import pandas as pda import numpy as np #数据预处理 data=pda.read_csv("titanic_train.csv") print(data.columns) #自定义缺失值检测函数 def not_null_num(column): column_null=pda.isnull(column) column_notnull = pda.notnull(column) null=column[column_null] notnull=column[column_notnull] return "缺失值数量:"+str(len(null)),\ "缺失值比例:"+str(round(len(null)/len(column)*100,2)),\ "非缺失值数量:" +str(len(notnull)),\ "非缺失值比例:"+str(round(len(notnull)/len(column)*100,2)) count_column_null=data.apply(not_null_num) print(count_column_null) print(count_column_null["Age"])