濯君

import pandas as pdtrain_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=['...

#统计缺失值train = pd.read_csv("train.csv")null_columns=train.columns[train.isnull().any()]train[null_columns].isnull().sum()

1.回归问题可以使用的模型Linear and Polynomial Regression,Neural Networks,Regression Trees,Random Forests,Support Vector Regression,Naive Bayes2.KNeighborsClassifier特点：解决分类问题；neighbors的值设的越小，模型越复杂，方差大；nei...

1.StandardScaler确保处理后的特征均值为0，方差为1，但是不确保特征任何特定的最大，最小值2.RobustScaler与StandardScaler类似，确保所有特征scale在同一规模，但是使用属性median，quartiles，忽视outliers的影响3.MinMaxScaler将特征值范围scale到0,14.Normalizer将数据点映射到半径为1的圆；...

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...