False,
+        help="Overwrite existing stage",
+    )
     parser.add_argument(
         "-d",
         "--deps",
@@ -146,6 +152,14 @@ def _add_common_args(parser):
         help="Declare dependencies for reproducible cmd.",
         metavar="<path>",
     ).complete = completion.FILE
+    parser.add_argument(
+        "-p",
+        "--params",
+        action="append",
+        default=[],
+        help="Declare parameter to use as additional dependency.",
+        metavar="[<filename>:]<params_list>",
+    ).complete = completion.FILE
     parser.add_argument(
         "-o",
         "--outs",
@@ -164,13 +178,36 @@ def _add_common_args(parser):
         metavar="<filename>",
     ).complete = completion.FILE
     parser.add_argument(
-        "-p",
-        "--params",
+        "-c",
+        "--checkpoints",
         action="append",
         default=[],
-        help="Declare parameter to use as additional dependency.",
-        metavar="[<filename>:]<params_list>",
+        help="Declare checkpoint output file or directory for 'dvc exp run'. "
+        "Not compatible with 'dvc repro'.",
+        metavar="<filename>",
     ).complete = completion.FILE
+    parser.add_argument(
+        "--external",
+        action="store_true",
+        default=False,
+        help="Allow outputs that are outside of the DVC repository.",
+    )
+    parser.add_argument(
+        "--outs-persist",
+        action="append",
+        default=[],
+        help="Declare output file or directory that will not be "
+        "removed upon repro.",
+        metavar="<filename>",
+    )
+    parser.add_argument(
+        "--outs-persist-no-cache",
+        action="append",
+        default=[],
+        help="Declare output file or directory that will not be "
+        "removed upon repro (do not put into DVC cache).",
+        metavar="<filename>",
+    )
     parser.add_argument(
         "-m",
         "--metrics",
@@ -213,7 +250,7 @@ def _add_common_args(parser):
         "--live-no-summary",
         action="store_true",
         default=False,
-        help="Signal dvclive logger to not dump latest metrics file.",
+        help=argparse.SUPPRESS,
     )
     parser.add_argument(
         "--live-no-html",
@@ -227,50 +264,12 @@ def _add_common_args(parser):
         help="Directory within your repo to run your command in.",
         metavar="<path>",
     )
-    parser.add_argument(
-        "-f",
-        "--force",
-        action="store_true",
-        default=False,
-        help="Overwrite existing stage",
-    )
-    parser.add_argument(
-        "--outs-persist",
-        action="append",
-        default=[],
-        help="Declare output file or directory that will not be "
-        "removed upon repro.",
-        metavar="<filename>",
-    )
-    parser.add_argument(
-        "--outs-persist-no-cache",
-        action="append",
-        default=[],
-        help="Declare output file or directory that will not be "
-        "removed upon repro (do not put into DVC cache).",
-        metavar="<filename>",
-    )
-    parser.add_argument(
-        "-c",
-        "--checkpoints",
-        action="append",
-        default=[],
-        help="Declare checkpoint output file or directory for 'dvc exp run'. "
-        "Not compatible with 'dvc repro'.",
-        metavar="<filename>",
-    ).complete = completion.FILE
     parser.add_argument(
         "--always-changed",
         action="store_true",
         default=False,
         help="Always consider this DVC-file as changed.",
     )
-    parser.add_argument(
-        "--external",
-        action="store_true",
-        default=False,
-        help="Allow outputs that are outside of the DVC repository.",
-    )
     parser.add_argument(
         "--desc",
         type=str,
@@ -357,6 +356,7 @@ def add_parser(subparsers, parent_parser):
         help="List all stages inside the specified directory.",
     )
     stage_list_parser.add_argument(
+        "--name-only",
         "--names-only",
         action="store_true",
         default=False,

dvc/commands/status.py

@@ -1,6 +1,6 @@
 import logging
 
-from dvc.command.data_sync import CmdDataBase
+from dvc.commands.data_sync import CmdDataBase
 from dvc.exceptions import DvcException
 from dvc.ui import ui
 from dvc.utils import format_link

dvc/commands/unprotect.py

@@ -1,8 +1,9 @@
 import argparse
 import logging
 
-from dvc.command import completion
-from dvc.command.base import CmdBase, append_doc_link
+from dvc.cli import completion
+from dvc.cli.command import CmdBase
+from dvc.cli.utils import append_doc_link
 from dvc.exceptions import DvcException
 
 logger = logging.getLogger(__name__)

dvc/commands/update.py

@@ -1,8 +1,9 @@
 import argparse
 import logging
 
-from dvc.command import completion
-from dvc.command.base import CmdBase, append_doc_link
+from dvc.cli import completion
+from dvc.cli.command import CmdBase
+from dvc.cli.utils import append_doc_link
 from dvc.exceptions import DvcException
 
 logger = logging.getLogger(__name__)
@@ -17,6 +18,7 @@ class CmdUpdate(CmdBase):
                 rev=self.args.rev,
                 recursive=self.args.recursive,
                 to_remote=self.args.to_remote,
+                no_download=self.args.no_download,
                 remote=self.args.remote,
                 jobs=self.args.jobs,
             )
@@ -27,7 +29,10 @@ class CmdUpdate(CmdBase):
 
 
 def add_parser(subparsers, parent_parser):
-    UPDATE_HELP = "Update data artifacts imported from other DVC repositories."
+    UPDATE_HELP = (
+        "Update data artifact imported (via dvc import or dvc import-url) "
+        "from an external DVC repository or URL."
+    )
     update_parser = subparsers.add_parser(
         "update",
         parents=[parent_parser],
@@ -51,6 +56,13 @@ def add_parser(subparsers, parent_parser):
         default=False,
         help="Update all stages in the specified directory.",
     )
+    update_parser.add_argument(
+        "--no-download",
+        action="store_true",
+        default=False,
+        help="Update .dvc file git revision/hash value(s)"
+        " but do not download the file(s).",
+    )
     update_parser.add_argument(
         "--to-remote",
         action="store_true",
@@ -70,7 +82,6 @@ def add_parser(subparsers, parent_parser):
         help=(
             "Number of jobs to run simultaneously. "
             "The default value is 4 * cpu_count(). "
-            "For SSH remotes, the default is 4. "
         ),
         metavar="<number>",
     )

dvc/commands/version.py

@@ -1,7 +1,8 @@
 import argparse
 import logging
 
-from dvc.command.base import CmdBaseNoRepo, append_doc_link
+from dvc.cli.command import CmdBaseNoRepo
+from dvc.cli.utils import append_doc_link
 from dvc.ui import ui
 
 logger = logging.getLogger(__name__)

dvc/compare.py

@@ -11,6 +11,7 @@ from typing import (
     List,
     Mapping,
     MutableSequence,
+    Optional,
     Sequence,
     Set,
     Tuple,
@@ -21,6 +22,7 @@ from typing import (
 from funcy import reraise
 
 if TYPE_CHECKING:
+    from dvc.types import StrPath
     from dvc.ui.table import CellT
 
 
@@ -37,11 +39,21 @@ class TabularData(MutableSequence[Sequence["CellT"]]):
         self._columns: Dict[str, Column] = {name: Column() for name in columns}
         self._keys: List[str] = list(columns)
         self._fill_value = fill_value
+        self._protected: Set[str] = set()
 
     @property
     def columns(self) -> List[Column]:
         return list(map(self.column, self.keys()))
 
+    def is_protected(self, col_name) -> bool:
+        return col_name in self._protected
+
+    def protect(self, *col_names: str):
+        self._protected.update(col_names)
+
+    def unprotect(self, *col_names: str):
+        self._protected = self._protected.difference(col_names)
+
     def column(self, name: str) -> Column:
         return self._columns[name]
 
@@ -125,9 +137,10 @@ class TabularData(MutableSequence[Sequence["CellT"]]):
         return len(self.columns), len(self)
 
     def drop(self, *col_names: str) -> None:
-        for col_name in col_names:
-            self._keys.remove(col_name)
-            self._columns.pop(col_name)
+        for col in col_names:
+            if not self.is_protected(col):
+                self._keys.remove(col)
+                self._columns.pop(col)
 
     def rename(self, from_col_name: str, to_col_name: str) -> None:
         self._columns[to_col_name] = self._columns.pop(from_col_name)
@@ -153,6 +166,24 @@ class TabularData(MutableSequence[Sequence["CellT"]]):
             writer.writerow(row)
         return buff.getvalue()
 
+    def to_parallel_coordinates(
+        self, output_path: "StrPath", color_by: str = None
+    ) -> "StrPath":
+        from dvc_render.html import render_html
+        from dvc_render.plotly import ParallelCoordinatesRenderer
+
+        render_html(
+            renderers=[
+                ParallelCoordinatesRenderer(
+                    self.as_dict(),
+                    color_by=color_by,
+                    fill_value=self._fill_value,
+                )
+            ],
+            output_file=output_path,
+        )
+        return output_path
+
     def add_column(self, name: str) -> None:
         self._columns[name] = Column([self._fill_value] * len(self))
         self._keys.append(name)
@@ -184,7 +215,12 @@ class TabularData(MutableSequence[Sequence["CellT"]]):
             {k: self._columns[k][i] for k in keys} for i in range(len(self))
         ]
 
-    def dropna(self, axis: str = "rows", how="any"):
+    def dropna(
+        self,
+        axis: str = "rows",
+        how="any",
+        subset: Optional[Iterable[str]] = None,
+    ):
         if axis not in ["rows", "cols"]:
             raise ValueError(
                 f"Invalid 'axis' value {axis}."
@@ -196,13 +232,15 @@ class TabularData(MutableSequence[Sequence["CellT"]]):
             )
 
         match_line: Set = set()
-        match = True
+        match_any = True
         if how == "all":
-            match = False
+            match_any = False
 
         for n_row, row in enumerate(self):
             for n_col, col in enumerate(row):
-                if (col == self._fill_value) is match:
+                if subset and self.keys()[n_col] not in subset:
+                    continue
+                if (col == self._fill_value) is match_any:
                     if axis == "rows":
                         match_line.add(n_row)
                         break
@@ -229,7 +267,12 @@ class TabularData(MutableSequence[Sequence["CellT"]]):
         else:
             self.drop(*to_drop)
 
-    def drop_duplicates(self, axis: str = "rows"):
+    def drop_duplicates(
+        self,
+        axis: str = "rows",
+        subset: Optional[Iterable[str]] = None,
+        ignore_empty: bool = True,
+    ):
         if axis not in ["rows", "cols"]:
             raise ValueError(
                 f"Invalid 'axis' value {axis}."
@@ -239,8 +282,12 @@ class TabularData(MutableSequence[Sequence["CellT"]]):
         if axis == "cols":
             cols_to_drop: List[str] = []
             for n_col, col in enumerate(self.columns):
+                if subset and self.keys()[n_col] not in subset:
+                    continue
                 # Cast to str because Text is not hashable error
-                unique_vals = {str(x) for x in col if x != self._fill_value}
+                unique_vals = {str(x) for x in col}
+                if ignore_empty and self._fill_value in unique_vals:
+                    unique_vals -= {self._fill_value}
                 if len(unique_vals) == 1:
                     cols_to_drop.append(self.keys()[n_col])
             self.drop(*cols_to_drop)
@@ -249,6 +296,13 @@ class TabularData(MutableSequence[Sequence["CellT"]]):
             unique_rows = []
             rows_to_drop: List[int] = []
             for n_row, row in enumerate(self):
+                if subset:
+                    row = [
+                        col
+                        for n_col, col in enumerate(row)
+                        if self.keys()[n_col] in subset
+                    ]
+
                 tuple_row = tuple(row)
                 if tuple_row in unique_rows:
                     rows_to_drop.append(n_row)

dvc/config.py

@@ -86,22 +86,21 @@ class Config(dict):
     def __init__(
         self, dvc_dir=None, validate=True, fs=None, config=None
     ):  # pylint: disable=super-init-not-called
-        from dvc.fs.local import LocalFileSystem
+        from dvc.fs import LocalFileSystem
 
         self.dvc_dir = dvc_dir
+        self.wfs = LocalFileSystem()
+        self.fs = fs or self.wfs
 
         if not dvc_dir:
             try:
                 from dvc.repo import Repo
 
-                self.dvc_dir = os.path.join(Repo.find_dvc_dir())
+                self.dvc_dir = Repo.find_dvc_dir()
             except NotDvcRepoError:
                 self.dvc_dir = None
         else:
-            self.dvc_dir = os.path.abspath(os.path.realpath(dvc_dir))
-
-        self.wfs = LocalFileSystem(url=self.dvc_dir)
-        self.fs = fs or self.wfs
+            self.dvc_dir = self.fs.path.abspath(self.fs.path.realpath(dvc_dir))
 
         self.load(validate=validate, config=config)
 
@@ -124,8 +123,8 @@ class Config(dict):
         }
 
         if self.dvc_dir is not None:
-            files["repo"] = os.path.join(self.dvc_dir, self.CONFIG)
-            files["local"] = os.path.join(self.dvc_dir, self.CONFIG_LOCAL)
+            files["repo"] = self.fs.path.join(self.dvc_dir, self.CONFIG)
+            files["local"] = self.fs.path.join(self.dvc_dir, self.CONFIG_LOCAL)
 
         return files
 
@@ -177,7 +176,10 @@ class Config(dict):
 
         if fs.exists(filename):
             with fs.open(filename) as fobj:
-                conf_obj = ConfigObj(fobj)
+                try:
+                    conf_obj = ConfigObj(fobj)
+                except UnicodeDecodeError as exc:
+                    raise ConfigError(str(exc)) from exc
         else:
             conf_obj = ConfigObj()
         return _parse_named(_lower_keys(conf_obj.dict()))
@@ -188,7 +190,7 @@ class Config(dict):
         filename = self.files[level]
         fs = self._get_fs(level)
 
-        logger.debug(f"Writing '{filename}'.")
+        logger.debug("Writing '%s'.", filename)
 
         fs.makedirs(os.path.dirname(filename))
 
@@ -228,7 +230,7 @@ class Config(dict):
 
     @staticmethod
     def _to_relpath(conf_dir, path):
-        from dvc.fs.local import localfs
+        from dvc.fs import localfs
         from dvc.utils import relpath
 
         from .config_schema import RelPath
@@ -266,7 +268,12 @@ class Config(dict):
                     "key_path": func,
                 }
             },
-            "machine": {str: {"startup_script": func}},
+            "machine": {
+                str: {
+                    "startup_script": func,
+                    "setup_script": func,
+                }
+            },
         }
         return Schema(dirs_schema, extra=ALLOW_EXTRA)(conf)
 

dvc/config_schema.py

@@ -78,14 +78,16 @@ REMOTE_COMMON = {
     "url": str,
     "checksum_jobs": All(Coerce(int), Range(1)),
     "jobs": All(Coerce(int), Range(1)),
+    Optional("worktree"): Bool,
     Optional("no_traverse"): Bool,  # obsoleted
-    "verify": Bool,
+    Optional("version_aware"): Bool,
 }
 LOCAL_COMMON = {
     "type": supported_cache_type,
     Optional("protected", default=False): Bool,  # obsoleted
     "shared": All(Lower, Choices("group")),
     Optional("slow_link_warning", default=True): Bool,
+    Optional("verify", default=False): Bool,
 }
 HTTP_COMMON = {
     "auth": All(Lower, Choices("basic", "digest", "custom")),
@@ -95,6 +97,7 @@ HTTP_COMMON = {
     "ask_password": Bool,
     "ssl_verify": Any(Bool, str),
     "method": str,
+    Optional("verify", default=False): Bool,
 }
 WEBDAV_COMMON = {
     "user": str,
@@ -105,6 +108,7 @@ WEBDAV_COMMON = {
     "key_path": str,
     "timeout": Coerce(int),
     "ssl_verify": Any(Bool, str),
+    Optional("verify", default=False): Bool,
 }
 
 SCHEMA = {
@@ -150,6 +154,8 @@ SCHEMA = {
                     "ssl_verify": Any(Bool, str),
                     "sse": str,
                     "sse_kms_key_id": str,
+                    "sse_customer_algorithm": str,
+                    "sse_customer_key": str,
                     "acl": str,
                     "grant_read": str,
                     "grant_read_acp": str,
@@ -158,11 +164,14 @@ SCHEMA = {
                     "cache_regions": bool,
                     "read_timeout": Coerce(int),
                     "connect_timeout": Coerce(int),
+                    Optional("verify", default=False): Bool,
                     **REMOTE_COMMON,
                 },
                 "gs": {
                     "projectname": str,
                     "credentialpath": str,
+                    "endpointurl": str,
+                    Optional("verify", default=False): Bool,
                     **REMOTE_COMMON,
                 },
                 "ssh": {
@@ -171,10 +180,13 @@ SCHEMA = {
                     "user": str,
                     "password": str,
                     "ask_password": Bool,
+                    "passphrase": str,
+                    "ask_passphrase": Bool,
                     "keyfile": str,
                     "timeout": Coerce(int),
                     "gss_auth": Bool,
                     "allow_agent": Bool,
+                    Optional("verify", default=False): Bool,
                     **REMOTE_COMMON,
                 },
                 "hdfs": {"user": str, "kerb_ticket": str, **REMOTE_COMMON},
@@ -185,6 +197,7 @@ SCHEMA = {
                     "ssl_verify": Any(Bool, str),
                     "token": str,
                     "use_https": Bool,
+                    Optional("verify", default=False): Bool,
                     **REMOTE_COMMON,
                 },
                 "azure": {
@@ -200,15 +213,18 @@ SCHEMA = {
                     "exclude_visual_studio_code_credential": Bool,
                     "exclude_shared_token_cache_credential": Bool,
                     "exclude_managed_identity_credential": Bool,
+                    Optional("verify", default=False): Bool,
                     **REMOTE_COMMON,
                 },
                 "oss": {
                     "oss_key_id": str,
                     "oss_key_secret": str,
                     "oss_endpoint": str,
+                    Optional("verify", default=True): Bool,
                     **REMOTE_COMMON,
                 },
                 "gdrive": {
+                    "profile": str,
                     "gdrive_use_service_account": Bool,
                     "gdrive_client_id": str,
                     "gdrive_client_secret": str,
@@ -216,6 +232,8 @@ SCHEMA = {
                     "gdrive_service_account_user_email": str,
                     "gdrive_service_account_json_file_path": str,
                     Optional("gdrive_trash_only", default=False): Bool,
+                    Optional("gdrive_acknowledge_abuse", default=False): Bool,
+                    Optional("verify", default=True): Bool,
                     **REMOTE_COMMON,
                 },
                 "http": {**HTTP_COMMON, **REMOTE_COMMON},
@@ -248,6 +266,7 @@ SCHEMA = {
             "instance_gpu": Lower,
             "ssh_private": str,
             "startup_script": str,
+            "setup_script": str,
         },
     },
     # section for experimental features
@@ -256,7 +275,11 @@ SCHEMA = {
         # enabled by default. It's of no use, kept for backward compatibility.
         Optional("parametrization", default=True): Bool,
     },
-    "plots": {"html_template": str},
+    "plots": {
+        "html_template": str,
+        Optional("auto_open", default=False): Bool,
+        "out_dir": str,
+    },
     "exp": {
         "code": str,
         "data": str,
@@ -266,4 +289,13 @@ SCHEMA = {
         "plots": str,
         "live": str,
     },
+    "parsing": {
+        "bool": All(Lower, Choices("store_true", "boolean_optional")),
+        "list": All(Lower, Choices("nargs", "append")),
+    },
+    "hydra": {
+        Optional("enabled", default=False): Bool,
+        "config_dir": str,
+        "config_name": str,
+    },
 }

dvc/daemon.py

@@ -6,6 +6,7 @@ import os
 import platform
 import sys
 from subprocess import Popen
+from typing import List
 
 from dvc.env import DVC_DAEMON
 from dvc.utils import fix_env, is_binary
@@ -42,7 +43,7 @@ def _spawn_windows(cmd, env):
 
 
 def _spawn_posix(cmd, env):
-    from dvc.main import main
+    from dvc.cli import main
 
     # NOTE: using os._exit instead of sys.exit, because dvc built
     # with PyInstaller has trouble with SystemExit exception and throws
@@ -81,7 +82,7 @@ def _spawn_posix(cmd, env):
 
 
 def _spawn(cmd, env):
-    logger.debug(f"Trying to spawn '{cmd}'")
+    logger.debug("Trying to spawn '%s'", cmd)
 
     if os.name == "nt":
         _spawn_windows(cmd, env)
@@ -90,7 +91,7 @@ def _spawn(cmd, env):
     else:
         raise NotImplementedError
 
-    logger.debug(f"Spawned '{cmd}'")
+    logger.debug("Spawned '%s'", cmd)
 
 
 def daemon(args):
@@ -99,15 +100,18 @@ def daemon(args):
     Args:
         args (list): list of arguments to append to `dvc daemon` command.
     """
+    daemonize(["daemon", "-q"] + args)
+
+
+def daemonize(cmd: List[str]):
     if os.environ.get(DVC_DAEMON):
         logger.debug("skipping launching a new daemon.")
         return
 
-    cmd = ["daemon", "-q"] + args
-
     env = fix_env()
-    file_path = os.path.abspath(inspect.stack()[0][1])
-    env["PYTHONPATH"] = os.path.dirname(os.path.dirname(file_path))
+    if not is_binary():
+        file_path = os.path.abspath(inspect.stack()[0][1])
+        env["PYTHONPATH"] = os.path.dirname(os.path.dirname(file_path))
     env[DVC_DAEMON] = "1"
 
     _spawn(cmd, env)

dvc/data_cloud.py

@@ -3,15 +3,38 @@
 import logging
 from typing import TYPE_CHECKING, Iterable, Optional
 
-from dvc.objects.db import get_index
+from funcy import cached_property
+
+from dvc_data.hashfile.db import get_index
 
 if TYPE_CHECKING:
-    from dvc.hash_info import HashInfo
-    from dvc.objects.db.base import ObjectDB
+    from dvc_data.hashfile.db import HashFileDB
+    from dvc_data.hashfile.hash_info import HashInfo
+    from dvc_data.hashfile.status import CompareStatusResult
+    from dvc_data.hashfile.transfer import TransferResult
 
 logger = logging.getLogger(__name__)
 
 
+class Remote:
+    def __init__(self, path, fs, **config):
+        self.path = path
+        self.fs = fs
+
+        self.worktree = config.pop("worktree", False)
+        self.config = config
+
+    @cached_property
+    def odb(self):
+        from dvc_data.hashfile.db import get_odb
+
+        path = self.path
+        if self.worktree:
+            path = self.fs.path.join(path, ".dvc", "cache")
+
+        return get_odb(self.fs, path, **self.config)
+
+
 class DataCloud:
     """Class that manages dvc remotes.
 
@@ -26,18 +49,23 @@ class DataCloud:
     def __init__(self, repo):
         self.repo = repo
 
-    def get_remote_odb(
+    def get_remote(
         self,
         name: Optional[str] = None,
         command: str = "<command>",
-    ) -> "ObjectDB":
+    ) -> "Remote":
         from dvc.config import NoRemoteError
 
         if not name:
             name = self.repo.config["core"].get("remote")
 
         if name:
-            return self._init_odb(name)
+            from dvc.fs import get_cloud_fs
+
+            cls, config, fs_path = get_cloud_fs(self.repo, name=name)
+            fs = cls(**config)
+            config["tmp_dir"] = self.repo.index_db_dir
+            return Remote(fs_path, fs, **config)
 
         if bool(self.repo.config["remote"]):
             error_msg = (
@@ -54,21 +82,43 @@ class DataCloud:
 
         raise NoRemoteError(error_msg)
 
-    def _init_odb(self, name):
-        from dvc.fs import get_cloud_fs
-        from dvc.objects.db import get_odb
+    def get_remote_odb(
+        self,
+        name: Optional[str] = None,
+        command: str = "<command>",
+    ) -> "HashFileDB":
+        remote = self.get_remote(name=name, command=command)
+        return remote.odb
 
-        cls, config, fs_path = get_cloud_fs(self.repo, name=name)
-        config["tmp_dir"] = self.repo.index_db_dir
-        return get_odb(cls(**config), fs_path, **config)
+    def _log_missing(self, status: "CompareStatusResult"):
+        if status.missing:
+            missing_desc = "\n".join(
+                f"name: {hash_info.obj_name}, {hash_info}"
+                for hash_info in status.missing
+            )
+            logger.warning(
+                "Some of the cache files do not exist neither locally "
+                f"nor on remote. Missing cache files:\n{missing_desc}"
+            )
+
+    def transfer(
+        self,
+        src_odb: "HashFileDB",
+        dest_odb: "HashFileDB",
+        objs: Iterable["HashInfo"],
+        **kwargs,
+    ) -> "TransferResult":
+        from dvc_data.hashfile.transfer import transfer
+
+        return transfer(src_odb, dest_odb, objs, **kwargs)
 
     def push(
         self,
         objs: Iterable["HashInfo"],
         jobs: Optional[int] = None,
         remote: Optional[str] = None,
-        odb: Optional["ObjectDB"] = None,
-    ):
+        odb: Optional["HashFileDB"] = None,
+    ) -> "TransferResult":
         """Push data items in a cloud-agnostic way.
 
         Args:
@@ -78,17 +128,15 @@ class DataCloud:
                 By default remote from core.remote config option is used.
             odb: optional ODB to push to. Overrides remote.
         """
-        from dvc.objects.transfer import transfer
-
-        if not odb:
-            odb = self.get_remote_odb(remote, "push")
-        return transfer(
+        odb = odb or self.get_remote_odb(remote, "push")
+        return self.transfer(
             self.repo.odb.local,
             odb,
             objs,
             jobs=jobs,
             dest_index=get_index(odb),
             cache_odb=self.repo.odb.local,
+            validate_status=self._log_missing,
         )
 
     def pull(
@@ -96,8 +144,8 @@ class DataCloud:
         objs: Iterable["HashInfo"],
         jobs: Optional[int] = None,
         remote: Optional[str] = None,
-        odb: Optional["ObjectDB"] = None,
-    ):
+        odb: Optional["HashFileDB"] = None,
+    ) -> "TransferResult":
         """Pull data items in a cloud-agnostic way.
 
         Args:
@@ -107,11 +155,8 @@ class DataCloud:
                 By default remote from core.remote config option is used.
             odb: optional ODB to pull from. Overrides remote.
         """
-        from dvc.objects.transfer import transfer
-
-        if not odb:
-            odb = self.get_remote_odb(remote, "pull")
-        return transfer(
+        odb = odb or self.get_remote_odb(remote, "pull")
+        return self.transfer(
             odb,
             self.repo.odb.local,
             objs,
@@ -119,6 +164,7 @@ class DataCloud:
             src_index=get_index(odb),
             cache_odb=self.repo.odb.local,
             verify=odb.verify,
+            validate_status=self._log_missing,
         )
 
     def status(
@@ -126,7 +172,7 @@ class DataCloud:
         objs: Iterable["HashInfo"],
         jobs: Optional[int] = None,
         remote: Optional[str] = None,
-        odb: Optional["ObjectDB"] = None,
+        odb: Optional["HashFileDB"] = None,
         log_missing: bool = True,
     ):
         """Check status of data items in a cloud-agnostic way.
@@ -141,7 +187,7 @@ class DataCloud:
             log_missing: log warning messages if file doesn't exist
                 neither in cache, neither in cloud.
         """
-        from dvc.objects.status import compare_status
+        from dvc_data.hashfile.status import compare_status
 
         if not odb:
             odb = self.get_remote_odb(remote, "status")
@@ -157,5 +203,5 @@ class DataCloud:
 
     def get_url_for(self, remote, checksum):
         odb = self.get_remote_odb(remote)
-        path = odb.hash_to_path(checksum)
+        path = odb.oid_to_path(checksum)
         return odb.fs.unstrip_protocol(path)

dvc/dependency/__init__.py

@@ -18,7 +18,7 @@ SCHEMA: Mapping[str, Any] = {
 }
 
 
-def _get(stage, p, info):
+def _get(stage, p, info, fs_config=None):
     if info and info.get(RepoDependency.PARAM_REPO):
         repo = info.pop(RepoDependency.PARAM_REPO)
         return RepoDependency(repo, stage, p, info)
@@ -27,7 +27,7 @@ def _get(stage, p, info):
         params = info.pop(ParamsDependency.PARAM_PARAMS)
         return ParamsDependency(stage, p, params)
 
-    return Dependency(stage, p, info)
+    return Dependency(stage, p, info, fs_config=fs_config)
 
 
 def loadd_from(stage, d_list):
@@ -38,25 +38,46 @@ def loadd_from(stage, d_list):
     return ret
 
 
-def loads_from(stage, s_list, erepo=None):
+def loads_from(stage, s_list, erepo=None, fs_config=None):
     assert isinstance(s_list, list)
     info = {RepoDependency.PARAM_REPO: erepo} if erepo else {}
-    return [_get(stage, s, info.copy()) for s in s_list]
+    return [
+        _get(
+            stage,
+            s,
+            info.copy(),
+            fs_config=fs_config,
+        )
+        for s in s_list
+    ]
 
 
 def _merge_params(s_list):
     d = defaultdict(list)
     default_file = ParamsDependency.DEFAULT_PARAMS_FILE
+
+    # figure out completely tracked params file, and ignore specific keys
+    wholly_tracked = set()
+    for key in s_list:
+        if not isinstance(key, dict):
+            continue
+        wholly_tracked.update(k for k, params in key.items() if not params)
+
     for key in s_list:
         if isinstance(key, str):
-            d[default_file].append(key)
+            if default_file not in wholly_tracked:
+                d[default_file].append(key)
             continue
+
         if not isinstance(key, dict):
             msg = "Only list of str/dict is supported. Got: "
             msg += f"'{type(key).__name__}'."
             raise ValueError(msg)
 
         for k, params in key.items():
+            if k in wholly_tracked:
+                d[k] = []
+                continue
             if not isinstance(params, list):
                 msg = "Expected list of params for custom params file "
                 msg += f"'{k}', got '{type(params).__name__}'."