def test_training_set():
matrix_train, matrix_test, dependent_train, dependent_test = training_set(
*features_and_dependent_vars(import_data()))
assert matrix_train.shape == (8, 3)
assert matrix_test.shape == (2, 3)
assert dependent_train.shape == (8, 1)
assert dependent_test.shape == (2, 1)
def test_feature_scaling():
matrix, dep_vars = cleanup_data(import_data())
matrix_train, matrix_test, dependent_train, dependent_test = training_set(
encode_feature(matrix), encode_feature(dep_vars))
scaled_matrix_train, scaled_matrix_test = feature_scaling(
matrix_train, matrix_test)
assert scaled_matrix_train.shape == matrix_train.shape
def test_training_and_test_sets():
train_x, test_x, train_y, test_y = dp.training_set(
*dp.features_and_dependent_vars(dp.import_data(DATA_FILE)),
test_size=1 / 3)
assert train_x[0][0] == 2.9
assert test_x[0][0] == 1.5
assert train_y[0][0] == 56642
assert test_y[0][0] == 37731
def test_predict():
train_x, test_x, train_y, test_y = dp.training_set(
*dp.features_and_dependent_vars(dp.import_data(DATA_FILE)),
test_size=1 / 3)
machine = train_the_machine(train_x, train_y)
predicted = predict(machine, train_x)
data, max_error = error(train_y, predicted)
assert max_error < 0.2
assert data['err'].mean() < 0.1
def test_train_the_machine():
train_x, _, train_y, _ = dp.training_set(*dp.features_and_dependent_vars(
dp.import_data(DATA_FILE)),
test_size=1 / 3)
machine = train_the_machine(train_x, train_y)
assert isinstance(machine, LinearRegression)
def test_read_data():
data = dp.import_data(DATA_FILE)
assert data.iloc[0, 0] == 1.1
matrix, depend = dp.features_and_dependent_vars(data)
assert matrix[0][0] == 1.1 and depend[0][0] == 39343
def test_encode_data():
original_data, data_with_dummies, dependent_vars = encode_data(
import_data())
assert original_data[6, 2] is not np.nan
assert data_with_dummies.shape == (10, 5)
assert dependent_vars[0] == 0
def test_categorical_data():
matrix = encode_feature(
cleanup_data(import_data())[0], slice(None, None), 0)
assert set(matrix[:, 0]) == {0, 1, 2}
assert create_dummy_variables(matrix, [0]).shape == (10, 5)
def test_cleanup_data():
matrix, _ = cleanup_data(import_data())
assert matrix[4, 2] == 63777.77777777778
def test_import_data():
dataset = import_data()
assert dataset is not None
def test_features_matrix():
matrix, dep_vars = features_and_dependent_vars(import_data())
assert matrix[0][0] == 'France'
assert dep_vars[0][0] == 'No'