import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
#缺失值处理
movie = pd.read_csv("./BRNN/data/IMDB-Movie-Data.csv")
#显示所有列
pd.set_option('display.max_columns', None)
# print(movie)
x1 = movie.head()
# print(x1)
x2 = pd.notnull(movie)
# print(x2)
# 返回False说明有缺失值
x3 = np.all(pd.notnull(movie))
# print(x3)
# 返回True说明有缺失值
np.any(pd.isnull(movie))
#处理方式
#1.1删除
# data = movie.dropna()
# #判断是否还有缺失值
# np.all(pd.notnull(movie))
#1.2 替换
#求平均值
#表中的那一列求平均值
x4 = movie["Revenue (Millions)"].mean()
print(x4)
#替换方法
# movie["Revenue (Millions)"].fillna(movie["Revenue (Millions)"].mean(), inplace=True)
# movie["Revenue (Millions)"]这是选择的要替换的列 fillna()空的替换函数 替换的内容为 movie["Revenue (Millions)"].mean()
# print(movie)
#循环替换
for i in movie.columns:
if np.any(pd.isnull(movie[i])) == True:
print(i)
movie[i].fillna(movie[i].mean(), inplace=True)
x6 = np.any(pd.isnull(movie))
print(x6)
如果不是NAN,空值是? 怎么操作