iris练习

iris练习

from sklearn.datasets import load_iris
iris_data=load_iris()
# print("keys:\n{}".format(iris_data.keys())) #data是一个（150,4)形状的数组，target是每组数据被分成的类别，target_name表示具体每个类别的名字
# print("data:\n{}".format(iris_data['data'][:5]))
# print("target:\n{}".format(iris_data['target']))
from sklearn.model_selection import  train_test_split
X_train,X_test,y_train,y_test=train_test_split(iris_data['data'],iris_data['target'],random_state=1)
#train_test_split利用伪随机数生成器将数据集打乱（因为target按照顺序排放），确保测试集包含所有类别的数据，
print(X_train.shape)
print(y_train.shape)
from sklearn.neighbors import KNeighborsClassifier
knn=KNeighborsClassifier(n_neighbors=1)
knn.fit(X_train,y_train)
print(knn.predict(X_test))
print(y_test)
print('test set score:{:.2f}'.format(knn.score(X_test,y_test)))