2022.04.14

课时44

 

import pandas as pd
from matplotlib import pyplot as plt
import numpy as np


df=pd.read_csv(" ")

#获取分类

temp_list=df["title"].srt.split(": ").to_list()
cate_list=list(set([i[0]] for i in temp_list))
#多添加一列放入结果
cate_df=pd.DataFrame(np.array(cate_list)).reshape((df.shape[0],1),collumns=cate_list)
#构造全为0的数组
df["cate"]=pd.DataFrame(np.zeros(df.shape[0],len(cate_list)),columns=cate_list)


#赋值
for cate in cate_list:
    zeros_df[cate][df["title"].str.contains(cate)]=1
    #print(zeros_df)
    #break
#print(zeros_df)

#for i in range(df.shape[0]):
    #zeros_df.loc[i,temp_list[i][0]]=1
sum_ret=zeros_df.sum(axis=0)
print(sum_ret)

 

 

 

 

 

 课时45 pandasa时间序列