Python compat.lzip方法代码示例

# 需要导入模块: from pandas import compat [as 别名]
# 或者: from pandas.compat import lzip [as 别名]
def _factorize_from_iterables(iterables):
    """
    A higher-level wrapper over `_factorize_from_iterable`.

    *This is an internal function*

    Parameters
    ----------
    iterables : list-like of list-likes

    Returns
    -------
    codes_list : list of ndarrays
    categories_list : list of Indexes

    Notes
    -----
    See `_factorize_from_iterable` for more info.
    """
    if len(iterables) == 0:
        # For consistency, it should return a list of 2 lists.
        return [[], []]
    return map(list, lzip(*[_factorize_from_iterable(it) for it in iterables])) 

# 需要导入模块: from pandas import compat [as 别名]
# 或者: from pandas.compat import lzip [as 别名]
def test_merge_on_multikey(self):
        joined = self.data.join(self.to_join, on=['key1', 'key2'])

        join_key = Index(lzip(self.data['key1'], self.data['key2']))
        indexer = self.to_join.index.get_indexer(join_key)
        ex_values = self.to_join.values.take(indexer, axis=0)
        ex_values[indexer == -1] = np.nan
        expected = self.data.join(DataFrame(ex_values,
                                            columns=self.to_join.columns))

        # TODO: columns aren't in the same order yet
        assert_frame_equal(joined, expected.loc[:, joined.columns])

        left = self.data.join(self.to_join, on=['key1', 'key2'], sort=True)
        right = expected.loc[:, joined.columns].sort_values(['key1', 'key2'],
                                                            kind='mergesort')
        assert_frame_equal(left, right) 

# 需要导入模块: from pandas import compat [as 别名]
# 或者: from pandas.compat import lzip [as 别名]
def union(self, other):
        """
        Form the union of two MultiIndex objects, sorting if possible

        Parameters
        ----------
        other : MultiIndex or array / Index of tuples

        Returns
        -------
        Index

        >>> index.union(index2)
        """
        self._assert_can_do_setop(other)
        other, result_names = self._convert_can_do_setop(other)

        if len(other) == 0 or self.equals(other):
            return self

        uniq_tuples = lib.fast_unique_multiple([self._ndarray_values,
                                                other._ndarray_values])
        return MultiIndex.from_arrays(lzip(*uniq_tuples), sortorder=0,
                                      names=result_names) 

# 需要导入模块: from pandas import compat [as 别名]
# 或者: from pandas.compat import lzip [as 别名]
def union(self, other):
        """
        Form the union of two MultiIndex objects, sorting if possible

        Parameters
        ----------
        other : MultiIndex or array / Index of tuples

        Returns
        -------
        Index
        """
        self._assert_can_do_setop(other)

        if len(other) == 0 or self.equals(other):
            return self

        result_names = self.names if self.names == other.names else None

        uniq_tuples = lib.fast_unique_multiple([self.values, other.values])
        return MultiIndex.from_arrays(lzip(*uniq_tuples), sortorder=0,
                                      names=result_names) 

# 需要导入模块: from pandas import compat [as 别名]
# 或者: from pandas.compat import lzip [as 别名]
def get_schema(frame, name, flavor, keys=None):
    "Return a CREATE TABLE statement to suit the contents of a DataFrame."
    lookup_type = lambda dtype: get_sqltype(dtype.type, flavor)
    # Replace spaces in DataFrame column names with _.
    safe_columns = [s.replace(' ', '_').strip() for s in frame.dtypes.index]
    column_types = lzip(safe_columns, map(lookup_type, frame.dtypes))
    if flavor == 'sqlite':
        columns = ',\n  '.join('[%s] %s' % x for x in column_types)
    else:
        columns = ',\n  '.join('`%s` %s' % x for x in column_types)

    keystr = ''
    if keys is not None:
        if isinstance(keys, compat.string_types):
            keys = (keys,)
        keystr = ', PRIMARY KEY (%s)' % ','.join(keys)
    template = """CREATE TABLE %(name)s (
                  %(columns)s
                  %(keystr)s
                  );"""
    create_statement = template % {'name': name, 'columns': columns,
                                   'keystr': keystr}
    return create_statement 

# 需要导入模块: from pandas import compat [as 别名]
# 或者: from pandas.compat import lzip [as 别名]
def union(self, other):
        """
        Form the union of two MultiIndex objects, sorting if possible

        Parameters
        ----------
        other : MultiIndex or array / Index of tuples

        Returns
        -------
        Index

        >>> index.union(index2)
        """
        self._assert_can_do_setop(other)
        other, result_names = self._convert_can_do_setop(other)

        if len(other) == 0 or self.equals(other):
            return self

        uniq_tuples = lib.fast_unique_multiple([self._values, other._values])
        return MultiIndex.from_arrays(lzip(*uniq_tuples), sortorder=0,
                                      names=result_names) 

# 需要导入模块: from pandas import compat [as 别名]
# 或者: from pandas.compat import lzip [as 别名]
def get_kwargs_from_breaks(self, breaks, closed='right'):
        """
        converts intervals in breaks format to a dictionary of kwargs to
        specific to the format expected by IntervalIndex.from_tuples
        """
        if len(breaks) == 0:
            return {'data': breaks}

        tuples = lzip(breaks[:-1], breaks[1:])
        if isinstance(breaks, (list, tuple)):
            return {'data': tuples}
        elif is_categorical_dtype(breaks):
            return {'data': breaks._constructor(tuples)}
        return {'data': com.asarray_tuplesafe(tuples)} 

# 需要导入模块: from pandas import compat [as 别名]
# 或者: from pandas.compat import lzip [as 别名]
def test_is_():
    mi = MultiIndex.from_tuples(lzip(range(10), range(10)))
    assert mi.is_(mi)
    assert mi.is_(mi.view())
    assert mi.is_(mi.view().view().view().view())
    mi2 = mi.view()
    # names are metadata, they don't change id
    mi2.names = ["A", "B"]
    assert mi2.is_(mi)
    assert mi.is_(mi2)

    assert mi.is_(mi.set_names(["C", "D"]))
    mi2 = mi.view()
    mi2.set_names(["E", "F"], inplace=True)
    assert mi.is_(mi2)
    # levels are inherent properties, they change identity
    mi3 = mi2.set_levels([lrange(10), lrange(10)])
    assert not mi3.is_(mi2)
    # shouldn't change
    assert mi2.is_(mi)
    mi4 = mi3.view()

    # GH 17464 - Remove duplicate MultiIndex levels
    mi4.set_levels([lrange(10), lrange(10)], inplace=True)
    assert not mi4.is_(mi3)
    mi5 = mi.view()
    mi5.set_levels(mi5.levels, inplace=True)
    assert not mi5.is_(mi) 

# 需要导入模块: from pandas import compat [as 别名]
# 或者: from pandas.compat import lzip [as 别名]
def test_boxplot_legacy2(self):
        tuples = lzip(string.ascii_letters[:10], range(10))
        df = DataFrame(np.random.rand(10, 3),
                       index=MultiIndex.from_tuples(tuples))
        grouped = df.groupby(level=1)
        with tm.assert_produces_warning(UserWarning):
            axes = _check_plot_works(grouped.boxplot, return_type='axes')
        self._check_axes_shape(list(axes.values), axes_num=10, layout=(4, 3))

        axes = _check_plot_works(grouped.boxplot, subplots=False,
                                 return_type='axes')
        self._check_axes_shape(axes, axes_num=1, layout=(1, 1)) 

# 需要导入模块: from pandas import compat [as 别名]
# 或者: from pandas.compat import lzip [as 别名]
def test_boxplot_legacy3(self):
        tuples = lzip(string.ascii_letters[:10], range(10))
        df = DataFrame(np.random.rand(10, 3),
                       index=MultiIndex.from_tuples(tuples))
        grouped = df.unstack(level=1).groupby(level=0, axis=1)
        with tm.assert_produces_warning(UserWarning):
            axes = _check_plot_works(grouped.boxplot, return_type='axes')
        self._check_axes_shape(list(axes.values), axes_num=3, layout=(2, 2))
        axes = _check_plot_works(grouped.boxplot, subplots=False,
                                 return_type='axes')
        self._check_axes_shape(axes, axes_num=1, layout=(1, 1)) 

# 需要导入模块: from pandas import compat [as 别名]
# 或者: from pandas.compat import lzip [as 别名]
def test_series_getitem_not_sorted(self):
        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)

        arrays = [np.array(x) for x in zip(*index.values)]

        result = s['qux']
        result2 = s.loc['qux']
        expected = s[arrays[0] == 'qux']
        expected.index = expected.index.droplevel(0)
        tm.assert_series_equal(result, expected)
        tm.assert_series_equal(result2, expected) 

# 需要导入模块: from pandas import compat [as 别名]
# 或者: from pandas.compat import lzip [as 别名]
def test_drop(self):
        simple = DataFrame({"A": [1, 2, 3, 4], "B": [0, 1, 2, 3]})
        assert_frame_equal(simple.drop("A", axis=1), simple[['B']])
        assert_frame_equal(simple.drop(["A", "B"], axis='columns'),
                           simple[[]])
        assert_frame_equal(simple.drop([0, 1, 3], axis=0), simple.loc[[2], :])
        assert_frame_equal(simple.drop(
            [0, 3], axis='index'), simple.loc[[1, 2], :])

        pytest.raises(KeyError, simple.drop, 5)
        pytest.raises(KeyError, simple.drop, 'C', 1)
        pytest.raises(KeyError, simple.drop, [1, 5])
        pytest.raises(KeyError, simple.drop, ['A', 'C'], 1)

        # errors = 'ignore'
        assert_frame_equal(simple.drop(5, errors='ignore'), simple)
        assert_frame_equal(simple.drop([0, 5], errors='ignore'),
                           simple.loc[[1, 2, 3], :])
        assert_frame_equal(simple.drop('C', axis=1, errors='ignore'), simple)
        assert_frame_equal(simple.drop(['A', 'C'], axis=1, errors='ignore'),
                           simple[['B']])

        # non-unique - wheee!
        nu_df = DataFrame(lzip(range(3), range(-3, 1), list('abc')),
                          columns=['a', 'a', 'b'])
        assert_frame_equal(nu_df.drop('a', axis=1), nu_df[['b']])
        assert_frame_equal(nu_df.drop('b', axis='columns'), nu_df['a'])
        assert_frame_equal(nu_df.drop([]), nu_df)  # GH 16398

        nu_df = nu_df.set_index(pd.Index(['X', 'Y', 'X']))
        nu_df.columns = list('abc')
        assert_frame_equal(nu_df.drop('X', axis='rows'), nu_df.loc[["Y"], :])
        assert_frame_equal(nu_df.drop(['X', 'Y'], axis=0), nu_df.loc[[], :])

        # inplace cache issue
        # GH 5628
        df = pd.DataFrame(np.random.randn(10, 3), columns=list('abc'))
        expected = df[~(df.b > 0)]
        df.drop(labels=df[df.b > 0].index, inplace=True)
        assert_frame_equal(df, expected) 

# 需要导入模块: from pandas import compat [as 别名]
# 或者: from pandas.compat import lzip [as 别名]
def test_setitem_list_of_tuples(self):
        tuples = lzip(self.frame['A'], self.frame['B'])
        self.frame['tuples'] = tuples

        result = self.frame['tuples']
        expected = Series(tuples, index=self.frame.index, name='tuples')
        assert_series_equal(result, expected) 

# 需要导入模块: from pandas import compat [as 别名]
# 或者: from pandas.compat import lzip [as 别名]
def _sparsify(label_list, start=0, sentinel=''):
    pivoted = lzip(*label_list)
    k = len(label_list)

    result = pivoted[:start + 1]
    prev = pivoted[start]

    for cur in pivoted[start + 1:]:
        sparse_cur = []

        for i, (p, t) in enumerate(zip(prev, cur)):
            if i == k - 1:
                sparse_cur.append(t)
                result.append(sparse_cur)
                break

            if p == t:
                sparse_cur.append(sentinel)
            else:
                sparse_cur.extend(cur[i:])
                result.append(sparse_cur)
                break

        prev = cur

    return lzip(*result) 

# 需要导入模块: from pandas import compat [as 别名]
# 或者: from pandas.compat import lzip [as 别名]
def groups(self):
        """ dict {group name -> group labels} """
        if len(self.groupings) == 1:
            return self.groupings[0].groups
        else:
            to_groupby = lzip(*(ping.grouper for ping in self.groupings))
            to_groupby = Index(to_groupby)
            return self.axis.groupby(to_groupby)