朴素贝叶斯特征探索

from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.naive_bayes import GaussianNB
X, y = load_iris(return_X_y=True)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.5, random_state=0)
gnb = GaussianNB()
gnb.fit(X_train, y_train)
print(gnb.score(X_test,y_test))
#高斯分布就是正态分布，用于分类问题
import sklearn.datasets as datasets
iris=datasets.load_iris()
X=iris['data']
y=iris['target']
from sklearn.model_selection import train_test_split
X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.2)
import matplotlib.pyplot as plt
plt.hist(X[:,0],bins=20)#第1维特征
plt.hist(X[:,0])

plt.hist(X[:,1],bins=20)#第2维特征
plt.hist(X[:,1])

plt.hist(X[:,2],bins=20)#第3维特征
plt.hist(X[:,2])

plt.hist(X[:,-1],bins=20)#第4维特征
plt.hist(X[:,-1])
from sklearn.naive_bayes import GaussianNB
gnb=GaussianNB()
gnb.fit(X_train,y_train)
print(gnb.score(X_test,y_test))