import pandas as pd
import random
file=open(r"/home/hadoop/SparkProgram/chapter4-data01.txt","r",encoding="utf-8")
datas=file.read()
file.close()
rs=datas.replace("\n",",")
data=rs.split(",")
names=data[::3]
num=len(set(names))
Classids=["class0"+str(random.randint(1,11))for n in range(num)]
dataframe=pd.DataFrame(Classids,list(set(names)))
dataframe.to_csv("/home/hadoop/SparkProgram/class.csv",encoding="utf-8")
print("successful")