[ML]차원축소
Author : tmlab / Date : 2017. 12. 29. 19:10 / Category : Analytics
In [49]:
from sklearn.datasets import make_swiss_roll
X, t = make_swiss_roll(n_samples=1000, noise=0.2, random_state=42)
axes = [-11.5, 14, -2, 23, -12, 15]
fig = plt.figure(figsize=(6, 5))
ax = fig.add_subplot(111, projection='3d')
ax.scatter(X[:, 0], X[:, 1], X[:, 2], c=t, cmap=plt.cm.hot)
ax.view_init(10, -70)
ax.set_xlabel("$x_1$", fontsize=18)
ax.set_ylabel("$x_2$", fontsize=18)
ax.set_zlabel("$x_3$", fontsize=18)
ax.set_xlim(axes[0:2])
ax.set_ylim(axes[2:4])
ax.set_zlim(axes[4:6])
plt.show()
In [51]:
plt.figure(figsize=(11, 4))
plt.subplot(121)
plt.scatter(X[:, 0], X[:, 1], c=t, cmap=plt.cm.hot)
plt.axis(axes[:4])
plt.xlabel("$x_1$", fontsize=18)
plt.ylabel("$x_2$", fontsize=18, rotation=0)
plt.grid(True)
plt.subplot(122)
plt.scatter(t, X[:, 1], c=t, cmap=plt.cm.hot)
plt.axis([4, 15, axes[2], axes[3]])
plt.xlabel("$z_1$", fontsize=18)
plt.grid(True)
plt.show()
In [6]:
import numpy as np
import pandas as pd
In [8]:
v = np.random.randn(10,40)
d = pd.DataFrame(v)
d.head()
Out[8]:
In [11]:
from sklearn.decomposition import PCA
pca = PCA(n_components = 2)
X2D = pca.fit_transform(d)
X2D
Out[11]:
In [12]:
print(pca.explained_variance_ratio_)
In [19]:
pca = PCA() #주성분 개수 지정하지 않고 클래스생성
pca.fit(v) #주성분 분석
cumsum = np.cumsum(pca.explained_variance_ratio_) #분산의 설명량을 누적합
num_d = np.argmax(cumsum >= 0.95) + 1 # 분산의 설명량이 95%이상 되는 차원의 수
In [20]:
num_d
Out[20]:
In [16]:
pca = PCA(n_components=0.95) #95%이상의 분산을 설명력을 갖는 차원축소
new_d = pca.fit_transform(d)
In [18]:
pd.DataFrame(new_d)
Out[18]:
In [28]:
from six.moves import urllib
from sklearn.datasets import fetch_mldata
mnist = fetch_mldata('MNIST original')
In [29]:
from sklearn.model_selection import train_test_split
X = mnist["data"]
y = mnist["target"]
X_train, X_test, y_train, y_test = train_test_split(X, y)
In [32]:
from sklearn.decomposition import IncrementalPCA
n_batches = 100
inc_pca = IncrementalPCA(n_components=154)
for X_batch in np.array_split(X_train, n_batches):
inc_pca.partial_fit(X_batch)
X_mnist_reduced = inc_pca.transform(X_train)
In [37]:
print(len(X_mnist_reduced[0]), len(X_mnist_reduced))
In [38]:
rnd_pca = PCA(n_components=154, svd_solver="randomized")
X_reduced = rnd_pca.fit_transform(X_train)
print(len(X_mnist_reduced[0]), len(X_mnist_reduced))
In [54]:
X, t = make_swiss_roll(n_samples=1000, noise=0.2, random_state=42)
In [55]:
from sklearn.decomposition import KernelPCA
rbf_pca = KernelPCA(n_components = 2, kernel="rbf", gamma=0.04)
X_reduced = rbf_pca.fit_transform(X)
In [56]:
X_reduced
Out[56]:
In [58]:
from sklearn.decomposition import KernelPCA
lin_pca = KernelPCA(n_components = 2, kernel="linear", fit_inverse_transform=True)
rbf_pca = KernelPCA(n_components = 2, kernel="rbf", gamma=0.0433, fit_inverse_transform=True)
sig_pca = KernelPCA(n_components = 2, kernel="sigmoid", gamma=0.001, coef0=1, fit_inverse_transform=True)
y = t > 6.9
plt.figure(figsize=(11, 4))
for subplot, pca, title in ((131, lin_pca, "Linear kernel"),
(132, rbf_pca, "RBF kernel, $\gamma=0.04$"),
(133, sig_pca, "Sigmoid kernel, $\gamma=10^{-3}, r=1$")):
X_reduced = pca.fit_transform(X)
if subplot == 132:
X_reduced_rbf = X_reduced
plt.subplot(subplot)
#plt.plot(X_reduced[y, 0], X_reduced[y, 1], "gs")
#plt.plot(X_reduced[~y, 0], X_reduced[~y, 1], "y^")
plt.title(title, fontsize=14)
plt.scatter(X_reduced[:, 0], X_reduced[:, 1], c=t, cmap=plt.cm.hot)
plt.xlabel("$z_1$", fontsize=18)
if subplot == 131:
plt.ylabel("$z_2$", fontsize=18, rotation=0)
plt.grid(True)
plt.show()
In [60]:
plt.figure(figsize=(6, 5))
X_inverse = pca.inverse_transform(X_reduced_rbf)
ax = plt.subplot(111, projection='3d')
ax.view_init(10, -70)
ax.scatter(X_inverse[:, 0], X_inverse[:, 1], X_inverse[:, 2], c=t, cmap=plt.cm.hot, marker="x")
ax.set_xlabel("")
ax.set_ylabel("")
ax.set_zlabel("")
ax.set_xticklabels([])
ax.set_yticklabels([])
ax.set_zticklabels([])
plt.show()
In [61]:
X_reduced = rbf_pca.fit_transform(X)
plt.figure(figsize=(11, 4))
plt.subplot(132)
plt.scatter(X_reduced[:, 0], X_reduced[:, 1], c=t, cmap=plt.cm.hot, marker="x")
plt.xlabel("$z_1$", fontsize=18)
plt.ylabel("$z_2$", fontsize=18, rotation=0)
plt.grid(True)
In [62]:
from sklearn.model_selection import GridSearchCV
from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import Pipeline
In [63]:
clf = Pipeline([
("kpca", KernelPCA(n_components=2)),
("log_reg", LogisticRegression())
])
param_grid = [{
"kpca__gamma": np.linspace(0.03, 0.05, 10),
"kpca__kernel": ["rbf", "sigmoid"]
}]
grid_search = GridSearchCV(clf, param_grid, cv=3)
grid_search.fit(X, y)
Out[63]:
In [64]:
print(grid_search.best_params_)
In [65]:
X, t = make_swiss_roll(n_samples=1000, noise=0.2, random_state=42)
In [66]:
from sklearn.manifold import LocallyLinearEmbedding
lle = LocallyLinearEmbedding(n_components=2, n_neighbors=10)
X_reduced = lle.fit_transform(X)
In [68]:
plt.title("Unrolled swiss roll using LLE", fontsize=14)
plt.scatter(X_reduced[:, 0], X_reduced[:, 1], c=t, cmap=plt.cm.hot)
plt.xlabel("$z_1$", fontsize=18)
plt.ylabel("$z_2$", fontsize=18)
plt.axis([-0.065, 0.055, -0.1, 0.12])
plt.grid(True)
plt.show()
In [69]:
from sklearn.manifold import MDS
mds = MDS(n_components=2, random_state=42)
X_reduced_mds = mds.fit_transform(X)
In [70]:
from sklearn.manifold import Isomap
isomap = Isomap(n_components=2)
X_reduced_isomap = isomap.fit_transform(X)
In [71]:
from sklearn.manifold import TSNE
tsne = TSNE(n_components=2, random_state=42)
X_reduced_tsne = tsne.fit_transform(X)
In [72]:
titles = ["MDS", "Isomap", "t-SNE"]
plt.figure(figsize=(11,4))
for subplot, title, X_reduced in zip((131, 132, 133), titles,
(X_reduced_mds, X_reduced_isomap, X_reduced_tsne)):
plt.subplot(subplot)
plt.title(title, fontsize=14)
plt.scatter(X_reduced[:, 0], X_reduced[:, 1], c=t, cmap=plt.cm.hot)
plt.xlabel("$z_1$", fontsize=18)
if subplot == 131:
plt.ylabel("$z_2$", fontsize=18, rotation=0)
plt.grid(True)
plt.show()
