dvc_pipeline.sh

# Install DVC
$ pip install dvc

# Initialize DVC repository
$ dvc init

# Download a file and put to data/ directory.
$ dvc import https://s3-us-west-2.amazonaws.com/dvc-share/so/25K/Posts.xml.tgz data/

# Extract XML from the archive.
$ dvc run tar zxf data/Posts.xml.tgz -C data/

# Prepare data.
$ dvc run python code/xml_to_tsv.py data/Posts.xml data/Posts.tsv python

# Split training and testing dataset. Two output files.
# 0.33 is the test dataset splitting ratio. 20170426 is a seed for randomization.
$ dvc run python code/split_train_test.py data/Posts.tsv 0.33 20170426 data/Posts-train.tsv data/Posts-test.tsv

# Extract features from text data. Two TSV inputs and two pickle matrixes outputs.
$ dvc run python code/featurization.py data/Posts-train.tsv data/Posts-test.tsv data/matrix-train.p data/matrix-test.p

# Train ML model out of the training dataset. 20170426 is another seed value.
$ dvc run python code/train_model.py data/matrix-train.p 20170426 data/model.p

# Evaluate the model by the testing dataset.
$ dvc run python code/evaluate.py data/model.p data/matrix-test.p data/evaluation.txt

# The result.
$ cat data/evaluation.txt
AUC: 0.596182