def setup_training_data(self, train_file, target):
# Loading training data
self.train_data = data_io.get_data(setup.get_datasets_path(),
train_file)
# Setting what to predict
self.target_column = target
def setUp(self):
self.data = data_io.get_data(setup.get_datasets_path(),
"titanic_train.csv")
self.data["Nonsense"] = np.nan
self.data = self.data.apply(pd.to_numeric, errors='coerce')
self.data.loc[self.data.shape[0]] = [np.nan] * self.data.shape[1]
self.target = 'Survived'
self.start = self.data.shape
def standard_pred_type(self, filename, target, goal, message):
# Arrange
data = data_io.get_data(setup.get_datasets_path(), filename)
# Act
ml_type = dataset_insight.get_prediction_type(data[target])
# Assert
self.assertEqual(ml_type, goal, msg=message)
def test_scaling(self):
# Arrange
data = data_io.get_data(setup.get_datasets_path(),
"winequality-red.csv")
# Act
target = data_scaling.scale_numeric_data(data)
target = pd.DataFrame.as_matrix(target)
# Assert
self.assertAlmostEqual(target.mean(), 0, 5)
self.assertAlmostEqual(target.std(), 1, 5)
def test_data_split(self):
# Arrange
data = data_io.get_data(setup.get_datasets_path(),
"winequality-red.csv")
# Act
x_train, x_test, y_train, y_test = data_splitting.get_train_test(
data, "quality")
# Assert
self.assertEqual(len(x_train[:, 0]), len(y_train))
self.assertEqual(len(x_test[:, 0]), len(y_test))
self.assertAlmostEqual(len(y_train) / len(y_test), 4, 2)
def setUp(self):
self.data = data_io.get_data(setup.get_datasets_path(),
"winequality-red.csv")
self.target = 'quality'
self.start = self.data.shape
def setUp(self):
self.data = data_io.get_data(setup.get_datasets_path(), "titanic_train.csv")
def setUp(self):
self.data = data_io.get_data(setup.get_datasets_path(),
"winequality-red.csv")
self.strategy = filler_strategy.FillerStrategy(self.data)
def setUp(self):
self.data = data_io.get_data(setup.get_datasets_path(), "titanic_train.csv")
self.data["Nonsense"] = np.nan
self.data["Filled"] = 1
self.data = self.data.apply(pd.to_numeric,errors='coerce')
def setup_test_data(self, test_file):
# Loading testing data
self.test_data = data_io.get_data(setup.get_datasets_path(), test_file)