import pandas as pd import numpy as np from sklearn.metrics import r2_score from sklearn import metrics from math import sqrt features = pd.read_csv('/Users/mac/Desktop/111.csv', encoding='gbk') print('The shape of our features is:', features.shape) # one-hot 編碼 features = pd.get_dummies(features) labels = np.array(features['price']) # 數據 features = features.drop('price', axis=1) # 轉變成列表 feature_list = list(features.columns) # 轉變成np.array格式 features = np.array(features) # 訓練集與測試集劃分 from sklearn.model_selection import train_test_split train_features, test_features, train_labels, test_labels = train_test_split(features, labels, test_size=0.25,random_state=0) from sklearn import linear_model reg=linear_model.LinearRegression() reg.fit(train_features,train_labels) predictions =reg.predict(test_features) # 計算絕對誤差，abs為生成絕對值 errors = abs(predictions - test_labels) #alen為標簽的個數 n = np.alen(test_labels) # 計算 平均絕對百分誤差mean absolute percentage error (MAPE) #round對指定位數值進行四舍五入 MAPE = np.sum(errors / test_labels) / n print('Mean Absolute Percentage Error:', round(MAPE, 2)) #計算R2 R2=r2_score(test_labels, predictions) print('R2:',round(R2,2)) #計算模型準確率 mape = np.mean(100*(errors/test_labels)) accuracy = 100 - np.mean(mape) print('Accuracy:', round(accuracy, 2), '%.') import matplotlib.pyplot as plt #plt.rcParams['font.sans-serif'] = [u'SimHei'] plt.rcParams['axes.unicode_minus'] = False #設置圖片長寬比 plt.rcParams['figure.figsize']=(20.0,4.0) #設置圖片像素 plt.rcParams['savefig.dpi']=600 acture_price = test_labels # 實際值數據 reg_Pricing_price = predictions # 預測值數據 plt.plot(acture_price, color="r", label="acture_price") # 顏色表示 plt.plot(reg_Pricing_price, color='b', label="HP_Pricing_price") plt.xlabel("sample") # x軸命名表示 plt.ylabel("price") # y軸命名表示 plt.title("Actual Price vs Pricing Price") plt.legend() # 增加圖例 plt.show() # 顯示圖

總結

以上是生活随笔為你收集整理的线性回归预测的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。