Python pandas.core.algorithms.match() Examples

The following are 29 code examples of pandas.core.algorithms.match(). 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.algorithms , or try the search function .
Example #1
Source File: test_algos.py    From twitter-stock-recommendation with MIT License 6 votes vote down vote up 
def test_ints(self):
        values = np.array([0, 2, 1])
        to_match = np.array([0, 1, 2, 2, 0, 1, 3, 0])

        result = algos.match(to_match, values)
        expected = np.array([0, 2, 1, 1, 0, 2, -1, 0], dtype=np.int64)
        tm.assert_numpy_array_equal(result, expected)

        result = Series(algos.match(to_match, values, np.nan))
        expected = Series(np.array([0, 2, 1, 1, 0, 2, np.nan, 0]))
        tm.assert_series_equal(result, expected)

        s = Series(np.arange(5), dtype=np.float32)
        result = algos.match(s, [2, 4])
        expected = np.array([-1, -1, 0, -1, 1], dtype=np.int64)
        tm.assert_numpy_array_equal(result, expected)

        result = Series(algos.match(s, [2, 4], np.nan))
        expected = Series(np.array([np.nan, np.nan, 0, np.nan, 1]))
        tm.assert_series_equal(result, expected)
Example #2
Source File: test_algos.py    From vnpy_crypto with MIT License 6 votes vote down vote up 
def test_ints(self):
        values = np.array([0, 2, 1])
        to_match = np.array([0, 1, 2, 2, 0, 1, 3, 0])

        result = algos.match(to_match, values)
        expected = np.array([0, 2, 1, 1, 0, 2, -1, 0], dtype=np.int64)
        tm.assert_numpy_array_equal(result, expected)

        result = Series(algos.match(to_match, values, np.nan))
        expected = Series(np.array([0, 2, 1, 1, 0, 2, np.nan, 0]))
        tm.assert_series_equal(result, expected)

        s = Series(np.arange(5), dtype=np.float32)
        result = algos.match(s, [2, 4])
        expected = np.array([-1, -1, 0, -1, 1], dtype=np.int64)
        tm.assert_numpy_array_equal(result, expected)

        result = Series(algos.match(s, [2, 4], np.nan))
        expected = Series(np.array([np.nan, np.nan, 0, np.nan, 1]))
        tm.assert_series_equal(result, expected)
Example #3
Source File: test_algos.py    From elasticintel with GNU General Public License v3.0 6 votes vote down vote up 
def test_ints(self):
        values = np.array([0, 2, 1])
        to_match = np.array([0, 1, 2, 2, 0, 1, 3, 0])

        result = algos.match(to_match, values)
        expected = np.array([0, 2, 1, 1, 0, 2, -1, 0], dtype=np.int64)
        tm.assert_numpy_array_equal(result, expected)

        result = Series(algos.match(to_match, values, np.nan))
        expected = Series(np.array([0, 2, 1, 1, 0, 2, np.nan, 0]))
        tm.assert_series_equal(result, expected)

        s = Series(np.arange(5), dtype=np.float32)
        result = algos.match(s, [2, 4])
        expected = np.array([-1, -1, 0, -1, 1], dtype=np.int64)
        tm.assert_numpy_array_equal(result, expected)

        result = Series(algos.match(s, [2, 4], np.nan))
        expected = Series(np.array([np.nan, np.nan, 0, np.nan, 1]))
        tm.assert_series_equal(result, expected)
Example #4
Source File: test_algos.py    From predictive-maintenance-using-machine-learning with Apache License 2.0 6 votes vote down vote up 
def test_ints(self):
        values = np.array([0, 2, 1])
        to_match = np.array([0, 1, 2, 2, 0, 1, 3, 0])

        result = algos.match(to_match, values)
        expected = np.array([0, 2, 1, 1, 0, 2, -1, 0], dtype=np.int64)
        tm.assert_numpy_array_equal(result, expected)

        result = Series(algos.match(to_match, values, np.nan))
        expected = Series(np.array([0, 2, 1, 1, 0, 2, np.nan, 0]))
        tm.assert_series_equal(result, expected)

        s = Series(np.arange(5), dtype=np.float32)
        result = algos.match(s, [2, 4])
        expected = np.array([-1, -1, 0, -1, 1], dtype=np.int64)
        tm.assert_numpy_array_equal(result, expected)

        result = Series(algos.match(s, [2, 4], np.nan))
        expected = Series(np.array([np.nan, np.nan, 0, np.nan, 1]))
        tm.assert_series_equal(result, expected)
Example #5
Source File: test_algos.py    From recruit with Apache License 2.0 6 votes vote down vote up 
def test_ints(self):
        values = np.array([0, 2, 1])
        to_match = np.array([0, 1, 2, 2, 0, 1, 3, 0])

        result = algos.match(to_match, values)
        expected = np.array([0, 2, 1, 1, 0, 2, -1, 0], dtype=np.int64)
        tm.assert_numpy_array_equal(result, expected)

        result = Series(algos.match(to_match, values, np.nan))
        expected = Series(np.array([0, 2, 1, 1, 0, 2, np.nan, 0]))
        tm.assert_series_equal(result, expected)

        s = Series(np.arange(5), dtype=np.float32)
        result = algos.match(s, [2, 4])
        expected = np.array([-1, -1, 0, -1, 1], dtype=np.int64)
        tm.assert_numpy_array_equal(result, expected)

        result = Series(algos.match(s, [2, 4], np.nan))
        expected = Series(np.array([np.nan, np.nan, 0, np.nan, 1]))
        tm.assert_series_equal(result, expected)
Example #6
Source File: test_algos.py    From predictive-maintenance-using-machine-learning with Apache License 2.0 5 votes vote down vote up 
def test_strings(self):
        values = ['foo', 'bar', 'baz']
        to_match = ['bar', 'foo', 'qux', 'foo', 'bar', 'baz', 'qux']

        result = algos.match(to_match, values)
        expected = np.array([1, 0, -1, 0, 1, 2, -1], dtype=np.int64)
        tm.assert_numpy_array_equal(result, expected)

        result = Series(algos.match(to_match, values, np.nan))
        expected = Series(np.array([1, 0, np.nan, 0, 1, 2, np.nan]))
        tm.assert_series_equal(result, expected)
Example #7
Source File: test_algos.py    From twitter-stock-recommendation with MIT License 5 votes vote down vote up 
def test_strings(self):
        values = ['foo', 'bar', 'baz']
        to_match = ['bar', 'foo', 'qux', 'foo', 'bar', 'baz', 'qux']

        result = algos.match(to_match, values)
        expected = np.array([1, 0, -1, 0, 1, 2, -1], dtype=np.int64)
        tm.assert_numpy_array_equal(result, expected)

        result = Series(algos.match(to_match, values, np.nan))
        expected = Series(np.array([1, 0, np.nan, 0, 1, 2, np.nan]))
        tm.assert_series_equal(result, expected)
Example #8
Source File: pytables.py    From elasticintel with GNU General Public License v3.0 5 votes vote down vote up 
def validate_attr(self, append):
        """validate that we have the same order as the existing & same dtype"""
        if append:
            existing_fields = getattr(self.attrs, self.kind_attr, None)
            if (existing_fields is not None and
                    existing_fields != list(self.values)):
                raise ValueError("appended items do not match existing items"
                                 " in table!")

            existing_dtype = getattr(self.attrs, self.dtype_attr, None)
            if (existing_dtype is not None and
                    existing_dtype != self.dtype):
                raise ValueError("appended items dtype do not match existing "
                                 "items dtype in table!")
Example #9
Source File: pytables.py    From elasticintel with GNU General Public License v3.0 5 votes vote down vote up 
def __contains__(self, key):
        """ check for existance of this key
              can match the exact pathname or the pathnm w/o the leading '/'
              """
        node = self.get_node(key)
        if node is not None:
            name = node._v_pathname
            if name == key or name[1:] == key:
                return True
        return False
Example #10
Source File: api.py    From elasticintel with GNU General Public License v3.0 5 votes vote down vote up 
def match(*args, **kwargs):

    import warnings
    warnings.warn("pd.match() is deprecated and will be removed "
                  "in a future version",
                  FutureWarning, stacklevel=2)
    from pandas.core.algorithms import match
    return match(*args, **kwargs)
Example #11
Source File: test_algos.py    From elasticintel with GNU General Public License v3.0 5 votes vote down vote up 
def test_strings(self):
        values = ['foo', 'bar', 'baz']
        to_match = ['bar', 'foo', 'qux', 'foo', 'bar', 'baz', 'qux']

        result = algos.match(to_match, values)
        expected = np.array([1, 0, -1, 0, 1, 2, -1], dtype=np.int64)
        tm.assert_numpy_array_equal(result, expected)

        result = Series(algos.match(to_match, values, np.nan))
        expected = Series(np.array([1, 0, np.nan, 0, 1, 2, np.nan]))
        tm.assert_series_equal(result, expected)
Example #12
Source File: pytables.py    From Splunking-Crime with GNU Affero General Public License v3.0 5 votes vote down vote up 
def validate_attr(self, append):
        """validate that we have the same order as the existing & same dtype"""
        if append:
            existing_fields = getattr(self.attrs, self.kind_attr, None)
            if (existing_fields is not None and
                    existing_fields != list(self.values)):
                raise ValueError("appended items do not match existing items"
                                 " in table!")

            existing_dtype = getattr(self.attrs, self.dtype_attr, None)
            if (existing_dtype is not None and
                    existing_dtype != self.dtype):
                raise ValueError("appended items dtype do not match existing "
                                 "items dtype in table!")
Example #13
Source File: pytables.py    From Splunking-Crime with GNU Affero General Public License v3.0 5 votes vote down vote up 
def __contains__(self, key):
        """ check for existance of this key
              can match the exact pathname or the pathnm w/o the leading '/'
              """
        node = self.get_node(key)
        if node is not None:
            name = node._v_pathname
            if name == key or name[1:] == key:
                return True
        return False
Example #14
Source File: api.py    From Splunking-Crime with GNU Affero General Public License v3.0 5 votes vote down vote up 
def match(*args, **kwargs):

    import warnings
    warnings.warn("pd.match() is deprecated and will be removed "
                  "in a future version",
                  FutureWarning, stacklevel=2)
    from pandas.core.algorithms import match
    return match(*args, **kwargs)
Example #15
Source File: pytables.py    From predictive-maintenance-using-machine-learning with Apache License 2.0 5 votes vote down vote up 
def validate_attr(self, append):
        """validate that we have the same order as the existing & same dtype"""
        if append:
            existing_fields = getattr(self.attrs, self.kind_attr, None)
            if (existing_fields is not None and
                    existing_fields != list(self.values)):
                raise ValueError("appended items do not match existing items"
                                 " in table!")

            existing_dtype = getattr(self.attrs, self.dtype_attr, None)
            if (existing_dtype is not None and
                    existing_dtype != self.dtype):
                raise ValueError("appended items dtype do not match existing "
                                 "items dtype in table!")
Example #16
Source File: test_algos.py    From predictive-maintenance-using-machine-learning with Apache License 2.0 5 votes vote down vote up 
def test_int64_add_overflow():
    # see gh-14068
    msg = "Overflow in int64 addition"
    m = np.iinfo(np.int64).max
    n = np.iinfo(np.int64).min

    with pytest.raises(OverflowError, match=msg):
        algos.checked_add_with_arr(np.array([m, m]), m)
    with pytest.raises(OverflowError, match=msg):
        algos.checked_add_with_arr(np.array([m, m]), np.array([m, m]))
    with pytest.raises(OverflowError, match=msg):
        algos.checked_add_with_arr(np.array([n, n]), n)
    with pytest.raises(OverflowError, match=msg):
        algos.checked_add_with_arr(np.array([n, n]), np.array([n, n]))
    with pytest.raises(OverflowError, match=msg):
        algos.checked_add_with_arr(np.array([m, n]), np.array([n, n]))
    with pytest.raises(OverflowError, match=msg):
        algos.checked_add_with_arr(np.array([m, m]), np.array([m, m]),
                                   arr_mask=np.array([False, True]))
    with pytest.raises(OverflowError, match=msg):
        algos.checked_add_with_arr(np.array([m, m]), np.array([m, m]),
                                   b_mask=np.array([False, True]))
    with pytest.raises(OverflowError, match=msg):
        algos.checked_add_with_arr(np.array([m, m]), np.array([m, m]),
                                   arr_mask=np.array([False, True]),
                                   b_mask=np.array([False, True]))
    with pytest.raises(OverflowError, match=msg):
        with tm.assert_produces_warning(RuntimeWarning):
            algos.checked_add_with_arr(np.array([m, m]),
                                       np.array([np.nan, m]))

    # Check that the nan boolean arrays override whether or not
    # the addition overflows. We don't check the result but just
    # the fact that an OverflowError is not raised.
    algos.checked_add_with_arr(np.array([m, m]), np.array([m, m]),
                               arr_mask=np.array([True, True]))
    algos.checked_add_with_arr(np.array([m, m]), np.array([m, m]),
                               b_mask=np.array([True, True]))
    algos.checked_add_with_arr(np.array([m, m]), np.array([m, m]),
                               arr_mask=np.array([True, False]),
                               b_mask=np.array([False, True]))
Example #17
Source File: test_algos.py    From predictive-maintenance-using-machine-learning with Apache License 2.0 5 votes vote down vote up 
def test_too_many_ndims(self):
        arr = np.array([[[1, 2, 3], [4, 5, 6], [7, 8, 9]]])
        msg = "Array with ndim > 2 are not supported"

        with pytest.raises(TypeError, match=msg):
            algos.rank(arr)
Example #18
Source File: test_algos.py    From predictive-maintenance-using-machine-learning with Apache License 2.0 5 votes vote down vote up 
def test_vector_resize(self, writable, htable, uniques, dtype,
                           safely_resizes, nvals):
        # Test for memory errors after internal vector
        # reallocations (GH 7157)
        vals = np.array(np.random.randn(1000), dtype=dtype)

        # GH 21688 ensures we can deal with read-only memory views
        vals.setflags(write=writable)

        # initialise instances; cannot initialise in parametrization,
        # as otherwise external views would be held on the array (which is
        # one of the things this test is checking)
        htable = htable()
        uniques = uniques()

        # get_labels may append to uniques
        htable.get_labels(vals[:nvals], uniques, 0, -1)
        # to_array() sets an external_view_exists flag on uniques.
        tmp = uniques.to_array()
        oldshape = tmp.shape

        # subsequent get_labels() calls can no longer append to it
        # (except for StringHashTables + ObjectVector)
        if safely_resizes:
            htable.get_labels(vals, uniques, 0, -1)
        else:
            with pytest.raises(ValueError, match='external reference.*'):
                htable.get_labels(vals, uniques, 0, -1)

        uniques.to_array()   # should not raise here
        assert tmp.shape == oldshape
Example #19
Source File: pytables.py    From Computable with MIT License 5 votes vote down vote up 
def validate_attr(self, append):
        """validate that we have the same order as the existing & same dtype"""
        if append:
            existing_fields = getattr(self.attrs, self.kind_attr, None)
            if (existing_fields is not None and
                    existing_fields != list(self.values)):
                raise ValueError("appended items do not match existing items"
                                 " in table!")

            existing_dtype = getattr(self.attrs, self.dtype_attr, None)
            if (existing_dtype is not None and
                    existing_dtype != self.dtype):
                raise ValueError("appended items dtype do not match existing "
                                 "items dtype in table!")
Example #20
Source File: pytables.py    From Computable with MIT License 5 votes vote down vote up 
def __contains__(self, key):
        """ check for existance of this key
              can match the exact pathname or the pathnm w/o the leading '/'
              """
        node = self.get_node(key)
        if node is not None:
            name = node._v_pathname
            if name == key or name[1:] == key:
                return True
        return False
Example #21
Source File: pytables.py    From vnpy_crypto with MIT License 5 votes vote down vote up 
def validate_attr(self, append):
        """validate that we have the same order as the existing & same dtype"""
        if append:
            existing_fields = getattr(self.attrs, self.kind_attr, None)
            if (existing_fields is not None and
                    existing_fields != list(self.values)):
                raise ValueError("appended items do not match existing items"
                                 " in table!")

            existing_dtype = getattr(self.attrs, self.dtype_attr, None)
            if (existing_dtype is not None and
                    existing_dtype != self.dtype):
                raise ValueError("appended items dtype do not match existing "
                                 "items dtype in table!")
Example #22
Source File: pytables.py    From vnpy_crypto with MIT License 5 votes vote down vote up 
def __contains__(self, key):
        """ check for existence of this key
              can match the exact pathname or the pathnm w/o the leading '/'
              """
        node = self.get_node(key)
        if node is not None:
            name = node._v_pathname
            if name == key or name[1:] == key:
                return True
        return False
Example #23
Source File: api.py    From vnpy_crypto with MIT License 5 votes vote down vote up 
def match(*args, **kwargs):

    import warnings
    warnings.warn("pd.match() is deprecated and will be removed "
                  "in a future version",
                  FutureWarning, stacklevel=2)
    from pandas.core.algorithms import match
    return match(*args, **kwargs)
Example #24
Source File: test_algos.py    From vnpy_crypto with MIT License 5 votes vote down vote up 
def test_strings(self):
        values = ['foo', 'bar', 'baz']
        to_match = ['bar', 'foo', 'qux', 'foo', 'bar', 'baz', 'qux']

        result = algos.match(to_match, values)
        expected = np.array([1, 0, -1, 0, 1, 2, -1], dtype=np.int64)
        tm.assert_numpy_array_equal(result, expected)

        result = Series(algos.match(to_match, values, np.nan))
        expected = Series(np.array([1, 0, np.nan, 0, 1, 2, np.nan]))
        tm.assert_series_equal(result, expected)
Example #25
Source File: pytables.py    From recruit with Apache License 2.0 5 votes vote down vote up 
def validate_attr(self, append):
        """validate that we have the same order as the existing & same dtype"""
        if append:
            existing_fields = getattr(self.attrs, self.kind_attr, None)
            if (existing_fields is not None and
                    existing_fields != list(self.values)):
                raise ValueError("appended items do not match existing items"
                                 " in table!")

            existing_dtype = getattr(self.attrs, self.dtype_attr, None)
            if (existing_dtype is not None and
                    existing_dtype != self.dtype):
                raise ValueError("appended items dtype do not match existing "
                                 "items dtype in table!")
Example #26
Source File: test_algos.py    From recruit with Apache License 2.0 5 votes vote down vote up 
def test_int64_add_overflow():
    # see gh-14068
    msg = "Overflow in int64 addition"
    m = np.iinfo(np.int64).max
    n = np.iinfo(np.int64).min

    with pytest.raises(OverflowError, match=msg):
        algos.checked_add_with_arr(np.array([m, m]), m)
    with pytest.raises(OverflowError, match=msg):
        algos.checked_add_with_arr(np.array([m, m]), np.array([m, m]))
    with pytest.raises(OverflowError, match=msg):
        algos.checked_add_with_arr(np.array([n, n]), n)
    with pytest.raises(OverflowError, match=msg):
        algos.checked_add_with_arr(np.array([n, n]), np.array([n, n]))
    with pytest.raises(OverflowError, match=msg):
        algos.checked_add_with_arr(np.array([m, n]), np.array([n, n]))
    with pytest.raises(OverflowError, match=msg):
        algos.checked_add_with_arr(np.array([m, m]), np.array([m, m]),
                                   arr_mask=np.array([False, True]))
    with pytest.raises(OverflowError, match=msg):
        algos.checked_add_with_arr(np.array([m, m]), np.array([m, m]),
                                   b_mask=np.array([False, True]))
    with pytest.raises(OverflowError, match=msg):
        algos.checked_add_with_arr(np.array([m, m]), np.array([m, m]),
                                   arr_mask=np.array([False, True]),
                                   b_mask=np.array([False, True]))
    with pytest.raises(OverflowError, match=msg):
        with tm.assert_produces_warning(RuntimeWarning):
            algos.checked_add_with_arr(np.array([m, m]),
                                       np.array([np.nan, m]))

    # Check that the nan boolean arrays override whether or not
    # the addition overflows. We don't check the result but just
    # the fact that an OverflowError is not raised.
    algos.checked_add_with_arr(np.array([m, m]), np.array([m, m]),
                               arr_mask=np.array([True, True]))
    algos.checked_add_with_arr(np.array([m, m]), np.array([m, m]),
                               b_mask=np.array([True, True]))
    algos.checked_add_with_arr(np.array([m, m]), np.array([m, m]),
                               arr_mask=np.array([True, False]),
                               b_mask=np.array([False, True]))
Example #27
Source File: test_algos.py    From recruit with Apache License 2.0 5 votes vote down vote up 
def test_too_many_ndims(self):
        arr = np.array([[[1, 2, 3], [4, 5, 6], [7, 8, 9]]])
        msg = "Array with ndim > 2 are not supported"

        with pytest.raises(TypeError, match=msg):
            algos.rank(arr)
Example #28
Source File: test_algos.py    From recruit with Apache License 2.0 5 votes vote down vote up 
def test_vector_resize(self, writable, htable, uniques, dtype,
                           safely_resizes, nvals):
        # Test for memory errors after internal vector
        # reallocations (GH 7157)
        vals = np.array(np.random.randn(1000), dtype=dtype)

        # GH 21688 ensures we can deal with read-only memory views
        vals.setflags(write=writable)

        # initialise instances; cannot initialise in parametrization,
        # as otherwise external views would be held on the array (which is
        # one of the things this test is checking)
        htable = htable()
        uniques = uniques()

        # get_labels may append to uniques
        htable.get_labels(vals[:nvals], uniques, 0, -1)
        # to_array() sets an external_view_exists flag on uniques.
        tmp = uniques.to_array()
        oldshape = tmp.shape

        # subsequent get_labels() calls can no longer append to it
        # (except for StringHashTables + ObjectVector)
        if safely_resizes:
            htable.get_labels(vals, uniques, 0, -1)
        else:
            with pytest.raises(ValueError, match='external reference.*'):
                htable.get_labels(vals, uniques, 0, -1)

        uniques.to_array()   # should not raise here
        assert tmp.shape == oldshape
Example #29
Source File: test_algos.py    From recruit with Apache License 2.0 5 votes vote down vote up 
def test_strings(self):
        values = ['foo', 'bar', 'baz']
        to_match = ['bar', 'foo', 'qux', 'foo', 'bar', 'baz', 'qux']

        result = algos.match(to_match, values)
        expected = np.array([1, 0, -1, 0, 1, 2, -1], dtype=np.int64)
        tm.assert_numpy_array_equal(result, expected)

        result = Series(algos.match(to_match, values, np.nan))
        expected = Series(np.array([1, 0, np.nan, 0, 1, 2, np.nan]))
        tm.assert_series_equal(result, expected)