Python pandas.SparseSeries方法代码示例

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import SparseSeries [as 别名]
def test_get(self):
        s = pd.SparseSeries([1, np.nan, np.nan, 3, np.nan])
        assert s.get(0) == 1
        assert np.isnan(s.get(1))
        assert s.get(5) is None

        s = pd.SparseSeries([1, np.nan, 0, 3, 0], index=list('ABCDE'))
        assert s.get('A') == 1
        assert np.isnan(s.get('B'))
        assert s.get('C') == 0
        assert s.get('XX') is None

        s = pd.SparseSeries([1, np.nan, 0, 3, 0], index=list('ABCDE'),
                            fill_value=0)
        assert s.get('A') == 1
        assert np.isnan(s.get('B'))
        assert s.get('C') == 0
        assert s.get('XX') is None 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import SparseSeries [as 别名]
def test_sparse_bool(self):
        # GH 13110
        s = pd.SparseSeries([True, False, False, True, False, False],
                            fill_value=False)
        result = repr(s)
        dtype = '' if use_32bit_repr else ', dtype=int32'
        exp = ("0     True\n1    False\n2    False\n"
               "3     True\n4    False\n5    False\n"
               "dtype: Sparse[bool, False]\nBlockIndex\n"
               "Block locations: array([0, 3]{0})\n"
               "Block lengths: array([1, 1]{0})".format(dtype))
        assert result == exp

        with option_context("display.max_rows", 3):
            result = repr(s)
            exp = ("0     True\n     ...  \n5    False\n"
                   "Length: 6, dtype: Sparse[bool, False]\nBlockIndex\n"
                   "Block locations: array([0, 3]{0})\n"
                   "Block lengths: array([1, 1]{0})".format(dtype))
            assert result == exp 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import SparseSeries [as 别名]
def test_concat(self, kind):
        val1 = np.array([1, 2, np.nan, np.nan, 0, np.nan])
        val2 = np.array([3, np.nan, 4, 0, 0])

        sparse1 = pd.SparseSeries(val1, name='x', kind=kind)
        sparse2 = pd.SparseSeries(val2, name='y', kind=kind)

        res = pd.concat([sparse1, sparse2])
        exp = pd.concat([pd.Series(val1), pd.Series(val2)])
        exp = pd.SparseSeries(exp, kind=kind)
        tm.assert_sp_series_equal(res, exp, consolidate_block_indices=True)

        sparse1 = pd.SparseSeries(val1, fill_value=0, name='x', kind=kind)
        sparse2 = pd.SparseSeries(val2, fill_value=0, name='y', kind=kind)

        res = pd.concat([sparse1, sparse2])
        exp = pd.concat([pd.Series(val1), pd.Series(val2)])
        exp = pd.SparseSeries(exp, fill_value=0, kind=kind)
        tm.assert_sp_series_equal(res, exp, consolidate_block_indices=True) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import SparseSeries [as 别名]
def test_concat_different_fill(self):
        val1 = np.array([1, 2, np.nan, np.nan, 0, np.nan])
        val2 = np.array([3, np.nan, 4, 0, 0])

        for kind in ['integer', 'block']:
            sparse1 = pd.SparseSeries(val1, name='x', kind=kind)
            sparse2 = pd.SparseSeries(val2, name='y', kind=kind, fill_value=0)

            with tm.assert_produces_warning(PerformanceWarning):
                res = pd.concat([sparse1, sparse2])

            exp = pd.concat([pd.Series(val1), pd.Series(val2)])
            exp = pd.SparseSeries(exp, kind=kind)
            tm.assert_sp_series_equal(res, exp)

            with tm.assert_produces_warning(PerformanceWarning):
                res = pd.concat([sparse2, sparse1])

            exp = pd.concat([pd.Series(val2), pd.Series(val1)])
            exp = pd.SparseSeries(exp, kind=kind, fill_value=0)
            tm.assert_sp_series_equal(res, exp) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import SparseSeries [as 别名]
def test_concat_different_kind(self):
        val1 = np.array([1, 2, np.nan, np.nan, 0, np.nan])
        val2 = np.array([3, np.nan, 4, 0, 0])

        sparse1 = pd.SparseSeries(val1, name='x', kind='integer')
        sparse2 = pd.SparseSeries(val2, name='y', kind='block')

        res = pd.concat([sparse1, sparse2])
        exp = pd.concat([pd.Series(val1), pd.Series(val2)])
        exp = pd.SparseSeries(exp, kind=sparse1.kind)
        tm.assert_sp_series_equal(res, exp)

        res = pd.concat([sparse2, sparse1])
        exp = pd.concat([pd.Series(val2), pd.Series(val1)])
        exp = pd.SparseSeries(exp, kind=sparse2.kind)
        tm.assert_sp_series_equal(res, exp, consolidate_block_indices=True) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import SparseSeries [as 别名]
def test_constructor_dtype(self):
        arr = SparseSeries([np.nan, 1, 2, np.nan])
        assert arr.dtype == SparseDtype(np.float64)
        assert np.isnan(arr.fill_value)

        arr = SparseSeries([np.nan, 1, 2, np.nan], fill_value=0)
        assert arr.dtype == SparseDtype(np.float64, 0)
        assert arr.fill_value == 0

        arr = SparseSeries([0, 1, 2, 4], dtype=np.int64, fill_value=np.nan)
        assert arr.dtype == SparseDtype(np.int64, np.nan)
        assert np.isnan(arr.fill_value)

        arr = SparseSeries([0, 1, 2, 4], dtype=np.int64)
        assert arr.dtype == SparseDtype(np.int64, 0)
        assert arr.fill_value == 0

        arr = SparseSeries([0, 1, 2, 4], fill_value=0, dtype=np.int64)
        assert arr.dtype == SparseDtype(np.int64, 0)
        assert arr.fill_value == 0 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import SparseSeries [as 别名]
def test_to_dense_fill_value(self):
        s = pd.Series([1, np.nan, np.nan, 3, np.nan])
        res = SparseSeries(s).to_dense()
        tm.assert_series_equal(res, s)

        res = SparseSeries(s, fill_value=0).to_dense()
        tm.assert_series_equal(res, s)

        s = pd.Series([1, np.nan, 0, 3, 0])
        res = SparseSeries(s, fill_value=0).to_dense()
        tm.assert_series_equal(res, s)

        res = SparseSeries(s, fill_value=0).to_dense()
        tm.assert_series_equal(res, s)

        s = pd.Series([np.nan, np.nan, np.nan, np.nan, np.nan])
        res = SparseSeries(s).to_dense()
        tm.assert_series_equal(res, s)

        s = pd.Series([np.nan, np.nan, np.nan, np.nan, np.nan])
        res = SparseSeries(s, fill_value=0).to_dense()
        tm.assert_series_equal(res, s) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import SparseSeries [as 别名]
def test_to_frame(self):
        # GH 9850
        s = pd.SparseSeries([1, 2, 0, nan, 4, nan, 0], name='x')
        exp = pd.SparseDataFrame({'x': [1, 2, 0, nan, 4, nan, 0]})
        tm.assert_sp_frame_equal(s.to_frame(), exp)

        exp = pd.SparseDataFrame({'y': [1, 2, 0, nan, 4, nan, 0]})
        tm.assert_sp_frame_equal(s.to_frame(name='y'), exp)

        s = pd.SparseSeries([1, 2, 0, nan, 4, nan, 0], name='x', fill_value=0)
        exp = pd.SparseDataFrame({'x': [1, 2, 0, nan, 4, nan, 0]},
                                 default_fill_value=0)

        tm.assert_sp_frame_equal(s.to_frame(), exp)
        exp = pd.DataFrame({'y': [1, 2, 0, nan, 4, nan, 0]})
        tm.assert_frame_equal(s.to_frame(name='y').to_dense(), exp) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import SparseSeries [as 别名]
def test_getitem_slice(self):
        idx = self.bseries.index
        res = self.bseries[::2]
        assert isinstance(res, SparseSeries)

        expected = self.bseries.reindex(idx[::2])
        tm.assert_sp_series_equal(res, expected)

        res = self.bseries[:5]
        assert isinstance(res, SparseSeries)
        tm.assert_sp_series_equal(res, self.bseries.reindex(idx[:5]))

        res = self.bseries[5:]
        tm.assert_sp_series_equal(res, self.bseries.reindex(idx[5:]))

        # negative indices
        res = self.bseries[:-3]
        tm.assert_sp_series_equal(res, self.bseries.reindex(idx[:-3])) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import SparseSeries [as 别名]
def test_unary_operators(self, values, op, fill_value):
        # https://github.com/pandas-dev/pandas/issues/22835
        values = np.asarray(values)
        if op is operator.invert:
            new_fill_value = not fill_value
        else:
            new_fill_value = op(fill_value)
        s = SparseSeries(values,
                         fill_value=fill_value,
                         index=['a', 'b', 'c', 'd'],
                         name='name')
        result = op(s)
        expected = SparseSeries(op(values),
                                fill_value=new_fill_value,
                                index=['a', 'b', 'c', 'd'],
                                name='name')
        tm.assert_sp_series_equal(result, expected) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import SparseSeries [as 别名]
def test_dropna(self):
        sp = SparseSeries([0, 0, 0, nan, nan, 5, 6], fill_value=0)

        sp_valid = sp.dropna()

        expected = sp.to_dense().dropna()
        expected = expected[expected != 0]
        exp_arr = pd.SparseArray(expected.values, fill_value=0, kind='block')
        tm.assert_sp_array_equal(sp_valid.values, exp_arr)
        tm.assert_index_equal(sp_valid.index, expected.index)
        assert len(sp_valid.sp_values) == 2

        result = self.bseries.dropna()
        expected = self.bseries.to_dense().dropna()
        assert not isinstance(result, SparseSeries)
        tm.assert_series_equal(result, expected) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import SparseSeries [as 别名]
def test_shift(self):
        series = SparseSeries([nan, 1., 2., 3., nan, nan], index=np.arange(6))

        shifted = series.shift(0)
        # assert shifted is not series
        tm.assert_sp_series_equal(shifted, series)

        f = lambda s: s.shift(1)
        _dense_series_compare(series, f)

        f = lambda s: s.shift(-2)
        _dense_series_compare(series, f)

        series = SparseSeries([nan, 1., 2., 3., nan, nan],
                              index=bdate_range('1/1/2000', periods=6))
        f = lambda s: s.shift(2, freq='B')
        _dense_series_compare(series, f)

        f = lambda s: s.shift(2, freq=BDay())
        _dense_series_compare(series, f) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import SparseSeries [as 别名]
def test_concat(self):
        val1 = np.array([1, 2, np.nan, np.nan, 0, np.nan])
        val2 = np.array([3, np.nan, 4, 0, 0])

        for kind in ['integer', 'block']:
            sparse1 = pd.SparseSeries(val1, name='x', kind=kind)
            sparse2 = pd.SparseSeries(val2, name='y', kind=kind)

            res = pd.concat([sparse1, sparse2])
            exp = pd.concat([pd.Series(val1), pd.Series(val2)])
            exp = pd.SparseSeries(exp, kind=kind)
            tm.assert_sp_series_equal(res, exp)

            sparse1 = pd.SparseSeries(val1, fill_value=0, name='x', kind=kind)
            sparse2 = pd.SparseSeries(val2, fill_value=0, name='y', kind=kind)

            res = pd.concat([sparse1, sparse2])
            exp = pd.concat([pd.Series(val1), pd.Series(val2)])
            exp = pd.SparseSeries(exp, fill_value=0, kind=kind)
            tm.assert_sp_series_equal(res, exp,
                                      consolidate_block_indices=True) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import SparseSeries [as 别名]
def test_concat_different_fill(self):
        val1 = np.array([1, 2, np.nan, np.nan, 0, np.nan])
        val2 = np.array([3, np.nan, 4, 0, 0])

        for kind in ['integer', 'block']:
            sparse1 = pd.SparseSeries(val1, name='x', kind=kind)
            sparse2 = pd.SparseSeries(val2, name='y', kind=kind, fill_value=0)

            with tm.assert_produces_warning(PerformanceWarning):
                res = pd.concat([sparse1, sparse2])
            exp = pd.concat([pd.Series(val1), pd.Series(val2)])
            exp = pd.SparseSeries(exp, kind=kind)
            tm.assert_sp_series_equal(res, exp)

            with tm.assert_produces_warning(PerformanceWarning):
                res = pd.concat([sparse2, sparse1])
            exp = pd.concat([pd.Series(val2), pd.Series(val1)])
            exp = pd.SparseSeries(exp, kind=kind, fill_value=0)
            tm.assert_sp_series_equal(res, exp) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import SparseSeries [as 别名]
def test_concat_different_kind(self):
        val1 = np.array([1, 2, np.nan, np.nan, 0, np.nan])
        val2 = np.array([3, np.nan, 4, 0, 0])

        sparse1 = pd.SparseSeries(val1, name='x', kind='integer')
        sparse2 = pd.SparseSeries(val2, name='y', kind='block', fill_value=0)

        with tm.assert_produces_warning(PerformanceWarning):
            res = pd.concat([sparse1, sparse2])
        exp = pd.concat([pd.Series(val1), pd.Series(val2)])
        exp = pd.SparseSeries(exp, kind='integer')
        tm.assert_sp_series_equal(res, exp)

        with tm.assert_produces_warning(PerformanceWarning):
            res = pd.concat([sparse2, sparse1])
        exp = pd.concat([pd.Series(val2), pd.Series(val1)])
        exp = pd.SparseSeries(exp, kind='block', fill_value=0)
        tm.assert_sp_series_equal(res, exp)