切断球体上的流形学习方法#

将不同的流形学习技术应用于球形数据集。在这里，我们可以看到降维的使用，以便对流形学习方法获得一些直觉。关于数据集，球体的极点被切除，以及沿着其侧面的一薄片。这使得流形学习技术能够在将其投影到二维空间时“将其展开”。

有关将这些方法应用于 S 曲线数据集的类似示例，请参见流形学习方法的比较

请注意，MDS 的目的是找到数据的低维表示（这里为 2D），其中距离很好地反映了原始高维空间中的距离，与其他流形学习算法不同，它不寻求数据的低维空间的各向同性表示。这里，流形问题相当符合用地图投影来表示地球的平面地图。

Manifold Learning with 1000 points, 10 neighbors, LLE (0.058 sec), LTSA (0.1 sec), Hessian LLE (0.17 sec), Modified LLE (0.12 sec), Isomap (0.2 sec), MDS (0.76 sec), Spectral Embedding (0.046 sec), t-SNE (3.9 sec)

standard: 0.058 sec
ltsa: 0.1 sec
hessian: 0.17 sec
modified: 0.12 sec
ISO: 0.2 sec
MDS: 0.76 sec
Spectral Embedding: 0.046 sec
t-SNE: 3.9 sec

# Author: Jaques Grobler <[email protected]>
# License: BSD 3 clause

from time import time

import matplotlib.pyplot as plt

# Unused but required import for doing 3d projections with matplotlib < 3.2
import mpl_toolkits.mplot3d  # noqa: F401
import numpy as np
from matplotlib.ticker import NullFormatter

from sklearn import manifold
from sklearn.utils import check_random_state

# Variables for manifold learning.
n_neighbors = 10
n_samples = 1000

# Create our sphere.
random_state = check_random_state(0)
p = random_state.rand(n_samples) * (2 * np.pi - 0.55)
t = random_state.rand(n_samples) * np.pi

# Sever the poles from the sphere.
indices = (t < (np.pi - (np.pi / 8))) & (t > ((np.pi / 8)))
colors = p[indices]
x, y, z = (
    np.sin(t[indices]) * np.cos(p[indices]),
    np.sin(t[indices]) * np.sin(p[indices]),
    np.cos(t[indices]),
)

# Plot our dataset.
fig = plt.figure(figsize=(15, 8))
plt.suptitle(
    "Manifold Learning with %i points, %i neighbors" % (1000, n_neighbors), fontsize=14
)

ax = fig.add_subplot(251, projection="3d")
ax.scatter(x, y, z, c=p[indices], cmap=plt.cm.rainbow)
ax.view_init(40, -10)

sphere_data = np.array([x, y, z]).T

# Perform Locally Linear Embedding Manifold learning
methods = ["standard", "ltsa", "hessian", "modified"]
labels = ["LLE", "LTSA", "Hessian LLE", "Modified LLE"]

for i, method in enumerate(methods):
    t0 = time()
    trans_data = (
        manifold.LocallyLinearEmbedding(
            n_neighbors=n_neighbors, n_components=2, method=method, random_state=42
        )
        .fit_transform(sphere_data)
        .T
    )
    t1 = time()
    print("%s: %.2g sec" % (methods[i], t1 - t0))

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

# Perform Isomap Manifold learning.
t0 = time()
trans_data = (
    manifold.Isomap(n_neighbors=n_neighbors, n_components=2)
    .fit_transform(sphere_data)
    .T
)
t1 = time()
print("%s: %.2g sec" % ("ISO", t1 - t0))

ax = fig.add_subplot(257)
plt.scatter(trans_data[0], trans_data[1], c=colors, cmap=plt.cm.rainbow)
plt.title("%s (%.2g sec)" % ("Isomap", t1 - t0))
ax.xaxis.set_major_formatter(NullFormatter())
ax.yaxis.set_major_formatter(NullFormatter())
plt.axis("tight")

# Perform Multi-dimensional scaling.
t0 = time()
mds = manifold.MDS(2, max_iter=100, n_init=1, random_state=42)
trans_data = mds.fit_transform(sphere_data).T
t1 = time()
print("MDS: %.2g sec" % (t1 - t0))

ax = fig.add_subplot(258)
plt.scatter(trans_data[0], trans_data[1], c=colors, cmap=plt.cm.rainbow)
plt.title("MDS (%.2g sec)" % (t1 - t0))
ax.xaxis.set_major_formatter(NullFormatter())
ax.yaxis.set_major_formatter(NullFormatter())
plt.axis("tight")

# Perform Spectral Embedding.
t0 = time()
se = manifold.SpectralEmbedding(
    n_components=2, n_neighbors=n_neighbors, random_state=42
)
trans_data = se.fit_transform(sphere_data).T
t1 = time()
print("Spectral Embedding: %.2g sec" % (t1 - t0))

ax = fig.add_subplot(259)
plt.scatter(trans_data[0], trans_data[1], c=colors, cmap=plt.cm.rainbow)
plt.title("Spectral Embedding (%.2g sec)" % (t1 - t0))
ax.xaxis.set_major_formatter(NullFormatter())
ax.yaxis.set_major_formatter(NullFormatter())
plt.axis("tight")

# Perform t-distributed stochastic neighbor embedding.
t0 = time()
tsne = manifold.TSNE(n_components=2, random_state=0)
trans_data = tsne.fit_transform(sphere_data).T
t1 = time()
print("t-SNE: %.2g sec" % (t1 - t0))

ax = fig.add_subplot(2, 5, 10)
plt.scatter(trans_data[0], trans_data[1], c=colors, cmap=plt.cm.rainbow)
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()

脚本总运行时间：（0 分钟 5.977 秒）