回归预测4：机器学习处理加利福尼亚房价数据集

1 介绍

我们使用California Housing Prices数据集进行预测，数据集地址：https://download.csdn.net/download/ww596520206/87506282

2 工具箱导入

import numpy as np
import pandas as pd
from sklearn.ensemble import RandomForestRegressor,GradientBoostingRegressor
from sklearn.metrics import mean_squared_error,r2_score
from sklearn.model_selection import train_test_split
import matplotlib.pyplot as plt
np.random.seed(123)

3 导入数据 数据分析

data = pd.read_csv("housing.csv")
print(data.describe())
print(data.shape)
print(data.info())
data.dropna(inplace= True) #剔除空值
data.hist(bins=60, figsize=(15,9))
plt.show()

4 拆分标签和特征

x = data.drop(["median_house_value"],axis=1)
y = data["median_house_value"]

5 ocean_proximity特征编码

from category_encoders import MEstimateEncoder
encoder = MEstimateEncoder(cols=['ocean_proximity'],m=0.5)
encoder.fit(x,y)
x= encoder.transform(x)

6 划分训练集-测试集

X_train, X_test, y_train, y_test = train_test_split(x, y,train_size=0.7,shuffle = True,random_state=123)

7 模型训练和验证

from sklearn.linear_model import LinearRegression
rf = LinearRegression()
rf.fit(X_train, y_train)
y_pred = rf.predict(X_test)
print("mse:{}".format(mean_squared_error(y_test, y_pred)))
print("r2-score:{}".format(r2_score(y_test, y_pred)))

from sklearn.ensemble import RandomForestRegressor
rf = RandomForestRegressor()
rf.fit(X_train, y_train)
y_pred = rf.predict(X_test)
print("mse:{}".format(mean_squared_error(y_test, y_pred)))
print("r2-score:{}".format(r2_score(y_test, y_pred)))

mse:4628881884.279629
r2-score:0.6444582617950347
mse:2428501108.0044303
r2-score:0.8134682355786766