matplotlib sklearn数据降维可视化

matplotlib sklearn数据降维可视化

使用说明具体见官方的文档
https://scikit-learn.org/stable/modules/generated/sklearn.manifold.TSNE.html

这里挑选了一个简单的例子来重构成了一个方便调用的接口

%matplotlib inline

# Author: Jake Vanderplas -- 

print(__doc__)

from time import time

import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
from matplotlib.ticker import NullFormatter

from sklearn import manifold, datasets

# Next line to silence pyflakes. This import is needed.
Axes3D


def Comparison_of_Manifold_Learning_methods(X, color, n_neighbors=10):
    """
    改写了官网的案例，接受高维数据X和其对应的color来进行流形降维
    https://scikit-learn.org/stable/auto_examples/manifold/plot_compare_methods.html#sphx-glr-auto-examples-manifold-plot-compare-methods-py
    n_components : int, optional (must be: 2)
    Dimension of the embedded space.
    """
    n_points = len(X)
    n_neighbors = 10
    n_components = 2

    fig = plt.figure(figsize=(15, 8))
    plt.suptitle("Manifold Learning with %i points, %i neighbors"
                 % (n_points, n_neighbors), fontsize=14)

    if X[0].size == 3:
        ax = fig.add_subplot(251, projection='3d')
        ax.scatter(X[:, 0], X[:, 1], X[:, 2], c=color, cmap=plt.cm.Spectral)
        ax.view_init(4, -72)

    methods = ['standard', 'ltsa', 'hessian', 'modified']
    labels = ['LLE', 'LTSA', 'Hessian LLE', 'Modified LLE']

    for i, method in enumerate(methods):
        t0 = time()
        Y = manifold.LocallyLinearEmbedding(n_neighbors, n_components,
                                            eigen_solver='auto',
                                            method=method).fit_transform(X)
        t1 = time()
        print("%s: %.2g sec" % (methods[i], t1 - t0))

        ax = fig.add_subplot(252 + i)
        plt.scatter(Y[:, 0], Y[:, 1], c=color, cmap=plt.cm.Spectral)
        plt.title("%s (%.2g sec)" % (labels[i], t1 - t0))
        ax.xaxis.set_major_formatter(NullFormatter())
        ax.yaxis.set_major_formatter(NullFormatter())
        plt.axis('tight')

    t0 = time()
    Y = manifold.Isomap(n_neighbors, n_components).fit_transform(X)
    t1 = time()
    print("Isomap: %.2g sec" % (t1 - t0))
    ax = fig.add_subplot(257)
    plt.scatter(Y[:, 0], Y[:, 1], c=color, cmap=plt.cm.Spectral)
    plt.title("Isomap (%.2g sec)" % (t1 - t0))
    ax.xaxis.set_major_formatter(NullFormatter())
    ax.yaxis.set_major_formatter(NullFormatter())
    plt.axis('tight')

    t0 = time()
    mds = manifold.MDS(n_components, max_iter=100, n_init=1)
    Y = mds.fit_transform(X)
    t1 = time()
    print("MDS: %.2g sec" % (t1 - t0))
    ax = fig.add_subplot(258)
    plt.scatter(Y[:, 0], Y[:, 1], c=color, cmap=plt.cm.Spectral)
    plt.title("MDS (%.2g sec)" % (t1 - t0))
    ax.xaxis.set_major_formatter(NullFormatter())
    ax.yaxis.set_major_formatter(NullFormatter())
    plt.axis('tight')

    t0 = time()
    se = manifold.SpectralEmbedding(n_components=n_components,
                                    n_neighbors=n_neighbors)
    Y = se.fit_transform(X)
    t1 = time()
    print("SpectralEmbedding: %.2g sec" % (t1 - t0))
    ax = fig.add_subplot(259)
    plt.scatter(Y[:, 0], Y[:, 1], c=color, cmap=plt.cm.Spectral)
    plt.title("SpectralEmbedding (%.2g sec)" % (t1 - t0))
    ax.xaxis.set_major_formatter(NullFormatter())
    ax.yaxis.set_major_formatter(NullFormatter())
    plt.axis('tight')

    t0 = time()
    tsne = manifold.TSNE(n_components=n_components, init='pca', random_state=0)
    Y = tsne.fit_transform(X)
    t1 = time()
    print("t-SNE: %.2g sec" % (t1 - t0))
    ax = fig.add_subplot(2, 5, 10)
    plt.scatter(Y[:, 0], Y[:, 1], c=color, cmap=plt.cm.Spectral)
    plt.title("t-SNE (%.2g sec)" % (t1 - t0))
    ax.xaxis.set_major_formatter(NullFormatter())
    ax.yaxis.set_major_formatter(NullFormatter())
    plt.axis('tight')

    plt.show()

Automatically created module for IPython interactive environment

使用方法

n_points = 1000
X, color = datasets.samples_generator.make_s_curve(n_points, random_state=0)

Comparison_of_Manifold_Learning_methods(X, color)

standard: 0.16 sec
ltsa: 0.27 sec
hessian: 0.31 sec
modified: 0.23 sec
Isomap: 0.5 sec
MDS: 4.1 sec
SpectralEmbedding: 0.08 sec
t-SNE: 22 sec