Python numpy.random.randn() Examples

def test_mixed_depth_pop(self):
        arrays = [['a', 'top', 'top', 'routine1', 'routine1', 'routine2'],
                  ['', 'OD', 'OD', 'result1', 'result2', 'result1'],
                  ['', 'wx', 'wy', '', '', '']]

        tuples = sorted(zip(*arrays))
        index = MultiIndex.from_tuples(tuples)
        df = DataFrame(randn(4, 6), columns=index)

        df1 = df.copy()
        df2 = df.copy()
        result = df1.pop('a')
        expected = df2.pop(('a', '', ''))
        tm.assert_series_equal(expected, result, check_names=False)
        tm.assert_frame_equal(df1, df2)
        assert result.name == 'a'

        expected = df1['top']
        df1 = df1.drop(['top'], axis=1)
        result = df2.pop('top')
        tm.assert_frame_equal(expected, result)
        tm.assert_frame_equal(df1, df2) 

def setup_method(self, method):
        # aggregate multiple columns
        self.df = DataFrame({'key1': get_test_data(),
                             'key2': get_test_data(),
                             'data1': np.random.randn(N),
                             'data2': np.random.randn(N)})

        # exclude a couple keys for fun
        self.df = self.df[self.df['key2'] > 1]

        self.df2 = DataFrame({'key1': get_test_data(n=N // 5),
                              'key2': get_test_data(ngroups=NGROUPS // 2,
                                                    n=N // 5),
                              'value': np.random.randn(N // 5)})

        index, data = tm.getMixedTypeDict()
        self.target = DataFrame(data, index=index)

        # Join on string value
        self.source = DataFrame({'MergedA': data['A'], 'MergedD': data['D']},
                                index=data['C']) 

def test_rolling_kurt_edge_cases(self):

        all_nan = Series([np.NaN] * 5)

        # yields all NaN (0 variance)
        d = Series([1] * 5)
        x = d.rolling(window=5).kurt()
        tm.assert_series_equal(all_nan, x)

        # yields all NaN (window too small)
        d = Series(np.random.randn(5))
        x = d.rolling(window=3).kurt()
        tm.assert_series_equal(all_nan, x)

        # yields [NaN, NaN, NaN, 1.224307, 2.671499]
        d = Series([-1.50837035, -0.1297039, 0.19501095, 1.73508164, 0.41941401
                    ])
        expected = Series([np.NaN, np.NaN, np.NaN, 1.224307, 2.671499])
        x = d.rolling(window=4).kurt()
        tm.assert_series_equal(expected, x) 

def test_rolling_skew_edge_cases(self):

        all_nan = Series([np.NaN] * 5)

        # yields all NaN (0 variance)
        d = Series([1] * 5)
        x = d.rolling(window=5).skew()
        tm.assert_series_equal(all_nan, x)

        # yields all NaN (window too small)
        d = Series(np.random.randn(5))
        x = d.rolling(window=2).skew()
        tm.assert_series_equal(all_nan, x)

        # yields [NaN, NaN, NaN, 0.177994, 1.548824]
        d = Series([-1.50837035, -0.1297039, 0.19501095, 1.73508164, 0.41941401
                    ])
        expected = Series([np.NaN, np.NaN, np.NaN, 0.177994, 1.548824])
        x = d.rolling(window=4).skew()
        tm.assert_series_equal(expected, x) 

def setup_method(self):
        self.index = MultiIndex(levels=[['foo', 'bar', 'baz', 'qux'],
                                        ['one', 'two', 'three']],
                                codes=[[0, 0, 0, 1, 1, 2, 2, 3, 3, 3],
                                       [0, 1, 2, 0, 1, 1, 2, 0, 1, 2]],
                                names=['first', 'second'])
        self.to_join = DataFrame(np.random.randn(10, 3), index=self.index,
                                 columns=['j_one', 'j_two', 'j_three'])

        # a little relevant example with NAs
        key1 = ['bar', 'bar', 'bar', 'foo', 'foo', 'baz', 'baz', 'qux',
                'qux', 'snap']
        key2 = ['two', 'one', 'three', 'one', 'two', 'one', 'two', 'two',
                'three', 'one']

        data = np.random.randn(len(key1))
        self.data = DataFrame({'key1': key1, 'key2': key2,
                               'data': data}) 

def test_errors(self):
        x = np.random.randn(1, 2, 3)
        assert_raises_regex(np.AxisError, 'source.*out of bounds',
                            np.moveaxis, x, 3, 0)
        assert_raises_regex(np.AxisError, 'source.*out of bounds',
                            np.moveaxis, x, -4, 0)
        assert_raises_regex(np.AxisError, 'destination.*out of bounds',
                            np.moveaxis, x, 0, 5)
        assert_raises_regex(ValueError, 'repeated axis in `source`',
                            np.moveaxis, x, [0, 0], [0, 1])
        assert_raises_regex(ValueError, 'repeated axis in `destination`',
                            np.moveaxis, x, [0, 1], [1, 1])
        assert_raises_regex(ValueError, 'must have the same number',
                            np.moveaxis, x, 0, [0, 1])
        assert_raises_regex(ValueError, 'must have the same number',
                            np.moveaxis, x, [0, 1], [0]) 

def test_count_level_series(self):
        index = MultiIndex(levels=[['foo', 'bar', 'baz'], ['one', 'two',
                                                           'three', 'four']],
                           codes=[[0, 0, 0, 2, 2], [2, 0, 1, 1, 2]])

        s = Series(np.random.randn(len(index)), index=index)

        result = s.count(level=0)
        expected = s.groupby(level=0).count()
        tm.assert_series_equal(
            result.astype('f8'), expected.reindex(result.index).fillna(0))

        result = s.count(level=1)
        expected = s.groupby(level=1).count()
        tm.assert_series_equal(
            result.astype('f8'), expected.reindex(result.index).fillna(0)) 

def test_flex_binary_frame(self, method):
        series = self.frame[1]

        res = getattr(series.rolling(window=10), method)(self.frame)
        res2 = getattr(self.frame.rolling(window=10), method)(series)
        exp = self.frame.apply(lambda x: getattr(
            series.rolling(window=10), method)(x))

        tm.assert_frame_equal(res, exp)
        tm.assert_frame_equal(res2, exp)

        frame2 = self.frame.copy()
        frame2.values[:] = np.random.randn(*frame2.shape)

        res3 = getattr(self.frame.rolling(window=10), method)(frame2)
        exp = DataFrame({k: getattr(self.frame[k].rolling(
            window=10), method)(frame2[k]) for k in self.frame})
        tm.assert_frame_equal(res3, exp) 

def test_concat_dict(self):
        frames = {'foo': DataFrame(np.random.randn(4, 3)),
                  'bar': DataFrame(np.random.randn(4, 3)),
                  'baz': DataFrame(np.random.randn(4, 3)),
                  'qux': DataFrame(np.random.randn(4, 3))}

        sorted_keys = sorted(frames)

        result = concat(frames)
        expected = concat([frames[k] for k in sorted_keys], keys=sorted_keys)
        tm.assert_frame_equal(result, expected)

        result = concat(frames, axis=1)
        expected = concat([frames[k] for k in sorted_keys], keys=sorted_keys,
                          axis=1)
        tm.assert_frame_equal(result, expected)

        keys = ['baz', 'foo', 'bar']
        result = concat(frames, keys=keys)
        expected = concat([frames[k] for k in keys], keys=keys)
        tm.assert_frame_equal(result, expected) 

def test_sort_index_level_large_cardinality(self):

        # #2684 (int64)
        index = MultiIndex.from_arrays([np.arange(4000)] * 3)
        df = DataFrame(np.random.randn(4000), index=index, dtype=np.int64)

        # it works!
        result = df.sort_index(level=0)
        assert result.index.lexsort_depth == 3

        # #2684 (int32)
        index = MultiIndex.from_arrays([np.arange(4000)] * 3)
        df = DataFrame(np.random.randn(4000), index=index, dtype=np.int32)

        # it works!
        result = df.sort_index(level=0)
        assert (result.dtypes.values == df.dtypes.values).all()
        assert result.index.lexsort_depth == 3 

def test_window_with_args(self):
        # make sure that we are aggregating window functions correctly with arg
        r = Series(np.random.randn(100)).rolling(window=10, min_periods=1,
                                                 win_type='gaussian')
        expected = concat([r.mean(std=10), r.mean(std=.01)], axis=1)
        expected.columns = ['<lambda>', '<lambda>']
        result = r.aggregate([lambda x: x.mean(std=10),
                              lambda x: x.mean(std=.01)])
        tm.assert_frame_equal(result, expected)

        def a(x):
            return x.mean(std=10)

        def b(x):
            return x.mean(std=0.01)

        expected = concat([r.mean(std=10), r.mean(std=.01)], axis=1)
        expected.columns = ['a', 'b']
        result = r.aggregate([a, b])
        tm.assert_frame_equal(result, expected) 

def test_std_var_pass_ddof(self):
        index = MultiIndex.from_arrays([np.arange(5).repeat(10), np.tile(
            np.arange(10), 5)])
        df = DataFrame(np.random.randn(len(index), 5), index=index)

        for meth in ['var', 'std']:
            ddof = 4
            alt = lambda x: getattr(x, meth)(ddof=ddof)

            result = getattr(df[0], meth)(level=0, ddof=ddof)
            expected = df[0].groupby(level=0).agg(alt)
            tm.assert_series_equal(result, expected)

            result = getattr(df, meth)(level=0, ddof=ddof)
            expected = df.groupby(level=0).agg(alt)
            tm.assert_frame_equal(result, expected) 

def test_cmov_window_corner(self):
        # GH 8238
        # all nan
        vals = pd.Series([np.nan] * 10)
        result = vals.rolling(5, center=True, win_type='boxcar').mean()
        assert np.isnan(result).all()

        # empty
        vals = pd.Series([])
        result = vals.rolling(5, center=True, win_type='boxcar').mean()
        assert len(result) == 0

        # shorter than window
        vals = pd.Series(np.random.randn(5))
        result = vals.rolling(10, win_type='boxcar').mean()
        assert np.isnan(result).all()
        assert len(result) == 5 

def test_crossed_dtypes_weird_corner(self):
        columns = ['A', 'B', 'C', 'D']
        df1 = DataFrame({'A': np.array([1, 2, 3, 4], dtype='f8'),
                         'B': np.array([1, 2, 3, 4], dtype='i8'),
                         'C': np.array([1, 2, 3, 4], dtype='f8'),
                         'D': np.array([1, 2, 3, 4], dtype='i8')},
                        columns=columns)

        df2 = DataFrame({'A': np.array([1, 2, 3, 4], dtype='i8'),
                         'B': np.array([1, 2, 3, 4], dtype='f8'),
                         'C': np.array([1, 2, 3, 4], dtype='i8'),
                         'D': np.array([1, 2, 3, 4], dtype='f8')},
                        columns=columns)

        appended = df1.append(df2, ignore_index=True)
        expected = DataFrame(np.concatenate([df1.values, df2.values], axis=0),
                             columns=columns)
        tm.assert_frame_equal(appended, expected)

        df = DataFrame(np.random.randn(1, 3), index=['a'])
        df2 = DataFrame(np.random.randn(1, 4), index=['b'])
        result = concat(
            [df, df2], keys=['one', 'two'], names=['first', 'second'])
        assert result.index.names == ('first', 'second') 

def test_concat_single_with_key(self):
        df = DataFrame(np.random.randn(10, 4))

        result = concat([df], keys=['foo'])
        expected = concat([df, df], keys=['foo', 'bar'])
        tm.assert_frame_equal(result, expected[:10]) 

def test_unicode_repr_level_names(self):
        index = MultiIndex.from_tuples([(0, 0), (1, 1)],
                                       names=[u('\u0394'), 'i1'])

        s = Series(lrange(2), index=index)
        df = DataFrame(np.random.randn(2, 4), index=index)
        repr(s)
        repr(df) 

def right():
    """right dataframe (multi-indexed) for multi-index join tests"""
    index = MultiIndex(levels=[['foo', 'bar', 'baz', 'qux'],
                               ['one', 'two', 'three']],
                       codes=[[0, 0, 0, 1, 1, 2, 2, 3, 3, 3],
                              [0, 1, 2, 0, 1, 1, 2, 0, 1, 2]],
                       names=['key1', 'key2'])

    return DataFrame(np.random.randn(10, 3), index=index,
                     columns=['j_one', 'j_two', 'j_three']) 

def test_left_merge_na_buglet(self):
        left = DataFrame({'id': list('abcde'), 'v1': randn(5),
                          'v2': randn(5), 'dummy': list('abcde'),
                          'v3': randn(5)},
                         columns=['id', 'v1', 'v2', 'dummy', 'v3'])
        right = DataFrame({'id': ['a', 'b', np.nan, np.nan, np.nan],
                           'sv3': [1.234, 5.678, np.nan, np.nan, np.nan]})

        result = merge(left, right, on='id', how='left')

        rdf = right.drop(['id'], axis=1)
        expected = left.join(rdf)
        tm.assert_frame_equal(result, expected) 

def test_concat_exclude_none(self):
        df = DataFrame(np.random.randn(10, 4))

        pieces = [df[:5], None, None, df[5:]]
        result = concat(pieces)
        tm.assert_frame_equal(result, df)
        with pytest.raises(ValueError, match="All objects passed were None"):
            concat([None, None]) 

def test_concat_series_axis1_same_names_ignore_index(self):
        dates = date_range('01-Jan-2013', '01-Jan-2014', freq='MS')[0:-1]
        s1 = Series(randn(len(dates)), index=dates, name='value')
        s2 = Series(randn(len(dates)), index=dates, name='value')

        result = concat([s1, s2], axis=1, ignore_index=True)
        expected = Index([0, 1])

        tm.assert_index_equal(result.columns, expected) 

def test_concat_multiindex_rangeindex(self):
        # GH13542
        # when multi-index levels are RangeIndex objects
        # there is a bug in concat with objects of len 1

        df = DataFrame(np.random.randn(9, 2))
        df.index = MultiIndex(levels=[pd.RangeIndex(3), pd.RangeIndex(3)],
                              codes=[np.repeat(np.arange(3), 3),
                                     np.tile(np.arange(3), 3)])

        res = concat([df.iloc[[2, 3, 4], :], df.iloc[[5], :]])
        exp = df.iloc[[2, 3, 4, 5], :]
        tm.assert_frame_equal(res, exp) 

def test_concat_copy(self):
        df = DataFrame(np.random.randn(4, 3))
        df2 = DataFrame(np.random.randint(0, 10, size=4).reshape(4, 1))
        df3 = DataFrame({5: 'foo'}, index=range(4))

        # These are actual copies.
        result = concat([df, df2, df3], axis=1, copy=True)

        for b in result._data.blocks:
            assert b.values.base is None

        # These are the same.
        result = concat([df, df2, df3], axis=1, copy=False)

        for b in result._data.blocks:
            if b.is_float:
                assert b.values.base is df._data.blocks[0].values.base
            elif b.is_integer:
                assert b.values.base is df2._data.blocks[0].values.base
            elif b.is_object:
                assert b.values.base is not None

        # Float block was consolidated.
        df4 = DataFrame(np.random.randn(4, 1))
        result = concat([df, df2, df3, df4], axis=1, copy=False)
        for b in result._data.blocks:
            if b.is_float:
                assert b.values.base is None
            elif b.is_integer:
                assert b.values.base is df2._data.blocks[0].values.base
            elif b.is_object:
                assert b.values.base is not None 

def test_drop_preserve_names(self):
        index = MultiIndex.from_arrays([[0, 0, 0, 1, 1, 1],
                                        [1, 2, 3, 1, 2, 3]],
                                       names=['one', 'two'])

        df = DataFrame(np.random.randn(6, 3), index=index)

        result = df.drop([(0, 2)])
        assert result.index.names == ('one', 'two') 

def test_multilevel_consolidate(self):
        index = MultiIndex.from_tuples([('foo', 'one'), ('foo', 'two'), (
            'bar', 'one'), ('bar', 'two')])
        df = DataFrame(np.random.randn(4, 4), index=index, columns=index)
        df['Totals', ''] = df.sum(1)
        df = df._consolidate() 

def test_unstack_number_of_levels_larger_than_int32(self):
        # GH 20601
        df = DataFrame(np.random.randn(2 ** 16, 2),
                       index=[np.arange(2 ** 16), np.arange(2 ** 16)])
        with pytest.raises(ValueError, match='int32 overflow'):
            df.unstack() 

def test_unstack_unobserved_keys(self):
        # related to #2278 refactoring
        levels = [[0, 1], [0, 1, 2, 3]]
        codes = [[0, 0, 1, 1], [0, 2, 0, 2]]

        index = MultiIndex(levels, codes)

        df = DataFrame(np.random.randn(4, 2), index=index)

        result = df.unstack()
        assert len(result.columns) == 4

        recons = result.stack()
        tm.assert_frame_equal(recons, df) 

def test_unstack_multiple_no_empty_columns(self):
        index = MultiIndex.from_tuples([(0, 'foo', 0), (0, 'bar', 0), (
            1, 'baz', 1), (1, 'qux', 1)])

        s = Series(np.random.randn(4), index=index)

        unstacked = s.unstack([1, 2])
        expected = unstacked.dropna(axis=1, how='all')
        tm.assert_frame_equal(unstacked, expected) 

def test_delevel_infer_dtype(self):
        tuples = [tuple
                  for tuple in cart_product(
                      ['foo', 'bar'], [10, 20], [1.0, 1.1])]
        index = MultiIndex.from_tuples(tuples, names=['prm0', 'prm1', 'prm2'])
        df = DataFrame(np.random.randn(8, 3), columns=['A', 'B', 'C'],
                       index=index)
        deleveled = df.reset_index()
        assert is_integer_dtype(deleveled['prm1'])
        assert is_float_dtype(deleveled['prm2']) 

def test_dataframe_constructor(self):
        multi = DataFrame(np.random.randn(4, 4),
                          index=[np.array(['a', 'a', 'b', 'b']),
                                 np.array(['x', 'y', 'x', 'y'])])
        assert isinstance(multi.index, MultiIndex)
        assert not isinstance(multi.columns, MultiIndex)

        multi = DataFrame(np.random.randn(4, 4),
                          columns=[['a', 'a', 'b', 'b'],
                                   ['x', 'y', 'x', 'y']])
        assert isinstance(multi.columns, MultiIndex) 

def setup_method(self, method):

        index = MultiIndex(levels=[['foo', 'bar', 'baz', 'qux'], ['one', 'two',
                                                                  'three']],
                           codes=[[0, 0, 0, 1, 1, 2, 2, 3, 3, 3],
                                  [0, 1, 2, 0, 1, 1, 2, 0, 1, 2]],
                           names=['first', 'second'])
        self.frame = DataFrame(np.random.randn(10, 3), index=index,
                               columns=Index(['A', 'B', 'C'], name='exp'))

        self.single_level = MultiIndex(levels=[['foo', 'bar', 'baz', 'qux']],
                                       codes=[[0, 1, 2, 3]], names=['first'])

        # create test series object
        arrays = [['bar', 'bar', 'baz', 'baz', 'qux', 'qux', 'foo', 'foo'],
                  ['one', 'two', 'one', 'two', 'one', 'two', 'one', 'two']]
        tuples = lzip(*arrays)
        index = MultiIndex.from_tuples(tuples)
        s = Series(randn(8), index=index)
        s[3] = np.NaN
        self.series = s

        self.tdf = tm.makeTimeDataFrame(100)
        self.ymd = self.tdf.groupby([lambda x: x.year, lambda x: x.month,
                                     lambda x: x.day]).sum()

        # use Int64Index, to make sure things work
        self.ymd.index.set_levels([lev.astype('i8')
                                   for lev in self.ymd.index.levels],
                                  inplace=True)
        self.ymd.index.set_names(['year', 'month', 'day'], inplace=True)