データサイエンス開発環境のセットアップを整理する

pip install kaggle

mkdir ~/.kaggle
mv kaggle.json ~/.kaggle/
chmod 600 ~/.kaggle/kaggle.json

kaggle competitions download titanic
unzip titanic.zip

python -m venv .setupdatascience
source .setupdatascience/bin/activate

pip install -r requirements.txt

ERROR: awscli 1.25.7 has requirement docutils<0.17,>=0.10, but you'll have docutils 0.18.1 which is incompatible.

echo "pandas" >> requirements.txt
echo "sklearn" >> requirements.txt
echo "pytest" >> requirements.txt
echo "lightgbm" >> requirements.txt
echo "mlflow" >> requirements.txt

make requirements

# -*- coding: utf-8 -*-
import click
import logging
from pathlib import Path
from dotenv import find_dotenv, load_dotenv
import pandas as pd


@click.command()
@click.argument('input_filepath', type=click.Path(exists=True))
@click.argument('output_filepath', type=click.Path())
def main(input_filepath, output_filepath):
    """ Runs data processing scripts to turn raw data from (../raw) into
        cleaned data ready to be analyzed (saved in ../processed).
    """
    logger = logging.getLogger(__name__)
    logger.info('making final data set from raw data')
    train = pd.read_csv(Path(input_filepath, "train.csv"))
    train.to_csv(Path(output_filepath, "train.csv"))


if __name__ == '__main__':
    log_fmt = '%(asctime)s - %(name)s - %(levelname)s - %(message)s'
    logging.basicConfig(level=logging.INFO, format=log_fmt)

    # not used in this stub but often useful for finding various files
    project_dir = Path(__file__).resolve().parents[2]

    # find .env automagically by walking up directories until it's found, then
    # load up the .env entries as environment variables
    load_dotenv(find_dotenv())

    main()

make data

## Make Dataset
data: requirements
	$(PYTHON_INTERPRETER) src/data/make_dataset.py data/raw data/processed