python多元线性回归房价预测_附代码和数据

from sklearn.model_selection import KFold from sklearn.tree import DecisionTreeRegressor from sklearn.metrics import make_scorer from sklearn.model_selection import GridSearchCV # 利用GridSearchCV计算最优解 def fit_model(X, y): """ 基于输入数据 [X,y]，利于网格搜索找到最优的决策树模型"""  cross_validator = KFold(10, shuffle=True)
    regressor = DecisionTreeRegressor()
    params = {'max_depth': [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]}
    scoring_fnc = make_scorer(performance_metric)
    grid = GridSearchCV(estimator=regressor, param_grid=params, scoring=scoring_fnc, cv=cross_validator) # 基于输入数据 [X,y]，进行网格搜索  grid = grid.fit(X, y) #     print pd.DataFrame(grid.cv_results_)  return grid.best_estimator_ # 计算R2分数 def performance_metric(y_true, y_predict): """计算并返回预测值相比于预测值的分数"""  from sklearn.metrics import r2_score
    score = r2_score(y_true, y_predict) return score ######################################################调参优化模型 #########################可视化模型学习曲线，观察是否出现过拟合问题  import visuals as vs # 分析模型 vs.ModelLearning(features_train, prices_train)
vs.ModelComplexity(features_train, prices_train)
optimal_reg1 = fit_model(features_train, prices_train) # 输出最优模型的 'max_depth' 参数 print("最理想模型的参数'max_depth'是{} 。".format(optimal_reg1.get_params()['max_depth']))
predicted_value = optimal_reg1.predict(features_test)
r2 = performance_metric(prices_test, predicted_value) print("最优模型在测试数据上R^2分数{:,.2f}。".format(r2))