濯君

import pandas as pd import numpy as np def draw_missing_data_table(df): #得出缺失数据占总数的百分比 total=df.isnull().sum().sort_values(ascending=False) percent=(df.isnull().sum()/df.isnull().count()).sor...

import pandas as pd train_pd = pd.read_csv(path+'training.csv') #读取数据 test_pd = pd.read_csv(path+'sorted_test.csv') train_pd.info()#查看数据类型 train_pd.describe()#数值型变量的统计信息 train_pd.describe(include=['...

一：按缺失百分比去除缺失值过多的特征 #缺失超过77%的特征被去除 many_null_cols = [col for col in train_x.columns if train_x[col].isnull().sum() / train_x.shape[0] > 0.77] many_null_cols_test = [col for col in test.columns if te...