如何修改Python多元线性回归代码批量输出多组预测值

修改后可实现5组预测的完整代码 #

import pandas as pd
from sklearn import linear_model
import statsmodels.api as sm

Stock_Market = {'Year': [2017,2017,2017,2017,2017,2017,2017,2017,2017,2017,2017,2017,2016,2016,2016,2016,2016,2016,2016,2016,2016,2016,2016,2016],
                'Month': [12, 11,10,9,8,7,6,5,4,3,2,1,12,11,10,9,8,7,6,5,4,3,2,1],
                'Interest_Rate': [2.75,2.5,2.5,2.5,2.5,2.5,2.5,2.25,2.25,2.25,2,2,2,1.75,1.75,1.75,1.75,1.75,1.75,1.75,1.75,1.75,1.75,1.75],
                'Unemployment_Rate': [5.3,5.3,5.3,5.3,5.4,5.6,5.5,5.5,5.5,5.6,5.7,5.9,6,5.9,5.8,6.1,6.2,6.1,6.1,6.1,5.9,6.2,6.2,6.1],
                'Stock_Index_Price': [1464,1394,1357,1293,1256,1254,1234,1195,1159,1167,1130,1075,1047,965,943,958,971,949,884,866,876,822,704,719]        
                }

df = pd.DataFrame(Stock_Market,columns=['Year','Month','Interest_Rate','Unemployment_Rate','Stock_Index_Price'])

X = df[['Interest_Rate','Unemployment_Rate']]
Y = df['Stock_Index_Price']
 
# sklearn模型训练
regr = linear_model.LinearRegression()
regr.fit(X, Y)

print('Intercept: \n', regr.intercept_)
print('Coefficients: \n', regr.coef_)

# -------------------修改的预测部分开始-------------------
# 输入5组自变量
new_interest_rates = [2.75, 3, 4, 1, 2]
new_unemployment_rates = [5.3, 4, 3, 2, 1]
# 拼接为符合输入要求的二维数组，每行对应一组预测数据
new_X = [[i, u] for i, u in zip(new_interest_rates, new_unemployment_rates)]

# 输出5组预测结果
predicted_prices = regr.predict(new_X)
print("\nSklearn模型预测结果：")
for idx, price in enumerate(predicted_prices, 1):
    print(f"第{idx}组 利率={new_interest_rates[idx-1]} 失业率={new_unemployment_rates[idx-1]} 预测股指价格：{price:.2f}")
# -------------------修改的预测部分结束-------------------

# statsmodels模型训练
X_sm = sm.add_constant(X)
model = sm.OLS(Y, X_sm).fit()
predictions = model.predict(X_sm) 
print_model = model.summary()
print("\nStatsmodels模型报告：\n", print_model)

# （可选）Statsmodels模型多组预测
new_X_sm = sm.add_constant(new_X)
sm_predicted_prices = model.predict(new_X_sm)
print("\nStatsmodels模型预测结果：")
for idx, price in enumerate(sm_predicted_prices, 1):
    print(f"第{idx}组 利率={new_interest_rates[idx-1]} 失业率={new_unemployment_rates[idx-1]} 预测股指价格：{price:.2f}")

说明 #

• 核心修改逻辑是将原单组预测的标量输入替换为二维数组输入，predict方法支持传入多组数据批量输出预测结果
• 代码可直接在Jupyter Notebook中运行，输出会分别展示两种模型的5组预测结果
• 若不需要statsmodels的预测结果，删除对应可选部分即可

内容的提问来源于stack exchange，提问作者user2543