互分解 Cross Decomposition
优质
小牛编辑
120浏览
2023-12-01
互分解 / 范例一:Compare cross decomposition methods
这个范例目的是比较几个互分解的方法。互分解运算主要是使用潜在变量模式(Latent variable modeling)分析来寻找两个矩阵之间的主要相关成份。
对比于外显变量(Manifest variable),也就是一般的观察变量(Observational variable),潜在变量是可能会影响实验观察的一个未知因素。
(一)引入函式库及内建手写数字资料库
引入之函式库如下
- matplotlib.pyplot: 用来绘制影像
- sklearn.cross_decomposition: 互分解物件
- PLSCanonical: Partial Least Squares 净最小平方法
- PLSRegression: PLS 净最小平方迴归法
- CCA: Canonical correlation analysis 典型相关分析
import numpy as np
import matplotlib.pyplot as plt
from sklearn.cross_decomposition import PLSCanonical, PLSRegression, CCA
#首先产生500笔常态分布资料
n = 500
# 共有两个潜在变量:
l1 = np.random.normal(size=n)
l2 = np.random.normal(size=n)
# np.array([l1, l1, l2, l2]).shape = (4L, 500L)
# latents 为 500 x 4 之矩阵
latents = np.array([l1, l1, l2, l2]).T
#接下来加入乱数形成X, Y矩阵
X = latents + np.random.normal(size=4 * n).reshape((n, 4))
Y = latents + np.random.normal(size=4 * n).reshape((n, 4))
X_train = X[:n / 2]
Y_train = Y[:n / 2]
X_test = X[n / 2:]
Y_test = Y[n / 2:]
# numpy.corrcoef(x, y=None) 用来记算 Pearson product-moment 相关係数
print("Corr(X)")
print(np.round(np.corrcoef(X.T), 2))
print("Corr(Y)")
print(np.round(np.corrcoef(Y.T), 2))
Corr(X)
[[ 1. 0.48 0.02 0. ]
[ 0.48 1. 0.02 -0.02]
[ 0.02 0.02 1. 0.51]
[ 0. -0.02 0.51 1. ]]
Corr(Y)
[[ 1. 0.49 -0.01 0.05]
[ 0.49 1. -0.06 0.06]
[-0.01 -0.06 1. 0.53]
[ 0.05 0.06 0.53 1. ]]
# Canonical (symmetric) PLS
# Transform data
# ~~~~~~~~~~~~~~
plsca = PLSCanonical(n_components=2)
plsca.fit(X_train, Y_train)
X_train_r, Y_train_r = plsca.transform(X_train, Y_train)
X_test_r, Y_test_r = plsca.transform(X_test, Y_test)
# Scatter plot of scores
# ~~~~~~~~~~~~~~~~~~~~~~
# 1) On diagonal plot X vs Y scores on each components
#figure = plt.figure(figsize=(30,20), dpi=300)
plt.figure(figsize=(12, 8), dpi=600)
plt.subplot(221)
plt.plot(X_train_r[:, 0], Y_train_r[:, 0], "ob", label="train")
plt.plot(X_test_r[:, 0], Y_test_r[:, 0], "or", label="test")
plt.xlabel("x scores")
plt.ylabel("y scores")
plt.title('Comp. 1: X vs Y (test corr = %.2f)' %
np.corrcoef(X_test_r[:, 0], Y_test_r[:, 0])[0, 1])
plt.xticks(())
plt.yticks(())
plt.legend(loc="best")
plt.subplot(224)
plt.plot(X_train_r[:, 1], Y_train_r[:, 1], "ob", label="train")
plt.plot(X_test_r[:, 1], Y_test_r[:, 1], "or", label="test")
plt.xlabel("x scores")
plt.ylabel("y scores")
plt.title('Comp. 2: X vs Y (test corr = %.2f)' %
np.corrcoef(X_test_r[:, 1], Y_test_r[:, 1])[0, 1])
plt.xticks(())
plt.yticks(())
plt.legend(loc="best")
# 2) Off diagonal plot components 1 vs 2 for X and Y
plt.subplot(222)
plt.plot(X_train_r[:, 0], X_train_r[:, 1], "*b", label="train")
plt.plot(X_test_r[:, 0], X_test_r[:, 1], "*r", label="test")
plt.xlabel("X comp. 1")
plt.ylabel("X comp. 2")
plt.title('X comp. 1 vs X comp. 2 (test corr = %.2f)'
% np.corrcoef(X_test_r[:, 0], X_test_r[:, 1])[0, 1])
plt.legend(loc="best")
plt.xticks(())
plt.yticks(())
plt.subplot(223)
plt.plot(Y_train_r[:, 0], Y_train_r[:, 1], "*b", label="train")
plt.plot(Y_test_r[:, 0], Y_test_r[:, 1], "*r", label="test")
plt.xlabel("Y comp. 1")
plt.ylabel("Y comp. 2")
plt.title('Y comp. 1 vs Y comp. 2 , (test corr = %.2f)'
% np.corrcoef(Y_test_r[:, 0], Y_test_r[:, 1])[0, 1])
plt.legend(loc="best")
plt.xticks(())
plt.yticks(())
plt.show()
###############################################################################
# PLS regression, with multivariate response, a.k.a. PLS2
n = 1000
q = 3
p = 10
X = np.random.normal(size=n * p).reshape((n, p))
B = np.array([[1, 2] + [0] * (p - 2)] * q).T
# each Yj = 1*X1 + 2*X2 + noize
Y = np.dot(X, B) + np.random.normal(size=n * q).reshape((n, q)) + 5
pls2 = PLSRegression(n_components=3)
pls2.fit(X, Y)
print("True B (such that: Y = XB + Err)")
print(B)
# compare pls2.coef_ with B
print("Estimated B")
print(np.round(pls2.coef_, 1))
pls2.predict(X)
###############################################################################
# PLS regression, with univariate response, a.k.a. PLS1
n = 1000
p = 10
X = np.random.normal(size=n * p).reshape((n, p))
y = X[:, 0] + 2 * X[:, 1] + np.random.normal(size=n * 1) + 5
pls1 = PLSRegression(n_components=3)
pls1.fit(X, y)
# note that the number of compements exceeds 1 (the dimension of y)
print("Estimated betas")
print(np.round(pls1.coef_, 1))
###############################################################################
# CCA (PLS mode B with symmetric deflation)
cca = CCA(n_components=2)
cca.fit(X_train, Y_train)
X_train_r, Y_train_r = plsca.transform(X_train, Y_train)
X_test_r, Y_test_r = plsca.transform(X_test, Y_test)
True B (such that: Y = XB + Err)
[[1 1 1]
[2 2 2]
[0 0 0]
[0 0 0]
[0 0 0]
[0 0 0]
[0 0 0]
[0 0 0]
[0 0 0]
[0 0 0]]
Estimated B
[[ 1. 1. 1. ]
[ 2. 1.9 2. ]
[ 0. 0. 0. ]
[ 0. 0. 0. ]
[ 0. 0. 0. ]
[ 0. 0. -0.1]
[ 0. 0. 0. ]
[ 0. 0. 0.1]
[ 0. 0. 0. ]
[ 0. 0. 0. ]]
Estimated betas
[[ 1. ]
[ 2. ]
[ 0. ]
[ 0. ]
[ 0. ]
[ 0. ]
[ 0. ]
[-0.1]
[ 0. ]
[ 0. ]]
(四)完整程式码
Python source code: plot_compare_cross_decomposition.py
http://scikit-learn.org/stable/_downloads/plot_compare_cross_decomposition.py
print(__doc__)
import numpy as np
import matplotlib.pyplot as plt
from sklearn.cross_decomposition import PLSCanonical, PLSRegression, CCA
###############################################################################
# Dataset based latent variables model
n = 500
# 2 latents vars:
l1 = np.random.normal(size=n)
l2 = np.random.normal(size=n)
latents = np.array([l1, l1, l2, l2]).T
X = latents + np.random.normal(size=4 * n).reshape((n, 4))
Y = latents + np.random.normal(size=4 * n).reshape((n, 4))
X_train = X[:n / 2]
Y_train = Y[:n / 2]
X_test = X[n / 2:]
Y_test = Y[n / 2:]
print("Corr(X)")
print(np.round(np.corrcoef(X.T), 2))
print("Corr(Y)")
print(np.round(np.corrcoef(Y.T), 2))
###############################################################################
# Canonical (symmetric) PLS
# Transform data
# ~~~~~~~~~~~~~~
plsca = PLSCanonical(n_components=2)
plsca.fit(X_train, Y_train)
X_train_r, Y_train_r = plsca.transform(X_train, Y_train)
X_test_r, Y_test_r = plsca.transform(X_test, Y_test)
# Scatter plot of scores
# ~~~~~~~~~~~~~~~~~~~~~~
# 1) On diagonal plot X vs Y scores on each components
plt.figure(figsize=(12, 8))
plt.subplot(221)
plt.plot(X_train_r[:, 0], Y_train_r[:, 0], "ob", label="train")
plt.plot(X_test_r[:, 0], Y_test_r[:, 0], "or", label="test")
plt.xlabel("x scores")
plt.ylabel("y scores")
plt.title('Comp. 1: X vs Y (test corr = %.2f)' %
np.corrcoef(X_test_r[:, 0], Y_test_r[:, 0])[0, 1])
plt.xticks(())
plt.yticks(())
plt.legend(loc="best")
plt.subplot(224)
plt.plot(X_train_r[:, 1], Y_train_r[:, 1], "ob", label="train")
plt.plot(X_test_r[:, 1], Y_test_r[:, 1], "or", label="test")
plt.xlabel("x scores")
plt.ylabel("y scores")
plt.title('Comp. 2: X vs Y (test corr = %.2f)' %
np.corrcoef(X_test_r[:, 1], Y_test_r[:, 1])[0, 1])
plt.xticks(())
plt.yticks(())
plt.legend(loc="best")
# 2) Off diagonal plot components 1 vs 2 for X and Y
plt.subplot(222)
plt.plot(X_train_r[:, 0], X_train_r[:, 1], "*b", label="train")
plt.plot(X_test_r[:, 0], X_test_r[:, 1], "*r", label="test")
plt.xlabel("X comp. 1")
plt.ylabel("X comp. 2")
plt.title('X comp. 1 vs X comp. 2 (test corr = %.2f)'
% np.corrcoef(X_test_r[:, 0], X_test_r[:, 1])[0, 1])
plt.legend(loc="best")
plt.xticks(())
plt.yticks(())
plt.subplot(223)
plt.plot(Y_train_r[:, 0], Y_train_r[:, 1], "*b", label="train")
plt.plot(Y_test_r[:, 0], Y_test_r[:, 1], "*r", label="test")
plt.xlabel("Y comp. 1")
plt.ylabel("Y comp. 2")
plt.title('Y comp. 1 vs Y comp. 2 , (test corr = %.2f)'
% np.corrcoef(Y_test_r[:, 0], Y_test_r[:, 1])[0, 1])
plt.legend(loc="best")
plt.xticks(())
plt.yticks(())
plt.show()
###############################################################################
# PLS regression, with multivariate response, a.k.a. PLS2
n = 1000
q = 3
p = 10
X = np.random.normal(size=n * p).reshape((n, p))
B = np.array([[1, 2] + [0] * (p - 2)] * q).T
# each Yj = 1*X1 + 2*X2 + noize
Y = np.dot(X, B) + np.random.normal(size=n * q).reshape((n, q)) + 5
pls2 = PLSRegression(n_components=3)
pls2.fit(X, Y)
print("True B (such that: Y = XB + Err)")
print(B)
# compare pls2.coef_ with B
print("Estimated B")
print(np.round(pls2.coef_, 1))
pls2.predict(X)
###############################################################################
# PLS regression, with univariate response, a.k.a. PLS1
n = 1000
p = 10
X = np.random.normal(size=n * p).reshape((n, p))
y = X[:, 0] + 2 * X[:, 1] + np.random.normal(size=n * 1) + 5
pls1 = PLSRegression(n_components=3)
pls1.fit(X, y)
# note that the number of compements exceeds 1 (the dimension of y)
print("Estimated betas")
print(np.round(pls1.coef_, 1))
###############################################################################
# CCA (PLS mode B with symmetric deflation)
cca = CCA(n_components=2)
cca.fit(X_train, Y_train)
X_train_r, Y_train_r = plsca.transform(X_train, Y_train)
X_test_r, Y_test_r = plsca.transform(X_test, Y_test)