def test_random_forest_classifier_fit(): mp_table = MyPyTable(interview_header, interview_table) # Formulate X_train and y_train y_train = mp_table.get_column('interviewed_well') X_train_col_names = ["level", "lang", "tweets", "phd"] X_train = mp_table.get_rows(X_train_col_names) myRF = MyRandomForestClassifier(N=4, M=2, F=4) myRF.fit(X_train, y_train) assert len(myRF.M_attr_sets) == myRF.M
def test_random_forest_classifier_predict(): X_test = [["Mid", "Python", "no", "no", "True"], ["Mid", "R", "yes", "yes", "True"], ["Mid", "Python", "no", "yes", "True"]] y_test = ["True", "True", "True"] mp_table = MyPyTable(interview_header, interview_table) # Formulate X_train and y_train y_train = mp_table.get_column('interviewed_well') X_train_col_names = ["level", "lang", "tweets", "phd"] X_train = mp_table.get_rows(X_train_col_names) myRF = MyRandomForestClassifier(N=4, M=2, F=4) myRF.fit(X_train, y_train) predictions = myRF.predict(X_test) for i in range(0, len(predictions)): assert predictions[i] == y_test[i]