Book a Demo!
CoCalc Logo Icon
StoreFeaturesDocsShareSupportNewsAboutPoliciesSign UpSign In
Download

📚 The CoCalc Library - books, templates and other resources

132928 views
License: OTHER
Tweet
Share
Share
1
import matplotlib.pyplot as plt

2
import numpy as np

3
from sklearn.datasets import make_blobs

4
from sklearn.cluster import AgglomerativeClustering

5
from sklearn.neighbors import KernelDensity

6


7


8
def plot_agglomerative_algorithm():

9
    # generate synthetic two-dimensional data

10
    X, y = make_blobs(random_state=0, n_samples=12)

11


12
    agg = AgglomerativeClustering(n_clusters=X.shape[0], compute_full_tree=True).fit(X)

13


14
    fig, axes = plt.subplots(X.shape[0] // 5, 5, subplot_kw={'xticks': (),

15
                                                             'yticks': ()},

16
                             figsize=(20, 8))

17


18
    eps = X.std() / 2

19


20
    x_min, x_max = X[:, 0].min() - eps, X[:, 0].max() + eps

21
    y_min, y_max = X[:, 1].min() - eps, X[:, 1].max() + eps

22


23
    xx, yy = np.meshgrid(np.linspace(x_min, x_max, 100), np.linspace(y_min, y_max, 100))

24
    gridpoints = np.c_[xx.ravel().reshape(-1, 1), yy.ravel().reshape(-1, 1)]

25


26
    for i, ax in enumerate(axes.ravel()):

27
        ax.set_xlim(x_min, x_max)

28
        ax.set_ylim(y_min, y_max)

29
        agg.n_clusters = X.shape[0] - i

30
        agg.fit(X)

31
        ax.set_title("Step %d" % i)

32
        ax.scatter(X[:, 0], X[:, 1], s=60, c='grey')

33
        bins = np.bincount(agg.labels_)

34
        for cluster in range(agg.n_clusters):

35
            if bins[cluster] > 1:

36
                points = X[agg.labels_ == cluster]

37
                other_points = X[agg.labels_ != cluster]

38


39
                kde = KernelDensity(bandwidth=.5).fit(points)

40
                scores = kde.score_samples(gridpoints)

41
                score_inside = np.min(kde.score_samples(points))

42
                score_outside = np.max(kde.score_samples(other_points))

43
                levels = .8 * score_inside + .2 * score_outside

44
                ax.contour(xx, yy, scores.reshape(100, 100), levels=[levels],

45
                           colors='k', linestyles='solid', linewidths=2)

46


47
    axes[0, 0].set_title("Initialization")

48


49


50
def plot_agglomerative():

51
    X, y = make_blobs(random_state=0, n_samples=12)

52
    agg = AgglomerativeClustering(n_clusters=3)

53


54
    eps = X.std() / 2.

55


56
    x_min, x_max = X[:, 0].min() - eps, X[:, 0].max() + eps

57
    y_min, y_max = X[:, 1].min() - eps, X[:, 1].max() + eps

58


59
    xx, yy = np.meshgrid(np.linspace(x_min, x_max, 100), np.linspace(y_min, y_max, 100))

60
    gridpoints = np.c_[xx.ravel().reshape(-1, 1), yy.ravel().reshape(-1, 1)]

61


62
    ax = plt.gca()

63
    for i, x in enumerate(X):

64
        ax.text(x[0] + .1, x[1], "%d" % i, horizontalalignment='left', verticalalignment='center')

65


66
    ax.scatter(X[:, 0], X[:, 1], s=60, c='grey')

67
    ax.set_xticks(())

68
    ax.set_yticks(())

69


70
    for i in range(11):

71
        agg.n_clusters = X.shape[0] - i

72
        agg.fit(X)

73


74
        bins = np.bincount(agg.labels_)

75
        for cluster in range(agg.n_clusters):

76
            if bins[cluster] > 1:

77
                points = X[agg.labels_ == cluster]

78
                other_points = X[agg.labels_ != cluster]

79


80
                kde = KernelDensity(bandwidth=.5).fit(points)

81
                scores = kde.score_samples(gridpoints)

82
                score_inside = np.min(kde.score_samples(points))

83
                score_outside = np.max(kde.score_samples(other_points))

84
                levels = .8 * score_inside + .2 * score_outside

85
                ax.contour(xx, yy, scores.reshape(100, 100), levels=[levels],

86
                           colors='k', linestyles='solid', linewidths=1)

87


88
    ax.set_xlim(x_min, x_max)

89
    ax.set_ylim(y_min, y_max)

90


91