def testNormal(self):
m = [[1, 0, 2, 0], [2, 0, 3, 0]]
r = clusters.scaledown(m, distance=clusters.euclid_dist, rate=0.1)
self.assertEquals(2, len(r))
self.assertAlmostEquals(clusters.euclid_dist(m[0], m[1]),
clusters.euclid_dist(r[0], r[1]))
def testNormal(self):
m = [[1, 0, 2, 0],
[2, 0, 3, 0]]
r = clusters.scaledown(m, distance=clusters.euclid_dist, rate=0.1)
self.assertEquals(2, len(r))
self.assertAlmostEquals(clusters.euclid_dist(m[0], m[1]),
clusters.euclid_dist(r[0], r[1]))
def visualize(tweets, jpeg="tweets.jpg"):
ids = [tweet["id_str"] for tweet in tweets]
texts = [tweet["text"] for tweet in tweets]
matrix = distances(texts)
coords = scaledown(matrix)
# draw2d(coords, ids, jpeg=jpeg)
return ids, matrix, coords
def prefer2d():
reload(clusters)
blognames,words,data=clusters.readfile('blogdata.txt')
coords=clusters.scaledown(data)
clusters.draw2d(coords,blognames,jpeg='blogs2d.jpg')
import clusters
blognames, words, data = clusters.readfile('blogdata.txt')
coords, itercount = clusters.scaledown(data)
clusters.draw2d(coords, labels=blognames, jpeg='mds.jpg')
print ('Iteration count: %d' % itercount)
#!/usr/bin/env python
import clusters
datafile = '../data/word_data_tfidf.tsv';
blognames,words,data=clusters.readfile(datafile)
iterations, coords=clusters.scaledown(data)
clusters.draw2d(coords,blognames,jpeg='../question5c.jpg')
print "iterations: {}".format(iterations)
def multidim():
jobnames,projects,data=clusters.readfile('job_projects')
coords = clusters.scaledown(data)
clusters.draw2d(coords,jobnames,jpeg='job_multidim.jpg')
def createMDS():
blognames,words,data=clusters.readfile('blogdata.txt')
coords=clusters.scaledown(data)
clusters.draw2d(coords,blognames,jpeg='blogs2d.jpg')
#!/usr/local/bin/python
import clusters
(blognames, words, data)=clusters.readfile('blogdata.txt')
daata = clusters.scaledown(data)
clusters.draw2d(daata, blognames, jpeg='MDS.jpg')
for i in range(len(v1)):
d += (v1[i] - v2[i])**2
return math.sqrt(d)
#getBlogs()
#main()
blognames, words, data = clusters.readfile('similarblogdata.txt')
print(blognames)
print(words)
print(data)
for i in range(len(data[1:])):
if len(data[i + 1]) != len(data[i]):
print(blognames[i + 1])
print(len(data[i + 1]))
print(blognames[i])
print(len(data[i]))
clust = clusters.hcluster(data)
clusters.printclust(clust, labels=blognames)
clusters.drawdendrogram(clust, blognames, jpeg='sblogclust.jpg')
kclust = clusters.kcluster(data, k=5)
printkclustValues(kclust)
kclust = clusters.kcluster(data, k=10)
printkclustValues(kclust)
kclust = clusters.kcluster(data, k=20)
printkclustValues(kclust)
coords = clusters.scaledown(data)
clusters.draw2d(coords, blognames, jpeg='sblogs2d.jpg')
import clusters
blognames, words, data = clusters.readfile("blogdata.txt")
# hierarchy clustering
# clust=clusters.hcluster(data)
##clusters.printclust(clust, labels=blognames)
# clusters.drawdendrogram(clust, blognames, jpeg='blogclust.jpg')
# column clustering
# rdata = clusters.rotatematrix(data)
# clust=clusters.hcluster(rdata)
# clusters.drawdendrogram(clust, words, jpeg='wordclust.jpg')
# k-means clustering
# kclust=clusters.kcluster(data, k=10)
# print [blognames[r] for r in kclust[0]]
# zebo.txt
# wants, people, data=clusters.readfile('zebo.txt')
# clust = clusters.hcluster(data, distance = clusters.tanimoto)
# clusters.drawdendrogram(clust, wants, jpeg='zebo_wants_clust.jpg')
# mds
wants, people, data = clusters.readfile("zebo.txt")
loc = clusters.scaledown(data, wants)
clusters.draw2d(loc, wants)
print "hello world"
def createMDS():
blognames,words,data=clusters.readfile('blogVector.txt')
coords,iterationCount=clusters.scaledown(data)
clusters.draw2d(coords,blognames,jpeg='blogs2d.jpg')
print 'iterationCount', iterationCount
'''
clust = cl.hcluster(data)
cl.printclust(clust,labels=blognames)
cl.drawdendrogram(clust,blognames,jpeg='blogclust.jpg')
rdata = cl.rotatematrix(data)
wordclust = cl.hcluster(rdata)
cl.printclust(wordclust,labels=words)
cl.drawdendrogram(wordclust,words,jpeg='wordclust.jpg')
k = 4
kclust = cl.kcluster(data,k=k)
l = [[blognames[r] for r in kclust[i]] for i in range(k)]
for ll in l:
print len(ll),ll
kclust = cl.kcluster_np(data,k=k)
l = [[blognames[r] for r in kclust[i]] for i in range(k)]
for ll in l:
print len(ll),ll
wants,people,data = cl.readfile('zebo')
clust = cl.hcluster(data,distance=cl.tanimoto)
cl.drawdendrogram(clust,wants)
'''
coords = cl.scaledown(data)
cl.draw2d(coords, blognames, jpeg='blogs2d.jpg')
import clusters
name, word, data = clusters.readfile('blogdata1 (copy).txt')
cluster = clusters.scaledown(data)
clusters.draw2d(cluster, name, jpeg='mds.jpg')
def text():
blognames, words, data = clusters.readfile('Outputs/blogdata.txt')
coords = clusters.scaledown(data)
kclust = clusters.kcluster(data, k=4)
#!/usr/local/bin/python
import clusters
blog,words,data=clusters.readfile('blogdata.txt')
coordinates = clusters.scaledown(data)
clusters.draw2d(coordinates, blog, jpeg='blogs.jpg')
#!/usr/local/bin/python
import clusters
blog, words, data = clusters.readfile('blogdata.txt')
coordinates = clusters.scaledown(data)
clusters.draw2d(coordinates, blog, jpeg='blogs.jpg')
def mds():
blognames, words, data = clusters.readfile('blogdata.txt')
coords, itercount = clusters.scaledown(data)
clusters.draw2d(coords, labels=blognames, jpeg='mds.jpg')
print ('Iteration count: %d' % itercount)
#!/usr/local/bin/python
# all code here stolen shamelessly from
# "Programming Collective Intelligence, Chapter 3"
import sys
sys.path.insert(0, '../libs')
import clusters
blognames,words,data=clusters.readfile('../q1/blogdata500.txt')
coords = clusters.scaledown(data)
clusters.draw2d(coords, blognames, jpeg='blogs2d.jpg')
def main():
blognames,words,data=clusters.readfile('blogdata.txt')
coords=clusters.scaledown(data)
clusters.draw2d(coords,blognames,jpeg='blogs2d.jpg')
