Python pandas.core.strings.str_contains() Examples

The following are 2 code examples of pandas.core.strings.str_contains(). 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.strings , or try the search function .
Example #1
Source File: test_strings.py    From recruit with Apache License 2.0 4 votes vote down vote up 
def test_contains(self):
        values = np.array(['foo', NA, 'fooommm__foo',
                           'mmm_', 'foommm[_]+bar'], dtype=np.object_)
        pat = 'mmm[_]+'

        result = strings.str_contains(values, pat)
        expected = np.array([False, NA, True, True, False], dtype=np.object_)
        tm.assert_numpy_array_equal(result, expected)

        result = strings.str_contains(values, pat, regex=False)
        expected = np.array([False, NA, False, False, True], dtype=np.object_)
        tm.assert_numpy_array_equal(result, expected)

        values = ['foo', 'xyz', 'fooommm__foo', 'mmm_']
        result = strings.str_contains(values, pat)
        expected = np.array([False, False, True, True])
        assert result.dtype == np.bool_
        tm.assert_numpy_array_equal(result, expected)

        # case insensitive using regex
        values = ['Foo', 'xYz', 'fOOomMm__fOo', 'MMM_']
        result = strings.str_contains(values, 'FOO|mmm', case=False)
        expected = np.array([True, False, True, True])
        tm.assert_numpy_array_equal(result, expected)

        # case insensitive without regex
        result = strings.str_contains(values, 'foo', regex=False, case=False)
        expected = np.array([True, False, True, False])
        tm.assert_numpy_array_equal(result, expected)

        # mixed
        mixed = ['a', NA, 'b', True, datetime.today(), 'foo', None, 1, 2.]
        rs = strings.str_contains(mixed, 'o')
        xp = np.array([False, NA, False, NA, NA, True, NA, NA, NA],
                      dtype=np.object_)
        tm.assert_numpy_array_equal(rs, xp)

        rs = Series(mixed).str.contains('o')
        xp = Series([False, NA, False, NA, NA, True, NA, NA, NA])
        assert isinstance(rs, Series)
        tm.assert_series_equal(rs, xp)

        # unicode
        values = np.array([u'foo', NA, u'fooommm__foo', u'mmm_'],
                          dtype=np.object_)
        pat = 'mmm[_]+'

        result = strings.str_contains(values, pat)
        expected = np.array([False, np.nan, True, True], dtype=np.object_)
        tm.assert_numpy_array_equal(result, expected)

        result = strings.str_contains(values, pat, na=False)
        expected = np.array([False, False, True, True])
        tm.assert_numpy_array_equal(result, expected)

        values = np.array(['foo', 'xyz', 'fooommm__foo', 'mmm_'],
                          dtype=np.object_)
        result = strings.str_contains(values, pat)
        expected = np.array([False, False, True, True])
        assert result.dtype == np.bool_
        tm.assert_numpy_array_equal(result, expected)
Example #2
Source File: test_strings.py    From predictive-maintenance-using-machine-learning with Apache License 2.0 4 votes vote down vote up 
def test_contains(self):
        values = np.array(['foo', NA, 'fooommm__foo',
                           'mmm_', 'foommm[_]+bar'], dtype=np.object_)
        pat = 'mmm[_]+'

        result = strings.str_contains(values, pat)
        expected = np.array([False, NA, True, True, False], dtype=np.object_)
        tm.assert_numpy_array_equal(result, expected)

        result = strings.str_contains(values, pat, regex=False)
        expected = np.array([False, NA, False, False, True], dtype=np.object_)
        tm.assert_numpy_array_equal(result, expected)

        values = ['foo', 'xyz', 'fooommm__foo', 'mmm_']
        result = strings.str_contains(values, pat)
        expected = np.array([False, False, True, True])
        assert result.dtype == np.bool_
        tm.assert_numpy_array_equal(result, expected)

        # case insensitive using regex
        values = ['Foo', 'xYz', 'fOOomMm__fOo', 'MMM_']
        result = strings.str_contains(values, 'FOO|mmm', case=False)
        expected = np.array([True, False, True, True])
        tm.assert_numpy_array_equal(result, expected)

        # case insensitive without regex
        result = strings.str_contains(values, 'foo', regex=False, case=False)
        expected = np.array([True, False, True, False])
        tm.assert_numpy_array_equal(result, expected)

        # mixed
        mixed = ['a', NA, 'b', True, datetime.today(), 'foo', None, 1, 2.]
        rs = strings.str_contains(mixed, 'o')
        xp = np.array([False, NA, False, NA, NA, True, NA, NA, NA],
                      dtype=np.object_)
        tm.assert_numpy_array_equal(rs, xp)

        rs = Series(mixed).str.contains('o')
        xp = Series([False, NA, False, NA, NA, True, NA, NA, NA])
        assert isinstance(rs, Series)
        tm.assert_series_equal(rs, xp)

        # unicode
        values = np.array([u'foo', NA, u'fooommm__foo', u'mmm_'],
                          dtype=np.object_)
        pat = 'mmm[_]+'

        result = strings.str_contains(values, pat)
        expected = np.array([False, np.nan, True, True], dtype=np.object_)
        tm.assert_numpy_array_equal(result, expected)

        result = strings.str_contains(values, pat, na=False)
        expected = np.array([False, False, True, True])
        tm.assert_numpy_array_equal(result, expected)

        values = np.array(['foo', 'xyz', 'fooommm__foo', 'mmm_'],
                          dtype=np.object_)
        result = strings.str_contains(values, pat)
        expected = np.array([False, False, True, True])
        assert result.dtype == np.bool_
        tm.assert_numpy_array_equal(result, expected)