我有以下DataFrame（df）：
import numpy as np
import pandas as pd
df = pd.DataFrame(np.random.rand(10, 5))
我通过分配添加更多列：
df['mean'] = df.mean(1)
如何将列的意思移到前面，即将其设置为第一列，而其他列的顺序保持不变？
当前回答
一种简单的方法是使用set（），特别是当您有一长串列并且不想手动处理它们时：
cols = list(set(df.columns.tolist()) - set(['mean']))
cols.insert(0, 'mean')
df = df[cols]
其他回答
您可以使用可用于两个轴的重新索引：
df
# 0 1 2 3 4 mean
# 0 0.943825 0.202490 0.071908 0.452985 0.678397 0.469921
# 1 0.745569 0.103029 0.268984 0.663710 0.037813 0.363821
# 2 0.693016 0.621525 0.031589 0.956703 0.118434 0.484254
# 3 0.284922 0.527293 0.791596 0.243768 0.629102 0.495336
# 4 0.354870 0.113014 0.326395 0.656415 0.172445 0.324628
# 5 0.815584 0.532382 0.195437 0.829670 0.019001 0.478415
# 6 0.944587 0.068690 0.811771 0.006846 0.698785 0.506136
# 7 0.595077 0.437571 0.023520 0.772187 0.862554 0.538182
# 8 0.700771 0.413958 0.097996 0.355228 0.656919 0.444974
# 9 0.263138 0.906283 0.121386 0.624336 0.859904 0.555009
df.reindex(['mean', *range(5)], axis=1)
# mean 0 1 2 3 4
# 0 0.469921 0.943825 0.202490 0.071908 0.452985 0.678397
# 1 0.363821 0.745569 0.103029 0.268984 0.663710 0.037813
# 2 0.484254 0.693016 0.621525 0.031589 0.956703 0.118434
# 3 0.495336 0.284922 0.527293 0.791596 0.243768 0.629102
# 4 0.324628 0.354870 0.113014 0.326395 0.656415 0.172445
# 5 0.478415 0.815584 0.532382 0.195437 0.829670 0.019001
# 6 0.506136 0.944587 0.068690 0.811771 0.006846 0.698785
# 7 0.538182 0.595077 0.437571 0.023520 0.772187 0.862554
# 8 0.444974 0.700771 0.413958 0.097996 0.355228 0.656919
# 9 0.555009 0.263138 0.906283 0.121386 0.624336 0.859904
要根据其他列的名称将现有列设置为右侧/左侧，请执行以下操作：
def df_move_column(df, col_to_move, col_left_of_destiny="", right_of_col_bool=True):
cols = list(df.columns.values)
index_max = len(cols) - 1
if not right_of_col_bool:
# set left of a column "c", is like putting right of column previous to "c"
# ... except if left of 1st column, then recursive call to set rest right to it
aux = cols.index(col_left_of_destiny)
if not aux:
for g in [x for x in cols[::-1] if x != col_to_move]:
df = df_move_column(
df,
col_to_move=g,
col_left_of_destiny=col_to_move
)
return df
col_left_of_destiny = cols[aux - 1]
index_old = cols.index(col_to_move)
index_new = 0
if len(col_left_of_destiny):
index_new = cols.index(col_left_of_destiny) + 1
if index_old == index_new:
return df
if index_new < index_old:
index_new = np.min([index_new, index_max])
cols = (
cols[:index_new]
+ [cols[index_old]]
+ cols[index_new:index_old]
+ cols[index_old + 1 :]
)
else:
cols = (
cols[:index_old]
+ cols[index_old + 1 : index_new]
+ [cols[index_old]]
+ cols[index_new:]
)
df = df[cols]
return df
E.g.
cols = list("ABCD")
df2 = pd.DataFrame(np.arange(4)[np.newaxis, :], columns=cols)
for k in cols:
print(30 * "-")
for g in [x for x in cols if x != k]:
df_new = df_move_column(df2, k, g)
print(f"{k} after {g}: {df_new.columns.values}")
for k in cols:
print(30 * "-")
for g in [x for x in cols if x != k]:
df_new = df_move_column(df2, k, g, right_of_col_bool=False)
print(f"{k} before {g}: {df_new.columns.values}")
输出：
我尝试了创建一个order函数，您可以使用Stata的order命令对列进行重新排序/移动。最好创建一个py文件（其名称可能是order.py），并将其保存在目录中并调用它的函数
def order(dataframe,cols,f_or_l=None,before=None, after=None):
#만든이: 김완석, Stata로 뚝딱뚝딱 저자, blog.naver.com/sanzo213 운영
# 갖다 쓰시거나 수정을 하셔도 되지만 출처는 꼭 밝혀주세요
# cols옵션 및 befor/after옵션에 튜플이 가능하게끔 수정했으며, 오류문구 수정함(2021.07.12,1)
# 칼럼이 멀티인덱스인 상태에서 reset_index()메소드 사용했을 시 적용안되는 걸 수정함(2021.07.12,2)
import pandas as pd
if (type(cols)==str) or (type(cols)==int) or (type(cols)==float) or (type(cols)==bool) or type(cols)==tuple:
cols=[cols]
dd=list(dataframe.columns)
for i in cols:
i
dd.remove(i) #cols요소를 제거함
if (f_or_l==None) & ((before==None) & (after==None)):
print('f_or_l옵션을 쓰시거나 아니면 before옵션/after옵션 쓰셔야되요')
if ((f_or_l=='first') or (f_or_l=='last')) & ~((before==None) & (after==None)):
print('f_or_l옵션 사용시 before after 옵션 사용불가입니다.')
if (f_or_l=='first') & (before==None) & (after==None):
new_order=cols+dd
dataframe=dataframe[new_order]
return dataframe
if (f_or_l=='last') & (before==None) & (after==None):
new_order=dd+cols
dataframe=dataframe[new_order]
return dataframe
if (before!=None) & (after!=None):
print('before옵션 after옵션 둘다 쓸 수 없습니다.')
if (before!=None) & (after==None) & (f_or_l==None):
if not((type(before)==str) or (type(before)==int) or (type(before)==float) or
(type(before)==bool) or ((type(before)!=list)) or
((type(before)==tuple))):
print('before옵션은 칼럼 하나만 입력가능하며 리스트 형태로도 입력하지 마세요.')
else:
b=dd[:dd.index(before)]
a=dd[dd.index(before):]
new_order=b+cols+a
dataframe=dataframe[new_order]
return dataframe
if (after!=None) & (before==None) & (f_or_l==None):
if not((type(after)==str) or (type(after)==int) or (type(after)==float) or
(type(after)==bool) or ((type(after)!=list)) or
((type(after)==tuple))):
print('after옵션은 칼럼 하나만 입력가능하며 리스트 형태로도 입력하지 마세요.')
else:
b=dd[:dd.index(after)+1]
a=dd[dd.index(after)+1:]
new_order=b+cols+a
dataframe=dataframe[new_order]
return dataframe
下面的python代码是我制作的order函数的一个示例。我希望您可以使用我的order函数轻松地对列进行重新排序：）
# module
import pandas as pd
import numpy as np
from order import order # call order function from order.py file
# make a dataset
columns='a b c d e f g h i j k'.split()
dic={}
n=-1
for i in columns:
n+=1
dic[i]=list(range(1+n,10+1+n))
data=pd.DataFrame(dic)
print(data)
# use order function (1) : order column e in the first
data2=order(data,'e',f_or_l='first')
print(data2)
# use order function (2): order column e in the last , "data" dataframe
print(order(data,'e',f_or_l='last'))
# use order function (3) : order column i before column c in "data" dataframe
print(order(data,'i',before='c'))
# use order function (4) : order column g after column b in "data" dataframe
print(order(data,'g',after='b'))
# use order function (4) : order columns ['c', 'd', 'e'] after column i in "data" dataframe
print(order(data,['c', 'd', 'e'],after='i'))
将任意列移动到任意位置：
import pandas as pd
df = pd.DataFrame({"A": [1,2,3],
"B": [2,4,8],
"C": [5,5,5]})
cols = df.columns.tolist()
column_to_move = "C"
new_position = 1
cols.insert(new_position, cols.pop(cols.index(column_to_move)))
df = df[cols]
只需键入要更改的列名，然后为新位置设置索引。
def change_column_order(df, col_name, index):
cols = df.columns.tolist()
cols.remove(col_name)
cols.insert(index, col_name)
return df[cols]
对于您的情况，这将是：
df = change_column_order(df, 'mean', 0)
推荐文章
- Numpy Max vs amax vs maximum
- 我应该在.gitignore文件中添加Django迁移文件吗?
- 每n行有熊猫
- 实例属性attribute_name定义在__init__之外
- 如何获取在Python中捕获的异常的名称?
- 第一次出现的值大于现有值的Numpy
- 如何从Python函数中返回两个值?
- 前一个月的Python日期
- Python中方括号括起来的列表和圆括号括起来的列表有什么区别?
- Python日志记录不输出任何东西
- 每n秒运行特定代码
- SQLAlchemy是否有与Django的get_or_create等价的函数?
- 如何将python datetime转换为字符串，具有可读格式的日期?
- 美丽的汤和提取div及其内容的ID
- 在Python中重置生成器对象
