Python pandas.core.dtypes.common.is_sparse() Examples

The following are 12 code examples of pandas.core.dtypes.common.is_sparse(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module pandas.core.dtypes.common , or try the search function .
Example #1
Source File: managers.py    From recruit with Apache License 2.0 6 votes vote down vote up 
def __init__(self, blocks, axes, do_integrity_check=True):
        self.axes = [ensure_index(ax) for ax in axes]
        self.blocks = tuple(blocks)

        for block in blocks:
            if block.is_sparse:
                if len(block.mgr_locs) != 1:
                    raise AssertionError("Sparse block refers to multiple "
                                         "items")
            else:
                if self.ndim != block.ndim:
                    raise AssertionError(
                        'Number of Block dimensions ({block}) must equal '
                        'number of axes ({self})'.format(block=block.ndim,
                                                         self=self.ndim))

        if do_integrity_check:
            self._verify_integrity()

        self._consolidate_check()

        self._rebuild_blknos_and_blklocs()
Example #2
Source File: managers.py    From predictive-maintenance-using-machine-learning with Apache License 2.0 6 votes vote down vote up 
def __init__(self, blocks, axes, do_integrity_check=True):
        self.axes = [ensure_index(ax) for ax in axes]
        self.blocks = tuple(blocks)

        for block in blocks:
            if block.is_sparse:
                if len(block.mgr_locs) != 1:
                    raise AssertionError("Sparse block refers to multiple "
                                         "items")
            else:
                if self.ndim != block.ndim:
                    raise AssertionError(
                        'Number of Block dimensions ({block}) must equal '
                        'number of axes ({self})'.format(block=block.ndim,
                                                         self=self.ndim))

        if do_integrity_check:
            self._verify_integrity()

        self._consolidate_check()

        self._rebuild_blknos_and_blklocs()
Example #3
Source File: test_combine_concat.py    From recruit with Apache License 2.0 5 votes vote down vote up 
def test_concat_sparse_dense_cols(self, fill_value, sparse_idx, dense_idx):
        # See GH16874, GH18914 and #18686 for why this should be a DataFrame
        from pandas.core.dtypes.common import is_sparse

        frames = [self.dense1, self.dense3]

        sparse_frame = [frames[dense_idx],
                        frames[sparse_idx].to_sparse(fill_value=fill_value)]
        dense_frame = [frames[dense_idx], frames[sparse_idx]]

        # This will try both directions sparse + dense and dense + sparse
        for _ in range(2):
            res = pd.concat(sparse_frame, axis=1)
            exp = pd.concat(dense_frame, axis=1)
            cols = [i for (i, x) in enumerate(res.dtypes) if is_sparse(x)]

            for col in cols:
                exp.iloc[:, col] = exp.iloc[:, col].astype("Sparse")

            for column in frames[dense_idx].columns:
                if dense_idx == sparse_idx:
                    tm.assert_frame_equal(res[column], exp[column])
                else:
                    tm.assert_series_equal(res[column], exp[column])

            tm.assert_frame_equal(res, exp)

            sparse_frame = sparse_frame[::-1]
            dense_frame = dense_frame[::-1]
Example #4
Source File: test_common.py    From recruit with Apache License 2.0 5 votes vote down vote up 
def test_is_sparse(check_scipy):
    assert com.is_sparse(pd.SparseArray([1, 2, 3]))
    assert com.is_sparse(pd.SparseSeries([1, 2, 3]))

    assert not com.is_sparse(np.array([1, 2, 3]))

    if check_scipy:
        import scipy.sparse
        assert not com.is_sparse(scipy.sparse.bsr_matrix([1, 2, 3]))
Example #5
Source File: managers.py    From recruit with Apache License 2.0 5 votes vote down vote up 
def _interleave(self):
        """
        Return ndarray from blocks with specified item order
        Items must be contained in the blocks
        """
        from pandas.core.dtypes.common import is_sparse
        dtype = _interleaved_dtype(self.blocks)

        # TODO: https://github.com/pandas-dev/pandas/issues/22791
        # Give EAs some input on what happens here. Sparse needs this.
        if is_sparse(dtype):
            dtype = dtype.subtype
        elif is_extension_array_dtype(dtype):
            dtype = 'object'

        result = np.empty(self.shape, dtype=dtype)

        itemmask = np.zeros(self.shape[0])

        for blk in self.blocks:
            rl = blk.mgr_locs
            result[rl.indexer] = blk.get_values(dtype)
            itemmask[rl.indexer] = 1

        if not itemmask.all():
            raise AssertionError('Some items were not contained in blocks')

        return result
Example #6
Source File: test_common.py    From vnpy_crypto with MIT License 5 votes vote down vote up 
def test_is_sparse(check_scipy):
    assert com.is_sparse(pd.SparseArray([1, 2, 3]))
    assert com.is_sparse(pd.SparseSeries([1, 2, 3]))

    assert not com.is_sparse(np.array([1, 2, 3]))

    if check_scipy:
        import scipy.sparse
        assert not com.is_sparse(scipy.sparse.bsr_matrix([1, 2, 3]))
Example #7
Source File: test_combine_concat.py    From predictive-maintenance-using-machine-learning with Apache License 2.0 5 votes vote down vote up 
def test_concat_sparse_dense_cols(self, fill_value, sparse_idx, dense_idx):
        # See GH16874, GH18914 and #18686 for why this should be a DataFrame
        from pandas.core.dtypes.common import is_sparse

        frames = [self.dense1, self.dense3]

        sparse_frame = [frames[dense_idx],
                        frames[sparse_idx].to_sparse(fill_value=fill_value)]
        dense_frame = [frames[dense_idx], frames[sparse_idx]]

        # This will try both directions sparse + dense and dense + sparse
        for _ in range(2):
            res = pd.concat(sparse_frame, axis=1)
            exp = pd.concat(dense_frame, axis=1)
            cols = [i for (i, x) in enumerate(res.dtypes) if is_sparse(x)]

            for col in cols:
                exp.iloc[:, col] = exp.iloc[:, col].astype("Sparse")

            for column in frames[dense_idx].columns:
                if dense_idx == sparse_idx:
                    tm.assert_frame_equal(res[column], exp[column])
                else:
                    tm.assert_series_equal(res[column], exp[column])

            tm.assert_frame_equal(res, exp)

            sparse_frame = sparse_frame[::-1]
            dense_frame = dense_frame[::-1]
Example #8
Source File: test_common.py    From predictive-maintenance-using-machine-learning with Apache License 2.0 5 votes vote down vote up 
def test_is_sparse(check_scipy):
    assert com.is_sparse(pd.SparseArray([1, 2, 3]))
    assert com.is_sparse(pd.SparseSeries([1, 2, 3]))

    assert not com.is_sparse(np.array([1, 2, 3]))

    if check_scipy:
        import scipy.sparse
        assert not com.is_sparse(scipy.sparse.bsr_matrix([1, 2, 3]))
Example #9
Source File: managers.py    From predictive-maintenance-using-machine-learning with Apache License 2.0 5 votes vote down vote up 
def _interleave(self):
        """
        Return ndarray from blocks with specified item order
        Items must be contained in the blocks
        """
        from pandas.core.dtypes.common import is_sparse
        dtype = _interleaved_dtype(self.blocks)

        # TODO: https://github.com/pandas-dev/pandas/issues/22791
        # Give EAs some input on what happens here. Sparse needs this.
        if is_sparse(dtype):
            dtype = dtype.subtype
        elif is_extension_array_dtype(dtype):
            dtype = 'object'

        result = np.empty(self.shape, dtype=dtype)

        itemmask = np.zeros(self.shape[0])

        for blk in self.blocks:
            rl = blk.mgr_locs
            result[rl.indexer] = blk.get_values(dtype)
            itemmask[rl.indexer] = 1

        if not itemmask.all():
            raise AssertionError('Some items were not contained in blocks')

        return result
Example #10
Source File: test_common.py    From elasticintel with GNU General Public License v3.0 5 votes vote down vote up 
def test_is_sparse():
    assert com.is_sparse(pd.SparseArray([1, 2, 3]))
    assert com.is_sparse(pd.SparseSeries([1, 2, 3]))

    assert not com.is_sparse(np.array([1, 2, 3]))

    # This test will only skip if the previous assertions
    # pass AND scipy is not installed.
    sparse = pytest.importorskip("scipy.sparse")
    assert not com.is_sparse(sparse.bsr_matrix([1, 2, 3]))
Example #11
Source File: test_combine_concat.py    From coffeegrindsize with MIT License 5 votes vote down vote up 
def test_concat_sparse_dense_cols(self, fill_value, sparse_idx, dense_idx):
        # See GH16874, GH18914 and #18686 for why this should be a DataFrame
        from pandas.core.dtypes.common import is_sparse

        frames = [self.dense1, self.dense3]

        sparse_frame = [frames[dense_idx],
                        frames[sparse_idx].to_sparse(fill_value=fill_value)]
        dense_frame = [frames[dense_idx], frames[sparse_idx]]

        # This will try both directions sparse + dense and dense + sparse
        for _ in range(2):
            res = pd.concat(sparse_frame, axis=1)
            exp = pd.concat(dense_frame, axis=1)
            cols = [i for (i, x) in enumerate(res.dtypes) if is_sparse(x)]

            for col in cols:
                exp.iloc[:, col] = exp.iloc[:, col].astype("Sparse")

            for column in frames[dense_idx].columns:
                if dense_idx == sparse_idx:
                    tm.assert_frame_equal(res[column], exp[column])
                else:
                    tm.assert_series_equal(res[column], exp[column])

            tm.assert_frame_equal(res, exp)

            sparse_frame = sparse_frame[::-1]
            dense_frame = dense_frame[::-1]
Example #12
Source File: test_common.py    From twitter-stock-recommendation with MIT License 5 votes vote down vote up 
def test_is_sparse(check_scipy):
    assert com.is_sparse(pd.SparseArray([1, 2, 3]))
    assert com.is_sparse(pd.SparseSeries([1, 2, 3]))

    assert not com.is_sparse(np.array([1, 2, 3]))

    if check_scipy:
        import scipy.sparse
        assert not com.is_sparse(scipy.sparse.bsr_matrix([1, 2, 3]))