我有以下数据帧，其中一列是一个对象(列表类型单元格):
df = pd.DataFrame({'A': [1, 2], 'B': [[1, 2], [1, 2]]})
输出:
A B
0 1 [1, 2]
1 2 [1, 2]
我的期望输出是:
A B
0 1 1
1 1 2
3 2 1
4 2 2
我该怎么做才能做到这一点呢?
相关的问题
Pandas列的列表，为每个列表元素创建一行
很好的问题和答案，但只处理一个列与列表(在我的回答自定义函数将工作于多个列，也接受的答案是使用最耗时的应用，这是不建议的，检查更多信息当我(不)想要使用熊猫应用()在我的代码?)
当前回答
# Here's the answer to the related question in:
# https://stackoverflow.com/q/56708671/11426125
# initial dataframe
df12=pd.DataFrame({'Date':['2007-12-03','2008-09-07'],'names':
[['Peter','Alex'],['Donald','Stan']]})
# convert dataframe to array for indexing list values (names)
a = np.array(df12.values)
# create a new, dataframe with dimensions for unnested
b = np.ndarray(shape = (4,2))
df2 = pd.DataFrame(b, columns = ["Date", "names"], dtype = str)
# implement loops to assign date/name values as required
i = range(len(a[0]))
j = range(len(a[0]))
for x in i:
for y in j:
df2.iat[2*x+y, 0] = a[x][0]
df2.iat[2*x+y, 1] = a[x][1][y]
# set Date column as Index
df2.Date=pd.to_datetime(df2.Date)
df2.index=df2.Date
df2.drop('Date',axis=1,inplace =True)
其他回答
我把这个问题推广了一下，以便适用于更多的专栏。
我的解决方案的总结:
In[74]: df
Out[74]:
A B C columnD
0 A1 B1 [C1.1, C1.2] D1
1 A2 B2 [C2.1, C2.2] [D2.1, D2.2, D2.3]
2 A3 B3 C3 [D3.1, D3.2]
In[75]: dfListExplode(df,['C','columnD'])
Out[75]:
A B C columnD
0 A1 B1 C1.1 D1
1 A1 B1 C1.2 D1
2 A2 B2 C2.1 D2.1
3 A2 B2 C2.1 D2.2
4 A2 B2 C2.1 D2.3
5 A2 B2 C2.2 D2.1
6 A2 B2 C2.2 D2.2
7 A2 B2 C2.2 D2.3
8 A3 B3 C3 D3.1
9 A3 B3 C3 D3.2
完整的例子:
实际的爆炸由3行组成。剩下的是化妆品(多列爆炸，处理字符串而不是爆炸列中的列表，……)。
import pandas as pd
import numpy as np
df=pd.DataFrame( {'A': ['A1','A2','A3'],
'B': ['B1','B2','B3'],
'C': [ ['C1.1','C1.2'],['C2.1','C2.2'],'C3'],
'columnD': [ 'D1',['D2.1','D2.2', 'D2.3'],['D3.1','D3.2']],
})
print('df',df, sep='\n')
def dfListExplode(df, explodeKeys):
if not isinstance(explodeKeys, list):
explodeKeys=[explodeKeys]
# recursive handling of explodeKeys
if len(explodeKeys)==0:
return df
elif len(explodeKeys)==1:
explodeKey=explodeKeys[0]
else:
return dfListExplode( dfListExplode(df, explodeKeys[:1]), explodeKeys[1:])
# perform explosion/unnesting for key: explodeKey
dfPrep=df[explodeKey].apply(lambda x: x if isinstance(x,list) else [x]) #casts all elements to a list
dfIndExpl=pd.DataFrame([[x] + [z] for x, y in zip(dfPrep.index,dfPrep.values) for z in y ], columns=['explodedIndex',explodeKey])
dfMerged=dfIndExpl.merge(df.drop(explodeKey, axis=1), left_on='explodedIndex', right_index=True)
dfReind=dfMerged.reindex(columns=list(df))
return dfReind
dfExpl=dfListExplode(df,['C','columnD'])
print('dfExpl',dfExpl, sep='\n')
感谢文友本的回答
我有另一个好方法来解决这个问题当你有不止一列要爆炸的时候。
df=pd.DataFrame({'A':[1,2],'B':[[1,2],[1,2]], 'C':[[1,2,3],[1,2,3]]})
print(df)
A B C
0 1 [1, 2] [1, 2, 3]
1 2 [1, 2] [1, 2, 3]
我想爆炸B和C列，首先爆炸B，第二爆炸C，然后从原来的df中去掉B和C。之后，我将在3个dfs上做一个索引连接。
explode_b = df.explode('B')['B']
explode_c = df.explode('C')['C']
df = df.drop(['B', 'C'], axis=1)
df = df.join([explode_b, explode_c])
有些东西不太推荐(至少在这种情况下有用):
df=pd.concat([df]*2).sort_index()
it=iter(df['B'].tolist()[0]+df['B'].tolist()[0])
df['B']=df['B'].apply(lambda x:next(it))
Concat + sort_index + iter + apply + next。
Now:
print(df)
Is:
A B
0 1 1
0 1 2
1 2 1
1 2 2
如果关心索引:
df=df.reset_index(drop=True)
Now:
print(df)
Is:
A B
0 1 1
1 1 2
2 2 1
3 2 2
选项1
如果另一列的所有子列表都是相同的长度，numpy可以是一个有效的选项:
vals = np.array(df.B.values.tolist())
a = np.repeat(df.A, vals.shape[1])
pd.DataFrame(np.column_stack((a, vals.ravel())), columns=df.columns)
A B
0 1 1
1 1 2
2 2 1
3 2 2
选项2
如果子列表有不同的长度，你需要额外的步骤:
vals = df.B.values.tolist()
rs = [len(r) for r in vals]
a = np.repeat(df.A, rs)
pd.DataFrame(np.column_stack((a, np.concatenate(vals))), columns=df.columns)
A B
0 1 1
1 1 2
2 2 1
3 2 2
选项3
我尝试将其推广到平展N列和平铺M列，稍后我会让它更有效:
df = pd.DataFrame({'A': [1,2,3], 'B': [[1,2], [1,2,3], [1]],
'C': [[1,2,3], [1,2], [1,2]], 'D': ['A', 'B', 'C']})
A B C D
0 1 [1, 2] [1, 2, 3] A
1 2 [1, 2, 3] [1, 2] B
2 3 [1] [1, 2] C
def unnest(df, tile, explode):
vals = df[explode].sum(1)
rs = [len(r) for r in vals]
a = np.repeat(df[tile].values, rs, axis=0)
b = np.concatenate(vals.values)
d = np.column_stack((a, b))
return pd.DataFrame(d, columns = tile + ['_'.join(explode)])
unnest(df, ['A', 'D'], ['B', 'C'])
A D B_C
0 1 A 1
1 1 A 2
2 1 A 1
3 1 A 2
4 1 A 3
5 2 B 1
6 2 B 2
7 2 B 3
8 2 B 1
9 2 B 2
10 3 C 1
11 3 C 1
12 3 C 2
功能
def wen1(df):
return df.set_index('A').B.apply(pd.Series).stack().reset_index(level=0).rename(columns={0: 'B'})
def wen2(df):
return pd.DataFrame({'A':df.A.repeat(df.B.str.len()),'B':np.concatenate(df.B.values)})
def wen3(df):
s = pd.DataFrame({'B': np.concatenate(df.B.values)}, index=df.index.repeat(df.B.str.len()))
return s.join(df.drop('B', 1), how='left')
def wen4(df):
return pd.DataFrame([[x] + [z] for x, y in df.values for z in y],columns=df.columns)
def chris1(df):
vals = np.array(df.B.values.tolist())
a = np.repeat(df.A, vals.shape[1])
return pd.DataFrame(np.column_stack((a, vals.ravel())), columns=df.columns)
def chris2(df):
vals = df.B.values.tolist()
rs = [len(r) for r in vals]
a = np.repeat(df.A.values, rs)
return pd.DataFrame(np.column_stack((a, np.concatenate(vals))), columns=df.columns)
计时
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
from timeit import timeit
res = pd.DataFrame(
index=['wen1', 'wen2', 'wen3', 'wen4', 'chris1', 'chris2'],
columns=[10, 50, 100, 500, 1000, 5000, 10000],
dtype=float
)
for f in res.index:
for c in res.columns:
df = pd.DataFrame({'A': [1, 2], 'B': [[1, 2], [1, 2]]})
df = pd.concat([df]*c)
stmt = '{}(df)'.format(f)
setp = 'from __main__ import df, {}'.format(f)
res.at[f, c] = timeit(stmt, setp, number=50)
ax = res.div(res.min()).T.plot(loglog=True)
ax.set_xlabel("N")
ax.set_ylabel("time (relative)")
性能
# Here's the answer to the related question in:
# https://stackoverflow.com/q/56708671/11426125
# initial dataframe
df12=pd.DataFrame({'Date':['2007-12-03','2008-09-07'],'names':
[['Peter','Alex'],['Donald','Stan']]})
# convert dataframe to array for indexing list values (names)
a = np.array(df12.values)
# create a new, dataframe with dimensions for unnested
b = np.ndarray(shape = (4,2))
df2 = pd.DataFrame(b, columns = ["Date", "names"], dtype = str)
# implement loops to assign date/name values as required
i = range(len(a[0]))
j = range(len(a[0]))
for x in i:
for y in j:
df2.iat[2*x+y, 0] = a[x][0]
df2.iat[2*x+y, 1] = a[x][1][y]
# set Date column as Index
df2.Date=pd.to_datetime(df2.Date)
df2.index=df2.Date
df2.drop('Date',axis=1,inplace =True)
