class TestDataset(unittest.TestCase):
def setUp(self):
self._data = {'col1': [1, 2], 'col2': [3, 4], 'col4': [5, 6]}
self._dataframe = pd.DataFrame(data=self._data)
self._dataset = DataModel(self._dataframe)
def test_validate_columns_invalid(self):
with self.assertRaises(RuntimeError):
self._dataset.validate_columns(['col3'])
def test_validate_columns(self):
self._dataset.validate_columns(['col1'])
def test_feature_columns(self):
intended_columns = ['col1', 'col2']
self._dataset.set_feature_columns(intended_columns)
feature_columns = self._dataset.get_feature_columns()
result_columns = list(feature_columns.columns.values)
self.assertEqual(result_columns, intended_columns)
def test_target_column(self):
intended_column = 'col1'
self._dataset.set_target_column(intended_column)
target_column = self._dataset.get_target_column()
self.assertEqual(target_column.tolist(), self._data[intended_column])
class TestDataSetSplitter(unittest.TestCase):
def setUp(self):
self._data = {
'target': [0, 1, 2, 3, 4, 5, 6, 7, 8, 9],
'feature_1': [0, 1, 2, 3, 4, 5, 6, 7, 8, 9],
'feature_2': [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]
}
self._dataframe = pd.DataFrame(data=self._data)
self._data_model = DataModel(self._dataframe)
self._data_model.set_tf_feature_columns([
tf.feature_column.numeric_column('feature_1'),
tf.feature_column.numeric_column('feature_2')
])
self._data_model.set_target_column('target')
def test_split_data(self):
splitter = DataSetSplitter(self._data_model)
evaluation_data, train_data = splitter.split_by_ratio(ratios=[20, 80])
train_features = train_data.get_feature_columns()
train_target = train_data.get_target_column()
eval_features = evaluation_data.get_feature_columns()
eval_target = evaluation_data.get_target_column()
self.assertEqual(len(train_target), 8)
self.assertEqual(len(train_features), 8)
self.assertEqual(len(eval_target), 2)
self.assertEqual(len(eval_features), 2)
def setUp(self):
data_array = {'feat_A': [1, 2, 3], 'feat_B': [8, 6, 4], 'target': [9, 8, 7]}
df2 = df = pd.DataFrame(data_array)
train_model = DataModel(df)
train_model.set_target_column('target')
train_model.set_feature_columns(['feat_A', 'feat_B'])
eval_model = DataModel(df2)
eval_model.set_target_column('target')
eval_model.set_feature_columns(['feat_A', 'feat_B'])
self.arti = AI('test', 'test/test')
self.arti.training_data = train_model
self.arti.evaluation_data = eval_model