p3.py 文件源码

def run_statsmodels_models(train, test, model_description):
    """
    Run logistic regression model to predict whether a signed up driver ever actually drove.
    :param input_df: Data frame prepared for statsmodels regression
    :type input_df: pd.DataFrame
    :return: AUC for model generated
    :rtype: float
    """
    # Run model on all observations
    # Use dmatrices to format data
    logging.info('Running model w/ description: %s' %model_description)
    logging.debug('Train df: \n%s' % train.describe())
    logging.debug('Test df: \n%s' % test.describe())
    y_train, X_train = dmatrices(model_description, data=train, return_type='dataframe', NA_action='drop')
    y_test, X_test = dmatrices(model_description, data=test, return_type='dataframe', NA_action='drop')

    # Create, fit model
    mod = sm.Logit(endog=y_train, exog=X_train)
    res = mod.fit(method='bfgs', maxiter=100)

    # Output model summary
    print train['city_name'].value_counts()
    print train['signup_channel'].value_counts()
    print res.summary()

    # Create, output AUC
    predicted = res.predict(X_test)
    auc = roc_auc_score(y_true=y_test, y_score=predicted)
    print 'AUC for 20%% holdout: %s' %auc

    # Return AUC for model generated
    return auc



# Main section