titanic_dvc/dvc.yaml

stages:
  make_dataset:
    desc: Download data from Kaggle, create data dictionary and summary dtable
    cmd: python3 src/data/make_dataset.py -c titanic -tr train.csv -te test.csv -o
      ./data/raw
    deps:
      - src/data/make_dataset.py
    params:
      - dtypes
    outs:
      - data/raw/test.csv
      - data/raw/train.csv
      - reports/figures/data_dictionary.tex
      - reports/figures/table_one.tex
  encode_labels:
    desc: Convert categorical labels to integer values and save mapping
    cmd: python3 src/data/encode_labels.py -tr data/raw/train.csv -te data/raw/test.csv
      -o data/interim
    deps:
      - data/raw/test.csv
      - data/raw/train.csv
      - src/data/encode_labels.py
    params:
      - dtypes
    outs:
      - data/interim/label_encoding.yaml
      - data/interim/test_categorized.csv
      - data/interim/train_categorized.csv
  impute_nan:
    desc: Replace missing values for age with mean values from training dataset.
    cmd: python3 src/data/replace_nan.py -tr data/interim/train_categorized.csv -te
      data/interim/test_categorized.csv -o data/interim
    deps:
      - data/interim/test_categorized.csv
      - data/interim/train_categorized.csv
      - src/data/replace_nan.py
    params:
      - imputation
    outs:
      - data/interim/test_nan_imputed.csv
      - data/interim/train_nan_imputed.csv