Dataframe 按条件替换某列中的元素

最新推荐文章于 2023-03-31 16:31:58 发布

DeniuHe

最新推荐文章于 2023-03-31 16:31:58 发布

阅读量2.5k

点赞数

分类专栏： Python学习文章标签： python

本文链接：https://blog.csdn.net/DeniuHe/article/details/122482852

版权

Python学习专栏收录该内容

239 篇文章 13 订阅

订阅专栏

import numpy as np
import pandas as pd

df = pd.read_csv(r"D:\OCdata\ObesityDataSet_raw_and_data_sinthetic.csv")

# print(df.loc[df['Gender']=='Female',"Gender"])
df.loc[df['Gender']=='Female',"Gender"] = 0.
df.loc[df['Gender']=='Male',"Gender"] = 1.

df.loc[df['family_history_with_overweight']=='no','family_history_with_overweight'] = 0.
df.loc[df['family_history_with_overweight']=='yes','family_history_with_overweight'] = 1.

df.loc[df['FAVC']=='no','FAVC'] = 0.
df.loc[df['FAVC']=='yes','FAVC'] = 1.

df.loc[df['CAEC']=='Always','CAEC'] = 0.
df.loc[df['CAEC']=='Frequently','CAEC'] = 1.
df.loc[df['CAEC']=='Sometimes','CAEC'] = 2.
df.loc[df['CAEC']=='no','CAEC'] = 3.

df.loc[df['SMOKE']=='no','SMOKE'] = 0.
df.loc[df['SMOKE']=='yes','SMOKE'] = 1.

df.loc[df['SCC']=='no','SCC'] = 0.
df.loc[df['SCC']=='yes','SCC'] = 1.

df.loc[df['CALC']=='Always','CALC'] = 0.
df.loc[df['CALC']=='Frequently','CALC'] = 1.
df.loc[df['CALC']=='Sometimes','CALC'] = 2.
df.loc[df['CALC']=='no','CALC'] = 3.


df.loc[df['MTRANS']=='Walking','MTRANS'] = 0.
df.loc[df['MTRANS']=='Bike','MTRANS'] = 1.
df.loc[df['MTRANS']=='Public_Transportation','MTRANS'] = 2.
df.loc[df['MTRANS']=='Motorbike','MTRANS'] = 3.
df.loc[df['MTRANS']=='Automobile','MTRANS'] = 4.

df.loc[df['NObeyesdad']=='Insufficient_Weight','NObeyesdad'] = 0
df.loc[df['NObeyesdad']=='Normal_Weight','NObeyesdad'] = 1
df.loc[df['NObeyesdad']=='Obesity_Type_I','NObeyesdad'] = 2
df.loc[df['NObeyesdad']=='Obesity_Type_II','NObeyesdad'] = 3
df.loc[df['NObeyesdad']=='Obesity_Type_III','NObeyesdad'] = 4
df.loc[df['NObeyesdad']=='Overweight_Level_I','NObeyesdad'] = 5
df.loc[df['NObeyesdad']=='Overweight_Level_II','NObeyesdad'] = 6



df.to_csv(r"D:\OCdata\OBESITY1.csv",header=None,index=None)