sklearn常用导包路径

from matplotlib import pyplot as plt
import numpy as np
import pandas as pd

#训练集，测试集划分
from sklearn.model_selection import train_test_split

x_train,x_test,y_train,y_test=train_test_split(newdata.iloc[:,0:7],newdata['winPlacePerc'])

#标准化
from sklearn.preprocessing import StandardScaler

trainsfer=StandardScaler()
x_train=trainsfer.fit_transform(x_train)
x_test=trainsfer.transform(x_test)

#K近邻算法
from sklearn.neighbors import KNeighborsClassifier

#sklearn模型的保存和加载API
from sklearn.externals import joblib

保存：joblib.dump(estimator, 'test.pkl')
加载：estimator = joblib.load('test.pkl')

from sklearn.feature_selection import VarianceThreshold

#特征降维：1：皮尔逊相关系数，2：斯皮尔曼相关系数
from scipy.stats import pearsonr,spearmanr

#主成分分析PCA（n_components=None)

#n_components:

• 小数：表示保留百分之多少的信息
• 整数：减少到多少特征

from sklearn.decomposition import PCA

#线性回归
from sklearn.linear_model import Ridge,RidgeCV,LinearRegression

#决策树算法
from sklearn.tree import DecisionTreeClassifier, export_graphviz

#均方误差
from sklearn.metrics import mean_squared_error,mean_absolute_error