3.4.8.11. 加州房价数据上的简单回归分析

这里我们对加州房价数据进行简单的回归分析，探索两种类型的回归器。

from sklearn.datasets import fetch_california_housing

data = fetch_california_housing(as_frame=True)

打印要预测的数量的直方图：价格

import matplotlib.pyplot as plt

plt.figure(figsize=(4, 3))
plt.hist(data.target)
plt.xlabel("price ($100k)")
plt.ylabel("count")
plt.tight_layout()

打印每个特征的联合直方图

for index, feature_name in enumerate(data.feature_names):
    plt.figure(figsize=(4, 3))
    plt.scatter(data.data[feature_name], data.target)
    plt.ylabel("Price", size=15)
    plt.xlabel(feature_name, size=15)
    plt.tight_layout()

• 
• 
• 
• 
• 
• 
• 
• 

简单预测

from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split(data.data, data.target)

from sklearn.linear_model import LinearRegression

clf = LinearRegression()
clf.fit(X_train, y_train)
predicted = clf.predict(X_test)
expected = y_test

plt.figure(figsize=(4, 3))
plt.scatter(expected, predicted)
plt.plot([0, 8], [0, 8], "--k")
plt.axis("tight")
plt.xlabel("True price ($100k)")
plt.ylabel("Predicted price ($100k)")
plt.tight_layout()

使用梯度提升树预测

from sklearn.ensemble import GradientBoostingRegressor

clf = GradientBoostingRegressor()
clf.fit(X_train, y_train)

predicted = clf.predict(X_test)
expected = y_test

plt.figure(figsize=(4, 3))
plt.scatter(expected, predicted)
plt.plot([0, 5], [0, 5], "--k")
plt.axis("tight")
plt.xlabel("True price ($100k)")
plt.ylabel("Predicted price ($100k)")
plt.tight_layout()

打印错误率

import numpy as np

print(f"RMS: {np.sqrt(np.mean((predicted - expected) ** 2))!r} ")

plt.show()

RMS: np.float64(0.5314909993118918)