dvc_session/src/linear_svc.py

import plac
from sklearn.svm import LinearSVC

from src.utils import (
    dump_yaml,
    evaluate_model,
    print_results,
    read_data,
    read_yaml,
    save_results,
)


@plac.annotations(
    data_path=("Path to source data", "option", "i", str),
    out_path=("Path to save trained Model", "option", "o", str),
)
def main(data_path="data/features/", out_path="models/svc/"):
    X_train, X_test, y_train, y_test = read_data(data_path)

    name = "LinearSVC"
    params = read_yaml("params.yaml", "svc")
    model = LinearSVC(**params)
    model.fit(X_train, y_train)

    accuracy, c_matrix, fig = evaluate_model(model, X_test, y_test)
    print_results(accuracy, c_matrix, name)

    save_results(out_path, model, fig)
    dump_yaml(
        dict(accuracy=accuracy, confusion_matrix=c_matrix),
        f"{out_path}metrics.yaml",
    )


if __name__ == "__main__":
    plac.call(main)