sklearn库--KNN示例

分类

from sklearn.neighbors import KNeighborsClassifier as Knn
# 鸢尾花数据集
from sklearn.datasets import load_iris
# 数据集切分
from sklearn.model_selection import train_test_split

# 加载数据集
X, y = load_iris(return_X_y=True)
# 训练集数据、测试集数据、训练集标签、测试集标签、   数据集分割为 80%训练 20%测试
X_train, X_test, y_train, y_test = train_test_split(X, y, train_size=0.2)

# 构建模型
sk_knn = Knn(n_neighbors=5)
# 训练模型
sk_knn.fit(X=X_train, y=y_train)
# 模型预测
y_pred = sk_knn.predict(X=X_test)
# print(y_pred)
# print(y_test)

# 准确率
acc = (y_pred == y_test).mean()
print(acc)

回归

from sklearn.neighbors import KNeighborsRegressor as Knn
# 数据集切分
from sklearn.model_selection import train_test_split
# 利福尼亚住房数据集
from sklearn.datasets import fetch_california_housing
# # # 波士顿房价预测数据
# from sklearn.datasets import load_boston

# 加载数据集
X, y = fetch_california_housing(return_X_y=True)
# 训练集数据、测试集数据、训练集标签、测试集标签、   数据集分割为 80%训练 20%测试
X_train, X_test, y_train, y_test = train_test_split(X, y, train_size=0.2)


# 构建模型
sk_knn = Knn(n_neighbors=5)
# 训练模型
sk_knn.fit(X=X_train, y=y_train)
# 模型预测
y_pred = sk_knn.predict(X=X_test)
# print(y_pred)
# print(y_test)


# 准确率 np格式 使用.mean()求均值  列表不可以
mse = ((y_pred - y_test) ** 2).mean()
print(mse)