一种使用.apply()改变列格式的简单方法，以便.explod()可以使用它:

import string
import pandas as pd
from io import StringIO

file = StringIO("""    var1  var2
0  a,b,c     1
1  d,e,f     2""")

df = pd.read_csv(file, sep=r'\s\s+')

df['var1'] = df['var1'].apply(lambda x : str(x).split(','))

df.explode('var1')

输出:

  var1  var2
0   a   1
0   b   1
0   c   1
1   d   2
1   e   2
1   f   2

这样怎么样:

In [55]: pd.concat([Series(row['var2'], row['var1'].split(','))              
                    for _, row in a.iterrows()]).reset_index()
Out[55]: 
  index  0
0     a  1
1     b  1
2     c  1
3     d  2
4     e  2
5     f  2

然后你只需要重命名列

使用split(___， expand=True)和reset_index()的level和name参数的一行代码:

>>> b = a.var1.str.split(',', expand=True).set_index(a.var2).stack().reset_index(level=0, name='var1')
>>> b
   var2 var1
0     1    a
1     1    b
2     1    c
0     2    d
1     2    e
2     2    f

如果你想让b看起来和问题中的一模一样，你还可以这样做:

>>> b = b.reset_index(drop=True)[['var1', 'var2']]
>>> b
  var1  var2
0    a     1
1    b     1
2    c     1
3    d     2
4    e     2
5    f     2

这是我为这个常见任务写的函数。它比Series/stack方法更有效。列的顺序和名称被保留。

def tidy_split(df, column, sep='|', keep=False):
    """
    Split the values of a column and expand so the new DataFrame has one split
    value per row. Filters rows where the column is missing.

    Params
    ------
    df : pandas.DataFrame
        dataframe with the column to split and expand
    column : str
        the column to split and expand
    sep : str
        the string used to split the column's values
    keep : bool
        whether to retain the presplit value as it's own row

    Returns
    -------
    pandas.DataFrame
        Returns a dataframe with the same columns as `df`.
    """
    indexes = list()
    new_values = list()
    df = df.dropna(subset=[column])
    for i, presplit in enumerate(df[column].astype(str)):
        values = presplit.split(sep)
        if keep and len(values) > 1:
            indexes.append(i)
            new_values.append(presplit)
        for value in values:
            indexes.append(i)
            new_values.append(value)
    new_df = df.iloc[indexes, :].copy()
    new_df[column] = new_values
    return new_df

有了这个函数，原来的问题就像这样简单:

tidy_split(a, 'var1', sep=',')

升级了MaxU的答案，支持MultiIndex

def explode(df, lst_cols, fill_value='', preserve_index=False):
    """
    usage:
        In [134]: df
        Out[134]:
           aaa  myid        num          text
        0   10     1  [1, 2, 3]  [aa, bb, cc]
        1   11     2         []            []
        2   12     3     [1, 2]      [cc, dd]
        3   13     4         []            []

        In [135]: explode(df, ['num','text'], fill_value='')
        Out[135]:
           aaa  myid num text
        0   10     1   1   aa
        1   10     1   2   bb
        2   10     1   3   cc
        3   11     2
        4   12     3   1   cc
        5   12     3   2   dd
        6   13     4
    """
    # make sure `lst_cols` is list-alike
    if (lst_cols is not None
        and len(lst_cols) > 0
        and not isinstance(lst_cols, (list, tuple, np.ndarray, pd.Series))):
        lst_cols = [lst_cols]
    # all columns except `lst_cols`
    idx_cols = df.columns.difference(lst_cols)
    # calculate lengths of lists
    lens = df[lst_cols[0]].str.len()
    # preserve original index values    
    idx = np.repeat(df.index.values, lens)
    res = (pd.DataFrame({
                col:np.repeat(df[col].values, lens)
                for col in idx_cols},
                index=idx)
             .assign(**{col:np.concatenate(df.loc[lens>0, col].values)
                            for col in lst_cols}))
    # append those rows that have empty lists
    if (lens == 0).any():
        # at least one list in cells is empty
        res = (res.append(df.loc[lens==0, idx_cols], sort=False)
                  .fillna(fill_value))
    # revert the original index order
    res = res.sort_index()
    # reset index if requested
    if not preserve_index:        
        res = res.reset_index(drop=True)

    # if original index is MultiIndex build the dataframe from the multiindex
    # create "exploded" DF
    if isinstance(df.index, pd.MultiIndex):
        res = res.reindex(
            index=pd.MultiIndex.from_tuples(
                res.index,
                names=['number', 'color']
            )
    )
    return res

在添加了这个页面上所有解决方案中的一些零碎内容后，我能够得到这样的东西(对于需要立即使用它的人来说)。 函数的参数是df(输入数据帧)和key(用分隔符分隔字符串的列)。如果分隔符与分号“;”不同，只需替换为分隔符。

def split_df_rows_for_semicolon_separated_key(key, df):
    df=df.set_index(df.columns.drop(key,1).tolist())[key].str.split(';', expand=True).stack().reset_index().rename(columns={0:key}).loc[:, df.columns]
    df=df[df[key] != '']
    return df