Python使用网格搜索与交叉验证的决策树算法实现波士顿房价预测（附波士顿房价数据集）.pdfVIP

Python使⽤⽹格搜索与交叉验证的决策树算法实现波⼠顿房价预测（附波⼠顿 房价数据集） 第⼀步：导⼊数据 #载⼊此项⽬所需要的库 import numpy as np import pandas as pd import visuals as vs # Supplementary code #检查你的Python版本 #from sys import version_info #if version_info.major !=3 and version_info.minor != 7: #raise Exception(请使⽤Python 3.7来完成此项⽬) %matplotlib inline #载⼊波⼠顿房屋的数据集 data = pd.read_csv(housing.csv) prices = data[MEDV] features = data.drop(MEDV, axis = 1) print(Boston housing dataset has {} datapoints with {} variables each. .format(*data.shape)) 第⼆步：分析数据 # ⽬标：计算价值的最⼩值 minimum_price = prices.min() print (minimum_price) # ⽬标：计算价值的最⼤值 maximum_price =prices.max() # ⽬标：计算价值的平均值 mean_price = prices.mean() # ⽬标：计算价值的中值 median_price = prices.median() # ⽬标：计算价值的标准差 std_price = prices.std() # ⽬标：输出计算的结果 print (Statistics for Boston housing dataset:\n) print (Minimum price: ${:,.2f}.format(minimum_price)) print (Maximum price: ${:,.2f}.format(maximum_price)) print (Mean price: ${:,.2f}.format(mean_price)) print (Median price ${:,.2f}.format(median_price)) print (Standard deviation of prices: ${:,.2f}.format(std_price)) 第三步：模型衡量标准 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 def performance_metric2(y_true, y_predict): 计算并返回预测值相⽐于预测值的分数 import numpy as np import math y_true_mean = np.mean(y_true) y_predict_mean = np.mean(y_predict) SSR = 0 varX = 0 varY = 0 for i in range(0, len(y_true)): #多少实例 diffxxBar = y_true[i] - y_true_mean diffyyBar = y_predict[i] - y_predict_mean SSR += (diffxxBar * diffyyBar) varX += diffxxBar ** 2 # 求平⽅然后累计起来 varY += diffyyBar ** 2 # 求平⽅然后累计起来 SST = math.sqrt(varX * varY) score = SSR/SST return score 第四步：分析模型的表现（偏差⽅差） #根据不同的训练集⼤⼩，和最⼤深度，⽣成学习曲线 vs.ModelLearning(X_train, y_train) # 根据不同的最⼤深度参数，⽣成复杂度曲线 vs.ModelComp