Python compat.u方法代码示例

# 需要导入模块: from pandas import compat [as 别名]
# 或者: from pandas.compat import u [as 别名]
def test_repr(self):
        i = RangeIndex(5, name='Foo')
        result = repr(i)
        if PY3:
            expected = "RangeIndex(start=0, stop=5, step=1, name='Foo')"
        else:
            expected = "RangeIndex(start=0, stop=5, step=1, name=u'Foo')"
        assert result == expected

        result = eval(result)
        tm.assert_index_equal(result, i, exact=True)

        i = RangeIndex(5, 0, -1)
        result = repr(i)
        expected = "RangeIndex(start=5, stop=0, step=-1)"
        assert result == expected

        result = eval(result)
        tm.assert_index_equal(result, i, exact=True) 

# 需要导入模块: from pandas import compat [as 别名]
# 或者: from pandas.compat import u [as 别名]
def test_categorical_repr(self):
        a = Series(Categorical([1, 2, 3, 4]))
        exp = u("0    1\n1    2\n2    3\n3    4\n" +
                "dtype: category\nCategories (4, int64): [1, 2, 3, 4]")

        assert exp == a.__unicode__()

        a = Series(Categorical(["a", "b"] * 25))
        exp = u("0     a\n1     b\n" + "     ..\n" + "48    a\n49    b\n" +
                "Length: 50, dtype: category\nCategories (2, object): [a, b]")
        with option_context("display.max_rows", 5):
            assert exp == repr(a)

        levs = list("abcdefghijklmnopqrstuvwxyz")
        a = Series(Categorical(["a", "b"], categories=levs, ordered=True))
        exp = u("0    a\n1    b\n" + "dtype: category\n"
                "Categories (26, object): [a < b < c < d ... w < x < y < z]")
        assert exp == a.__unicode__() 

# 需要导入模块: from pandas import compat [as 别名]
# 或者: from pandas.compat import u [as 别名]
def test_title(self):
        values = Series(["FOO", "BAR", NA, "Blah", "blurg"])

        result = values.str.title()
        exp = Series(["Foo", "Bar", NA, "Blah", "Blurg"])
        tm.assert_series_equal(result, exp)

        # mixed
        mixed = Series(["FOO", NA, "bar", True, datetime.today(), "blah", None,
                        1, 2.])
        mixed = mixed.str.title()
        exp = Series(["Foo", NA, "Bar", NA, NA, "Blah", NA, NA, NA])
        tm.assert_almost_equal(mixed, exp)

        # unicode
        values = Series([u("FOO"), NA, u("bar"), u("Blurg")])

        results = values.str.title()
        exp = Series([u("Foo"), NA, u("Bar"), u("Blurg")])

        tm.assert_series_equal(results, exp) 

# 需要导入模块: from pandas import compat [as 别名]
# 或者: from pandas.compat import u [as 别名]
def test_capitalize(self):
        values = Series(["FOO", "BAR", NA, "Blah", "blurg"])
        result = values.str.capitalize()
        exp = Series(["Foo", "Bar", NA, "Blah", "Blurg"])
        tm.assert_series_equal(result, exp)

        # mixed
        mixed = Series(["FOO", NA, "bar", True, datetime.today(), "blah", None,
                        1, 2.])
        mixed = mixed.str.capitalize()
        exp = Series(["Foo", NA, "Bar", NA, NA, "Blah", NA, NA, NA])
        tm.assert_almost_equal(mixed, exp)

        # unicode
        values = Series([u("FOO"), NA, u("bar"), u("Blurg")])
        results = values.str.capitalize()
        exp = Series([u("Foo"), NA, u("Bar"), u("Blurg")])
        tm.assert_series_equal(results, exp) 

# 需要导入模块: from pandas import compat [as 别名]
# 或者: from pandas.compat import u [as 别名]
def test_join(self):
        values = Series(['a_b_c', 'c_d_e', np.nan, 'f_g_h'])
        result = values.str.split('_').str.join('_')
        tm.assert_series_equal(values, result)

        # mixed
        mixed = Series(['a_b', NA, 'asdf_cas_asdf', True, datetime.today(),
                        'foo', None, 1, 2.])

        rs = Series(mixed).str.split('_').str.join('_')
        xp = Series(['a_b', NA, 'asdf_cas_asdf', NA, NA, 'foo', NA, NA, NA])

        assert isinstance(rs, Series)
        tm.assert_almost_equal(rs, xp)

        # unicode
        values = Series([u('a_b_c'), u('c_d_e'), np.nan, u('f_g_h')])
        result = values.str.split('_').str.join('_')
        tm.assert_series_equal(values, result) 

# 需要导入模块: from pandas import compat [as 别名]
# 或者: from pandas.compat import u [as 别名]
def test_len(self):
        values = Series(['foo', 'fooo', 'fooooo', np.nan, 'fooooooo'])

        result = values.str.len()
        exp = values.map(lambda x: len(x) if notna(x) else NA)
        tm.assert_series_equal(result, exp)

        # mixed
        mixed = Series(['a_b', NA, 'asdf_cas_asdf', True, datetime.today(),
                        'foo', None, 1, 2.])

        rs = Series(mixed).str.len()
        xp = Series([3, NA, 13, NA, NA, 3, NA, NA, NA])

        assert isinstance(rs, Series)
        tm.assert_almost_equal(rs, xp)

        # unicode
        values = Series([u('foo'), u('fooo'), u('fooooo'), np.nan, u(
            'fooooooo')])

        result = values.str.len()
        exp = values.map(lambda x: len(x) if notna(x) else NA)
        tm.assert_series_equal(result, exp) 

# 需要导入模块: from pandas import compat [as 别名]
# 或者: from pandas.compat import u [as 别名]
def test_findall(self):
        values = Series(['fooBAD__barBAD', NA, 'foo', 'BAD'])

        result = values.str.findall('BAD[_]*')
        exp = Series([['BAD__', 'BAD'], NA, [], ['BAD']])
        tm.assert_almost_equal(result, exp)

        # mixed
        mixed = Series(['fooBAD__barBAD', NA, 'foo', True, datetime.today(),
                        'BAD', None, 1, 2.])

        rs = Series(mixed).str.findall('BAD[_]*')
        xp = Series([['BAD__', 'BAD'], NA, [], NA, NA, ['BAD'], NA, NA, NA])

        assert isinstance(rs, Series)
        tm.assert_almost_equal(rs, xp)

        # unicode
        values = Series([u('fooBAD__barBAD'), NA, u('foo'), u('BAD')])

        result = values.str.findall('BAD[_]*')
        exp = Series([[u('BAD__'), u('BAD')], NA, [], [u('BAD')]])
        tm.assert_almost_equal(result, exp) 

# 需要导入模块: from pandas import compat [as 别名]
# 或者: from pandas.compat import u [as 别名]
def test_wrap(self):
        # test values are: two words less than width, two words equal to width,
        # two words greater than width, one word less than width, one word
        # equal to width, one word greater than width, multiple tokens with
        # trailing whitespace equal to width
        values = Series([u('hello world'), u('hello world!'), u(
            'hello world!!'), u('abcdefabcde'), u('abcdefabcdef'), u(
                'abcdefabcdefa'), u('ab ab ab ab '), u('ab ab ab ab a'), u(
                    '\t')])

        # expected values
        xp = Series([u('hello world'), u('hello world!'), u('hello\nworld!!'),
                     u('abcdefabcde'), u('abcdefabcdef'), u('abcdefabcdef\na'),
                     u('ab ab ab ab'), u('ab ab ab ab\na'), u('')])

        rs = values.str.wrap(12, break_long_words=True)
        assert_series_equal(rs, xp)

        # test with pre and post whitespace (non-unicode), NaN, and non-ascii
        # Unicode
        values = Series(['  pre  ', np.nan, u('\xac\u20ac\U00008000 abadcafe')
                         ])
        xp = Series(['  pre', NA, u('\xac\u20ac\U00008000 ab\nadcafe')])
        rs = values.str.wrap(6)
        assert_series_equal(rs, xp) 

# 需要导入模块: from pandas import compat [as 别名]
# 或者: from pandas.compat import u [as 别名]
def test_encode_decode_errors(self):
        encodeBase = Series([u('a'), u('b'), u('a\x9d')])

        pytest.raises(UnicodeEncodeError, encodeBase.str.encode, 'cp1252')

        f = lambda x: x.encode('cp1252', 'ignore')
        result = encodeBase.str.encode('cp1252', 'ignore')
        exp = encodeBase.map(f)
        tm.assert_series_equal(result, exp)

        decodeBase = Series([b'a', b'b', b'a\x9d'])

        pytest.raises(UnicodeDecodeError, decodeBase.str.decode, 'cp1252')

        f = lambda x: x.decode('cp1252', 'ignore')
        result = decodeBase.str.decode('cp1252', 'ignore')
        exp = decodeBase.map(f)

        tm.assert_series_equal(result, exp) 

# 需要导入模块: from pandas import compat [as 别名]
# 或者: from pandas.compat import u [as 别名]
def test_normalize(self):
        values = ['ABC', u'ＡＢＣ', u'１２３', np.nan, u'ｱｲｴ']
        s = Series(values, index=['a', 'b', 'c', 'd', 'e'])

        normed = [u'ABC', u'ABC', u'123', np.nan, u'アイエ']
        expected = Series(normed, index=['a', 'b', 'c', 'd', 'e'])

        result = s.str.normalize('NFKC')
        tm.assert_series_equal(result, expected)

        expected = Series([u'ABC', u'ＡＢＣ', u'１２３', np.nan, u'ｱｲｴ'],
                          index=['a', 'b', 'c', 'd', 'e'])

        result = s.str.normalize('NFC')
        tm.assert_series_equal(result, expected)

        with pytest.raises(ValueError, match="invalid normalization form"):
            s.str.normalize('xxx')

        s = Index([u'ＡＢＣ', u'１２３', u'ｱｲｴ'])
        expected = Index([u'ABC', u'123', u'アイエ'])
        result = s.str.normalize('NFKC')
        tm.assert_index_equal(result, expected) 

# 需要导入模块: from pandas import compat [as 别名]
# 或者: from pandas.compat import u [as 别名]
def test_unstack_level_binding(self):
        # GH9856
        mi = pd.MultiIndex(
            levels=[[u('foo'), u('bar')], [u('one'), u('two')],
                    [u('a'), u('b')]],
            codes=[[0, 0, 1, 1], [0, 1, 0, 1], [1, 0, 1, 0]],
            names=[u('first'), u('second'), u('third')])
        s = pd.Series(0, index=mi)
        result = s.unstack([1, 2]).stack(0)

        expected_mi = pd.MultiIndex(
            levels=[['foo', 'bar'], ['one', 'two']],
            codes=[[0, 0, 1, 1], [0, 1, 0, 1]],
            names=['first', 'second'])

        expected = pd.DataFrame(np.array([[np.nan, 0],
                                          [0, np.nan],
                                          [np.nan, 0],
                                          [0, np.nan]],
                                         dtype=np.float64),
                                index=expected_mi,
                                columns=pd.Index(['a', 'b'], name='third'))

        assert_frame_equal(result, expected) 

# 需要导入模块: from pandas import compat [as 别名]
# 或者: from pandas.compat import u [as 别名]
def test_isna_lists(self):
        result = isna([[False]])
        exp = np.array([[False]])
        tm.assert_numpy_array_equal(result, exp)

        result = isna([[1], [2]])
        exp = np.array([[False], [False]])
        tm.assert_numpy_array_equal(result, exp)

        # list of strings / unicode
        result = isna(['foo', 'bar'])
        exp = np.array([False, False])
        tm.assert_numpy_array_equal(result, exp)

        result = isna([u('foo'), u('bar')])
        exp = np.array([False, False])
        tm.assert_numpy_array_equal(result, exp)

        # GH20675
        result = isna([np.NaN, 'world'])
        exp = np.array([True, False])
        tm.assert_numpy_array_equal(result, exp) 

# 需要导入模块: from pandas import compat [as 别名]
# 或者: from pandas.compat import u [as 别名]
def test_is_scalar_builtin_scalars(self):
        assert is_scalar(None)
        assert is_scalar(True)
        assert is_scalar(False)
        assert is_scalar(Number())
        assert is_scalar(Fraction())
        assert is_scalar(0.)
        assert is_scalar(np.nan)
        assert is_scalar('foobar')
        assert is_scalar(b'foobar')
        assert is_scalar(u('efoobar'))
        assert is_scalar(datetime(2014, 1, 1))
        assert is_scalar(date(2014, 1, 1))
        assert is_scalar(time(12, 0))
        assert is_scalar(timedelta(hours=1))
        assert is_scalar(pd.NaT) 

# 需要导入模块: from pandas import compat [as 别名]
# 或者: from pandas.compat import u [as 别名]
def test_read_write_dta11(self):
        original = DataFrame([(1, 2, 3, 4)],
                             columns=['good', compat.u('b\u00E4d'), '8number',
                                      'astringwithmorethan32characters______'])
        formatted = DataFrame([(1, 2, 3, 4)],
                              columns=['good', 'b_d', '_8number',
                                       'astringwithmorethan32characters_'])
        formatted.index.name = 'index'
        formatted = formatted.astype(np.int32)

        with tm.ensure_clean() as path:
            with tm.assert_produces_warning(pd.io.stata.InvalidColumnName):
                original.to_stata(path, None)

            written_and_read_again = self.read_dta(path)
            tm.assert_frame_equal(
                written_and_read_again.set_index('index'), formatted) 

# 需要导入模块: from pandas import compat [as 别名]
# 或者: from pandas.compat import u [as 别名]
def test_invalid_variable_labels(self, version):
        original = pd.DataFrame({'a': [1, 2, 3, 4],
                                 'b': [1.0, 3.0, 27.0, 81.0],
                                 'c': ['Atlanta', 'Birmingham',
                                       'Cincinnati', 'Detroit']})
        original.index.name = 'index'
        variable_labels = {'a': 'very long' * 10,
                           'b': 'City Exponent',
                           'c': 'City'}
        with tm.ensure_clean() as path:
            msg = "Variable labels must be 80 characters or fewer"
            with pytest.raises(ValueError, match=msg):
                original.to_stata(path,
                                  variable_labels=variable_labels,
                                  version=version)

        variable_labels['a'] = u'invalid character Œ'
        with tm.ensure_clean() as path:
            msg = ("Variable labels must contain only characters that can be"
                   " encoded in Latin-1")
            with pytest.raises(ValueError, match=msg):
                original.to_stata(path,
                                  variable_labels=variable_labels,
                                  version=version)