Python机器学习预测汽车价格源码

import numpy as np import pandas as pd import matplotlib.pyplot as plt import seaborn as sns from sklearn.model_selection import train_test_split from sklearn.tree import DecisionTreeRegressor print('\n\n') data = pd.read_csv("CarPrice.csv") print(data.head()) print('\n\n') # 检查空值 print(data.isnull().sum()) print('\n\n') # 数据信息 print(data.info()) print('\n\n') # 数据描述 print(data.describe()) print('\n\n') # 去重 print(data.CarName.unique()) print('\n\n') # 设置样式 sns.set_style("whitegrid") plt.figure(figsize=(10, 5)) sns.distplot(data.price) # 显示 # plt.show() print('\n\n') # 相关性 print(data.corr()) print('\n\n') plt.figure(figsize=(10, 5)) correlations = data.corr() # 设置样式 sns.heatmap(correlations, cmap="coolwarm", annot=True) # 显示 # plt.show() # 预测项 predict = "price" # 原始数据 data = data[["symboling", "wheelbase", "carlength", "carwidth", "carheight", "curbweight", "enginesize", "boreratio", "stroke", "compressionratio", "horsepower", "peakrpm", "citympg", "highwaympg", "price"]] # 变量 x = np.array(data.drop([predict], 1)) # 结果 y = np.array(data[predict]) # 分配数据集 xtrain, xtest, ytrain, ytest = train_test_split(x, y, test_size=0.2) # 决策树回归算法 model = DecisionTreeRegressor() # 训练模型 model.fit(xtrain, ytrain) # 模型预测 predictions = model.predict(xtest) # 准确性指标 print(model.score(xtest, predictions))