pandas处理csv文件

import pandas as pd
import random
import numpy as np
first = pd.read_csv(r"/file",usecols=[1])
first.drop_duplicates(inplace=True)
#first = np.ndarray(first[:,0])
#print(type(first))

second = [random.randint(1,10) for i in range(0,1000000)]
third = [random.randint(1,2) for i in range(0,1000000)]

df1 = pd.DataFrame(np.array([first.values[:,0].tolist(),second,third]).T,columns=["user_id","predicted_age","predicted_gender"])#新建dataframe
print(type(first))
"""first = first.append(([second,third]),ignore_index=True)
first.columns = ["user_id","predicted_age","predicted_gender"]
print(type(second))"""
df1.to_csv(r"/file")

想了解更多代码，可以关注公众号喔