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

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

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=',')

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

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。

基于优秀的@DMulligan的解决方案，这里有一个通用的向量化(无循环)函数，它将数据帧的一列分割成多行，并将其合并回原始数据帧。它还从这个答案中使用了一个很棒的通用change_column_order函数。

def change_column_order(df, col_name, index):
    cols = df.columns.tolist()
    cols.remove(col_name)
    cols.insert(index, col_name)
    return df[cols]

def split_df(dataframe, col_name, sep):
    orig_col_index = dataframe.columns.tolist().index(col_name)
    orig_index_name = dataframe.index.name
    orig_columns = dataframe.columns
    dataframe = dataframe.reset_index()  # we need a natural 0-based index for proper merge
    index_col_name = (set(dataframe.columns) - set(orig_columns)).pop()
    df_split = pd.DataFrame(
        pd.DataFrame(dataframe[col_name].str.split(sep).tolist())
        .stack().reset_index(level=1, drop=1), columns=[col_name])
    df = dataframe.drop(col_name, axis=1)
    df = pd.merge(df, df_split, left_index=True, right_index=True, how='inner')
    df = df.set_index(index_col_name)
    df.index.name = orig_index_name
    # merge adds the column to the last place, so we need to move it back
    return change_column_order(df, col_name, orig_col_index)

例子:

df = pd.DataFrame([['a:b', 1, 4], ['c:d', 2, 5], ['e:f:g:h', 3, 6]], 
                  columns=['Name', 'A', 'B'], index=[10, 12, 13])
df
        Name    A   B
    10   a:b     1   4
    12   c:d     2   5
    13   e:f:g:h 3   6

split_df(df, 'Name', ':')
    Name    A   B
10   a       1   4
10   b       1   4
12   c       2   5
12   d       2   5
13   e       3   6
13   f       3   6    
13   g       3   6    
13   h       3   6    

注意，它保留了列的原始索引和顺序。它也适用于具有非连续索引的数据框架。