From e70ebb1e3d55e29dabdb403041a28dc08eae940b Mon Sep 17 00:00:00 2001 From: Ruslan Kuprieiev Date: Fri, 24 Nov 2017 18:52:43 +0200 Subject: [PATCH] functest: use new 'dvc run' semantics in tutorial Signed-off-by: Ruslan Kuprieiev --- functest/tutorial_end_to_end.sh | 21 ++++++++++++--------- 1 file changed, 12 insertions(+), 9 deletions(-) diff --git a/functest/tutorial_end_to_end.sh b/functest/tutorial_end_to_end.sh index f3d732845..ab37dee4a 100755 --- a/functest/tutorial_end_to_end.sh +++ b/functest/tutorial_end_to_end.sh @@ -23,16 +23,17 @@ git commit -m 'Download code' dvc init -dvc import https://s3-us-west-2.amazonaws.com/dvc-share/so/10K/Posts.xml.tgz data/ -dvc run tar zxf data/Posts.xml.tgz -C data/ +wget -P data/ https://s3-us-west-2.amazonaws.com/dvc-share/so/10K/Posts.xml.tgz +dvc add data/Posts.xml.tgz +dvc run -d data/Posts.xml.tgz -o data/Posts.xml 'tar zxf data/Posts.xml.tgz -C data/' -dvc run python code/xml_to_tsv.py data/Posts.xml data/Posts.tsv python -dvc run python code/split_train_test.py data/Posts.tsv 0.33 20170426 data/Posts-train.tsv data/Posts-test.tsv -dvc run python code/featurization.py data/Posts-train.tsv data/Posts-test.tsv data/matrix-train.p data/matrix-test.p +dvc run -d code/xml_to_tsv.py -d data/Posts.xml -o data/Posts.tsv 'python code/xml_to_tsv.py data/Posts.xml data/Posts.tsv python' +dvc run -d code/split_train_test.py -d data/Posts.tsv -o data/Posts-test.tsv 'python code/split_train_test.py data/Posts.tsv 0.33 20170426 data/Posts-train.tsv data/Posts-test.tsv' +dvc run -d code/featurization.py -d data/Posts-train.tsv -d data/Posts-test.tsv -o data/matrix-train.p -o data/matrix-test.p 'python code/featurization.py data/Posts-train.tsv data/Posts-test.tsv data/matrix-train.p data/matrix-test.p' -dvc run python code/train_model.py data/matrix-train.p 20170426 data/model.p +dvc run -d code/train_model.py -d data/matrix-train.p -o data/model.p 'python code/train_model.py data/matrix-train.p 20170426 data/model.p' -dvc run python code/evaluate.py data/model.p data/matrix-test.p data/evaluation.txt +dvc run -d code/evaluate.py -d data/model.p -d data/matrix-test.p -o data/evaluation.txt 'python code/evaluate.py data/model.p data/matrix-test.p data/evaluation.txt' cat data/evaluation.txt # AUC: 0.552980 @@ -43,8 +44,10 @@ exit 0 dvc remove data/Posts.xml.tgz #dvc import https://s3-us-west-2.amazonaws.com/dvc-share/so/100K/Posts.xml.tgz data/ -dvc import https://s3-us-west-2.amazonaws.com/dvc-share/so/25K/Posts.xml.tgz data/ -dvc repro data/evaluation.txt + +wget -P data/ https://s3-us-west-2.amazonaws.com/dvc-share/so/25K/Posts.xml.tgz +dvc add data/Posts.xml.tgz +dvc repro -v data/evaluation.txt cat data/evaluation.txt # AUC: 0.639861