Python pandas.util.testing.makePanel() Examples

def test_sparse_friendly(df):
    sdf = df[['C', 'D']].to_sparse()
    panel = tm.makePanel()
    tm.add_nans(panel)

    def _check_work(gp):
        gp.mean()
        gp.agg(np.mean)
        dict(iter(gp))

    # it works!
    _check_work(sdf.groupby(lambda x: x // 2))
    _check_work(sdf['C'].groupby(lambda x: x // 2))
    _check_work(sdf.groupby(df['A']))

    # do this someday
    # _check_work(panel.groupby(lambda x: x.month, axis=1)) 

def test_to_xarray(self):
        from xarray import DataArray

        with catch_warnings(record=True):
            simplefilter("ignore", FutureWarning)
            p = tm.makePanel()

            result = p.to_xarray()
            assert isinstance(result, DataArray)
            assert len(result.coords) == 3
            assert_almost_equal(list(result.coords.keys()),
                                ['items', 'major_axis', 'minor_axis'])
            assert len(result.dims) == 3

            # idempotency
            assert_panel_equal(result.to_pandas(), p)


# run all the tests, but wrap each in a warning catcher 

def test_transpose(self):
        msg = (r"transpose\(\) got multiple values for "
               r"keyword argument 'axes'")
        for s in [tm.makeFloatSeries(), tm.makeStringSeries(),
                  tm.makeObjectSeries()]:
            # calls implementation in pandas/core/base.py
            tm.assert_series_equal(s.transpose(), s)
        for df in [tm.makeTimeDataFrame()]:
            tm.assert_frame_equal(df.transpose().transpose(), df)

        with catch_warnings(record=True):
            simplefilter("ignore", FutureWarning)
            for p in [tm.makePanel()]:
                tm.assert_panel_equal(p.transpose(2, 0, 1)
                                      .transpose(1, 2, 0), p)
                with pytest.raises(TypeError, match=msg):
                    p.transpose(2, 0, 1, axes=(2, 0, 1)) 

def test_reshaping_panel_categorical(self):

        p = tm.makePanel()
        p['str'] = 'foo'
        df = p.to_frame()

        df['category'] = df['str'].astype('category')
        result = df['category'].unstack()

        c = Categorical(['foo'] * len(p.major_axis))
        expected = DataFrame({'A': c.copy(),
                              'B': c.copy(),
                              'C': c.copy(),
                              'D': c.copy()},
                             columns=Index(list('ABCD'), name='minor'),
                             index=p.major_axis.set_names('major'))
        tm.assert_frame_equal(result, expected) 

def test_numpy_transpose(self):
        msg = "the 'axes' parameter is not supported"

        s = tm.makeFloatSeries()
        tm.assert_series_equal(np.transpose(s), s)

        with pytest.raises(ValueError, match=msg):
            np.transpose(s, axes=1)

        df = tm.makeTimeDataFrame()
        tm.assert_frame_equal(np.transpose(np.transpose(df)), df)

        with pytest.raises(ValueError, match=msg):
            np.transpose(df, axes=1)

        with catch_warnings(record=True):
            simplefilter("ignore", FutureWarning)
            p = tm.makePanel()
            tm.assert_panel_equal(np.transpose(
                np.transpose(p, axes=(2, 0, 1)),
                axes=(1, 2, 0)), p) 

def test_take_invalid_kwargs(self):
        indices = [-3, 2, 0, 1]
        s = tm.makeFloatSeries()
        df = tm.makeTimeDataFrame()

        with catch_warnings(record=True):
            simplefilter("ignore", FutureWarning)
            p = tm.makePanel()

        for obj in (s, df, p):
            msg = r"take\(\) got an unexpected keyword argument 'foo'"
            with pytest.raises(TypeError, match=msg):
                obj.take(indices, foo=2)

            msg = "the 'out' parameter is not supported"
            with pytest.raises(ValueError, match=msg):
                obj.take(indices, out=indices)

            msg = "the 'mode' parameter is not supported"
            with pytest.raises(ValueError, match=msg):
                obj.take(indices, mode='clip') 

def test_sparse_friendly(df):
    sdf = df[['C', 'D']].to_sparse()
    panel = tm.makePanel()
    tm.add_nans(panel)

    def _check_work(gp):
        gp.mean()
        gp.agg(np.mean)
        dict(iter(gp))

    # it works!
    _check_work(sdf.groupby(lambda x: x // 2))
    _check_work(sdf['C'].groupby(lambda x: x // 2))
    _check_work(sdf.groupby(df['A']))

    # do this someday
    # _check_work(panel.groupby(lambda x: x.month, axis=1)) 

def test_take_invalid_kwargs(self):
        indices = [-3, 2, 0, 1]
        s = tm.makeFloatSeries()
        df = tm.makeTimeDataFrame()

        with catch_warnings(record=True):
            simplefilter("ignore", FutureWarning)
            p = tm.makePanel()

        for obj in (s, df, p):
            msg = r"take\(\) got an unexpected keyword argument 'foo'"
            with pytest.raises(TypeError, match=msg):
                obj.take(indices, foo=2)

            msg = "the 'out' parameter is not supported"
            with pytest.raises(ValueError, match=msg):
                obj.take(indices, out=indices)

            msg = "the 'mode' parameter is not supported"
            with pytest.raises(ValueError, match=msg):
                obj.take(indices, mode='clip') 

def test_numpy_transpose(self):
        msg = "the 'axes' parameter is not supported"

        s = tm.makeFloatSeries()
        tm.assert_series_equal(np.transpose(s), s)

        with pytest.raises(ValueError, match=msg):
            np.transpose(s, axes=1)

        df = tm.makeTimeDataFrame()
        tm.assert_frame_equal(np.transpose(np.transpose(df)), df)

        with pytest.raises(ValueError, match=msg):
            np.transpose(df, axes=1)

        with catch_warnings(record=True):
            simplefilter("ignore", FutureWarning)
            p = tm.makePanel()
            tm.assert_panel_equal(np.transpose(
                np.transpose(p, axes=(2, 0, 1)),
                axes=(1, 2, 0)), p) 

def test_transpose(self):
        msg = (r"transpose\(\) got multiple values for "
               r"keyword argument 'axes'")
        for s in [tm.makeFloatSeries(), tm.makeStringSeries(),
                  tm.makeObjectSeries()]:
            # calls implementation in pandas/core/base.py
            tm.assert_series_equal(s.transpose(), s)
        for df in [tm.makeTimeDataFrame()]:
            tm.assert_frame_equal(df.transpose().transpose(), df)

        with catch_warnings(record=True):
            simplefilter("ignore", FutureWarning)
            for p in [tm.makePanel()]:
                tm.assert_panel_equal(p.transpose(2, 0, 1)
                                      .transpose(1, 2, 0), p)
                with pytest.raises(TypeError, match=msg):
                    p.transpose(2, 0, 1, axes=(2, 0, 1)) 

def test_to_xarray(self):
        from xarray import DataArray

        with catch_warnings(record=True):
            simplefilter("ignore", FutureWarning)
            p = tm.makePanel()

            result = p.to_xarray()
            assert isinstance(result, DataArray)
            assert len(result.coords) == 3
            assert_almost_equal(list(result.coords.keys()),
                                ['items', 'major_axis', 'minor_axis'])
            assert len(result.dims) == 3

            # idempotency
            assert_panel_equal(result.to_pandas(), p)


# run all the tests, but wrap each in a warning catcher 

def test_sparse_friendly(df):
    sdf = df[['C', 'D']].to_sparse()
    with catch_warnings(record=True):
        panel = tm.makePanel()
        tm.add_nans(panel)

    def _check_work(gp):
        gp.mean()
        gp.agg(np.mean)
        dict(iter(gp))

    # it works!
    _check_work(sdf.groupby(lambda x: x // 2))
    _check_work(sdf['C'].groupby(lambda x: x // 2))
    _check_work(sdf.groupby(df['A']))

    # do this someday
    # _check_work(panel.groupby(lambda x: x.month, axis=1)) 

def test_reshaping_panel_categorical(self):

        p = tm.makePanel()
        p['str'] = 'foo'
        df = p.to_frame()

        df['category'] = df['str'].astype('category')
        result = df['category'].unstack()

        c = Categorical(['foo'] * len(p.major_axis))
        expected = DataFrame({'A': c.copy(),
                              'B': c.copy(),
                              'C': c.copy(),
                              'D': c.copy()},
                             columns=Index(list('ABCD'), name='minor'),
                             index=p.major_axis.set_names('major'))
        tm.assert_frame_equal(result, expected) 

def test_reshaping_panel_categorical(self):

        with catch_warnings(record=True):
            p = tm.makePanel()
            p['str'] = 'foo'
            df = p.to_frame()

        df['category'] = df['str'].astype('category')
        result = df['category'].unstack()

        c = Categorical(['foo'] * len(p.major_axis))
        expected = DataFrame({'A': c.copy(),
                              'B': c.copy(),
                              'C': c.copy(),
                              'D': c.copy()},
                             columns=Index(list('ABCD'), name='minor'),
                             index=p.major_axis.set_names('major'))
        tm.assert_frame_equal(result, expected) 

def test_legacy_table_write(self):
        raise nose.SkipTest("skipping for now")

        store = HDFStore(tm.get_data_path('legacy_hdf/legacy_table_%s.h5' % pandas.__version__), 'a')

        df = tm.makeDataFrame()
        wp = tm.makePanel()

        index = MultiIndex(levels=[['foo', 'bar', 'baz', 'qux'],
                                   ['one', 'two', 'three']],
                           labels=[[0, 0, 0, 1, 1, 2, 2, 3, 3, 3],
                                   [0, 1, 2, 0, 1, 1, 2, 0, 1, 2]],
                           names=['foo', 'bar'])
        df = DataFrame(np.random.randn(10, 3), index=index,
                       columns=['A', 'B', 'C'])
        store.append('mi', df)

        df = DataFrame(dict(A = 'foo', B = 'bar'),index=lrange(10))
        store.append('df', df, data_columns = ['B'], min_itemsize={'A' : 200 })
        store.append('wp', wp)

        store.close() 

def test_to_xarray(self):
        from xarray import DataArray

        with catch_warnings(record=True):
            p = tm.makePanel()

            result = p.to_xarray()
            assert isinstance(result, DataArray)
            assert len(result.coords) == 3
            assert_almost_equal(list(result.coords.keys()),
                                ['items', 'major_axis', 'minor_axis'])
            assert len(result.dims) == 3

            # idempotency
            assert_panel_equal(result.to_pandas(), p)


# run all the tests, but wrap each in a warning catcher 

def test_take_invalid_kwargs(self):
        indices = [-3, 2, 0, 1]
        s = tm.makeFloatSeries()
        df = tm.makeTimeDataFrame()

        with catch_warnings(record=True):
            p = tm.makePanel()

        for obj in (s, df, p):
            msg = r"take\(\) got an unexpected keyword argument 'foo'"
            tm.assert_raises_regex(TypeError, msg, obj.take,
                                   indices, foo=2)

            msg = "the 'out' parameter is not supported"
            tm.assert_raises_regex(ValueError, msg, obj.take,
                                   indices, out=indices)

            msg = "the 'mode' parameter is not supported"
            tm.assert_raises_regex(ValueError, msg, obj.take,
                                   indices, mode='clip') 

def test_transpose(self):
        msg = (r"transpose\(\) got multiple values for "
               r"keyword argument 'axes'")
        for s in [tm.makeFloatSeries(), tm.makeStringSeries(),
                  tm.makeObjectSeries()]:
            # calls implementation in pandas/core/base.py
            tm.assert_series_equal(s.transpose(), s)
        for df in [tm.makeTimeDataFrame()]:
            tm.assert_frame_equal(df.transpose().transpose(), df)

        with catch_warnings(record=True):
            for p in [tm.makePanel()]:
                tm.assert_panel_equal(p.transpose(2, 0, 1)
                                      .transpose(1, 2, 0), p)
                tm.assert_raises_regex(TypeError, msg, p.transpose,
                                       2, 0, 1, axes=(2, 0, 1)) 

def test_numpy_transpose(self):
        msg = "the 'axes' parameter is not supported"

        s = tm.makeFloatSeries()
        tm.assert_series_equal(
            np.transpose(s), s)
        tm.assert_raises_regex(ValueError, msg,
                               np.transpose, s, axes=1)

        df = tm.makeTimeDataFrame()
        tm.assert_frame_equal(np.transpose(
            np.transpose(df)), df)
        tm.assert_raises_regex(ValueError, msg,
                               np.transpose, df, axes=1)

        with catch_warnings(record=True):
            p = tm.makePanel()
            tm.assert_panel_equal(np.transpose(
                np.transpose(p, axes=(2, 0, 1)),
                axes=(1, 2, 0)), p) 

def test_conv_read_write(self):

        try:

            def roundtrip(key, obj,**kwargs):
                obj.to_hdf(self.path, key,**kwargs)
                return read_hdf(self.path, key)

            o = tm.makeTimeSeries()
            assert_series_equal(o, roundtrip('series',o))

            o = tm.makeStringSeries()
            assert_series_equal(o, roundtrip('string_series',o))

            o = tm.makeDataFrame()
            assert_frame_equal(o, roundtrip('frame',o))

            o = tm.makePanel()
            assert_panel_equal(o, roundtrip('panel',o))

            # table
            df = DataFrame(dict(A=lrange(5), B=lrange(5)))
            df.to_hdf(self.path,'table',append=True)
            result = read_hdf(self.path, 'table', where = ['index>2'])
            assert_frame_equal(df[df.index>2],result)

        finally:
            safe_remove(self.path) 

def test_wide_table(self):

        wp = tm.makePanel()
        self._check_roundtrip_table(wp, assert_panel_equal) 

def test_panel_concat_other_axes(self):
        panel = tm.makePanel()

        p1 = panel.iloc[:, :5, :]
        p2 = panel.iloc[:, 5:, :]

        result = concat([p1, p2], axis=1)
        tm.assert_panel_equal(result, panel)

        p1 = panel.iloc[:, :, :2]
        p2 = panel.iloc[:, :, 2:]

        result = concat([p1, p2], axis=2)
        tm.assert_panel_equal(result, panel)

        # if things are a bit misbehaved
        p1 = panel.iloc[:2, :, :2]
        p2 = panel.iloc[:, :, 2:]
        p1['ItemC'] = 'baz'

        result = concat([p1, p2], axis=2)

        expected = panel.copy()
        expected['ItemC'] = expected['ItemC'].astype('O')
        expected.loc['ItemC', :, :2] = 'baz'
        tm.assert_panel_equal(result, expected) 

def test_keys(self):

        with ensure_clean_store(self.path) as store:
            store['a'] = tm.makeTimeSeries()
            store['b'] = tm.makeStringSeries()
            store['c'] = tm.makeDataFrame()
            store['d'] = tm.makePanel()
            store['foo/bar'] = tm.makePanel()
            self.assertEquals(len(store), 5)
            self.assert_(set(
                    store.keys()) == set(['/a', '/b', '/c', '/d', '/foo/bar'])) 

def test_invalid_terms(self):

        with ensure_clean_store(self.path) as store:

            df = tm.makeTimeDataFrame()
            df['string'] = 'foo'
            df.ix[0:4,'string'] = 'bar'
            wp = tm.makePanel()
            p4d = tm.makePanel4D()
            store.put('df', df, format='table')
            store.put('wp', wp, format='table')
            store.put('p4d', p4d, format='table')

            # some invalid terms
            self.assertRaises(ValueError, store.select, 'wp', "minor=['A', 'B']")
            self.assertRaises(ValueError, store.select, 'wp', ["index=['20121114']"])
            self.assertRaises(ValueError, store.select, 'wp', ["index=['20121114', '20121114']"])
            self.assertRaises(TypeError, Term)

            # more invalid
            self.assertRaises(ValueError,  store.select, 'df','df.index[3]')
            self.assertRaises(SyntaxError, store.select, 'df','index>')
            self.assertRaises(ValueError,  store.select, 'wp', "major_axis<'20000108' & minor_axis['A', 'B']")

        # from the docs
        with ensure_clean_path(self.path) as path:
            dfq = DataFrame(np.random.randn(10,4),columns=list('ABCD'),index=date_range('20130101',periods=10))
            dfq.to_hdf(path,'dfq',format='table',data_columns=True)

            # check ok
            read_hdf(path,'dfq',where="index>Timestamp('20130104') & columns=['A', 'B']")
            read_hdf(path,'dfq',where="A>0 or C>0")

        # catch the invalid reference
        with ensure_clean_path(self.path) as path:
            dfq = DataFrame(np.random.randn(10,4),columns=list('ABCD'),index=date_range('20130101',periods=10))
            dfq.to_hdf(path,'dfq',format='table')

            self.assertRaises(ValueError, read_hdf, path,'dfq',where="A>0 or C>0") 

def test_wide_table_dups(self):
        wp = tm.makePanel()
        with ensure_clean_store(self.path) as store:
            store.put('panel', wp, format='table')
            store.put('panel', wp, format='table', append=True)

            with tm.assert_produces_warning(expected_warning=DuplicateWarning):
                recons = store['panel']

            assert_panel_equal(recons, wp) 

def test_panel_concat_other_axes(self):
        panel = tm.makePanel()

        p1 = panel.ix[:, :5, :]
        p2 = panel.ix[:, 5:, :]

        result = concat([p1, p2], axis=1)
        tm.assert_panel_equal(result, panel)

        p1 = panel.ix[:, :, :2]
        p2 = panel.ix[:, :, 2:]

        result = concat([p1, p2], axis=2)
        tm.assert_panel_equal(result, panel)

        # if things are a bit misbehaved
        p1 = panel.ix[:2, :, :2]
        p2 = panel.ix[:, :, 2:]
        p1['ItemC'] = 'baz'

        result = concat([p1, p2], axis=2)

        expected = panel.copy()
        expected['ItemC'] = expected['ItemC'].astype('O')
        expected.ix['ItemC', :, :2] = 'baz'
        tm.assert_panel_equal(result, expected) 

def test_panel_join_many(self):
        tm.K = 10
        panel = tm.makePanel()
        tm.K = 4

        panels = [panel.ix[:2], panel.ix[2:6], panel.ix[6:]]

        joined = panels[0].join(panels[1:])
        tm.assert_panel_equal(joined, panel)

        panels = [panel.ix[:2, :-5], panel.ix[2:6, 2:], panel.ix[6:, 5:-7]]

        data_dict = {}
        for p in panels:
            data_dict.update(compat.iteritems(p))

        joined = panels[0].join(panels[1:], how='inner')
        expected = Panel.from_dict(data_dict, intersect=True)
        tm.assert_panel_equal(joined, expected)

        joined = panels[0].join(panels[1:], how='outer')
        expected = Panel.from_dict(data_dict, intersect=False)
        tm.assert_panel_equal(joined, expected)

        # edge cases
        self.assertRaises(ValueError, panels[0].join, panels[1:],
                          how='outer', lsuffix='foo', rsuffix='bar')
        self.assertRaises(ValueError, panels[0].join, panels[1:],
                          how='right') 

def test_panel_join_overlap(self):
        panel = tm.makePanel()
        tm.add_nans(panel)

        p1 = panel.ix[['ItemA', 'ItemB', 'ItemC']]
        p2 = panel.ix[['ItemB', 'ItemC']]

        joined = p1.join(p2, lsuffix='_p1', rsuffix='_p2')
        p1_suf = p1.ix[['ItemB', 'ItemC']].add_suffix('_p1')
        p2_suf = p2.ix[['ItemB', 'ItemC']].add_suffix('_p2')
        no_overlap = panel.ix[['ItemA']]
        expected = p1_suf.join(p2_suf).join(no_overlap)
        tm.assert_panel_equal(joined, expected) 

def test_panel_join(self):
        panel = tm.makePanel()
        tm.add_nans(panel)

        p1 = panel.ix[:2, :10, :3]
        p2 = panel.ix[2:, 5:, 2:]

        # left join
        result = p1.join(p2)
        expected = p1.copy()
        expected['ItemC'] = p2['ItemC']
        tm.assert_panel_equal(result, expected)

        # right join
        result = p1.join(p2, how='right')
        expected = p2.copy()
        expected['ItemA'] = p1['ItemA']
        expected['ItemB'] = p1['ItemB']
        expected = expected.reindex(items=['ItemA', 'ItemB', 'ItemC'])
        tm.assert_panel_equal(result, expected)

        # inner join
        result = p1.join(p2, how='inner')
        expected = panel.ix[:, 5:10, 2:3]
        tm.assert_panel_equal(result, expected)

        # outer join
        result = p1.join(p2, how='outer')
        expected = p1.reindex(major=panel.major_axis,
                              minor=panel.minor_axis)
        expected = expected.join(p2.reindex(major=panel.major_axis,
                                            minor=panel.minor_axis))
        tm.assert_panel_equal(result, expected) 

def test_wide(self):

        wp = tm.makePanel()
        self._check_roundtrip(wp, assert_panel_equal)