另一种解决方案是使用python复制包

import copy
new_observations = list()
def pandas_explode(df, column_to_explode):
    new_observations = list()
    for row in df.to_dict(orient='records'):
        explode_values = row[column_to_explode]
        del row[column_to_explode]
        if type(explode_values) is list or type(explode_values) is tuple:
            for explode_value in explode_values:
                new_observation = copy.deepcopy(row)
                new_observation[column_to_explode] = explode_value
                new_observations.append(new_observation) 
        else:
            new_observation = copy.deepcopy(row)
            new_observation[column_to_explode] = explode_values
            new_observations.append(new_observation) 
    return_df = pd.DataFrame(new_observations)
    return return_df

df = pandas_explode(df, column_name)

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

只是从上面使用了jiln的优秀答案，但需要展开以拆分多个列。我想分享一下。

def splitDataFrameList(df,target_column,separator):
''' df = dataframe to split,
target_column = the column containing the values to split
separator = the symbol used to perform the split

returns: a dataframe with each entry for the target column separated, with each element moved into a new row. 
The values in the other columns are duplicated across the newly divided rows.
'''
def splitListToRows(row, row_accumulator, target_columns, separator):
    split_rows = []
    for target_column in target_columns:
        split_rows.append(row[target_column].split(separator))
    # Seperate for multiple columns
    for i in range(len(split_rows[0])):
        new_row = row.to_dict()
        for j in range(len(split_rows)):
            new_row[target_columns[j]] = split_rows[j][i]
        row_accumulator.append(new_row)
new_rows = []
df.apply(splitListToRows,axis=1,args = (new_rows,target_column,separator))
new_df = pd.DataFrame(new_rows)
return new_df

我一直在与内存不足的经验作斗争，使用各种方法来爆炸我的列表，所以我准备了一些基准来帮助我决定哪些答案应该点赞。我测试了列表长度与列表数量的不同比例的五种场景。分享以下结果:

时间:(越少越好，点击查看大版)

内存使用峰值:(越少越好)

结论:

@MaxU的回答(更新2)，code dename concatenate在几乎所有情况下都提供了最好的速度，同时保持peek内存使用低， 如果你需要用相对较小的列表处理大量的行，并且可以负担得起增加的峰值内存，请参阅@DMulligan的答案(代码堆栈)， 接受的@Chang的答案适用于有几行但非常大的列表的数据帧。

所有细节(函数和基准测试代码)都在GitHub要点中。请注意，基准测试问题被简化了，不包括将字符串拆分到列表中——大多数解决方案都以类似的方式执行。

类似的问题:pandas:如何将一列中的文本拆分为多行?

你可以这样做:

>> a=pd.DataFrame({"var1":"a,b,c d,e,f".split(),"var2":[1,2]})
>> s = a.var1.str.split(",").apply(pd.Series, 1).stack()
>> s.index = s.index.droplevel(-1)
>> del a['var1']
>> a.join(s)
   var2 var1
0     1    a
0     1    b
0     1    c
1     2    d
1     2    e
1     2    f

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