Carseats数据集决策树分类

import pandas as pd
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
carseats = pd.read_csv('https://liangdaima.com/static/data/statistics/Carseats.csv')
carseats['High'] = (carseats['Sales'] > 8).astype(int)
carseats['ShelveLoc'] = carseats['ShelveLoc'].map({'Bad': 0, 'Medium': 1, 'Good': 2})
carseats['Urban'] = (carseats['Urban'] == 'Yes').astype(int)
carseats['US'] = (carseats['US'] == 'Yes').astype(int)
X = carseats.drop(['Sales', 'High'], axis=1)
y = carseats['High']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=1)
tree = DecisionTreeClassifier(random_state=1)
tree.fit(X_train, y_train)
print('决策树测试准确率:', accuracy_score(y_test, tree.predict(X_test)))