Last active
March 8, 2020 02:34
-
-
Save freedomtowin/a196b8026b96a9264fdbd45aa77bae12 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from sklearn import datasets,mixture | |
import matplotlib.cm as cm | |
import matplotlib.pyplot as plt | |
import numpy as np | |
np.random.seed(1000) | |
y = datasets.load_iris().data | |
names = datasets.load_iris().feature_names | |
num_clusters = 3 | |
gmm = mixture.GaussianMixture(n_components=num_clusters,max_iter=100000,tol=0.00001).fit(y) | |
colors = cm.rainbow(np.linspace(0.1,0.9, num_clusters)) | |
dim_combos = [(i,j) for i in range(y.shape[1]) for j in range(y.shape[1]) if j>i] | |
log_prob_norm,log_prob = gmm._estimate_log_prob_resp(y) | |
gmm_mask = np.all(np.exp(log_prob)<0.9,axis=1) | |
col = ['green', 'red', 'indigo'] | |
dist = np.zeros((y.shape[0],num_clusters)) | |
count=1 | |
plt.figure(figsize=(10,15)) | |
for i,j in dim_combos: | |
plt.subplot(len(dim_combos),1,count) | |
for k in range(num_clusters): | |
w1 = gmm.means_[k,[i]] | |
w2 = gmm.means_[k,[j]] | |
k_cov = gmm.covariances_[k] | |
C = np.array([[k_cov[i,i],k_cov[i,j]],[k_cov[j,i],k_cov[j,j]]]) | |
eVa, eVe = np.linalg.eig(C) | |
R, S = eVe, np.diag(np.sqrt(eVa)) | |
#create circle (points) | |
z = np.arange(0,2*np.pi+np.pi/8,np.pi/8) | |
points = np.array([[np.cos(z[i]),np.sin(z[i])] for i in range(z.shape[0]-1)]) | |
points = np.concatenate([points,points[:1]]) | |
#1 std away | |
T = (S*1).dot(R.T) | |
points = points.dot(T) | |
points[:,0] = points[:,0]+w1 | |
points[:,1] = points[:,1]+w2 | |
plt.plot(points[:,0],points[:,1],color=col[k]) | |
points = np.array([[np.cos(z[i]),np.sin(z[i+1])] for i in range(z.shape[0]-1)]) | |
points = np.concatenate([points,points[:1]]) | |
#2 std away | |
T = (S*4).dot(R.T) | |
points = points.dot(T) | |
points[:,0] = points[:,0]+w1 | |
points[:,1] = points[:,1]+w2 | |
plt.plot(points[:,0],points[:,1],color=col[k]) | |
plt.plot(y[:,i],y[:,j],'.',color='black', markersize=8) | |
#low proba data points | |
plt.scatter(y[gmm_mask,i],y[gmm_mask,j], c=np.linspace(0,1,np.sum(gmm_mask)), cmap='rainbow', s=100, alpha=0.8) | |
plt.xlabel(names[i]) | |
plt.ylabel(names[j]) | |
count+=1 | |
plt.show() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment