def test_preprocessnumeric_normalize(self):
unnormal_data = [[5.0, 3, 1], [2.0, 2, 1], [10.0, 1, 1], [10.0, 1, 1]]
columns = ["col1", "col2", "col3"]
data = pd.DataFrame(unnormal_data, columns=columns)
preprocess = Data(x_train=data, test_split_percentage=0.5, report_name="test")
preprocess.normalize_numeric()
validate = preprocess.x_train.values.tolist()
self.assertTrue(True)
def test_report_preprocessing_standardize(self):
unnormal_data = [[5.0, 3, 1], [2.0, 2, 1], [10.0, 1, 1]]
columns = ["col1", "col2", "col3"]
data = pd.DataFrame(unnormal_data, columns=columns)
preprocess = Data(x_train=data,
test_split_percentage=0.5,
split=False,
report_name="test")
preprocess.normalize_numeric()
with open(preprocess.report.filename) as f:
content = f.read()
validate = "col1" in content and "col2" in content and "col3" in content
os.remove(preprocess.report.filename)
self.assertTrue(validate)
def test_preprocess_traindata(self):
unnormal_x_train = [[5.0, 3, 1], [2.0, 2, 1], [10.0, 1, 1]]
unnormal_x_test = [[5.0, 3, 1], [2.0, 2, 1], [10.0, 1, 1]]
columns = ["col1", "col2", "col3"]
x_train = pd.DataFrame(unnormal_x_train, columns=columns)
x_test = pd.DataFrame(unnormal_x_test, columns=columns)
preprocess = Data(
x_train=x_train,
x_test=x_test,
test_split_percentage=0.5,
report_name="test",
)
preprocess.normalize_numeric("col1", "col2", "col3")
validate_train = preprocess.x_train.values.tolist()
validate_test = preprocess.x_test.values.tolist()
self.assertListEqual(validate_train, validate_test)
