Merge branch 'master' into data-registry

example-get-started/generate.sh

@@ -41,25 +41,23 @@ dvc remote add -d --local storage s3://dvc-public/remote/get-started
 dvc remote add -d storage https://remote.dvc.org/get-started
 
 git add .
-git commit -a -m "Configure default HTTP remote (read-only)"
+git commit -m "Configure default HTTP remote (read-only)"
 git tag -a "2-remote" -m "Read-only remote storage configured."
 
 mkdir data
 wget https://data.dvc.org/get-started/data.xml -O data/data.xml
 dvc add data/data.xml
 git add data/.gitignore data/data.xml.dvc
-git commit -m "Add raw data with to project"
+git commit -m "Add raw data to project"
 git tag -a "3-add-file" -m "Data file added."
 dvc push
 
-mkdir src
 wget https://code.dvc.org/get-started/code.zip
 unzip code.zip
 rm -f code.zip
-echo "dvc[s3]" >> src/requirements.txt
 cp $HERE/code/README.md $REPO_PATH
 git add .
-git commit -m 'Add source code files to repo'
+git commit -m "Add source code files to repo"
 git tag -a "4-sources" -m "Source code added."
 
 pip install -r src/requirements.txt
@@ -98,17 +96,21 @@ dvc run -f evaluate.dvc \
         python src/evaluate.py model.pkl data/features auc.metric
 git add .gitignore evaluate.dvc auc.metric
 git commit -m "Create evaluation stage"
-git tag -a "baseline-experiment" -m "Baseline experiment"
+git tag -a "baseline-experiment" -m "Baseline experiment evaluation"
 git tag -a "8-evaluation" -m "Baseline evaluation stage created."
 dvc push
 
 sed -e s/max_features=5000\)/max_features=6000\,\ ngram_range=\(1\,\ 2\)\)/ -i "" \
     src/featurization.py
 
+dvc repro train.dvc
+git commit -am "Reproduce model using bigrams"
+git tag -a "9-bigrams-model" -m "Model retrained using bigrams."
+
 dvc repro evaluate.dvc
-git commit -a -m "Reproduce evaluation stage using bigrams"
-git tag -a "bigrams-experiment" -m "Bigrams experiment"
-git tag -a "9-bigrams" -m "Bigrams evaluation stage created."
+git commit -am "Evaluate bigrams model"
+git tag -a "bigrams-experiment" -m "Bigrams experiment evaluation"
+git tag -a "10-bigrams-experiment" -m "Evaluated bigrams model."
 dvc push
 
 popd
@@ -117,7 +119,7 @@ echo "`cat <<EOF-
 
 The Git repo generated by this script is intended to be published on
 https://github.com/iterative/example-get-started. Make sure the Github repo
-exists firt.
+exists first and that you have appropriate write permissions.
 
 To create it with https://hub.github.com/ for example, run:
 
@@ -133,6 +135,6 @@ git push --force origin --tags
 
 You may remove the generated repo with:
 
-rm -fR build
+rm -fR build/
 
 `"