def test_new_dataframe(self):
new_df = self.transform_event.newDataFrame
utils.validate_dataframe_struct(new_df, self)
new_df_column = new_df.schema[0]
df_column = modeldb_types.DataFrameColumn('0', 'int64')
expected_new_df = modeldb_types.DataFrame(-1, [df_column], 100,
'') # fix columns
utils.is_equal_dataframe(expected_new_df, new_df, self)
def test_old_dataframe(self):
old_df = self.transform_event.oldDataFrame
utils.validate_dataframe_struct(old_df, self)
expected_old_df = modeldb_types.DataFrame(
-1,
[],
100,
'')
utils.is_equal_dataframe(expected_old_df, old_df, self)
def test_dataframe_fit_event(self):
df = self.fit_event.df
utils.validate_dataframe_struct(df, self)
expected_df = modeldb_types.DataFrame(
-1,
[],
100,
'')
utils.is_equal_dataframe(expected_df, df, self)
def test_split_dataframes(self):
split_data_frames = self.random_split_event.splitDataFrames
self.assertEquals(len(split_data_frames), 2)
dataframe1 = split_data_frames[0]
dataframe2 = split_data_frames[1]
utils.validate_dataframe_struct(dataframe1, self)
utils.validate_dataframe_struct(dataframe2, self)
# Check if dataframes are split according to weights (within some margin of error)
self.assertIn(dataframe1.numRows, range(65, 75))
self.assertIn(dataframe2.numRows, range(25, 35))
self.assertEquals(dataframe1.numRows + dataframe2.numRows, 100)