scikit-learn源码学习之datasets.samples_generator.make_blobs

在看sklearn聚类部分的时候碰到的，可以按照需求生成数据，官方源码地址
读代码顺带把注释和心得写了上去

def make_blobs(n_samples=100, n_features=2, centers=3, cluster_std=1.0,
               center_box=(-10.0, 10.0), shuffle=True, random_state=None):
    """Generate isotropic Gaussian blobs for clustering.

    Read more in the :ref:`User Guide <sample_generators>`.

    Parameters
    ----------
    n_samples : int, optional (default=100)
        The total number of points equally divided among clusters.

    n_features : int, optional (default=2)
        The number of features for each sample.

    centers : int or array of shape [n_centers, n_features], optional
        (default=3)
        The number of centers to generate, or the fixed center locations.

    cluster_std : float or sequence of floats, optional (default=1.0)
        The standard deviation of the clusters.

    center_box : pair of floats (min, max), optional (default=(-10.0, 10.0))
        The bounding box for each cluster center when centers are
        generated at random.

    shuffle : boolean, optional (default=True)
        Shuffle the samples.

    random_state : int, RandomState instance or None, optional (default=None)
        If int, random_state is the seed used by the random number generator;
        If RandomState instance, random_state is the random number generator;
        If None, the random number generator is the RandomState instance used
        by `np.random`.

    Returns
    -------
    X : array of shape [n_samples, n_features]
        The generated samples.

    y : array of shape [n_samples]
        The integer labels for cluster membership of each sample.

    Examples
    --------
    >>> from sklearn.datasets.samples_generator import make_blobs
    >>> X, y = make_blobs(n_samples=10, centers=3, n_features=2,
    ...                   random_state=0)
    >>> print(X.shape)
    (10, 2)
    >>> y
    array([0, 0, 1, 0, 2, 2, 2, 1, 1, 0])

    See also
    --------
    make_classification: a more intricate variant
    """

    #根据random_state生成随机数生成器
    generator = check_random_state(random_state)

    #判断centers对象的类型
    #如果是int就根据center_box的范围来随机生成中心点
    if isinstance(centers, numbers.Integral):
        #uniform表示均匀分布采样
        #范围是(center_box[0],center_box[1])
        #形状是centers*n_features的
        centers = generator.uniform(center_box[0], center_box[1],
                                    size=(centers, n_features))
    #把centers转化np.array类型 并得到n_features
    else:
        centers = check_array(centers)
        n_features = centers.shape[1]

    #如果cluster_std是一个实数，表示每个中心的标准差都是cluster_std
    if isinstance(cluster_std, numbers.Real):
        cluster_std = np.ones(len(centers)) * cluster_std

    #存放样本的返回值
    X = []
    y = []

    n_centers = centers.shape[0]
    #//运算符表示整数除法 平均每个中心的样本数
    n_samples_per_center = [int(n_samples // n_centers)] * n_centers

    #把余数依次摊在前几个中心里
    for i in range(n_samples % n_centers):
        n_samples_per_center[i] += 1

    #enumrate的返回值为index,value
    #zip可以把长度一样的多个序列打包在一起，遍历时下标一样的在一起
    for i, (n, std) in enumerate(zip(n_samples_per_center, cluster_std)):
        #normal表示正态分布
        #根据scale和size生成随机数 然后加在中心点上，让其波动~~
        #array类型相加的时候有一个性质如下
        #>>> np.array([1,2])+np.array([[3,4],[5,6]])
        # array([[4, 6],[6, 8]])
        X.append(centers[i] + generator.normal(scale=std,
                                               size=(n, n_features)))
        #标签连续
        y += [i] * n

    #concatenate这个函数就是把原来的不同组的数列合在一起 理解起来有些绕
    #>>> np.concatenate([[[1,2],[3,4]],
                # ... [[5,6],[7,8]],
                # ... [[9,10],[10,11]]])
    # array([[ 1,  2],
    #      [ 3,  4],
    #      [ 5,  6],
    #      [ 7,  8],
    #      [ 9, 10],
    #      [10, 11]])
    #其实如果把上面的X.append换成X.extend就能省略这步比较难懂的操作了
    X = np.concatenate(X)
    y = np.array(y)

    #打乱次序
    if shuffle:
        #获取下标
        indices = np.arange(n_samples)
        #打乱下标
        generator.shuffle(indices)
        X = X[indices]
        y = y[indices]

    return X, y

中文注释都是个人见解，如果有写的不到位的地方，欢迎大家评论区拍砖