Python testing.assert_frame_equal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 assert_frame_equal [as 别名]
def test_rank_hits(self):
        ranks = pd.DataFrame(
            [
                [1., 4., 1., 5., 7.],
                [2., 6., 9., 2., 8.],
                [2., 2., 6., 8., 4.]
            ],
            index=['OTU_1', 'OTU_2', 'OTU_3'],
            columns=['MS_1', 'MS_2', 'MS_3', 'MS_4', 'MS_5']
        )
        res = rank_hits(ranks, k=2)
        exp = pd.DataFrame(
            [
                ['OTU_1', 5., 'MS_4'],
                ['OTU_2', 8., 'MS_5'],
                ['OTU_3', 6., 'MS_3'],
                ['OTU_1', 7., 'MS_5'],
                ['OTU_2', 9., 'MS_3'],
                ['OTU_3', 8., 'MS_4']
            ], columns=['src', 'rank', 'dest'],
        )

        pdt.assert_frame_equal(res, exp) 

# 需要导入模块: from pandas.util import testing [as 别名]
# 或者: from pandas.util.testing import assert_frame_equal [as 别名]
def test_dataframe_append_should_promote_string_column(library):
    data = np.zeros((2,), dtype=[('A', 'i4'), ('B', 'f4'), ('C', 'a10')])
    data[:] = [(1, 2., 'Hello'), (2, 3., "World")]
    df = DataFrame(data, index=DatetimeIndex(np.array([dt(2013, 1, 1),
                                                       dt(2013, 1, 2)]).astype('datetime64[ns]'), name='DATETIME'))
    data2 = np.zeros((1,), dtype=[('A', 'i4'), ('B', 'f4'), ('C', 'a30')])
    data2[:] = [(3, 4., 'Hello World - Good Morning')]
    df2 = DataFrame(data2, index=DatetimeIndex(np.array([dt(2013, 1, 3)]).astype('datetime64[ns]'), name='DATETIME'))
    expected_data = np.zeros((3,), dtype=[('A', 'i4'), ('B', 'f4'), ('C', 'a30')])
    expected_data[:] = [(1, 2., 'Hello'), (2, 3., "World"), (3, 4., 'Hello World - Good Morning')]
    expected = DataFrame(expected_data, index=DatetimeIndex(np.array([dt(2013, 1, 1),
                                                                       dt(2013, 1, 2),
                                                                       dt(2013, 1, 3)]).astype('datetime64[ns]'), name='DATETIME'))

    library.write('pandas', df)
    library.append('pandas', df2)
    actual = library.read('pandas').data

    assert_frame_equal(expected, actual) 

# 需要导入模块: from pandas.util import testing [as 别名]
# 或者: from pandas.util.testing import assert_frame_equal [as 别名]
def test_dataframe_append_should_add_new_column(library):
    data = np.zeros((2,), dtype=[('A', 'i4'), ('B', 'f4'), ('C', 'a10')])
    data[:] = [(1, 2., 'Hello'), (2, 3., "World")]
    df = DataFrame(data, index=DatetimeIndex(np.array([dt(2013, 1, 1),
                                                       dt(2013, 1, 2)]).astype('datetime64[ns]'), name='DATETIME'))
    data2 = np.zeros((1,), dtype=[('A', 'i4'), ('B', 'f4'), ('C', 'a10'), ('D', 'f4')])
    data2[:] = [(4, 5., 'Hi', 6.)]
    df2 = DataFrame(data2, index=DatetimeIndex(np.array([dt(2013, 1, 3)]).astype('datetime64[ns]'), name='DATETIME'))
    expected_data = np.zeros((3,), dtype=[('A', 'i4'), ('B', 'f4'), ('C', 'a10'), ('D', 'f4')])
    expected_data[:] = [(1, 2., 'Hello', np.nan), (2, 3., "World", np.nan), (4, 5., 'Hi', 6.)]
    expected = DataFrame(expected_data, index=DatetimeIndex(np.array([dt(2013, 1, 1),
                                                                       dt(2013, 1, 2),
                                                                       dt(2013, 1, 3)]).astype('datetime64[ns]'), name='DATETIME'))

    library.write('pandas', df)
    library.append('pandas', df2)
    actual = library.read('pandas').data

    assert_frame_equal(expected, actual) 

# 需要导入模块: from pandas.util import testing [as 别名]
# 或者: from pandas.util.testing import assert_frame_equal [as 别名]
def test_dataframe_append_should_add_new_columns_and_reorder(library):
    data = np.zeros((2,), dtype=[('A', 'i4'), ('B', 'f4'), ('C', 'a10')])
    data[:] = [(1, 2., 'Hello'), (2, 3., "World")]
    df = DataFrame(data, index=DatetimeIndex(np.array([dt(2013, 1, 1),
                                                       dt(2013, 1, 2)]).astype('datetime64[ns]'), name='DATETIME'))
    data2 = np.zeros((1,), dtype=[('C', 'a10'), ('A', 'i4'), ('E', 'a1'), ('B', 'f4'), ('D', 'f4'), ('F', 'i4')])
    data2[:] = [('Hi', 4, 'Y', 5., 6., 7)]
    df2 = DataFrame(data2, index=DatetimeIndex(np.array([dt(2013, 1, 3)]).astype('datetime64[ns]'), name='DATETIME'))
    expected_data = np.zeros((3,), dtype=[('C', 'a10'), ('A', 'i4'), ('E', 'a1'),
                                          ('B', 'f4'), ('D', 'f4'), ('F', 'i4')])
    expected_data[:] = [('Hello', 1, '', 2., np.nan, 0), ("World", 2, '', 3., np.nan, 0), ('Hi', 4, 'Y', 5., 6., 7)]
    expected = DataFrame(expected_data, index=DatetimeIndex(np.array([dt(2013, 1, 1),
                                                                       dt(2013, 1, 2),
                                                                       dt(2013, 1, 3)]).astype('datetime64[ns]'), name='DATETIME'))

    library.write('pandas', df)
    library.append('pandas', df2)
    actual = library.read('pandas').data

    assert_frame_equal(expected, actual)


# -- auto generated tests --- # 

# 需要导入模块: from pandas.util import testing [as 别名]
# 或者: from pandas.util.testing import assert_frame_equal [as 别名]
def test_daterange_large_DataFrame_middle(library):
    df = DataFrame(index=date_range(dt(2001, 1, 1), freq='S', periods=30 * 1024),
                   data=np.tile(np.arange(30 * 1024), 100).reshape((-1, 100)))
    df.columns = [str(c) for c in df.columns]
    library.write('MYARR', df)
    # middle
    start = 100
    for end in np.arange(200, 30000, 1000):
        result = library.read('MYARR', date_range=DateRange(df.index[start], df.index[end])).data
        assert_frame_equal(df[df.index[start]:df.index[end]], result, check_names=False)
    # middle following
    for start in np.arange(200, 30000, 1000):
        for offset in (100, 300, 500):
            end = start + offset
            result = library.read('MYARR', date_range=DateRange(df.index[start], df.index[end])).data
            assert_frame_equal(df[df.index[start]:df.index[end]], result, check_names=False) 

# 需要导入模块: from pandas.util import testing [as 别名]
# 或者: from pandas.util.testing import assert_frame_equal [as 别名]
def assert_frame_equal(self, left, right, *args, **kwargs):
        tm.assert_index_equal(
            left.columns, right.columns,
            exact=kwargs.get('check_column_type', 'equiv'),
            check_names=kwargs.get('check_names', True),
            check_exact=kwargs.get('check_exact', False),
            check_categorical=kwargs.get('check_categorical', True),
            obj='{obj}.columns'.format(obj=kwargs.get('obj', 'DataFrame')))

        jsons = (left.dtypes == 'json').index

        for col in jsons:
            self.assert_series_equal(left[col], right[col],
                                     *args, **kwargs)

        left = left.drop(columns=jsons)
        right = right.drop(columns=jsons)
        tm.assert_frame_equal(left, right, *args, **kwargs) 

# 需要导入模块: from pandas.util import testing [as 别名]
# 或者: from pandas.util.testing import assert_frame_equal [as 别名]
def test_custom_asserts(self):
        # This would always trigger the KeyError from trying to put
        # an array of equal-length UserDicts inside an ndarray.
        data = JSONArray([collections.UserDict({'a': 1}),
                          collections.UserDict({'b': 2}),
                          collections.UserDict({'c': 3})])
        a = pd.Series(data)
        self.assert_series_equal(a, a)
        self.assert_frame_equal(a.to_frame(), a.to_frame())

        b = pd.Series(data.take([0, 0, 1]))
        with pytest.raises(AssertionError):
            self.assert_series_equal(a, b)

        with pytest.raises(AssertionError):
            self.assert_frame_equal(a.to_frame(), b.to_frame()) 

# 需要导入模块: from pandas.util import testing [as 别名]
# 或者: from pandas.util.testing import assert_frame_equal [as 别名]
def assert_frame_equal(self, left, right, *args, **kwargs):
        # TODO(EA): select_dtypes
        tm.assert_index_equal(
            left.columns, right.columns,
            exact=kwargs.get('check_column_type', 'equiv'),
            check_names=kwargs.get('check_names', True),
            check_exact=kwargs.get('check_exact', False),
            check_categorical=kwargs.get('check_categorical', True),
            obj='{obj}.columns'.format(obj=kwargs.get('obj', 'DataFrame')))

        decimals = (left.dtypes == 'decimal').index

        for col in decimals:
            self.assert_series_equal(left[col], right[col],
                                     *args, **kwargs)

        left = left.drop(columns=decimals)
        right = right.drop(columns=decimals)
        tm.assert_frame_equal(left, right, *args, **kwargs) 

# 需要导入模块: from pandas.util import testing [as 别名]
# 或者: from pandas.util.testing import assert_frame_equal [as 别名]
def test_window_with_args(self):
        # make sure that we are aggregating window functions correctly with arg
        r = Series(np.random.randn(100)).rolling(window=10, min_periods=1,
                                                 win_type='gaussian')
        expected = concat([r.mean(std=10), r.mean(std=.01)], axis=1)
        expected.columns = ['<lambda>', '<lambda>']
        result = r.aggregate([lambda x: x.mean(std=10),
                              lambda x: x.mean(std=.01)])
        tm.assert_frame_equal(result, expected)

        def a(x):
            return x.mean(std=10)

        def b(x):
            return x.mean(std=0.01)

        expected = concat([r.mean(std=10), r.mean(std=.01)], axis=1)
        expected.columns = ['a', 'b']
        result = r.aggregate([a, b])
        tm.assert_frame_equal(result, expected) 

# 需要导入模块: from pandas.util import testing [as 别名]
# 或者: from pandas.util.testing import assert_frame_equal [as 别名]
def test_rolling_axis(self, axis_frame):
        # see gh-23372.
        df = DataFrame(np.ones((10, 20)))
        axis = df._get_axis_number(axis_frame)

        if axis == 0:
            expected = DataFrame({
                i: [np.nan] * 2 + [3.0] * 8
                for i in range(20)
            })
        else:
            # axis == 1
            expected = DataFrame([
                [np.nan] * 2 + [3.0] * 18
            ] * 10)

        result = df.rolling(3, axis=axis_frame).sum()
        tm.assert_frame_equal(result, expected) 

# 需要导入模块: from pandas.util import testing [as 别名]
# 或者: from pandas.util.testing import assert_frame_equal [as 别名]
def test_rolling_apply_with_pandas_objects(self, window):
        # 5071
        df = pd.DataFrame({'A': np.random.randn(5),
                           'B': np.random.randint(0, 10, size=5)},
                          index=pd.date_range('20130101', periods=5, freq='s'))

        # we have an equal spaced timeseries index
        # so simulate removing the first period
        def f(x):
            if x.index[0] == df.index[0]:
                return np.nan
            return x.iloc[-1]

        result = df.rolling(window).apply(f, raw=False)
        expected = df.iloc[2:].reindex_like(df)
        tm.assert_frame_equal(result, expected)

        with pytest.raises(AttributeError):
            df.rolling(window).apply(f, raw=True) 

# 需要导入模块: from pandas.util import testing [as 别名]
# 或者: from pandas.util.testing import assert_frame_equal [as 别名]
def test_flex_binary_frame(self, method):
        series = self.frame[1]

        res = getattr(series.rolling(window=10), method)(self.frame)
        res2 = getattr(self.frame.rolling(window=10), method)(series)
        exp = self.frame.apply(lambda x: getattr(
            series.rolling(window=10), method)(x))

        tm.assert_frame_equal(res, exp)
        tm.assert_frame_equal(res2, exp)

        frame2 = self.frame.copy()
        frame2.values[:] = np.random.randn(*frame2.shape)

        res3 = getattr(self.frame.rolling(window=10), method)(frame2)
        exp = DataFrame({k: getattr(self.frame[k].rolling(
            window=10), method)(frame2[k]) for k in self.frame})
        tm.assert_frame_equal(res3, exp) 

# 需要导入模块: from pandas.util import testing [as 别名]
# 或者: from pandas.util.testing import assert_frame_equal [as 别名]
def test_expanding_apply_args_kwargs(self, raw):

        def mean_w_arg(x, const):
            return np.mean(x) + const

        df = DataFrame(np.random.rand(20, 3))

        expected = df.expanding().apply(np.mean, raw=raw) + 20.

        result = df.expanding().apply(mean_w_arg,
                                      raw=raw,
                                      args=(20, ))
        tm.assert_frame_equal(result, expected)

        result = df.expanding().apply(mean_w_arg,
                                      raw=raw,
                                      kwargs={'const': 20})
        tm.assert_frame_equal(result, expected) 

# 需要导入模块: from pandas.util import testing [as 别名]
# 或者: from pandas.util.testing import assert_frame_equal [as 别名]
def test_rolling_functions_window_non_shrinkage(self, f):
        # GH 7764
        s = Series(range(4))
        s_expected = Series(np.nan, index=s.index)
        df = DataFrame([[1, 5], [3, 2], [3, 9], [-1, 0]], columns=['A', 'B'])
        df_expected = DataFrame(np.nan, index=df.index, columns=df.columns)

        try:
            s_result = f(s)
            tm.assert_series_equal(s_result, s_expected)

            df_result = f(df)
            tm.assert_frame_equal(df_result, df_expected)
        except (ImportError):

            # scipy needed for rolling_window
            pytest.skip("scipy not available") 

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

        # corr/cov return a MI DataFrame
        df = DataFrame([[1, 5], [3, 2], [3, 9], [-1, 0]],
                       columns=Index(['A', 'B'], name='foo'),
                       index=Index(range(4), name='bar'))
        df_expected = DataFrame(
            columns=Index(['A', 'B'], name='foo'),
            index=pd.MultiIndex.from_product([df.index, df.columns],
                                             names=['bar', 'foo']),
            dtype='float64')
        functions = [lambda x: (x.rolling(window=10, min_periods=5)
                                .cov(x, pairwise=True)),
                     lambda x: (x.rolling(window=10, min_periods=5)
                                .corr(x, pairwise=True))]
        for f in functions:
            df_result = f(df)
            tm.assert_frame_equal(df_result, df_expected)