def balance_dataset(dataset, classe):
y = dataset[classe]
X = dataset.drop(columns=[classe])
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=0)
sm = SMOTE(random_state=2)
X_train_res, y_train_res = sm.fit_sample(X_train, y_train.ravel())
return X_train, X_test, y_train, y_test, X_train_res, y_train_res
green_data['hinselmann'] = 0
green_data['schiller'] = 0
hinselmann_data['hinselmann'] = 1
hinselmann_data['schiller'] = 0
schiller_data['hinselmann'] = 0
schiller_data['schiller'] = 1
super_table = green_data.append(hinselmann_data)
super_table = super_table.append(schiller_data)
X, y = split_dataset(super_table, CLASS)
X = getKBest(X, y)
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.3,
random_state=0)
sm = SMOTE(random_state=2)
X_train_res, y_train_res = sm.fit_sample(X_train, y_train.ravel())
results = {}
for clf in base_clfs:
clf_name = type(clf).__name__
stats = classifier_statistics(clf, X_train_res, X_test, y_train_res,
y_test)
results[clf_name] = stats
measures = {}