upsampling

from sklearn.utils import shuffle

def upsample(features, target, repeat):
    '''Данная функция создана для того, чтобы
    увеличить выборку'''
    features_zeros = features[target == 0]
    features_ones = features[target == 1]
    target_zeros = target[target == 0]
    target_ones = target[target == 1]

    features_upsampled = pd.concat([features_zeros] + [features_ones] * repeat)
    target_upsampled = pd.concat([target_zeros] + [target_ones] * repeat)

    features_upsampled, target_upsampled = shuffle(
        features_upsampled, target_upsampled, random_state=12345)

    return features_upsampled, target_upsampled

features_upsampled, target_upsampled = upsample(features_train, target_train, 10)

model = RandomForestClassifier(random_state=12345, criterion='gini', max_depth=11,
                               min_samples_leaf=2, n_estimators=76, class_weight='balanced')
model.fit(features_upsampled, target_upsampled)
predicted_valid = model.predict(features_valid)

print("F1:", f1_score(target_valid, predicted_valid))

#OUTPUT F1: 0.5956471935853379