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

我提出了一个具有任意列数的数据框架的解决方案(同时一次仍然只分离一列的条目)。

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_column,separator):
        split_row = row[target_column].split(separator)
        for s in split_row:
            new_row = row.to_dict()
            new_row[target_column] = s
            row_accumulator.append(new_row)
    new_rows = []
    df.apply(splitListToRows,axis=1,args = (new_rows,target_column,separator))
    new_df = pandas.DataFrame(new_rows)
    return new_df

有可能在不改变数据框架结构的情况下拆分和爆炸数据框架

拆分和展开特定列的数据

输入:

    var1    var2
0   a,b,c   1
1   d,e,f   2



#Get the indexes which are repetative with the split 
df['var1'] = df['var1'].str.split(',')
df = df.explode('var1')

Out:

    var1    var2
0   a   1
0   b   1
0   c   1
1   d   2
1   e   2
1   f   2

Edit-1

对多列的行进行拆分和展开

Filename    RGB                                             RGB_type
0   A   [[0, 1650, 6, 39], [0, 1691, 1, 59], [50, 1402...   [r, g, b]
1   B   [[0, 1423, 16, 38], [0, 1445, 16, 46], [0, 141...   [r, g, b]

基于参考列重新索引，并将列值信息与堆栈对齐

df = df.reindex(df.index.repeat(df['RGB_type'].apply(len)))
df = df.groupby('Filename').apply(lambda x:x.apply(lambda y: pd.Series(y.iloc[0])))
df.reset_index(drop=True).ffill()

Out:

                Filename    RGB_type    Top 1 colour    Top 1 frequency Top 2 colour    Top 2 frequency
    Filename                            
 A  0       A   r   0   1650    6   39
    1       A   g   0   1691    1   59
    2       A   b   50  1402    49  187
 B  0       B   r   0   1423    16  38
    1       B   g   0   1445    16  46
    2       B   b   0   1419    16  39

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

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

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