sklearn常用功能使用

from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.neighbors import KNeighborsClassifier
from sklearn.metrics import accuracy_score



# 获取各种数据集
iris = datasets.load_iris()
iris_X = iris.data
iris_y = iris.target

# 自己生成数据集
x, y = datasets.make_classification(n_samples=30,n_features=4,n_classes=3,n_clusters_per_class=1)


print(x[:2, :])
print(y)

#生成测试集和训练集
x_train,x_test,y_train,y_test = train_test_split(x,y,test_size=0.3)
# print(y_train)

# 定义分类器
knn = KNeighborsClassifier()
# 训练
knn.fit(x_train,y_train)
# 预测
print(knn.predict(x_test))
print(y_test)
# 计算评估信息，此处选取acc
print(accuracy_score(y_test,knn.predict(x_test)))