def setUp(self):
raw_data = pd.read_csv('tests/test_data_old.txt', delimiter=';')
raw_data = raw_data.head(50)
self.clean_data = cleanse(raw_data)
self.train = self.clean_data[:5]
self.test = self.clean_data[5:]
self.cats = ['articleID', 'customerID', 'voucherID', 'productGroup']
def setUp(self):
raw_data = pd.read_csv('tests/test_data_old.txt', delimiter=';')
raw_data = raw_data.head(50)
self.clean_data = cleanse(raw_data)
self.train = self.clean_data[:5]
self.test = self.clean_data[5:]
self.cats = ['articleID', 'customerID', 'voucherID', 'productGroup']
def setUp(self):
self.raw_data = pd.read_csv('tests/test_data.txt', delimiter=';')
train_ids = ['a1000001', 'a1000002', 'a1000003']
test_ids = ['a1000007', 'a1000008']
clean_data = cleanse(self.raw_data)
self.data = {'data': clean_data, 'train_ids': train_ids, 'test_ids': test_ids}
def setUp(self):
raw_data = pd.read_csv('tests/test_data_old.txt', delimiter=';')
raw_data = raw_data.head(50)
clean_data = cleanse(raw_data)
featured_data = add_independent_features(clean_data)
self.X, self.Y = transform(featured_data)
self.X = self.X.toarray()
def setUp(self):
raw_data = pd.read_csv('tests/test_data.txt', delimiter=';')
train_ids = ['a1000001', 'a1000002', 'a1000003']
test_ids = ['a1000007', 'a1000008']
self.data = preprocessing.cleanse(raw_data)
self.train, self.test = preprocessing.split_train_test(self.data, train_ids, test_ids)
def setUp(self):
raw_data = pd.read_csv('tests/test_data_old.txt', delimiter=';')
raw_data = raw_data.head(50)
clean_data = cleanse(raw_data)
featured_data = add_independent_features(clean_data)
self.X, self.Y = transform(featured_data)
self.X = self.X.toarray()
def setUp(self):
raw_data = pd.read_csv('tests/test_data.txt', delimiter=';')
train_ids = ['a1000001', 'a1000002', 'a1000003']
test_ids = ['a1000007', 'a1000008']
self.data = preprocessing.cleanse(raw_data)
self.train, self.test = preprocessing.split_train_test(
self.data, train_ids, test_ids)
def setUp(self):
raw_data = pd.read_csv('tests/test_data_old.txt', delimiter=';')
raw_data = raw_data.head(50)
clean_data = cleanse(raw_data)
data = add_independent_features(clean_data)
X, Y = transform(data, scaler=normalize_features)
self.X_tr, self.Y_tr = X[:6], Y[:6]
self.X_te, self.Y_te = X[6:], Y[6:]
def setUp(self):
raw_data = pd.read_csv('tests/test_data_old.txt', delimiter=';')
raw_data = raw_data.head(50)
clean_data = cleanse(raw_data)
data = add_independent_features(clean_data)
X, Y = transform(data, scaler=normalize_features)
self.X_tr, self.Y_tr = X[:6], Y[:6]
self.X_te, self.Y_te = X[6:], Y[6:]
def test_cleanse(self):
df = cleanse(self.raw_data)
# Column values
self.assertTrue((df.quantity != 0).all())
self.assertTrue((df.quantity >= df.returnQuantity).all())
# Column types
self.assertTrue(df.orderDate.dtype == np.dtype('<M8[ns]'))
self.assertTrue(df.orderID.dtype == np.int)
self.assertTrue(df.articleID.dtype == np.int)
self.assertTrue(df.customerID.dtype == np.int)
self.assertTrue(df.voucherID.dtype == np.float)
def setUp(self):
self.raw_data = pd.read_csv('tests/test_data.txt', delimiter=';')
train_ids = ['a1000001', 'a1000002', 'a1000003']
test_ids = ['a1000007', 'a1000008']
clean_data = cleanse(self.raw_data)
self.data = {
'data': clean_data,
'train_ids': train_ids,
'test_ids': test_ids
}
def test_cleanse(self):
df = cleanse(self.raw_data)
# Column values
self.assertTrue((df.quantity != 0).all())
self.assertTrue((df.quantity >= df.returnQuantity).all())
# Column types
self.assertTrue(df.orderDate.dtype == np.dtype('<M8[ns]'))
self.assertTrue(df.orderID.dtype == np.int)
self.assertTrue(df.articleID.dtype == np.int)
self.assertTrue(df.customerID.dtype == np.int)
self.assertTrue(df.voucherID.dtype == np.float)
def setUp(self):
raw_data = pd.read_csv('tests/test_data_old.txt', delimiter=';')
raw_data = raw_data.head(50)
clean_data = cleanse(raw_data)
self.data = clean_data
def setUp(self):
raw_data = pd.read_csv('tests/test_data_old.txt', delimiter=';')
raw_data = raw_data.head(50)
clean_data = cleanse(raw_data)
self.data = clean_data
def test_cleanse(self):
cleanse(self.data)