Cookiecutter-MLOps/src/models/predict_model.py

import sys
import pandas as pd
from scipy.sparse import load_npz
from dagshub import DAGsHubLogger
import pickle
from sklearn.metrics import classification_report


def evaluate(processed_data_path, model_path):
    X_test = load_npz(processed_data_path + "X_test.npz")
    y_test = pd.read_csv(processed_data_path + "y_test.csv")["sentiment"]

    logger = DAGsHubLogger(
        metrics_path="reports/metrics.csv",
        should_log_hparams=False,
    )

    model = pickle.load(open(model_path + "model.pkl", "rb"))
    y_pred = model.predict(X_test)

    cr = classification_report(y_test, y_pred, output_dict=True)
    # Flatten Dict
    flatten_cr = pd.json_normalize(cr, sep="_").to_dict(orient="records")[0]

    logger.log_metrics(flatten_cr)

    logger.save()
    logger.close()


if __name__ == "__main__":
    if not (1 <= len(sys.argv) <= 3):
        print(
            "usage: %s <processed_data_folder (optional)> <model_folder (optional)>"
            % sys.argv[0],
            file=sys.stderr,
        )
        sys.exit(0)

    data_folder = sys.argv[1] if len(sys.argv) >= 2 else "data/processed/"
    model_folder = sys.argv[2] if len(sys.argv) == 3 else "models/"

    evaluate(data_folder, model_folder)