Last active
December 17, 2015 10:29
-
-
Save kyleabeauchamp/5595013 to your computer and use it in GitHub Desktop.
Example of Wards Clustering
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
import matplotlib.pyplot as plt | |
import scipy.cluster | |
import numpy as np | |
import fastcluster | |
num_samples = 1000 | |
similarities = np.loadtxt("./TanimotoMatrix0-1998") | |
distances0 = -1 * np.log(similarities / 1000.) | |
distances = scipy.cluster.hierarchy.distance.squareform(distances0) | |
#clustering = scipy.cluster.hierarchy.complete(distances) | |
clustering = fastcluster.ward(distances) | |
scipy.cluster.hierarchy.dendrogram(clustering) | |
assignments = scipy.cluster.hierarchy.fcluster(clustering, 2, criterion="maxclust") | |
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
import matplotlib.pyplot as plt | |
import scipy.cluster | |
import numpy as np | |
num_samples = 1000 | |
x = np.random.normal(size=(num_samples,2)) | |
x[0:num_samples / 2] += array([3,3]) | |
clustering = scipy.cluster.hierarchy.ward(x) | |
scipy.cluster.hierarchy.dendrogram(clustering) | |
assignments = scipy.cluster.hierarchy.fcluster(clustering, 2, criterion="maxclust") | |
plt.figure() | |
plt.title("Density") | |
plt.hexbin(*x.T) | |
plt.figure() | |
plt.title("Two state ward clustering of data") | |
plt.plot(x[assignments==1, 0], x[assignments==1, 1], 'x', label="1") | |
plt.plot(x[assignments==2, 0], x[assignments==2, 1], 'x', label="2") | |
plt.legend() | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment