Python实现基于PCA和随机森林的能源消费预测模型

import numpy as np
import pandas as pd
from sklearn.preprocessing import MinMaxScaler
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_squared_error
from sklearn.ensemble import RandomForestRegressor
from sklearn.pipeline import Pipeline
from sklearn.decomposition import PCA

# 成分数据矩阵
data = np.array([[0.758, 0.171, 0.049, 0.022],
                 [0.758, 0.172, 0.047, 0.023],
                 [0.762, 0.17, 0.047, 0.021],
                 [0.762, 0.17, 0.047, 0.021],
                 [0.76, 0.171, 0.047, 0.021],
                 [0.762, 0.166, 0.051, 0.021],
                 [0.761, 0.171, 0.048, 0.02],
                 [0.757, 0.175, 0.049, 0.019],
                 [0.747, 0.182, 0.052, 0.019],
                 [0.75, 0.174, 0.057, 0.019],
                 [0.746, 0.175, 0.061, 0.018],
                 [0.747, 0.18, 0.055, 0.018],
                 [0.715, 0.204, 0.062, 0.017],
                 [0.696, 0.215, 0.067, 0.022],
                 [0.68, 0.232, 0.066, 0.022],
                 [0.661, 0.246, 0.068, 0.025],
                 [0.653, 0.243, 0.077, 0.027],
                 [0.661, 0.234, 0.078, 0.027],
                 [0.702, 0.201, 0.074, 0.023],
                 [0.702, 0.199, 0.076, 0.023],
                 [0.724, 0.178, 0.074, 0.024],
                 [0.724, 0.175, 0.074, 0.027],
                 [0.725, 0.17, 0.075, 0.03],
                 [0.715, 0.167, 0.084, 0.034],
                 [0.716, 0.164, 0.085, 0.035],
                 [0.692, 0.174, 0.094, 0.04],
                 [0.702, 0.168, 0.084, 0.046],
                 [0.685, 0.17, 0.097, 0.048],
                 [0.674, 0.171, 0.102, 0.053],
                 [0.658, 0.173, 0.113, 0.056],
                 [0.638, 0.184, 0.12, 0.058],
                 [0.622, 0.187, 0.13, 0.061],
                 [0.606, 0.189, 0.136, 0.069],
                 [0.59, 0.189, 0.145, 0.076],
                 [0.577, 0.19, 0.153, 0.08],
                 [0.569, 0.188, 0.159, 0.084],
                 [0.559, 0.186, 0.167, 0.088],
                 [0.562, 0.179, 0.175, 0.084]])

# 转换为特征矩阵
feature_matrix = np.zeros((len(data) - 1, len(data[0])))
for i in range(len(data) - 1):
    feature_matrix[i] = data[i + 1] - data[i]

# 构建特征矩阵的DataFrame
df = pd.DataFrame(feature_matrix, columns=['Coal', 'Petroleum', 'Others', 'Gas'])

# 目标变量
target = data[:-1, 1]  # 使用第二列作为目标变量

# 数据归一化
scaler = MinMaxScaler()
df_scaled = scaler.fit_transform(df)

# 划分训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(df_scaled, target, test_size=0.13, random_state=42)

# 构建模型管道
model = Pipeline([
    ('pca', PCA(n_components=2)),  # 使用PCA进行特征降维
    ('regressor', RandomForestRegressor(n_estimators=100))  # 使用随机森林回归器作为模型
])

# 拟合模型
model.fit(X_train, y_train)

# 在测试集上进行预测
y_pred = model.predict(X_test)

# 计算CRMSE和CMAPE
crmse = np.sqrt(mean_squared_error(y_test, y_pred))
cmape = np.mean(np.abs((y_test - y_pred) / y_test)) * 100

print('CRMSE:', crmse)
print('CMAPE:', cmape)