balancedRF.py

from imblearn.ensemble import BalancedRandomForestClassifier
from sklearn.datasets import make_classification
from imblearn.pipeline import Pipeline
from sklearn.model_selection import train_test_split
from sklearn import metrics

X, y = make_classification(n_samples=1000, n_classes=3,
                           n_informative=4, weights=[0.2, 0.3, 0.5],
                           random_state=0)

X_train, X_test, y_train, y_test = train_test_split(X, y, stratify=y, test_size=0.2)

clf = BalancedRandomForestClassifier()

pipeline = Pipeline([ ('rf', clf)])

hyper_params = {'rf__max_depth': 20, 'rf__max_features': 2, 'rf__n_estimators': 1000}
pipeline.set_params(**hyper_params)

model = pipeline.fit(X_train, y_train)
y_pred = model.predict(X_test)

accuracy = metrics.accuracy_score(y_true=y_test, y_pred=y_pred)
# store accuracy in results

print('---------------------')
print('|      Accuracy      |')
print('---------------------')
print('\n    {}\n\n'.format(accuracy))