Milestone 3 / Readme

[yhan178]

Update Readme file. Please update your command to run the analysis here for synthesis。

[yhan178]

For performing EDA and saving plot, enter the following commands in the terminal in the project root:

# perform eda and save plots
python scripts/eda.py  \
  --data-file=data/van_weather_1990-01-01_2023-11-06.csv \
  --plot-to=results/figures

[dorisyycai]

Below command is for data cleaning and preprocessing, exporting train/test split and csv, saving model preprocessor in .pickle file #65

python scripts/drop_split_preprocess.py \
  --data-file=data/van_weather_1990-01-01_2023-11-06.csv \
  --data-to=data/processed  \
  --preprocessor-to=results/models \
  --seed=522

[dorisyycai]

Just a side note - I created a branch called readme specifically for updating README in milestone1 and milestone2. Please use the same branch to update README for consistency. Thanks.

[wqxxzd]

For downloading the data, please use the following command as the reference

python scripts/download_data.py \
        --url="https://archive-api.open-meteo.com/v1/archive" \
        --start-date=1990-01-01 \
        --end-date=2023-11-06\
        --write-to="./data"

[sivakornchong]

For running classification models, please use the command line below as reference. Output would be a trained model pickle file and 3 images.

python scripts/classification.py
  --x_train=data/processed/X_train.csv \
  --y_train=data/processed/y_train.csv \
  --x-test=data/processed/X_test.csv \
  --y-test=data/processed/y_test.csv \
  --preprocessor=results/models/precipit_preprocessor.pickle \
  --columns-to-drop=data/processed/columns_to_drop.csv \
  --pipeline-to=results/models \
  --plot-to=results/figures \
  --seed=522

[dorisyycai]

build HTML report and copy build to docs folder

jupyter-book build reports/milestone3
cp -r reports/milestone3/_build/html/* docs