def main():
x, y = load_iris(return_X_y=True)
indices = np.arange(len(x))
shuffle(indices)
# use 80% of samples for training
train_idx = indices[:int(0.8 * len(x))]
test_idx = indices[int(0.8 * len(x)):]
# Train the RF classifier
print("- Training Random Forest classifier with %s samples of Iris "
"dataset." % len(train_idx))
x_train = ds.array(x[train_idx], (10, 4))
y_train = ds.array(y[train_idx][:, np.newaxis], (10, 1))
forest = RandomForestClassifier(10)
forest.fit(x_train, y_train)
# Test the trained RF classifier
print("- Testing the classifier.", end='')
x_test = ds.array(x[test_idx], (10, 4))
y_real = ds.array(y[test_idx][:, np.newaxis], (10, 1))
y_pred = forest.predict(x_test)
score = compss_wait_on(forest.score(x_test, y_real))
# Put results in fancy dataframe and print the accuracy
df = pd.DataFrame(data=list(zip(y[test_idx], y_pred.collect())),
columns=['Label', 'Predicted'])
print(" Predicted values: \n\n%s" % df)
print("\n- Classifier accuracy: %s" % score)
def test_make_classification_hard_vote_predict(self):
"""Tests RandomForestClassifier predict with hard_vote."""
x, y = make_classification(
n_samples=3000,
n_features=10,
n_classes=3,
n_informative=4,
n_redundant=2,
n_repeated=1,
n_clusters_per_class=2,
shuffle=True,
random_state=0,
)
x_train = ds.array(x[::2], (300, 10))
y_train = ds.array(y[::2][:, np.newaxis], (300, 1))
x_test = ds.array(x[1::2], (300, 10))
y_test = y[1::2]
rf = RandomForestClassifier(random_state=0,
sklearn_max=10,
hard_vote=True)
rf.fit(x_train, y_train)
y_pred = rf.predict(x_test).collect()
accuracy = np.count_nonzero(y_pred == y_test) / len(y_test)
self.assertGreater(accuracy, 0.7)
def test_make_classification_predict_and_distr_depth(self):
"""Tests RandomForestClassifier fit and predict with a distr_depth."""
x, y = make_classification(n_samples=3000,
n_features=10,
n_classes=3,
n_informative=4,
n_redundant=2,
n_repeated=1,
n_clusters_per_class=2,
shuffle=True,
random_state=0)
x_train = ds.array(x[:len(x) // 2], (300, 10))
y_train = ds.array(y[:len(y) // 2][:, np.newaxis], (300, 1))
x_test = ds.array(x[len(x) // 2:], (300, 10))
y_test = y[len(y) // 2:]
rf = RandomForestClassifier(distr_depth=2, random_state=0)
rf.fit(x_train, y_train)
y_pred = rf.predict(x_test).collect()
accuracy = np.count_nonzero(y_pred == y_test) / len(y_test)
self.assertGreater(accuracy, 0.7)