Python pandas.util.testing.rands() Examples

def test_repr_truncation(self):
        max_len = 20
        with option_context("display.max_colwidth", max_len):
            df = DataFrame({'A': np.random.randn(10),
                            'B': [tm.rands(np.random.randint(
                                max_len - 1, max_len + 1)) for i in range(10)
            ]})
            r = repr(df)
            r = r[r.find('\n') + 1:]

            adj = fmt._get_adjustment()

            for line, value in lzip(r.split('\n'), df['B']):
                if adj.len(value) + 1 > max_len:
                    assert '...' in line
                else:
                    assert '...' not in line

        with option_context("display.max_colwidth", 999999):
            assert '...' not in repr(df)

        with option_context("display.max_colwidth", max_len + 2):
            assert '...' not in repr(df) 

def test_nonexistent_path(all_parsers):
    # gh-2428: pls no segfault
    # gh-14086: raise more helpful FileNotFoundError
    parser = all_parsers
    path = "%s.csv" % tm.rands(10)

    msg = ("does not exist" if parser.engine == "c"
           else r"\[Errno 2\]")
    with pytest.raises(compat.FileNotFoundError, match=msg) as e:
        parser.read_csv(path)

        filename = e.value.filename
        filename = filename.decode() if isinstance(
            filename, bytes) else filename

        assert path == filename 

def test_repr_truncation(self):
        max_len = 20
        with option_context("display.max_colwidth", max_len):
            df = DataFrame({'A': np.random.randn(10),
                            'B': [tm.rands(np.random.randint(
                                max_len - 1, max_len + 1)) for i in range(10)
            ]})
            r = repr(df)
            r = r[r.find('\n') + 1:]

            adj = fmt._get_adjustment()

            for line, value in lzip(r.split('\n'), df['B']):
                if adj.len(value) + 1 > max_len:
                    assert '...' in line
                else:
                    assert '...' not in line

        with option_context("display.max_colwidth", 999999):
            assert '...' not in repr(df)

        with option_context("display.max_colwidth", max_len + 2):
            assert '...' not in repr(df) 

def test_nonexistent_path(all_parsers):
    # gh-2428: pls no segfault
    # gh-14086: raise more helpful FileNotFoundError
    parser = all_parsers
    path = "%s.csv" % tm.rands(10)

    msg = ("does not exist" if parser.engine == "c"
           else r"\[Errno 2\]")
    with pytest.raises(compat.FileNotFoundError, match=msg) as e:
        parser.read_csv(path)

        filename = e.value.filename
        filename = filename.decode() if isinstance(
            filename, bytes) else filename

        assert path == filename 

def test_repr_truncation(self):
        max_len = 20
        with option_context("display.max_colwidth", max_len):
            df = DataFrame({'A': np.random.randn(10),
                            'B': [tm.rands(np.random.randint(
                                max_len - 1, max_len + 1)) for i in range(10)
            ]})
            r = repr(df)
            r = r[r.find('\n') + 1:]

            adj = fmt._get_adjustment()

            for line, value in lzip(r.split('\n'), df['B']):
                if adj.len(value) + 1 > max_len:
                    assert '...' in line
                else:
                    assert '...' not in line

        with option_context("display.max_colwidth", 999999):
            assert '...' not in repr(df)

        with option_context("display.max_colwidth", max_len + 2):
            assert '...' not in repr(df) 

def test_timestamp_compare(self):
        # make sure we can compare Timestamps on the right AND left hand side
        # GH4982
        df = DataFrame({'dates1': date_range('20010101', periods=10),
                        'dates2': date_range('20010102', periods=10),
                        'intcol': np.random.randint(1000000000, size=10),
                        'floatcol': np.random.randn(10),
                        'stringcol': list(tm.rands(10))})
        df.loc[np.random.rand(len(df)) > 0.5, 'dates2'] = pd.NaT
        ops = {'gt': 'lt', 'lt': 'gt', 'ge': 'le', 'le': 'ge', 'eq': 'eq',
               'ne': 'ne'}

        for left, right in ops.items():
            left_f = getattr(operator, left)
            right_f = getattr(operator, right)

            # no nats
            expected = left_f(df, Timestamp('20010109'))
            result = right_f(Timestamp('20010109'), df)
            assert_frame_equal(result, expected)

            # nats
            expected = left_f(df, Timestamp('nat'))
            result = right_f(Timestamp('nat'), df)
            assert_frame_equal(result, expected) 

def test_timestamp_compare(self):
        # make sure we can compare Timestamps on the right AND left hand side
        # GH4982
        df = DataFrame({'dates1': date_range('20010101', periods=10),
                        'dates2': date_range('20010102', periods=10),
                        'intcol': np.random.randint(1000000000, size=10),
                        'floatcol': np.random.randn(10),
                        'stringcol': list(tm.rands(10))})
        df.loc[np.random.rand(len(df)) > 0.5, 'dates2'] = pd.NaT
        ops = {'gt': 'lt', 'lt': 'gt', 'ge': 'le', 'le': 'ge', 'eq': 'eq',
               'ne': 'ne'}

        for left, right in ops.items():
            left_f = getattr(operator, left)
            right_f = getattr(operator, right)

            # no nats
            expected = left_f(df, Timestamp('20010109'))
            result = right_f(Timestamp('20010109'), df)
            assert_frame_equal(result, expected)

            # nats
            expected = left_f(df, Timestamp('nat'))
            result = right_f(Timestamp('nat'), df)
            assert_frame_equal(result, expected) 

def test_repr_truncation(self):
        max_len = 20
        with option_context("display.max_colwidth", max_len):
            df = DataFrame({'A': np.random.randn(10),
                            'B': [tm.rands(np.random.randint(
                                max_len - 1, max_len + 1)) for i in range(10)
            ]})
            r = repr(df)
            r = r[r.find('\n') + 1:]

            adj = fmt._get_adjustment()

            for line, value in lzip(r.split('\n'), df['B']):
                if adj.len(value) + 1 > max_len:
                    assert '...' in line
                else:
                    assert '...' not in line

        with option_context("display.max_colwidth", 999999):
            assert '...' not in repr(df)

        with option_context("display.max_colwidth", max_len + 2):
            assert '...' not in repr(df) 

def test_timestamp_compare(self):
        # make sure we can compare Timestamps on the right AND left hand side
        # GH4982
        df = DataFrame({'dates1': date_range('20010101', periods=10),
                        'dates2': date_range('20010102', periods=10),
                        'intcol': np.random.randint(1000000000, size=10),
                        'floatcol': np.random.randn(10),
                        'stringcol': list(tm.rands(10))})
        df.loc[np.random.rand(len(df)) > 0.5, 'dates2'] = pd.NaT
        ops = {'gt': 'lt', 'lt': 'gt', 'ge': 'le', 'le': 'ge', 'eq': 'eq',
               'ne': 'ne'}

        for left, right in ops.items():
            left_f = getattr(operator, left)
            right_f = getattr(operator, right)

            # no nats
            expected = left_f(df, Timestamp('20010109'))
            result = right_f(Timestamp('20010109'), df)
            assert_frame_equal(result, expected)

            # nats
            expected = left_f(df, Timestamp('nat'))
            result = right_f(Timestamp('nat'), df)
            assert_frame_equal(result, expected) 

def test_repr_truncation(self):
        max_len = 20
        with option_context("display.max_colwidth", max_len):
            df = DataFrame({'A': np.random.randn(10),
                            'B': [tm.rands(np.random.randint(
                                max_len - 1, max_len + 1)) for i in range(10)
            ]})
            r = repr(df)
            r = r[r.find('\n') + 1:]

            adj = fmt._get_adjustment()

            for line, value in lzip(r.split('\n'), df['B']):
                if adj.len(value) + 1 > max_len:
                    assert '...' in line
                else:
                    assert '...' not in line

        with option_context("display.max_colwidth", 999999):
            assert '...' not in repr(df)

        with option_context("display.max_colwidth", max_len + 2):
            assert '...' not in repr(df) 

def get_random_path():
    return u'__%s__.pickle' % tm.rands(10) 

def test_internal_eof_byte_to_file(all_parsers):
    # see gh-16559
    parser = all_parsers
    data = b'c1,c2\r\n"test \x1a    test", test\r\n'
    expected = DataFrame([["test \x1a    test", " test"]],
                         columns=["c1", "c2"])
    path = "__%s__.csv" % tm.rands(10)

    with tm.ensure_clean(path) as path:
        with open(path, "wb") as f:
            f.write(data)

        result = parser.read_csv(path)
        tm.assert_frame_equal(result, expected) 

def get_random_path():
    return u'__%s__.pickle' % tm.rands(10) 

def setup_method(self, method):
        self.path = '__%s__.msg' % tm.rands(10) 

def test_astype_unicode(self):
        # see gh-7758: A bit of magic is required to set
        # default encoding to utf-8
        digits = string.digits
        test_series = [
            Series([digits * 10, tm.rands(63), tm.rands(64), tm.rands(1000)]),
            Series([u('データーサイエンス、お前はもう死んでいる')]),
        ]

        former_encoding = None

        if not compat.PY3:
            # In Python, we can force the default encoding for this test
            former_encoding = sys.getdefaultencoding()
            reload(sys)  # noqa

            sys.setdefaultencoding("utf-8")
        if sys.getdefaultencoding() == "utf-8":
            test_series.append(Series([u('野菜食べないとやばい')
                                       .encode("utf-8")]))

        for s in test_series:
            res = s.astype("unicode")
            expec = s.map(compat.text_type)
            tm.assert_series_equal(res, expec)

        # Restore the former encoding
        if former_encoding is not None and former_encoding != "utf-8":
            reload(sys)  # noqa
            sys.setdefaultencoding(former_encoding) 

def test_rands():
    r = tm.rands(10)
    assert(len(r) == 10) 

def test_nonexistent_path(self):
        # gh-2428: pls no segfault
        # gh-14086: raise more helpful FileNotFoundError
        path = '%s.csv' % tm.rands(10)
        pytest.raises(compat.FileNotFoundError, self.read_csv, path) 

def test_internal_eof_byte_to_file(self):
        # see gh-16559
        data = b'c1,c2\r\n"test \x1a    test", test\r\n'
        expected = pd.DataFrame([["test \x1a    test", " test"]],
                                columns=["c1", "c2"])

        path = '__%s__.csv' % tm.rands(10)

        with tm.ensure_clean(path) as path:
            with open(path, "wb") as f:
                f.write(data)

            result = self.read_csv(path)
            tm.assert_frame_equal(result, expected) 

def test_astype_unicode(self):
        # see gh-7758: A bit of magic is required to set
        # default encoding to utf-8
        digits = string.digits
        test_series = [
            Series([digits * 10, tm.rands(63), tm.rands(64), tm.rands(1000)]),
            Series([u('データーサイエンス、お前はもう死んでいる')]),
        ]

        former_encoding = None

        if not compat.PY3:
            # In Python, we can force the default encoding for this test
            former_encoding = sys.getdefaultencoding()
            reload(sys)  # noqa

            sys.setdefaultencoding("utf-8")
        if sys.getdefaultencoding() == "utf-8":
            test_series.append(Series([u('野菜食べないとやばい')
                                       .encode("utf-8")]))

        for s in test_series:
            res = s.astype("unicode")
            expec = s.map(compat.text_type)
            tm.assert_series_equal(res, expec)

        # Restore the former encoding
        if former_encoding is not None and former_encoding != "utf-8":
            reload(sys)  # noqa
            sys.setdefaultencoding(former_encoding) 

def setup_method(self, method):
        self.path = '__%s__.msg' % tm.rands(10) 

def test_astype_unicode(self):
        # see gh-7758: A bit of magic is required to set
        # default encoding to utf-8
        digits = string.digits
        test_series = [
            Series([digits * 10, tm.rands(63), tm.rands(64), tm.rands(1000)]),
            Series([u('データーサイエンス、お前はもう死んでいる')]),
        ]

        former_encoding = None

        if not compat.PY3:
            # In Python, we can force the default encoding for this test
            former_encoding = sys.getdefaultencoding()
            reload(sys)  # noqa

            sys.setdefaultencoding("utf-8")
        if sys.getdefaultencoding() == "utf-8":
            test_series.append(Series([u('野菜食べないとやばい')
                                       .encode("utf-8")]))

        for s in test_series:
            res = s.astype("unicode")
            expec = s.map(compat.text_type)
            tm.assert_series_equal(res, expec)

        # Restore the former encoding
        if former_encoding is not None and former_encoding != "utf-8":
            reload(sys)  # noqa
            sys.setdefaultencoding(former_encoding) 

def test_rands():
    r = tm.rands(10)
    assert(len(r) == 10) 

def test_nonexistent_path(self):
        # gh-2428: pls no segfault
        # gh-14086: raise more helpful FileNotFoundError
        path = '%s.csv' % tm.rands(10)
        pytest.raises(compat.FileNotFoundError, self.read_csv, path) 

def test_internal_eof_byte_to_file(self):
        # see gh-16559
        data = b'c1,c2\r\n"test \x1a    test", test\r\n'
        expected = pd.DataFrame([["test \x1a    test", " test"]],
                                columns=["c1", "c2"])

        path = '__%s__.csv' % tm.rands(10)

        with tm.ensure_clean(path) as path:
            with open(path, "wb") as f:
                f.write(data)

            result = self.read_csv(path)
            tm.assert_frame_equal(result, expected) 

def get_random_path():
    return u'__%s__.pickle' % tm.rands(10) 

def test_timestamp_compare(self):
        # make sure we can compare Timestamps on the right AND left hand side
        # GH#4982
        df = pd. DataFrame({'dates1': pd.date_range('20010101', periods=10),
                            'dates2': pd.date_range('20010102', periods=10),
                            'intcol': np.random.randint(1000000000, size=10),
                            'floatcol': np.random.randn(10),
                            'stringcol': list(tm.rands(10))})
        df.loc[np.random.rand(len(df)) > 0.5, 'dates2'] = pd.NaT
        ops = {'gt': 'lt', 'lt': 'gt', 'ge': 'le', 'le': 'ge', 'eq': 'eq',
               'ne': 'ne'}

        for left, right in ops.items():
            left_f = getattr(operator, left)
            right_f = getattr(operator, right)

            # no nats
            if left in ['eq', 'ne']:
                expected = left_f(df, pd.Timestamp('20010109'))
                result = right_f(pd.Timestamp('20010109'), df)
                tm.assert_frame_equal(result, expected)
            else:
                with pytest.raises(TypeError):
                    left_f(df, pd.Timestamp('20010109'))
                with pytest.raises(TypeError):
                    right_f(pd.Timestamp('20010109'), df)
            # nats
            expected = left_f(df, pd.Timestamp('nat'))
            result = right_f(pd.Timestamp('nat'), df)
            tm.assert_frame_equal(result, expected) 

def test_rands():
    r = tm.rands(10)
    assert len(r) == 10 

def test_internal_eof_byte_to_file(all_parsers):
    # see gh-16559
    parser = all_parsers
    data = b'c1,c2\r\n"test \x1a    test", test\r\n'
    expected = DataFrame([["test \x1a    test", " test"]],
                         columns=["c1", "c2"])
    path = "__%s__.csv" % tm.rands(10)

    with tm.ensure_clean(path) as path:
        with open(path, "wb") as f:
            f.write(data)

        result = parser.read_csv(path)
        tm.assert_frame_equal(result, expected) 

def get_random_path():
    return u'__%s__.pickle' % tm.rands(10) 

def setup_method(self, method):
        self.path = '__%s__.msg' % tm.rands(10)