#%%庫函數(shù)導(dǎo)入
import warnings
warnings.filterwarnings('ignore')
import numpy as np
# 加載鶯尾花數(shù)據(jù)集
from sklearn import datasets
# 導(dǎo)入高斯樸素貝葉斯分類器
from sklearn.naive_bayes import GaussianNB
from sklearn.model_selection import train_test_split
#%%數(shù)據(jù)導(dǎo)入&分析
X, y = datasets.load_iris(return_X_y=True)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0)
#%%查看數(shù)據(jù)集
print(X)#特征集
print(y)#現(xiàn)象
#%%模型訓(xùn)練
# 假設(shè)每個特征都服正態(tài)分布，使用高斯樸素貝葉斯進(jìn)行計(jì)算
clf = GaussianNB(var_smoothing=1e-8)
clf.fit(X_train, y_train)
#%%模型預(yù)測
# 評估
y_pred = clf.predict(X_test)
acc = np.sum(y_test == y_pred) / X_test.shape[0]
print("Test Acc : %.3f" % acc)

# 預(yù)測
#對第一行數(shù)據(jù)預(yù)測
y_proba = clf.predict_proba(X_test[:1])
#使用predict()函數(shù)得到預(yù)測結(jié)果
print(clf.predict(X_test[:1]))
#輸出預(yù)測每個標(biāo)簽的概率，預(yù)測標(biāo)簽為0，1，2的概率分別為數(shù)組的三個值
print("預(yù)計(jì)的概率值:", y_proba)