Try:

vals = np.array(a.var1.str.split(",").values.tolist())    
var = np.repeat(a.var2, vals.shape[1])

out = pd.DataFrame(np.column_stack((var, vals.ravel())), columns=a.columns)
display(out)

      var1 var2
    0   1   a
    1   1   b
    2   1   c
    3   2   d
    4   2   e
    5   2   f

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=',')

我的版本的解决方案添加到这个集合!: -)

# Original problem
from pandas import DataFrame
import numpy as np
a = DataFrame([{'var1': 'a,b,c', 'var2': 1},
               {'var1': 'd,e,f', 'var2': 2}])
b = DataFrame([{'var1': 'a', 'var2': 1},
               {'var1': 'b', 'var2': 1},
               {'var1': 'c', 'var2': 1},
               {'var1': 'd', 'var2': 2},
               {'var1': 'e', 'var2': 2},
               {'var1': 'f', 'var2': 2}])
### My solution
import pandas as pd
import functools
def expand_on_cols(df, fuse_cols, delim=","):
    def expand_on_col(df, fuse_col):
        col_order = df.columns
        df_expanded = pd.DataFrame(
            df.set_index([x for x in df.columns if x != fuse_col])[fuse_col]
            .apply(lambda x: x.split(delim))
            .explode()
        ).reset_index()
        return df_expanded[col_order]
    all_expanded = functools.reduce(expand_on_col, fuse_cols, df)
    return all_expanded

assert(b.equals(expand_on_cols(a, ["var1"], delim=",")))

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

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。

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