Python testing.makeStringIndex方法代码示例

# 需要导入模块: from pandas.util import testing [as 别名]
# 或者: from pandas.util.testing import makeStringIndex [as 别名]
def setup_method(self, method):
        self.indices = dict(unicodeIndex=tm.makeUnicodeIndex(100),
                            strIndex=tm.makeStringIndex(100),
                            dateIndex=tm.makeDateIndex(100),
                            periodIndex=tm.makePeriodIndex(100),
                            tdIndex=tm.makeTimedeltaIndex(100),
                            intIndex=tm.makeIntIndex(100),
                            uintIndex=tm.makeUIntIndex(100),
                            rangeIndex=tm.makeRangeIndex(100),
                            floatIndex=tm.makeFloatIndex(100),
                            boolIndex=Index([True, False]),
                            catIndex=tm.makeCategoricalIndex(100),
                            empty=Index([]),
                            tuples=MultiIndex.from_tuples(lzip(
                                ['foo', 'bar', 'baz'], [1, 2, 3])),
                            repeats=Index([0, 0, 1, 1, 2, 2]))
        self.setup_indices() 

# 需要导入模块: from pandas.util import testing [as 别名]
# 或者: from pandas.util.testing import makeStringIndex [as 别名]
def get_objs():
    indexes = [
        tm.makeBoolIndex(10, name='a'),
        tm.makeIntIndex(10, name='a'),
        tm.makeFloatIndex(10, name='a'),
        tm.makeDateIndex(10, name='a'),
        tm.makeDateIndex(10, name='a').tz_localize(tz='US/Eastern'),
        tm.makePeriodIndex(10, name='a'),
        tm.makeStringIndex(10, name='a'),
        tm.makeUnicodeIndex(10, name='a')
    ]

    arr = np.random.randn(10)
    series = [Series(arr, index=idx, name='a') for idx in indexes]

    objs = indexes + series
    return objs 

# 需要导入模块: from pandas.util import testing [as 别名]
# 或者: from pandas.util.testing import makeStringIndex [as 别名]
def setup_method(self, method):
        super(TestIndex, self).setup_method(method)

        self.d = {
            'string': tm.makeStringIndex(100),
            'date': tm.makeDateIndex(100),
            'int': tm.makeIntIndex(100),
            'rng': tm.makeRangeIndex(100),
            'float': tm.makeFloatIndex(100),
            'empty': Index([]),
            'tuple': Index(zip(['foo', 'bar', 'baz'], [1, 2, 3])),
            'period': Index(period_range('2012-1-1', freq='M', periods=3)),
            'date2': Index(date_range('2013-01-1', periods=10)),
            'bdate': Index(bdate_range('2013-01-02', periods=10)),
            'cat': tm.makeCategoricalIndex(100),
            'interval': tm.makeIntervalIndex(100),
            'timedelta': tm.makeTimedeltaIndex(100, 'H')
        }

        self.mi = {
            'reg': MultiIndex.from_tuples([('bar', 'one'), ('baz', 'two'),
                                           ('foo', 'two'),
                                           ('qux', 'one'), ('qux', 'two')],
                                          names=['first', 'second']),
        } 

# 需要导入模块: from pandas.util import testing [as 别名]
# 或者: from pandas.util.testing import makeStringIndex [as 别名]
def setup_method(self, method):
        self.bool_index = tm.makeBoolIndex(10, name='a')
        self.int_index = tm.makeIntIndex(10, name='a')
        self.float_index = tm.makeFloatIndex(10, name='a')
        self.dt_index = tm.makeDateIndex(10, name='a')
        self.dt_tz_index = tm.makeDateIndex(10, name='a').tz_localize(
            tz='US/Eastern')
        self.period_index = tm.makePeriodIndex(10, name='a')
        self.string_index = tm.makeStringIndex(10, name='a')
        self.unicode_index = tm.makeUnicodeIndex(10, name='a')

        arr = np.random.randn(10)
        self.int_series = Series(arr, index=self.int_index, name='a')
        self.float_series = Series(arr, index=self.float_index, name='a')
        self.dt_series = Series(arr, index=self.dt_index, name='a')
        self.dt_tz_series = self.dt_tz_index.to_series(keep_tz=True)
        self.period_series = Series(arr, index=self.period_index, name='a')
        self.string_series = Series(arr, index=self.string_index, name='a')

        types = ['bool', 'int', 'float', 'dt', 'dt_tz', 'period', 'string',
                 'unicode']
        fmts = ["{0}_{1}".format(t, f)
                for t in types for f in ['index', 'series']]
        self.objs = [getattr(self, f)
                     for f in fmts if getattr(self, f, None) is not None] 

# 需要导入模块: from pandas.util import testing [as 别名]
# 或者: from pandas.util.testing import makeStringIndex [as 别名]
def test_constructor_dict_cast(self):
        # cast float tests
        test_data = {
            'A': {'1': 1, '2': 2},
            'B': {'1': '1', '2': '2', '3': '3'},
        }
        frame = DataFrame(test_data, dtype=float)
        assert len(frame) == 3
        assert frame['B'].dtype == np.float64
        assert frame['A'].dtype == np.float64

        frame = DataFrame(test_data)
        assert len(frame) == 3
        assert frame['B'].dtype == np.object_
        assert frame['A'].dtype == np.float64

        # can't cast to float
        test_data = {
            'A': dict(zip(range(20), tm.makeStringIndex(20))),
            'B': dict(zip(range(15), randn(15)))
        }
        frame = DataFrame(test_data, dtype=float)
        assert len(frame) == 20
        assert frame['A'].dtype == np.object_
        assert frame['B'].dtype == np.float64 

# 需要导入模块: from pandas.util import testing [as 别名]
# 或者: from pandas.util.testing import makeStringIndex [as 别名]
def test_to_html_filename(self):
        biggie = DataFrame({'A': np.random.randn(200),
                            'B': tm.makeStringIndex(200)},
                           index=lrange(200))

        biggie.loc[:20, 'A'] = np.nan
        biggie.loc[:20, 'B'] = np.nan
        with tm.ensure_clean('test.html') as path:
            biggie.to_html(path)
            with open(path, 'r') as f:
                s = biggie.to_html()
                s2 = f.read()
                assert s == s2

        frame = DataFrame(index=np.arange(200))
        with tm.ensure_clean('test.html') as path:
            frame.to_html(path)
            with open(path, 'r') as f:
                assert frame.to_html() == f.read() 

# 需要导入模块: from pandas.util import testing [as 别名]
# 或者: from pandas.util.testing import makeStringIndex [as 别名]
def setUp(self):
        super(TestIndex, self).setUp()

        self.d = {
            'string': tm.makeStringIndex(100),
            'date': tm.makeDateIndex(100),
            'int': tm.makeIntIndex(100),
            'float': tm.makeFloatIndex(100),
            'empty': Index([]),
            'tuple': Index(zip(['foo', 'bar', 'baz'], [1, 2, 3])),
            'period': Index(period_range('2012-1-1', freq='M', periods=3)),
            'date2': Index(date_range('2013-01-1', periods=10)),
            'bdate': Index(bdate_range('2013-01-02', periods=10)),
        }

        self.mi = {
            'reg': MultiIndex.from_tuples([('bar', 'one'), ('baz', 'two'), ('foo', 'two'),
                                           ('qux', 'one'), ('qux', 'two')], names=['first', 'second']),
        } 

# 需要导入模块: from pandas.util import testing [as 别名]
# 或者: from pandas.util.testing import makeStringIndex [as 别名]
def setup_method(self, method):
        self.indices = dict(unicodeIndex=tm.makeUnicodeIndex(100),
                            strIndex=tm.makeStringIndex(100),
                            dateIndex=tm.makeDateIndex(100),
                            periodIndex=tm.makePeriodIndex(100),
                            tdIndex=tm.makeTimedeltaIndex(100),
                            intIndex=tm.makeIntIndex(100),
                            uintIndex=tm.makeUIntIndex(100),
                            rangeIndex=tm.makeIntIndex(100),
                            floatIndex=tm.makeFloatIndex(100),
                            boolIndex=Index([True, False]),
                            catIndex=tm.makeCategoricalIndex(100),
                            empty=Index([]),
                            tuples=MultiIndex.from_tuples(lzip(
                                ['foo', 'bar', 'baz'], [1, 2, 3])),
                            repeats=Index([0, 0, 1, 1, 2, 2]))
        self.setup_indices() 

# 需要导入模块: from pandas.util import testing [as 别名]
# 或者: from pandas.util.testing import makeStringIndex [as 别名]
def setup_method(self, method):
        super(TestIndex, self).setup_method(method)

        self.d = {
            'string': tm.makeStringIndex(100),
            'date': tm.makeDateIndex(100),
            'int': tm.makeIntIndex(100),
            'rng': tm.makeRangeIndex(100),
            'float': tm.makeFloatIndex(100),
            'empty': Index([]),
            'tuple': Index(zip(['foo', 'bar', 'baz'], [1, 2, 3])),
            'period': Index(period_range('2012-1-1', freq='M', periods=3)),
            'date2': Index(date_range('2013-01-1', periods=10)),
            'bdate': Index(bdate_range('2013-01-02', periods=10)),
            'cat': tm.makeCategoricalIndex(100)
        }

        self.mi = {
            'reg': MultiIndex.from_tuples([('bar', 'one'), ('baz', 'two'),
                                           ('foo', 'two'),
                                           ('qux', 'one'), ('qux', 'two')],
                                          names=['first', 'second']),
        } 

# 需要导入模块: from pandas.util import testing [as 别名]
# 或者: from pandas.util.testing import makeStringIndex [as 别名]
def test_duplicated_large(keep):
    # GH 9125
    n, k = 200, 5000
    levels = [np.arange(n), tm.makeStringIndex(n), 1000 + np.arange(n)]
    codes = [np.random.choice(n, k * n) for lev in levels]
    mi = MultiIndex(levels=levels, codes=codes)

    result = mi.duplicated(keep=keep)
    expected = hashtable.duplicated_object(mi.values, keep=keep)
    tm.assert_numpy_array_equal(result, expected) 

# 需要导入模块: from pandas.util import testing [as 别名]
# 或者: from pandas.util.testing import makeStringIndex [as 别名]
def test_invalid_index_types(self):

        # test all index types
        for i in [tm.makeIntIndex(10), tm.makeFloatIndex(10),
                  tm.makePeriodIndex(10)]:
            pytest.raises(TypeError, lambda: frequencies.infer_freq(i))

        # GH 10822
        # odd error message on conversions to datetime for unicode
        if not is_platform_windows():
            for i in [tm.makeStringIndex(10), tm.makeUnicodeIndex(10)]:
                pytest.raises(ValueError, lambda: frequencies.infer_freq(i)) 

# 需要导入模块: from pandas.util import testing [as 别名]
# 或者: from pandas.util.testing import makeStringIndex [as 别名]
def setup_method(self, method):
        self.bool_index = tm.makeBoolIndex(10, name='a')
        self.int_index = tm.makeIntIndex(10, name='a')
        self.float_index = tm.makeFloatIndex(10, name='a')
        self.dt_index = tm.makeDateIndex(10, name='a')
        self.dt_tz_index = tm.makeDateIndex(10, name='a').tz_localize(
            tz='US/Eastern')
        self.period_index = tm.makePeriodIndex(10, name='a')
        self.string_index = tm.makeStringIndex(10, name='a')
        self.unicode_index = tm.makeUnicodeIndex(10, name='a')

        arr = np.random.randn(10)
        self.bool_series = Series(arr, index=self.bool_index, name='a')
        self.int_series = Series(arr, index=self.int_index, name='a')
        self.float_series = Series(arr, index=self.float_index, name='a')
        self.dt_series = Series(arr, index=self.dt_index, name='a')
        self.dt_tz_series = self.dt_tz_index.to_series(keep_tz=True)
        self.period_series = Series(arr, index=self.period_index, name='a')
        self.string_series = Series(arr, index=self.string_index, name='a')
        self.unicode_series = Series(arr, index=self.unicode_index, name='a')

        types = ['bool', 'int', 'float', 'dt', 'dt_tz', 'period', 'string',
                 'unicode']
        self.indexes = [getattr(self, '{}_index'.format(t)) for t in types]
        self.series = [getattr(self, '{}_series'.format(t)) for t in types]
        self.objs = self.indexes + self.series 

# 需要导入模块: from pandas.util import testing [as 别名]
# 或者: from pandas.util.testing import makeStringIndex [as 别名]
def test_head_tail(self):
        # GH5370

        o = self._construct(shape=10)

        # check all index types
        for index in [tm.makeFloatIndex, tm.makeIntIndex, tm.makeStringIndex,
                      tm.makeUnicodeIndex, tm.makeDateIndex,
                      tm.makePeriodIndex]:
            axis = o._get_axis_name(0)
            setattr(o, axis, index(len(getattr(o, axis))))

            # Panel + dims
            try:
                o.head()
            except (NotImplementedError):
                pytest.skip('not implemented on {0}'.format(
                    o.__class__.__name__))

            self._compare(o.head(), o.iloc[:5])
            self._compare(o.tail(), o.iloc[-5:])

            # 0-len
            self._compare(o.head(0), o.iloc[0:0])
            self._compare(o.tail(0), o.iloc[0:0])

            # bounded
            self._compare(o.head(len(o) + 1), o)
            self._compare(o.tail(len(o) + 1), o)

            # neg index
            self._compare(o.head(-3), o.head(7))
            self._compare(o.tail(-3), o.tail(7)) 

# 需要导入模块: from pandas.util import testing [as 别名]
# 或者: from pandas.util.testing import makeStringIndex [as 别名]
def test_combine_first(self):
        values = tm.makeIntIndex(20).values.astype(float)
        series = Series(values, index=tm.makeIntIndex(20))

        series_copy = series * 2
        series_copy[::2] = np.NaN

        # nothing used from the input
        combined = series.combine_first(series_copy)

        tm.assert_series_equal(combined, series)

        # Holes filled from input
        combined = series_copy.combine_first(series)
        assert np.isfinite(combined).all()

        tm.assert_series_equal(combined[::2], series[::2])
        tm.assert_series_equal(combined[1::2], series_copy[1::2])

        # mixed types
        index = tm.makeStringIndex(20)
        floats = Series(tm.randn(20), index=index)
        strings = Series(tm.makeStringIndex(10), index=index[::2])

        combined = strings.combine_first(floats)

        tm.assert_series_equal(strings, combined.loc[index[::2]])
        tm.assert_series_equal(floats[1::2].astype(object),
                               combined.loc[index[1::2]])

        # corner case
        s = Series([1., 2, 3], index=[0, 1, 2])
        result = s.combine_first(Series([], index=[]))
        assert_series_equal(s, result) 

# 需要导入模块: from pandas.util import testing [as 别名]
# 或者: from pandas.util.testing import makeStringIndex [as 别名]
def test_grouper_index_types(self):
        # related GH5375
        # groupby misbehaving when using a Floatlike index
        df = DataFrame(np.arange(10).reshape(5, 2), columns=list('AB'))
        for index in [tm.makeFloatIndex, tm.makeStringIndex,
                      tm.makeUnicodeIndex, tm.makeIntIndex, tm.makeDateIndex,
                      tm.makePeriodIndex]:

            df.index = index(len(df))
            df.groupby(list('abcde')).apply(lambda x: x)

            df.index = list(reversed(df.index.tolist()))
            df.groupby(list('abcde')).apply(lambda x: x)