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

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

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

这是一个相当直接的消息，它使用pandas str访问器的split方法，然后使用NumPy将每一行平铺成一个数组。

通过使用np.repeat以正确的次数重复未分割的列来检索相应的值。

var1 = df.var1.str.split(',', expand=True).values.ravel()
var2 = np.repeat(df.var2.values, len(var1) / len(df))

pd.DataFrame({'var1': var1,
              'var2': var2})

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

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)