Python testing.assert_series_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_series_equal [as 别名]
def test_isna(self, data_missing):
        expected_dtype = SparseDtype(bool,
                                     pd.isna(data_missing.dtype.fill_value))
        expected = SparseArray([True, False], dtype=expected_dtype)

        result = pd.isna(data_missing)
        self.assert_equal(result, expected)

        result = pd.Series(data_missing).isna()
        expected = pd.Series(expected)
        self.assert_series_equal(result, expected)

        # GH 21189
        result = pd.Series(data_missing).drop([0, 1]).isna()
        expected = pd.Series([], dtype=expected_dtype)
        self.assert_series_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_series_equal [as 别名]
def test_combine_le(self, data_repeated):
        # We return a Series[SparseArray].__le__ returns a
        # Series[Sparse[bool]]
        # rather than Series[bool]
        orig_data1, orig_data2 = data_repeated(2)
        s1 = pd.Series(orig_data1)
        s2 = pd.Series(orig_data2)
        result = s1.combine(s2, lambda x1, x2: x1 <= x2)
        expected = pd.Series(pd.SparseArray([
            a <= b for (a, b) in
            zip(list(orig_data1), list(orig_data2))
        ], fill_value=False))
        self.assert_series_equal(result, expected)

        val = s1.iloc[0]
        result = s1.combine(val, lambda x1, x2: x1 <= x2)
        expected = pd.Series(pd.SparseArray([
            a <= val for a in list(orig_data1)
        ], fill_value=False))
        self.assert_series_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_series_equal [as 别名]
def test_where_series(self, data, na_value):
        assert data[0] != data[1]
        cls = type(data)
        a, b = data[:2]

        ser = pd.Series(cls._from_sequence([a, a, b, b], dtype=data.dtype))

        cond = np.array([True, True, False, False])
        result = ser.where(cond)

        new_dtype = SparseDtype('float', 0.0)
        expected = pd.Series(cls._from_sequence([a, a, na_value, na_value],
                                                dtype=new_dtype))
        self.assert_series_equal(result, expected)

        other = cls._from_sequence([a, b, a, b], dtype=data.dtype)
        cond = np.array([True, False, True, True])
        result = ser.where(cond, other)
        expected = pd.Series(cls._from_sequence([a, b, b, b],
                                                dtype=data.dtype))
        self.assert_series_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_series_equal [as 别名]
def _compare_other(self, s, data, op_name, other):
        op = self.get_op_from_name(op_name)

        # array
        result = pd.Series(op(data, other))
        # hard to test the fill value, since we don't know what expected
        # is in general.
        # Rely on tests in `tests/sparse` to validate that.
        assert isinstance(result.dtype, SparseDtype)
        assert result.dtype.subtype == np.dtype('bool')

        with np.errstate(all='ignore'):
            expected = pd.Series(
                pd.SparseArray(op(np.asarray(data), np.asarray(other)),
                               fill_value=result.values.fill_value)
            )

        tm.assert_series_equal(result, expected)

        # series
        s = pd.Series(data)
        result = op(s, other)
        tm.assert_series_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_series_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_series_equal [as 别名]
def assert_series_equal(self, left, right, *args, **kwargs):
        def convert(x):
            # need to convert array([Decimal(NaN)], dtype='object') to np.NaN
            # because Series[object].isnan doesn't recognize decimal(NaN) as
            # NA.
            try:
                return math.isnan(x)
            except TypeError:
                return False

        if left.dtype == 'object':
            left_na = left.apply(convert)
        else:
            left_na = left.isna()
        if right.dtype == 'object':
            right_na = right.apply(convert)
        else:
            right_na = right.isna()

        tm.assert_series_equal(left_na, right_na)
        return tm.assert_series_equal(left[~left_na],
                                      right[~right_na],
                                      *args, **kwargs) 

# 需要导入模块: from pandas.util import testing [as 别名]
# 或者: from pandas.util.testing import assert_series_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_series_equal [as 别名]
def test_cmov_window_special_linear_range(self, win_types_special):
        # GH 8238
        kwds = {
            'kaiser': {'beta': 1.},
            'gaussian': {'std': 1.},
            'general_gaussian': {'power': 2., 'width': 2.},
            'slepian': {'width': 0.5}}

        vals = np.array(range(10), dtype=np.float)
        xp = vals.copy()
        xp[:2] = np.nan
        xp[-2:] = np.nan
        xp = Series(xp)

        rs = Series(vals).rolling(
            5, win_type=win_types_special, center=True).mean(
            **kwds[win_types_special])
        tm.assert_series_equal(xp, rs) 

# 需要导入模块: from pandas.util import testing [as 别名]
# 或者: from pandas.util.testing import assert_series_equal [as 别名]
def test_expanding_cov_diff_index(self):
        # GH 7512
        s1 = Series([1, 2, 3], index=[0, 1, 2])
        s2 = Series([1, 3], index=[0, 2])
        result = s1.expanding().cov(s2)
        expected = Series([None, None, 2.0])
        tm.assert_series_equal(result, expected)

        s2a = Series([1, None, 3], index=[0, 1, 2])
        result = s1.expanding().cov(s2a)
        tm.assert_series_equal(result, expected)

        s1 = Series([7, 8, 10], index=[0, 1, 3])
        s2 = Series([7, 9, 10], index=[0, 2, 3])
        result = s1.expanding().cov(s2)
        expected = Series([None, None, None, 4.5])
        tm.assert_series_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_series_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_series_equal [as 别名]
def test_rolling_skew_edge_cases(self):

        all_nan = Series([np.NaN] * 5)

        # yields all NaN (0 variance)
        d = Series([1] * 5)
        x = d.rolling(window=5).skew()
        tm.assert_series_equal(all_nan, x)

        # yields all NaN (window too small)
        d = Series(np.random.randn(5))
        x = d.rolling(window=2).skew()
        tm.assert_series_equal(all_nan, x)

        # yields [NaN, NaN, NaN, 0.177994, 1.548824]
        d = Series([-1.50837035, -0.1297039, 0.19501095, 1.73508164, 0.41941401
                    ])
        expected = Series([np.NaN, np.NaN, np.NaN, 0.177994, 1.548824])
        x = d.rolling(window=4).skew()
        tm.assert_series_equal(expected, x) 

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

        all_nan = Series([np.NaN] * 5)

        # yields all NaN (0 variance)
        d = Series([1] * 5)
        x = d.rolling(window=5).kurt()
        tm.assert_series_equal(all_nan, x)

        # yields all NaN (window too small)
        d = Series(np.random.randn(5))
        x = d.rolling(window=3).kurt()
        tm.assert_series_equal(all_nan, x)

        # yields [NaN, NaN, NaN, 1.224307, 2.671499]
        d = Series([-1.50837035, -0.1297039, 0.19501095, 1.73508164, 0.41941401
                    ])
        expected = Series([np.NaN, np.NaN, np.NaN, 1.224307, 2.671499])
        x = d.rolling(window=4).kurt()
        tm.assert_series_equal(expected, x) 

# 需要导入模块: from pandas.util import testing [as 别名]
# 或者: from pandas.util.testing import assert_series_equal [as 别名]
def test_rolling_max_gh6297(self):
        """Replicate result expected in GH #6297"""

        indices = [datetime(1975, 1, i) for i in range(1, 6)]
        # So that we can have 2 datapoints on one of the days
        indices.append(datetime(1975, 1, 3, 6, 0))
        series = Series(range(1, 7), index=indices)
        # Use floats instead of ints as values
        series = series.map(lambda x: float(x))
        # Sort chronologically
        series = series.sort_index()

        expected = Series([1.0, 2.0, 6.0, 4.0, 5.0],
                          index=[datetime(1975, 1, i, 0) for i in range(1, 6)])
        x = series.resample('D').max().rolling(window=1).max()
        tm.assert_series_equal(expected, x) 

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

        indices = [datetime(1975, 1, i) for i in range(1, 6)]
        # So that we can have 3 datapoints on last day (4, 10, and 20)
        indices.append(datetime(1975, 1, 5, 1))
        indices.append(datetime(1975, 1, 5, 2))
        series = Series(list(range(0, 5)) + [10, 20], index=indices)
        # Use floats instead of ints as values
        series = series.map(lambda x: float(x))
        # Sort chronologically
        series = series.sort_index()

        # Default how should be min
        expected = Series([0.0, 1.0, 2.0, 3.0, 4.0],
                          index=[datetime(1975, 1, i, 0) for i in range(1, 6)])
        r = series.resample('D').min().rolling(window=1)
        tm.assert_series_equal(expected, r.min()) 

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

        indices = [datetime(1975, 1, i) for i in range(1, 6)]
        # So that we can have 3 datapoints on last day (4, 10, and 20)
        indices.append(datetime(1975, 1, 5, 1))
        indices.append(datetime(1975, 1, 5, 2))
        series = Series(list(range(0, 5)) + [10, 20], index=indices)
        # Use floats instead of ints as values
        series = series.map(lambda x: float(x))
        # Sort chronologically
        series = series.sort_index()

        # Default how should be median
        expected = Series([0.0, 1.0, 2.0, 3.0, 10],
                          index=[datetime(1975, 1, i, 0) for i in range(1, 6)])
        x = series.resample('D').median().rolling(window=1).median()
        tm.assert_series_equal(expected, x)