波士顿房价预测

news2024/12/27 12:47:15

1.初始化库并导入数据

2.查看是否有缺失值，查看各个变量的相关性

3.探究各变量之间的相关关系

4.初始化并训练线性模型

5.可视化预测情况

6.模型优化

idea1：减少决策变量

idea2：数据归一化

idea3：尝试其他模型

XGB

Lasso 回归

Elasticnet

支持向量回归

决策树回归

1.初始化库并导入数据

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error
plt.style.use('ggplot')
data = pd.read_csv('boston.csv')
data.head()

2.查看是否有缺失值，查看各个变量的相关性

plt.figure(figsize=(12,8))
sns.heatmap(data.corr(),annot = True,fmt = '.2f',cmap='PuBu')
data.corr()['MEDV'].sort_values()

3.探究各变量之间的相关关系

sns.pairplot(data[["LSTAT","RM","PIRATIO","MEDV"]])

4.初始化并训练线性模型

X,y  =data[data.columns.delete(-1)],data['MEDV']
xtarin,xtest,ytrain,ytest = train_test_split(X,y,test_size=0.2,random_state=750)

linear_model = LinearRegression()
linear_model.fit(xtarin,ytrain)
coef = linear_model.coef_
line_predict = linear_model.predict(xtest)


print('Score:{:.4f}'.format(linear_model.score(xtest,ytest)))
print('RMSE:{:.4f}'.format(np.sqrt(mean_squared_error(ytest,line_predict))))
print(coef)

df_coef = pd.DataFrame()
df_coef['Title'] = data.columns.delete(-1)
df_coef['Coef'] = coef
df_coef

并可视化各个变量的决策参数

5.可视化预测情况

hos_predict = pd.DataFrame()


hos_predict['Truth'] =ytest
hos_predict['Predict'] = line_predict

hos_predict.reset_index(drop=True,inplace=True)

plt.scatter(ytest, line_predict,label='y')
plt.plot([ytest.min(), ytest.max()], [ytest.min(), ytest.max()], 'k--', lw=4,label='predicted')

6.模型优化

idea1：减少决策变量

取相关性最大的三个作为决策变量试试：

data.corr()['MEDV'].abs().sort_values(ascending=False).head(4)

x2 = np.array(data[['LSTAT','RM','PIRATIO']])
x2train,x2test,y2train,y2test = train_test_split(x2,y,random_state=750,test_size=0.2)
linear_model2 = LinearRegression()
linear_model2.fit(x2train,y2train)
print(linear_model2.intercept_)
print(linear_model2.coef_)
line2_pre = linear_model2.predict(x2test)  #预测值
print('SCORE:{:.4f}'.format(linear_model2.score(x2test, y2test)))#模型评分
print('RMSE:{:.4f}'.format(np.sqrt(mean_squared_error(y2test, line2_pre))))#RMSE(标准误差)

idea2：数据归一化

#归一化处理

from sklearn.preprocessing import StandardScaler
ss_x = StandardScaler()
x_train = ss_x.fit_transform(xtarin)
x_test = ss_x.transform(xtest)

ss_y = StandardScaler()
y_train = ss_y.fit_transform(ytrain.values.reshape(-1,1))
y_test = ss_y.transform(ytest.values.reshape(-1,1))

model3 = LinearRegression()
model3.fit(x_train,y_train)
print(model3.score(x_test,y_test))

idea3：尝试其他模型

XGB

X ,y = data[data.columns.delete(-1)], data['MEDV']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=9)

from sklearn import ensemble
#params = {'n_estimators': 500, 'max_depth': 4, 'min_samples_split': 1,'learning_rate': 0.01, 'loss': 'ls'}
#clf = ensemble.GradientBoostingRegressor(**params)
clf = ensemble.GradientBoostingRegressor()
clf.fit(X_train, y_train)
clf_pre=clf.predict(X_test) #预测值
print('SCORE:{:.4f}'.format(clf.score(X_test, y_test)))#模型评分
print('RMSE:{:.4f}'.format(np.sqrt(mean_squared_error(y_test, clf_pre))))#RMSE(标准误差)

Lasso 回归

# Lasso 回归
from sklearn.linear_model import Lasso
lasso = Lasso()
lasso.fit(X_train,y_train)
y_predict_lasso = lasso.predict(X_test)


print('SCORE:{:.4f}'.format( lasso.score(X_test, y_test)))#模型评分
print('RMSE:{:.4f}'.format(np.sqrt(mean_squared_error(y_test,y_predict_lasso))))#RMSE(标准误差)

Elasticnet

from sklearn.linear_model import ElasticNet
enet = ElasticNet()
enet.fit(X_train,y_train)
y_predict_enet = enet.predict(X_test)

print('SCORE:{:.4f}'.format( enet.score(X_test, y_test)))#模型评分
print('RMSE:{:.4f}'.format(np.sqrt(mean_squared_error(y_test,y_predict_enet))))#RMSE(标准误差)

支持向量回归

from sklearn.preprocessing import StandardScaler
ss_x = StandardScaler()
X_train = ss_x.fit_transform(X_train)
X_test = ss_x.transform(X_test)
ss_y = StandardScaler()
y_train = ss_y.fit_transform(y_train.values.reshape(-1, 1))
y_test = ss_y.transform(y_test.values.reshape(-1, 1))


poly_svr = SVR(kernel="poly")
poly_svr.fit(X_train, y_train)
poly_svr_pre = poly_svr.predict(X_test)#预测值
print('SCORE:{:.4f}'.format(poly_svr.score(X_test, y_test)))#模型评分
print('RMSE:{:.4f}'.format(np.sqrt(mean_squared_error(y_test, poly_svr_pre))))#RMSE(标准误差)

决策树回归

from sklearn.tree import DecisionTreeRegressor
tree_reg=DecisionTreeRegressor(max_depth=2)
tree_reg.fit(X_train, y_train)
tree_reg_pre = tree_reg.predict(X_test)#预测值
print('SCORE:{:.4f}'.format( tree_reg.score(X_test, y_test)))#模型评分
print('RMSE:{:.4f}'.format(np.sqrt(mean_squared_error(y_test,tree_reg_pre))))#RMSE(标准误差)