运用scikit-learn库进行回归分析（二）

本文主要介绍非线性回归分析，使用数据来自网站 房屋数据。

一、多项式回归

# 读取数据
import pandas as pd
df = pd.read_csv('housing.csv', header = None, sep = '\s+')
df.columns = ['CRIM', 'ZN', 'INDUS', 'CHAS', 
              'NOX', 'RM', 'AGE', 'DIS', 'RAD', 
              'TAX', 'PTRATIO', 'B', 'LSTAT', 'MEDV']
df.head()

# 拟合房屋价格和LSTAT之间的模型
# 获取数据
X = df[['LSTAT']].values
y = df['MEDV'].values

regr = LinearRegression()

# 导入多项式函数
from sklearn.preprocessing import PolynomialFeatures
# 创建多项式数据
quadratic = PolynomialFeatures(degree=2)
cubic = PolynomialFeatures(degree=3)
X_quad = quadratic.fit_transform(X)
X_cubic = cubic.fit_transform(X)

# 线性拟合
X_fit = np.arange(X.min(), X.max(), 1)[:, np.newaxis]
regr = regr.fit(X, y)
y_lin_fit = regr.predict(X_fit)
linear_r2 = r2_score(y, regr.predict(X))

# 二项式拟合
regr = regr.fit(X_quad, y)
y_quad_fit = regr.predict(quadratic.fit_transform(X_fit))
quadratic_r2 = r2_score(y, regr.predict(X_quad))

# 三项式拟合
regr = regr.fit(X_cubic, y)
y_cubic_fit = regr.predict(cubic.fit_transform(X_fit))
cubic_r2 = r2_score(y, regr.predict(X_cubic))

# 可视化结果
plt.scatter(X, y, label='training points', color='lightgray')

plt.plot(X_fit, y_lin_fit, 
         label='linear (d=1), $R^2=%.2f$' % linear_r2, 
         color='blue', 
         lw=2, 
         linestyle=':')

plt.plot(X_fit, y_quad_fit, 
         label='quadratic (d=2), $R^2=%.2f$' % quadratic_r2,
         color='red', 
         lw=2,
         linestyle='-')

plt.plot(X_fit, y_cubic_fit, 
         label='cubic (d=3), $R^2=%.2f$' % cubic_r2,
         color='green', 
         lw=2, 
         linestyle='--')

plt.xlabel('弱势群体人口所占比例（%）')
plt.ylabel('业主自住房屋的平均价格\n（以1000美元为例）')
plt.legend(loc='upper right')
plt.show()

将非线性拟合转换为线性拟合

# 转换特征进行线性拟合
X = df[['LSTAT']].values
y = df['MEDV'].values

# 转换特征
X_log = np.log(X)
y_sqrt = np.sqrt(y)

# 拟合特征
X_fit = np.arange(X_log.min()-1, X_log.max()+1, 1)[:, np.newaxis]

regr = regr.fit(X_log, y_sqrt)
y_lin_fit = regr.predict(X_fit)
linear_r2 = r2_score(y_sqrt, regr.predict(X_log))

# 可视化结果
plt.scatter(X_log, y_sqrt, label='training points', color='lightgray')

plt.plot(X_fit, y_lin_fit, 
         label='linear (d=1), $R^2=%.2f$' % linear_r2, 
         color='blue', 
         lw=2)

plt.xlabel('log(% 弱势群体人口所占比列)')
plt.ylabel('$\sqrt{Price \; in \; \$1000\'s [MEDV]}$')
plt.legend(loc='lower left')
plt.show()

二、随机森林回归

（一）决策树回归

from sklearn.tree import DecisionTreeRegressor

X = df[['LSTAT']].values
y = df['MEDV'].values

tree = DecisionTreeRegressor(max_depth=3)
tree.fit(X, y)

sort_idx = X.flatten().argsort()

lin_regplot(X[sort_idx], y[sort_idx], tree)
plt.xlabel('弱势群体人口所占比例（%）')
plt.ylabel('业主自住房屋的平均价格\n（以1000美元为例）')
plt.show()

（二）随机森林回归

# 获取数据，并分为训练数据和测试数据
X = df.iloc[:, :-1].values
y = df['MEDV'].values

X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.4, random_state=1)

from sklearn.ensemble import RandomForestRegressor

forest = RandomForestRegressor(n_estimators=1000, 
                               criterion='mse', 
                               random_state=1, 
                               n_jobs=-1)
forest.fit(X_train, y_train)
y_train_pred = forest.predict(X_train)
y_test_pred = forest.predict(X_test)

print('MSE train: %.3f, test: %.3f' % (
        mean_squared_error(y_train, y_train_pred),
        mean_squared_error(y_test, y_test_pred)))
print('R^2 train: %.3f, test: %.3f' % (
        r2_score(y_train, y_train_pred),
        r2_score(y_test, y_test_pred)))

# 可视化残差图
plt.scatter(y_train_pred,  
            y_train_pred - y_train, 
            c='black', 
            marker='o', 
            s=35,
            alpha=0.5,
            label='Training data')
plt.scatter(y_test_pred,  
            y_test_pred - y_test, 
            c='lightgreen', 
            marker='s', 
            s=35,
            alpha=0.7,
            label='Test data')

plt.xlabel('预测值')
plt.ylabel('残差')
plt.legend(loc='upper left')
plt.hlines(y=0, xmin=-10, xmax=50, lw=2, color='red')
plt.xlim([-10, 50])
plt.show()