Robot grip position (Python PCA principal component analysis)

import numpy as np
import scipy as sp
from sklearn.datasets import make_classification
from sklearn.decomposition import PCA
import matplotlib.pyplot as plt

#Generate sample data
X, y = make_classification(n_samples=200, n_features=2, n_redundant=0, n_informative=2,
                           n_classes=1, n_clusters_per_class=1, random_state=0)

#Principal component analysis
pca = PCA(n_components=2)
pca.fit(X)

#Visualization
plt.scatter(X[:, 0], X[:, 1], alpha=0.5)

l = pca.explained_variance_[1]
vector =  pca.components_[1]
v = vector * 3 * np.sqrt(l)
plt.annotate('',  pca.mean_ + v, pca.mean_ - v,
             arrowprops=dict(connectionstyle='arc3', width=2))



plt.axis('equal')
plt.show()

Recommended Posts