import pandas as pd
-from sklearn.model_selection import train_test_split
-
-data = pd.DataFrame({'年龄': ['<=30', '<=30', '31-40', '>40', '>40', '>40', '31-40', '<=30', '<=30', '>40', '<=30', '31-40', '31-40', '>40'],
- '收入': ['高', '高', '高', '中', '低', '低', '低', '中', '低', '中', '中', '中', '高', '中'],
- '是否为学生': ['否', '否', '否', '否', '是', '是', '是', '否', '是', '是', '是', '否', '是', '否'],
- '信誉': ['中', '优', '中', '中', '中', '优', '优', '中', '中', '中', '优', '优', '中', '优'],
- '购买计算机': ['否', '否', '是', '是', '是', '否', '是', '否', '是', '是', '是', '是', '是', '否']})
-
-X = data.drop('购买计算机', axis=1)
-y = data['购买计算机']
-
-X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.5, random_state=33)
-from sklearn.compose import ColumnTransformer
-from sklearn.preprocessing import OneHotEncoder, LabelEncoder
-
-# 对类别特征进行编码
-cat_features = ['年龄', '收入', '是否为学生', '信誉']
-ct = ColumnTransformer([('one_hot_encoder', OneHotEncoder(), cat_features)],
- remainder='passthrough')
-
-X_train_encoded = ct.fit_transform(X_train)
-X_test_encoded = ct.transform(X_test)
-from sklearn.naive_bayes import GaussianNB
-
-gnb = GaussianNB()
-gnb.fit(X_train_encoded, y_train)
-from sklearn.metrics import accuracy_score
-
-y_pred = gnb.predict(X_test_encoded)
-print('预测结果：', y_pred)
-print('实际结果：', y_test.values)
-print('模型得分：', accuracy_score(y_test, y_pred))
-
-