对于这个问题，我提出了以下解决方案:

def iter_var1(d):
    for _, row in d.iterrows():
        for v in row["var1"].split(","):
            yield (v, row["var2"])

new_a = DataFrame.from_records([i for i in iter_var1(a)],
        columns=["var1", "var2"])

我很欣赏“常舍”的回答，真的，但是iterrows()函数在大型数据集上花费很长时间。我面对了这个问题，然后我走到了这一步。

# First, reset_index to make the index a column
a = a.reset_index().rename(columns={'index':'duplicated_idx'})

# Get a longer series with exploded cells to rows
series = pd.DataFrame(a['var1'].str.split('/')
                      .tolist(), index=a.duplicated_idx).stack()

# New df from series and merge with the old one
b = series.reset_index([0, 'duplicated_idx'])
b = b.rename(columns={0:'var1'})

# Optional & Advanced: In case, there are other columns apart from var1 & var2
b.merge(
    a[a.columns.difference(['var1'])],
    on='duplicated_idx')

# Optional: Delete the "duplicated_index"'s column, and reorder columns
b = b[a.columns.difference(['duplicated_idx'])]

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

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

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

我有一个类似的问题，我的解决方案是将数据帧转换为字典列表，然后进行转换。函数如下:

import re
import pandas as pd

def separate_row(df, column_name):
    ls = []
    for row_dict in df.to_dict('records'):
        for word in re.split(',', row_dict[column_name]):
            row = row_dict.copy()
            row[column_name]=word
            ls.append(row)
    return pd.DataFrame(ls)

例子:

>>> from pandas import DataFrame
>>> import numpy as np
>>> a = DataFrame([{'var1': 'a,b,c', 'var2': 1},
               {'var1': 'd,e,f', 'var2': 2}])
>>> a
    var1  var2
0  a,b,c     1
1  d,e,f     2
>>> separate_row(a, "var1")
  var1  var2
0    a     1
1    b     1
2    c     1
3    d     2
4    e     2
5    f     2

您还可以稍微更改该函数以支持分离列表类型行。