pricing-house/main.py

import pandas as pd
from sklearn.metrics import mean_absolute_error
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestRegressor
from dagshub import DAGsHubLogger


if __name__ == "__main__":
    iowa_file_path = 'data/train.csv'

    home_data = pd.read_csv(iowa_file_path)
    # Create target object and call it y
    y = home_data.SalePrice
    # Create X
    features = ['LotArea', 'YearBuilt', '1stFlrSF', '2ndFlrSF', 'FullBath', 'BedroomAbvGr', 'TotRmsAbvGrd']
    X = home_data[features]

    # Split into validation and training data
    train_X, val_X, train_y, val_y = train_test_split(X, y, random_state=1)

    logger = DAGsHubLogger()
    logger.log_hyperparams(model="RandomForest")
    logger.log_hyperparams(criterion="mae")
    # Specify Model
    iowa_model = RandomForestRegressor(n_estimators=100, criterion='mae', random_state=0)
    # Fit Model
    iowa_model.fit(train_X, train_y)

    # Make validation predictions and calculate mean absolute error
    val_predictions = iowa_model.predict(val_X)
    val_mae = mean_absolute_error(val_predictions, val_y)
    logger.log_metrics(mae=val_mae)
    logger.save()
    logger.close()
    print("Validation MAE when not specifying max_leaf_nodes: {:,.0f}".format(val_mae))
    # Save predictions in format used for competition scoring
    output = pd.DataFrame({'Id': val_X.index,
                           'SalePrice': val_predictions})
    output.to_csv('submission.csv', index=False)