Skip to content
TheChatArchiveThe Chat Archive
gpt-3.5-turbo-0613· OpenAIAi2 WildChat-4.8M (AI2)

练习:对训练集trainx,不考虑trainy;只利用numpy实现kmeans(cluster=N)这个class;然后利用kmeans对testx进行测试预测效果

  1. User

    练习:对训练集trainx,不考虑trainy;只利用numpy实现kmeans(cluster=N)这个class;然后利用kmeans对testx进行测试预测效果

  2. Assistant

    import numpy as np

    class KMeans: def init(self, cluster): self.cluster = cluster

    def fit(self, X):
        self.centroids = X[np.random.choice(X.shape[0], size=self.cluster, replace=False)]
        while True:
            distance = np.linalg.norm(X[:, np.newaxis, :] - self.centroids, axis=2)
            labels = np.argmin(distance, axis=1)
            new_centroids = np.array([X[labels == i].mean(axis=0) for i in range(self.cluster)])
            if np.all(new_centroids == self.centroids):
                break
            self.centroids = new_centroids
    
    def predict(self, X):
        distance = np.linalg.norm(X[:, np.newaxis, :] - self.centroids, axis=2)
        return np.argmin(distance, axis=1)
    

    生成训练数据

    trainx = np.random.random((100, 2))

    生成测试数据

    testx = np.random.random((20, 2))

    创建KMeans对象并进行训练

    kmeans = KMeans(cluster=3) kmeans.fit(trainx)

    对测试数据进行预测

    predictions = kmeans.predict(testx)

    print(predictions)

  3. User

    练习:对训练集trainx,不考虑trainy;只利用numpy实现kmeans(cluster=N,max_iter = k)这个class;然后利用kmeans对testx进行测试预测效果

  4. Assistant

    import numpy as np

    class KMeans: def init(self, cluster, max_iter): self.cluster = cluster self.max_iter = max_iter

    def fit(self, X):
        self.centroids = X[np.random.choice(X.shape[0], size=self.cluster, replace=False)]
        
        for i in range(self.max_iter):
            distance = np.linalg.norm(X[:, np.newaxis, :] - self.centroids, axis=2)
            labels = np.argmin(distance, axis=1)
            new_centroids = np.array([X[labels == j].mean(axis=0) for j in range(self.cluster)])
            if np.all(new_centroids == self.centroids):
                break
            self.centroids = new_centroids
    
    def predict(self, X):
        distance = np.linalg.norm(X[:, np.newaxis, :] - self.centroids, axis=2)
        return np.argmin(distance, axis=1)
    

    生成训练数据

    trainx = np.random.random((100, 2))

    生成测试数据

    testx = np.random.random((20, 2))

    创建KMeans对象并进行训练

    kmeans = KMeans(cluster=3, max_iter=100) kmeans.fit(trainx)

    对测试数据进行预测

    predictions = kmeans.predict(testx)

    print(predictions)

  5. User

    练习:对训练集trainx,不考虑trainy;只利用numpy实现kmeans(cluster=N)这个class;然后利用kmeans对testx进行测试预测效果,并对迭代次数和距离有限制

  6. Assistant

    import numpy as np

    class KMeans: def init(self, cluster, max_iter=100, tol=1e-4): self.cluster = cluster self.max_iter = max_iter self.tol = tol

    def fit(self, X):
        self.centroids = X[np.random.choice(X.shape[0], size=self.cluster, replace=False)]
        
        for _ in range(self.max_iter):
            distance = np.linalg.norm(X[:, np.newaxis, :] - self.centroids, axis=2)
            labels = np.argmin(distance, axis=1)
            new_centroids = np.array([X[labels == j].mean(axis=0) for j in range(self.cluster)])
            if np.linalg.norm(new_centroids - self.centroids) < self.tol:
                break
            self.centroids = new_centroids
    
    def predict(self, X):
        distance = np.linalg.norm(X[:, np.newaxis, :] - self.centroids, axis=2)
        return np.argmin(distance, axis=1)
    

    生成训练数据

    trainx = np.random.random((100, 2))

    生成测试数据

    testx = np.random.random((20, 2))

    创建KMeans对象并进行训练

    kmeans = KMeans(cluster=3, max_iter=100, tol=1e-4) kmeans.fit(trainx)

    对测试数据进行预测

    predictions = kmeans.predict(testx)

    print(predictions)

Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.