Python人工智能机器学习二手车价格预测 pearson相关系数热力图绘制

import numpy as np import pandas as pd from matplotlib import pyplot as plt data = pd.read_csv("二手车价格数据集.csv") data["engine"] = data["engine"].apply(lambda x: int(x[:-3])) x = data.iloc[:, 1:] x = pd.get_dummies(x) # pearson corr = x.corr(method='pearson') # heatmap import seaborn as sns plt.figure(figsize=(20, 20)) sns.heatmap(corr, annot=True, cmap='RdYlGn', linewidths=0.2) plt.savefig('corr.png') plt.show() columns = x.columns y = pd.DataFrame(data.iloc[:, 0]) # standardization from sklearn.preprocessing import StandardScaler ss_x = StandardScaler() x = ss_x.fit_transform(x) ss_y = StandardScaler() y = ss_y.fit_transform(y) # split data from sklearn.model_selection import train_test_split x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2) from sklearn.linear_model import LinearRegression lr = LinearRegression() lr.fit(x_train, y_train) y_pred = lr.predict(x_test) importance = lr.coef_[0] result = pd.DataFrame([columns, importance]).T result.to_csv("result.csv", index=False) from sklearn.metrics import mean_squared_error, r2_score, mean_absolute_error print("均方误差MSE(mean_squared_error):", mean_squared_error(y_test, y_pred)) print("跟均方误差RMSE(root mean_squared_error):", np.sqrt(mean_squared_error(y_test, y_pred))) print("平均绝对值误差MAE(mean_absolute_error):", mean_absolute_error(y_test, y_pred)) print("训练集R^2:", r2_score(y_train, lr.predict(x_train))) print("测试集R^2:", r2_score(y_test, y_pred)) print("训练集R^2:", lr.score(x_train, y_train)) print("测试集R^2:", lr.score(x_test, y_test))