def test_train_test_split(self):
X = pd.DataFrame([1, 2, 3, 4, 5, 6, 7, 8, 9, 10])
train_X, test_X = train_test_split(X, test_size=0.2, random_state=42)
expected_train_X = pd.DataFrame([6, 1, 8, 3, 10, 5, 4, 7]).set_index(pd.Series([5, 0, 7, 2, 9, 4, 3, 6]))
expected_test_X = pd.DataFrame([9, 2]).set_index(pd.Series([8, 1]))
pandas.testing.assert_frame_equal(expected_train_X, train_X)
pandas.testing.assert_frame_equal(expected_test_X, test_X)
def plot_learning_curves(model, X, y):
X_train, X_val = train_test_split(X, test_size=0.2, random_state=42)
y_train, y_val = train_test_split(y, test_size=0.2, random_state=42)
train_errors, val_errors = [], []
for m in range(1, len(X_train)):
model.fit(X_train[:m], y_train[:m])
y_train_predict = model.predict(X_train[:m])
y_val_predict = model.predict(X_val)
train_errors.append(mean_squared_error(y_train[:m], y_train_predict))
val_errors.append(mean_squared_error(y_val, y_val_predict))
plt.xlabel('Training set size', fontsize=14)
plt.ylabel('RMSE', fontsize=14)
plt.plot(np.sqrt(train_errors), 'r-', linewidth=2, label='train')
plt.plot(np.sqrt(val_errors), 'b-', linewidth=2, label='val')
plt.legend(loc='upper right', fontsize=14)
plt.show()
def main():
"""
:brief: The main function executes the program.
"""
filename = os.path.join(datasets_path, 'bank.csv')
x, y, headers = read_dataset(filename, header=True, x_y=True)
# we create the train = 70% dataset and the test = 30% dataset
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.3)
adaboost_classifier = AdaBoostClassifier(
base_estimator=DecisionTree(max_depth=1), n_estimators=5)
adaboost_classifier.fit(x_train, y_train, headers=headers)
predictions = adaboost_classifier.predict(x_test)
accuracy = accuracy_score(y_test, predictions)
print("Accuracy of AdaBoost Classifier: {:.2f}% ".format(accuracy * 100))
def main():
"""
:brief: The main function executes the program.
"""
filename = os.path.join(datasets_path, 'bank.csv')
x, y, headers = read_dataset(filename, header=True, x_y=True)
# we create the train = 70% dataset and the test = 30% dataset
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.3)
decision_tree = DecisionTree(max_depth=4,
min_samples_split=5,
min_samples_leaf=2)
decision_tree.fit(x_train, y_train, headers=headers)
print(decision_tree)
predictions = decision_tree.predict(x_test)
accuracy = accuracy_score(y_test, predictions)
print("Accuracy of Decision Tree: {:.2f}% ".format(accuracy * 100))
def test_fit_predict(self):
data = pd.read_csv('learnml/linear_model/tests/test_data.csv')
train, test = train_test_split(data, test_size=0.2, random_state=42)
X_train = train.drop('y', axis=1).values
y_train = train['y'].values
X_test = test.drop('y', axis=1).values
y_test = test['y'].values
scaler = StandardScaler()
scaler.fit(X_train)
X_train = scaler.transform(X_train)
X_test = scaler.transform(X_test)
per_clf = Perceptron()
per_clf.fit(X_train, y_train)
y_pred = per_clf.predict(X_test)
accuracy_score = np.mean(y_pred == y_test)
self.assertTrue(accuracy_score >= 0.8)
def test_fit_predict(self):
data = pd.read_csv('learnml/neural_network/tests/test_data.csv')
train, test = train_test_split(data, 0.2, random_state=42)
X_train = train.drop('y', axis=1).values
y_train = train['y'].values
X_test = test.drop('y', axis=1).values
y_test = test['y'].values
scaler = StandardScaler()
scaler.fit(X_train)
X_train = scaler.transform(X_train)
X_test = scaler.transform(X_test)
nn_clf = NeuralNetwork(layer_dims=np.array([2, 1]),
learning_rate=1,
num_iterations=100)
nn_clf.fit(X_train, y_train)
y_pred = nn_clf.predict(X_test)
accuracy_score = np.mean(y_pred == y_test)
self.assertTrue(accuracy_score >= 0.8)
def test_fit_predict(self):
data = pd.read_csv('learnml/linear_model/tests/test_data.csv')
train, test = train_test_split(data, test_size=0.2, random_state=42)
X_train = train.drop('y', axis=1).values
y_train = train['y'].values
X_test = test.drop('y', axis=1).values
y_test = test['y'].values
scaler = StandardScaler()
scaler.fit(X_train)
X_train = scaler.transform(X_train)
X_test = scaler.transform(X_test)
for i, penalty in enumerate(['l2', 'l1']):
with self.subTest(penalty=penalty):
log_clf = SGDClassifier(penalty=penalty, max_iter=5000, eta0=1)
log_clf.fit(X_train, y_train)
y_pred = log_clf.predict(X_test)
accuracy_score = np.mean(y_pred == y_test)
self.assertTrue(accuracy_score >= 0.8)