python碎片|groupby

    def groupby(self, by=None, axis=0, level=None, as_index=True, sort=True,
                group_keys=True, squeeze=False, observed=False, **kwargs):
        """
        Group DataFrame or Series using a mapper or by a Series of columns.

        A groupby operation involves some combination of splitting the
        object, applying a function, and combining the results. This can be
        used to group large amounts of data and compute operations on these
        groups.

        Parameters
        ----------
        by : mapping, function, label, or list of labels
            Used to determine the groups for the groupby.
            If ``by`` is a function, it's called on each value of the object's
            index. If a dict or Series is passed, the Series or dict VALUES
            will be used to determine the groups (the Series' values are first
            aligned; see ``.align()`` method). If an ndarray is passed, the
            values are used as-is determine the groups. A label or list of
            labels may be passed to group by the columns in ``self``. Notice
            that a tuple is interpreted a (single) key.
        axis : {0 or 'index', 1 or 'columns'}, default 0
            Split along rows (0) or columns (1).
        level : int, level name, or sequence of such, default None
            If the axis is a MultiIndex (hierarchical), group by a particular
            level or levels.
        as_index : bool, default True
            For aggregated output, return object with group labels as the
            index. Only relevant for DataFrame input. as_index=False is
            effectively "SQL-style" grouped output.
        sort : bool, default True
            Sort group keys. Get better performance by turning this off.
            Note this does not influence the order of observations within each
            group. Groupby preserves the order of rows within each group.
        group_keys : bool, default True
            When calling apply, add group keys to index to identify pieces.
        squeeze : bool, default False
            Reduce the dimensionality of the return type if possible,
            otherwise return a consistent type.
        observed : bool, default False
            This only applies if any of the groupers are Categoricals.
            If True: only show observed values for categorical groupers.
            If False: show all values for categorical groupers.

            .. versionadded:: 0.23.0

        **kwargs
            Optional, only accepts keyword argument 'mutated' and is passed
            to groupby.

        Returns
        -------
        DataFrameGroupBy or SeriesGroupBy
            Depends on the calling object and returns groupby object that
            contains information about the groups.

        See Also
        --------
        resample : Convenience method for frequency conversion and resampling
            of time series.

        Notes
        -----
        See the `user guide
        <http://pandas.pydata.org/pandas-docs/stable/groupby.html>`_ for more.

        Examples
        --------
        >>> df = pd.DataFrame({'Animal' : ['Falcon', 'Falcon',
        ...                                'Parrot', 'Parrot'],
        ...                    'Max Speed' : [380., 370., 24., 26.]})
        >>> df
           Animal  Max Speed
        0  Falcon      380.0
        1  Falcon      370.0
        2  Parrot       24.0
        3  Parrot       26.0
        >>> df.groupby(['Animal']).mean()
                Max Speed
        Animal
        Falcon      375.0
        Parrot       25.0

        **Hierarchical Indexes**

        We can groupby different levels of a hierarchical index
        using the `level` parameter:

        >>> arrays = [['Falcon', 'Falcon', 'Parrot', 'Parrot'],
        ...           ['Capitve', 'Wild', 'Capitve', 'Wild']]
        >>> index = pd.MultiIndex.from_arrays(arrays, names=('Animal', 'Type'))
        >>> df = pd.DataFrame({'Max Speed' : [390., 350., 30., 20.]},
        ...                    index=index)
        >>> df
                        Max Speed
        Animal Type
        Falcon Capitve      390.0
               Wild         350.0
        Parrot Capitve       30.0
               Wild          20.0
        >>> df.groupby(level=0).mean()
                Max Speed
        Animal
        Falcon      370.0
        Parrot       25.0
        >>> df.groupby(level=1).mean()
                 Max Speed
        Type
        Capitve      210.0
        Wild         185.0
        """
        from pandas.core.groupby.groupby import groupby

        if level is None and by is None:
            raise TypeError("You have to supply one of 'by' and 'level'")
        axis = self._get_axis_number(axis)
        return groupby(self, by=by, axis=axis, level=level, as_index=as_index,
                       sort=sort, group_keys=group_keys, squeeze=squeeze,
                       observed=observed, **kwargs)

import pandas as pd
res=pd.read_excel('1026处理结果.xlsx',encoding='gbk')
res2=res.groupby('行业分类')
deal = res2['成交量(万元)'].sum()
bbd = res2['BBD(万元)'].sum()
print(deal,bbd)

运行结果：
C:\Users\Administrator\AppData\Local\Programs\Python\Python37\python.exe D:/python/顶牛数据.py
行业分类
专用设备    1899603.33
交运物流     588175.97
交运设备     248539.12
仪器仪表     939586.05
保险      1034671.48
Name: 成交量(万元), dtype: float64 

Process finished with exit code 0

• as_index=false

res=pd.read_excel('1026处理结果.xlsx',encoding='gbk')
res2=res.groupby('行业分类',as_index=False)
deal = res2['成交量(万元)'].sum()
bbd = res2['BBD(万元)'].sum()
print(deal.head())

运行结果：
C:\Users\Administrator\AppData\Local\Programs\Python\Python37\python.exe D:/python/顶牛数据.py
   行业分类     成交量(万元)
0  专用设备  1899603.33
1  交运物流   588175.97
2  交运设备   248539.12
3  仪器仪表   939586.05
4    保险  1034671.48