def createDendrogram():
blogs, colnames, data = clusters.readfile('blogdata.txt')
cluster = clusters.hcluster(data)
clusters.drawdendrogram(cluster, blogs, jpeg='Dendrogram.jpg')
f = open("ASCII.txt", 'w')
sys.stdout = f
clusters.printclust(cluster, labels=blogs)
f.close()
sys.stderr.close()
def main():
# returns blog titles, words in blog (10%-50% boundaries), list of frequency info
blognames,words,data=clusters.readfile('blogdata.txt')
# returns a tree of foo.id, foo.left, foo.right
clust=clusters.hcluster(data)
# walks tree and prints ascii approximation of a dendogram; distance measure is Pearson's r
clusters.printclust(clust,labels=blognames)
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')
#Shawn Jones
#!/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('blogdata1V2.txt')
clust = clusters.hcluster(data)
# print ASCII dendrogram
clusters.printclust(clust, labels=blognames)
# save JPEG dendrogram
clusters.drawdendrogram(clust, blognames, jpeg='blogclust.jpg')
def printclust(): reload(clusters) clusters.printclust(clust,labels=blognames)
import clusters
docs, words, data = clusters.readfile('titlesdata.txt')
rdata = clusters.rotatematrix(data)
clust = clusters.hcluster(rdata, distance=clusters.pearson)
print 'clusters by pearson correlation'
clusters.printclust(clust, labels=words)
clusters.drawdendrogram(clust, words, jpeg='wordsclustpearson.jpg')
clust = clusters.hcluster(rdata, distance=clusters.tanimoto)
print 'clusters by tanimoto coefficient'
clusters.printclust(clust, labels=words)
clusters.drawdendrogram(clust, words, jpeg='wordsclusttanimoto.jpg')
clust = clusters.hcluster(rdata, distance=clusters.euclidean)
print 'clusters by euclidean distance'
clusters.printclust(clust, labels=words)
clusters.drawdendrogram(clust, words, jpeg='wordsclusteuclidean.jpg')
import clusters
name, word, data = clusters.readfile('blogdata1 (copy).txt')
cluster = clusters.hcluster(data)
clusters.printclust(cluster, labels=name)
clusters.drawdendrogram(cluster, name, jpeg='BlogCluster.jpg')
import clusters
blognames, words, data = clusters.readfile('blogdata.txt')
cl = clusters.hcluster(data)
clusters.printclust(cl, labels=blognames) #ascii diagram
clusters.drawdendrogram(cl, blognames,
jpeg='blogcluster.jpg') #drawing the dendrogram
import clusters
blog, words, data = clusters.readfile('tfidf.txt')
variable = clusters.hcluster(data)
# print ASCII dendrogram
clusters.printclust(variable, labels=blog)
# save JPEG dendrogram
clusters.drawdendrogram(variable, blog, jpeg='clusterblogtfidf.jpg')
def createAsciiDendogram():
blognames,words,data=clusters.readfile('blogVector.txt')
clust=clusters.hcluster(data)
clusters.printclust(clust,labels=blognames)
import clusters
blog,words,data=clusters.readfile('tfidf.txt')
variable = clusters.hcluster(data)
# print ASCII dendrogram
clusters.printclust(variable, labels=blog)
# save JPEG dendrogram
clusters.drawdendrogram(variable, blog, jpeg='clusterblogtfidf.jpg')
def generateAscii():
blognames,words,data=clusters.readfile('blogdata.txt')
clust=clusters.hcluster(data)
clusters.printclust(clust,labels=blognames)
import clusters as cl
import numpy as np
import random
blognames, words, data = cl.readfile('blogdata.txt')
'''
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)
def draw_acii_dendogram():
blognames, words, data = clusters.readfile('Outputs/blogdata.txt')
clust = clusters.hcluster(data)
clusters.printclust(clust, labels=blognames)
