def test_unmarked_categorical_column_throws_warning():
df_titanic_train, df_titanic_test = utils.get_titanic_binary_classification_dataset(
)
column_descriptions = {
'survived': 'output'
# This is the column we are "forgetting" to mark as categorical
# , 'sex': 'categorical'
,
'embarked': 'categorical',
'pclass': 'categorical'
}
ml_predictor = Predictor(type_of_estimator='classifier',
column_descriptions=column_descriptions)
with warnings.catch_warnings(record=True) as caught_w:
ml_predictor.train(df_titanic_train)
print(
'we should be throwing a warning for the user to give them useful feedback on the unlabeled categorical column'
)
assert len(caught_w) == 1
ml_predictor.predict(df_titanic_test)
# We want to make sure the above does not throw an error
assert True
def test_unexpected_datetime_column_handled_without_errors():
df_titanic_train, df_titanic_test = utils.get_titanic_binary_classification_dataset(
)
column_descriptions = {
'survived': 'output',
'sex': 'categorical',
'embarked': 'categorical',
'pclass': 'categorical'
}
ml_predictor = Predictor(type_of_estimator='classifier',
column_descriptions=column_descriptions)
ml_predictor.train(df_titanic_train)
test_dict = df_titanic_test.sample(frac=0.1).to_dict('records')[0]
test_dict['unexpected_column'] = datetime.date.today()
test_dict['anoter_unexpected_column'] = datetime.datetime.today()
ml_predictor.predict(test_dict)
# We want to make sure the above does not throw an error
assert True
'LGBMClassifier',
'CatBoostClassifier',
'XGBClassifier',
], # chose all Classifiers
#optimize_final_model=True, # falls with an error :(
#feature_learning=True,
#fl_data=X_test.copy(),
ml_for_analytics=False,
verbose=False,
)
print(f'PREDICT ON FOLD {count}')
predictions = automl.predict_proba(X_test)
print('AUC: ', roc_auc_score(y_test, predictions[:, 1]))
y_test_predict_proba = predictions[:, 1]
y_test_predict = automl.predict(X_test)
END_EXPERIMENT = time.time()
#preds = pd.DataFrame(predictions)
#preds['Y'] = y_test.reset_index(drop=True)
# preds.to_csv(f'./result/predicts/{DATASET_NAME}_{MODEL_NAME}_predict_proba_exp_{EXPERIMENT}.csv', index=False,)
metrics.append({
'AUC':
round(roc_auc_score(y_test, y_test_predict_proba), 4),
'log_loss':
round(log_loss(y_test, y_test_predict_proba), 4),
'Accuracy':
round(accuracy_score(y_test, y_test_predict), 4),
'Time_min': (END_EXPERIMENT - START_EXPERIMENT) // 60,
