test_stata.py 文件源码

def test_categorical_order(self):
        # Directly construct using expected codes
        # Format is is_cat, col_name, labels (in order), underlying data
        expected = [(True, 'ordered', ['a', 'b', 'c', 'd', 'e'], np.arange(5)),
                    (True, 'reverse', ['a', 'b', 'c',
                                       'd', 'e'], np.arange(5)[::-1]),
                    (True, 'noorder', ['a', 'b', 'c', 'd',
                                       'e'], np.array([2, 1, 4, 0, 3])),
                    (True, 'floating', [
                     'a', 'b', 'c', 'd', 'e'], np.arange(0, 5)),
                    (True, 'float_missing', [
                     'a', 'd', 'e'], np.array([0, 1, 2, -1, -1])),
                    (False, 'nolabel', [
                     1.0, 2.0, 3.0, 4.0, 5.0], np.arange(5)),
                    (True, 'int32_mixed', ['d', 2, 'e', 'b', 'a'],
                     np.arange(5))]
        cols = []
        for is_cat, col, labels, codes in expected:
            if is_cat:
                cols.append((col, pd.Categorical.from_codes(codes, labels)))
            else:
                cols.append((col, pd.Series(labels, dtype=np.float32)))
        expected = DataFrame.from_items(cols)

        # Read with and with out categoricals, ensure order is identical
        parsed_115 = read_stata(self.dta19_115)
        parsed_117 = read_stata(self.dta19_117)
        tm.assert_frame_equal(expected, parsed_115)
        tm.assert_frame_equal(expected, parsed_117)

        # Check identity of codes
        for col in expected:
            if is_categorical_dtype(expected[col]):
                tm.assert_series_equal(expected[col].cat.codes,
                                       parsed_115[col].cat.codes)
                tm.assert_index_equal(expected[col].cat.categories,
                                      parsed_115[col].cat.categories)