예제 #1
0
    def test_profile_merge_edge_case(self):
        data = [2.0, 'not a float', 6.0, 'not a float']
        df = pd.Series(data).apply(str)
        profiler1 = FloatColumn("Float")
        profiler1.update(df)
        profiler1.match_count = 0

        data2 = [10.0, 'not a float', 15.0, 'not a float']
        df2 = pd.Series(data2).apply(str)
        profiler2 = FloatColumn("Float")
        profiler2.update(df2)

        profiler3 = profiler1 + profiler2
        self.assertEqual(profiler3.stddev, profiler2.stddev)

        # test merge with empty data
        df1 = pd.Series([], dtype=object)
        profiler1 = FloatColumn("Float")
        profiler1.update(df1)

        df2 = pd.Series([], dtype=object)
        profiler2 = FloatColumn("Float")
        profiler2.update(df2)

        profiler = profiler1 + profiler2
        self.assertEqual(profiler.min, None)
        self.assertEqual(profiler.max, None)

        df3 = pd.Series([2.0, 3.0]).apply(str)
        profiler3 = FloatColumn("Float")
        profiler3.update(df3)

        profiler = profiler1 + profiler3
        self.assertEqual(profiler.min, 2.0)
        self.assertEqual(profiler.max, 3.0)

        df4 = pd.Series([4.0, 5.0]).apply(str)
        profiler4 = FloatColumn("Float")
        profiler4.update(df4)

        profiler = profiler3 + profiler4
        self.assertEqual(profiler.min, 2.0)
        self.assertEqual(profiler.max, 5.0)
예제 #2
0
    def test_profile_merge_no_bin_overlap(self):

        data = [2.0, 'not a float', 6.0, 'not a float']
        df = pd.Series(data).apply(str)
        profiler1 = FloatColumn("Float")
        profiler1.update(df)
        profiler1.match_count = 0

        data2 = [10.0, 'not a float', 15.0, 'not a float']
        df2 = pd.Series(data2).apply(str)
        profiler2 = FloatColumn("Float")
        profiler2.update(df2)

        # set bin names so no overlap
        profiler1.histogram_bin_method_names = ['No overlap 1']
        profiler2.histogram_bin_method_names = ['No overlap 2']

        with self.assertRaisesRegex(
                ValueError, 'Profiles have no overlapping bin methods '
                'and therefore cannot be added together.'):
            profiler1 + profiler2