【机器学习之路】十三种回归模型预测房价

数据：https://www.kaggle.com/santibermejo/xgboost-for-house-price-prediction
这篇文章汇总了13个机器学习的回归算法，对比它们在同一个数据下的预测的效果。其实就是为了选模型的时候方便一点，一个一个试太麻烦了

• 导入需要的库

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import os
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
import warnings
# filter warnings
warnings.filterwarnings('ignore')
# 正常显示中文
from pylab import mpl
mpl.rcParams['font.sans-serif'] = ['SimHei']
# 正常显示符号
from matplotlib import rcParams
rcParams['axes.unicode_minus']=False

• 导入数据

os.chdir('E:\\kaggle\\house_price')
data=pd.read_csv('train.csv')

• 数据预处理

data['MSSubClass']=data['MSSubClass'].astype(str)  #MSSubClass是一个分类变量，所以要把他的数据类型改为‘’str‘’
Id=data.loc[:,'Id']   #ID先提取出来，后面合并表格要用
data=data.drop('Id',axis=1)

x=data.loc[:,data.columns!='SalePrice']
y=data.loc[:,'SalePrice']   
mean_cols=x.mean()
x=x.fillna(mean_cols)  #填充缺失值
x_dum=pd.get_dummies(x)    #独热编码
x_train,x_test,y_train,y_test = train_test_split(x_dum,y,test_size = 0.3,random_state = 1)

#再整理出一组标准化的数据，通过对比可以看出模型的效果有没有提高
x_dum=pd.get_dummies(x)
scale_x=StandardScaler()
x1=scale_x.fit_transform(x_dum)
scale_y=StandardScaler()
y=np.array(y).reshape(-1,1)
y1=scale_y.fit_transform(y)
y1=y1.ravel()
x_train1,x_test1,y_train1,y_test1 = train_test_split(x1,y1,test_size = 0.3,random_state = 1)

• 导入模型

from sklearn.linear_model import LinearRegression
from sklearn.neighbors import KNeighborsRegressor
from sklearn.svm import SVR
from sklearn.linear_model import Lasso
from sklearn.linear_model import Ridge
from sklearn.neural_network import MLPRegressor
from sklearn.tree import DecisionTreeRegressor
from sklearn.tree import ExtraTreeRegressor
from xgboost import XGBRegressor
from sklearn.ensemble import RandomForestRegressor
from sklearn.ensemble import AdaBoostRegressor
from sklearn.ensemble import GradientBoostingRegressor
from sklearn.ensemble import BaggingRegressor

将模型和他们的名字分别放到两个列表里，然后建一个空列表保存他们的得分

models=[LinearRegression(),KNeighborsRegressor(),SVR(),Ridge(),Lasso(),MLPRegressor(alpha=20),DecisionTreeRegressor(),ExtraTreeRegressor(),XGBRegressor(),RandomForestRegressor(),AdaBoostRegressor(),GradientBoostingRegressor(),BaggingRegressor()]
models_str=['LinearRegression','KNNRegressor','SVR','Ridge','Lasso','MLPRegressor','DecisionTree','ExtraTree','XGBoost','RandomForest','AdaBoost','GradientBoost','Bagging']
score_=[]