>>>fromsklearnimportdatasets
>>>iris=datasets.load_iris()
>>>iris.feature_names#四个特征的名字
['sepallength(cm)','sepalwidth(cm)','petallength(cm)','petalwidth(cm)']
>>>iris.data
array([[5.1,3.5,1.4,0.2],
[4.9,3.,1.4,0.2],
[4.7,3.2,1.3,0.2],
[4.6,3.1,1.5,0.2],
[5.,3.6,1.4,0.2],
[5.4,3.9,1.7,0.4],
[4.6,3.4,1.4,0.3],
[5.,3.4,1.5,0.2],
......
[6.5,3.,5.2,2.],
[6.2,3.4,5.4,2.3],
[5.9,3.,5.1,1.8]])#类型是numpy.array
>>>iris.data.size
600#共600/4=150个样本
>>>iris.target_names
array(['setosa','versicolor','virginica'],
dtype='|S10')
>>>iris.target
array([0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,.....,0,1,1,1,1,1,1,1,1,1,1,
1,1,1,1,1,......,2,2,2,2,2,2,2,2,2,2,2,2])
>>>iris.target.size
150
>>>fromsklearn.naive_bayesimportGaussianNB
>>>clf=GaussianNB()
>>>clf.fit(iris.data,iris.target)
>>>clf.predict(iris.data[0])
array([0])#预测正确
>>>clf.predict(iris.data[149])
array([2])#预测正确
>>>data=numpy.array([6,4,6,2])
>>>clf.predict(data)
array([2])#预测结果很合理