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)

经过痛苦的实验，我找到了比公认的答案更快的方法，我让这个方法起作用了。它在我试用的数据集上运行速度快了大约100倍。

如果有人知道如何使其更优雅，请务必修改我的代码。我找不到一种方法，不设置其他你想保留的列作为下标，然后重设下标，重命名列，但我想还有其他方法可以。

b = DataFrame(a.var1.str.split(',').tolist(), index=a.var2).stack()
b = b.reset_index()[[0, 'var2']] # var1 variable is currently labeled 0
b.columns = ['var1', 'var2'] # renaming var1

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。

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

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=',')