print("Any NaN in train target df 'crime_test' ?",
y_test.isnull().values.any())
print()
print()
print("scoring:", scoring)
print()
X_test_imputed = eu.reorder_ohencoded_X_test_columns(
X_train_imputed, X_test_imputed)
sltt['arrays'] = (X_train_imputed, X_test_imputed, y_train, y_test)
# end custom feat. engineering
print("Evaluation, training")
print()
# you already did encoding
auto_feat_eng_data = eu.auto_X_encoding(sltt,
random_state=seed,
encode=False)
print()
ev.perform_classic_cv_evaluation_and_calibration(auto_feat_eng_data,
scoring,
Y_type,
labels=labels,
random_state=seed)
print("X_train -- first row:", X_train.values[0])
print("y_train shape: ", y_train.shape)
print()
print("X_test shape: ", X_test.shape)
print("X_test -- first row:", X_test.values[0])
print("y_test shape: ", y_test.shape)
print()
print(y_train[:3])
print()
print("scoring:", scoring)
print()
auto_feat_eng_data = eu.auto_X_encoding(sltt, seed)
print()
eva.select_evaluation_strategy(auto_feat_eng_data,
target,
0.2,
odf,
scoring,
Y_type,
labels=classes,
d_name=d_name,
random_state=seed,
learn=learnm)
input("=== [End Of Program] Enter key to continue... \n")