朴素贝叶斯代码实现+鸢尾花数据集

import numpy as np import pandas as pd from sklearn.model_selection import train_test_split from sklearn.naive_bayes import GaussianNB, BernoulliNB, MultinomialNB from sklearn.preprocessing import LabelEncoder from sklearn.metrics import accuracy_score data = pd.read_csv('iris.data', header=None) # 获取X、Y值 X = data.iloc[:, :-1] Y = data.iloc[:, -1] # 预处理 # 标签值转为数字 label = LabelEncoder() Y = label.fit_transform(Y) # 划分数据集 x_train, x_test, y_train, y_test = train_test_split(X, Y, test_size=0.2, random_state=10) # 创建模型 gaussian = GaussianNB() # 高斯朴素贝叶斯 bernoull = BernoulliNB() # 伯努利朴素贝叶斯 multin = MultinomialNB() # 多项式朴素贝叶斯 lis = [gaussian, bernoull, multin] train_score = [] test_score = [] for model in lis: model.fit(x_train, y_train) train_score.append(model.score(x_train, y_train)) # 训练集评分 test_score.append(model.score(x_test, y_test)) # 测试集评分 # 精确度 model.score(x_train, y_train) y_hat = model.predict(x_train) print(train_score) print(test_score)