def PrintClust(self):
self.DataMatrix()
#creating canvas for printing cluster
self.maincanvas=Canvas(self.root,bg='#FFFFFF',width=100,height=320,)
self.maincanvas.grid(row=8,rowspan=8,column=1,columnspan=16,pady=10,sticky="WE")
self.xscrollbar = Scrollbar(self.root, orient=HORIZONTAL,command=self.maincanvas.xview)
self.xscrollbar.grid(row=15,column=1,columnspan=16,sticky="WSE")
self.yscrollbar = Scrollbar(self.root,orient=VERTICAL,command=self.maincanvas.yview)
self.yscrollbar.grid(column=17,row=8,rowspan=8,sticky="WNS")
self.maincanvas.config(xscrollcommand=self.xscrollbar,yscrollcommand=self.yscrollbar)
courses, words, data = clusters.readfile("data.txt")
#creating if condition for distance methods, tanimoto and pearson
if str(self.var.get())=="1":
clust=clusters.hcluster(data,distance=clusters.pearson)
self.printclust=clusters.clust2str(clust, labels=courses)
self.maincanvas.create_text(350,10,font="Helvetiva 10",text=self.printclust,anchor="nw")
elif str(self.var.get())=="2":
clust=clusters.hcluster(data,distance=clusters.tanimoto)
self.printclust=clusters.clust2str(clust, labels=courses)
self.maincanvas.create_text(350,10,font="Helvetiva 10",text=self.printclust,anchor="nw")
else:
tkMessageBox.showerror("ERROR","Please select distance method.")
self.DataMatrix()
def clustering(self, canvas): # Clusters District or Parties
columns, rows, percentages = clusters.readfile('data.txt')
clust = clusters.hcluster(percentages, distance=clusters.sim_distance)
clusters.drawdendrogram(clust, columns, jpeg='cl.jpg')
img = ImageTk.PhotoImage(Image.open("cl.jpg"))
canvas.create_image(20, 20, anchor=NW, image=img)
canvas.image = img
def do_stemmed():
generate_blogfile_stem()
blognames, words, data = clusters.readfile('datafiles/blogtop500_stemmed.txt')
clust = clusters.hcluster(data)
with open("datafiles/blogtop500stemmed_asciideno.txt", "w+") as out:
clusters.printclust2file(clust, out, labels=blognames)
clusters.drawdendrogram(clust, blognames, jpeg='datafiles/blogtop500stemmed_deno.jpg')
with open("datafiles/kmeans_blogtop500stemmed.txt", "w+") as kout:
for k in [5, 10, 20]:
print("For k=%d" % k)
kout.write("K=%d\n" % k)
kout.write("Iterations\n")
centriods = clusters.kcluster_toFile(data, k=k, out=kout)
kout.write("Centroid Values\n-------------------------\n")
for count, centriod in enumerate(centriods, 1):
print("Centroid #%d" % count)
kout.write("Centroid #%d\n" % count)
values = []
for idx in centriod:
print(blognames[idx])
values.append(blognames[idx])
kout.write("%s\n" % ', '.join(values))
kout.write("=================================\n")
print("-------")
with open("datafiles/dimensionReductionStemmed.txt", "w+") as dout:
scaled = clusters.scaledown_logiter(data, out=dout)
clusters.draw2d(scaled, blognames, jpg='datafiles/blogtop500stemmed_clust2d.jpg')
def kmeans(x):
jobnames,projects,data=clusters.readfile('job_projects')
cl, matches = clusters.kcluster(data, k=x)
#print cl
matches_with_names = []
for i in range(x):
matches_with_names.append([jobnames[r] for r in matches[i]])
return matches_with_names
def main():
blognames, words, data = clusters.readfile('blogdata.txt')
print "K value is 5"
kclust = clusters.kcluster(data, k=5)
print "K value is 10"
kclust = clusters.kcluster(data, k=10)
print "K value is 20"
kclust = clusters.kcluster(data, k=20)
def main():
blognames,words,data=clusters.readfile('blogdata.txt')
print "K value is 5"
kclust=clusters.kcluster(data,k=5)
print "K value is 10"
kclust=clusters.kcluster(data,k=10)
print "K value is 20"
kclust=clusters.kcluster(data,k=20)
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 cluster_parties(self):
self.state = "party" #if user clickes cluster parties state changes to party.
self.analysis_frame.pack(side=TOP, fill=BOTH)
self.canvas.delete("all") #clearing canvas
# https://stackoverflow.com/questions/15839491/how-to-clear-tkinter-canvas
self.party_list, self.district_list, self.data = clusters.readfile(
"matrix.txt")
clust = clusters.hcluster(self.data, distance=clusters.sim_distance)
clusters.drawdendrogram(clust, self.party_list, jpeg='parties.jpg')
self.insert_image("parties.jpg") #insert clustered image to canvas
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)
def createJPegDendogram():
'''
blognames,words,data=clusters.readfile('blogVector.txt')
clust=clusters.hcluster(data)
clusters.drawdendrogram(clust,blognames,jpeg='blogclust.jpg')
'''
blognames,words,data=clusters.readfile('blogVectorTFIDFVersion.txt')
clust=clusters.hcluster(data)
clusters.drawdendrogram(clust,blognames,jpeg='blogclustTFIDFVersion.jpg')
def createKMeansClusters(kValue):
if( kValue>0 ):
blognames,words,data=clusters.readfile('blogVector.txt')
kclust=clusters.kcluster(data,k=kValue)
count = 0
for cluster in kclust:
if( len(cluster) > 0 ):
print 'cluster', count
for instance in cluster:
print '...',blognames[instance]
count += 1
def cluster_district(self):
self.state = "district"
#if user clickes cluster districts state changes to district.
self.analysis_frame.pack(side=TOP, fill=BOTH)
self.canvas.delete("all") #clearing canvas
# https://stackoverflow.com/questions/15839491/how-to-clear-tkinter-canvas
self.party_list, self.district_list, self.data = clusters.readfile(
"matrix.txt")
new_data = clusters.rotatematrix(self.data)
#we need to rotated matrix to cluster districts.
clust = clusters.hcluster(new_data, distance=clusters.sim_distance)
clusters.drawdendrogram(clust,
self.district_list,
jpeg='districts.jpg')
self.insert_image("districts.jpg") #insert clustered image to canvas
def kmeans():
karr = [5, 10, 20]
blogs, colnames, data = clusters.readfile('Outputs/blogdata.txt')
for i in karr:
kclust, itercount = clusters.kcluster(data, k=i)
print(kclust)
f = open("Outputs/kclust_%d.txt" % i, 'w')
f.write("Iteration count: %d \n" % itercount)
print(len(kclust))
for cluster in kclust:
f.write("****************************\n")
f.write("[")
for blogid in cluster:
f.write(blogs[blogid] + ", ")
f.write("]\n")
def get_clusture(self, param):
"""
param - str -> Parameeter will be specified in self.writefiles
if param is Country it will show Country clusters
if param is Criterias it will show data clusters
"""
country_names, records, records_data = clusters.readfile(
self.writed_names)
if param == "Country":
clust = clusters.hcluster(records_data)
label = country_names
elif param == "Criterias":
rotated = clusters.rotatematrix(records_data)
clust = clusters.hcluster(rotated)
label = records
self.jpg_names = 'clustured2.jpg'
clusters.drawdendrogram(clust, labels=label, jpeg=self.jpg_names)
self.show_image()
def getKmeans():
blognames, words, data = clusters.readfile("blogdata.txt")
print "K value is 5"
kclust = clusters.kcluster(data, k=5)
print "\t\t" + str([blognames[r] for r in kclust[0]]) # print blognames in 1st centroid
print "\t\t" + str([blognames[r] for r in kclust[1]]) # print blognames in 2nd centroid
print "\t\t" + str([blognames[r] for r in kclust[2]]) # print blognames in 3rd centroid
print "\t\t" + str([blognames[r] for r in kclust[3]]) # print blognames in 4th centroid
print "\t\t" + str([blognames[r] for r in kclust[4]]) # print blognames in 5th centroid
print "K value is 10"
kclust = clusters.kcluster(data, k=10)
print "\t\t" + str([blognames[r] for r in kclust[0]]) # print blognames in 1st centroid
print "\t\t" + str([blognames[r] for r in kclust[1]]) # print blognames in 2nd centroid
print "\t\t" + str([blognames[r] for r in kclust[2]]) # print blognames in 3rd centroid
print "\t\t" + str([blognames[r] for r in kclust[3]]) # print blognames in 4th centroid
print "\t\t" + str([blognames[r] for r in kclust[4]]) # print blognames in 5th centroid
print "\t\t" + str([blognames[r] for r in kclust[5]]) # print blognames in 6th centroid
print "\t\t" + str([blognames[r] for r in kclust[6]]) # print blognames in 7th centroid
print "\t\t" + str([blognames[r] for r in kclust[7]]) # print blognames in 8th centroid
print "\t\t" + str([blognames[r] for r in kclust[8]]) # print blognames in 9th centroid
print "\t\t" + str([blognames[r] for r in kclust[9]]) # print blognames in 10th centroid
print "K value is 20"
kclust = clusters.kcluster(data, k=20)
print "\t\t" + str([blognames[r] for r in kclust[0]]) # print blognames in 1st centroid
print "\t\t" + str([blognames[r] for r in kclust[1]]) # print blognames in 2nd centroid
print "\t\t" + str([blognames[r] for r in kclust[2]]) # print blognames in 3rd centroid
print "\t\t" + str([blognames[r] for r in kclust[3]]) # print blognames in 4th centroid
print "\t\t" + str([blognames[r] for r in kclust[4]]) # print blognames in 5th centroid
print "\t\t" + str([blognames[r] for r in kclust[5]]) # print blognames in 6th centroid
print "\t\t" + str([blognames[r] for r in kclust[6]]) # print blognames in 7th centroid
print "\t\t" + str([blognames[r] for r in kclust[7]]) # print blognames in 8th centroid
print "\t\t" + str([blognames[r] for r in kclust[8]]) # print blognames in 9th centroid
print "\t\t" + str([blognames[r] for r in kclust[9]]) # print blognames in 10th centroid
print "\t\t" + str([blognames[r] for r in kclust[10]]) # print blognames in 11th centroid
print "\t\t" + str([blognames[r] for r in kclust[11]]) # print blognames in 12th centroid
print "\t\t" + str([blognames[r] for r in kclust[12]]) # print blognames in 13th centroid
print "\t\t" + str([blognames[r] for r in kclust[13]]) # print blognames in 14th centroid
print "\t\t" + str([blognames[r] for r in kclust[14]]) # print blognames in 15th centroid
print "\t\t" + str([blognames[r] for r in kclust[15]]) # print blognames in 16th centroid
print "\t\t" + str([blognames[r] for r in kclust[16]]) # print blognames in 17th centroid
print "\t\t" + str([blognames[r] for r in kclust[17]]) # print blognames in 18th centroid
print "\t\t" + str([blognames[r] for r in kclust[18]]) # print blognames in 19th centroid
print "\t\t" + str([blognames[r] for r in kclust[19]]) # print blognames in 20th centroid
def getKmeans():
blognames,words,data=clusters.readfile('blogdata.txt')
print "K value is 5"
kclust=clusters.kcluster(data,k=5)
print "\t\t"+str([blognames[r] for r in kclust[0]])
print "\t\t"+str([blognames[r] for r in kclust[1]])
print "\t\t"+str([blognames[r] for r in kclust[2]])
print "\t\t"+str([blognames[r] for r in kclust[3]])
print "\t\t"+str([blognames[r] for r in kclust[4]])
print "K value is 10"
kclust=clusters.kcluster(data,k=10)
print "\t\t"+str([blognames[r] for r in kclust[0]])
print "\t\t"+str([blognames[r] for r in kclust[1]])
print "\t\t"+str([blognames[r] for r in kclust[2]])
print "\t\t"+str([blognames[r] for r in kclust[3]])
print "\t\t"+str([blognames[r] for r in kclust[4]])
print "\t\t"+str([blognames[r] for r in kclust[5]])
print "\t\t"+str([blognames[r] for r in kclust[6]])
print "\t\t"+str([blognames[r] for r in kclust[7]])
print "\t\t"+str([blognames[r] for r in kclust[8]])
print "\t\t"+str([blognames[r] for r in kclust[9]])
print "K value is 20"
kclust=clusters.kcluster(data,k=20)
print "\t\t"+str([blognames[r] for r in kclust[0]])
print "\t\t"+str([blognames[r] for r in kclust[1]])
print "\t\t"+str([blognames[r] for r in kclust[2]])
print "\t\t"+str([blognames[r] for r in kclust[3]])
print "\t\t"+str([blognames[r] for r in kclust[4]])
print "\t\t"+str([blognames[r] for r in kclust[5]])
print "\t\t"+str([blognames[r] for r in kclust[6]])
print "\t\t"+str([blognames[r] for r in kclust[7]])
print "\t\t"+str([blognames[r] for r in kclust[8]])
print "\t\t"+str([blognames[r] for r in kclust[9]])
print "\t\t"+str([blognames[r] for r in kclust[10]])
print "\t\t"+str([blognames[r] for r in kclust[11]])
print "\t\t"+str([blognames[r] for r in kclust[12]])
print "\t\t"+str([blognames[r] for r in kclust[13]])
print "\t\t"+str([blognames[r] for r in kclust[14]])
print "\t\t"+str([blognames[r] for r in kclust[15]])
print "\t\t"+str([blognames[r] for r in kclust[16]])
print "\t\t"+str([blognames[r] for r in kclust[17]])
print "\t\t"+str([blognames[r] for r in kclust[18]])
print "\t\t"+str([blognames[r] for r in kclust[19]])
def kMean():
kMeanValues = [5, 10, 20]
blogs, colnames, data = clusters.readfile('blogdata.txt')
for i in kMeanValues:
kclust, itercount = clusters.kcluster(data, k=i)
print(kclust)
f = open("kclust_%d.txt" % i, 'w')
f.write("Total Number Of Iterations: %d \n" % itercount)
print(len(kclust))
clusterCount = 1
for cluster in kclust:
i = 1
f.write("---\n")
f.write("Cluster %d \n" % clusterCount)
for blogid in cluster:
f.write(str(i) + ".\t" + blogs[blogid] + "\n")
i += 1
f.write("\n")
clusterCount += 1
def Clustering(self):
try:
dic = self.fetcher_Journalist_with_Titles()
if len(data_dict1) == 0:
self.Error_Message()
return
Matrix = self.Make_Matrix()
Journlist, word, freq = clusters.readfile('Matrix')
if self.Radio_Values3.get() == 0:
H_clustering = hcluster(freq)
self.All_Results.delete(0, END)
for i in range(
len(
clust2str(H_clustering,
labels=Journlist).split('\n'))):
self.All_Results.insert(
END,
clust2str(H_clustering,
labels=Journlist).split('\n')[i])
elif self.Radio_Values3.get() == 1:
K_Vlaue = self.Valueof_k.get()
Cluster_Value = kcluster(freq, k=int(K_Vlaue))
Journalists = dic.keys()
list = [(len(i), i) for i in Cluster_Value]
list.sort(reverse=True)
counter = 0
self.All_Results.delete(0, END)
for i, j in list:
list1 = [Journalists[k] for k in range(len(j))]
new_str = ""
for i in list1:
new_str += str(i) + " "
self.All_Results.insert(
END,
"Cluster %d:{" % (counter + 1) + new_str + "}" + "\n")
counter += 1
except:
pass
def main():
file = ''
with open('1000_terms.csv') as f:
file = f.readlines()
users, words, data = clusters.readfile(file)
kclust5, kclust10, kclust20 = get_clusts(data)
five = get_users_clust(kclust5, users)
ten = get_users_clust(kclust10, users)
twenty = get_users_clust(kclust20, users)
print(five)
print(ten)
print(twenty)
output_clusters(five, 5)
output_clusters(ten, 10)
output_clusters(twenty, 20)
return 0
def clustering_button(self):
if len(database) == 0:
self.Error_Message_Function()
return
prof_names, words, data = clusters.readfile("Will_be_Cluestered.txt")
type_of_clustering = values_of_clustering[int(
self.Radio_Values3.get())]
#Determining the type of clustering with the dictionary.
if type_of_clustering == "Hierarcial":
clust = clusters.hcluster(data)
self.All_Results_Part.delete(0, END)
for i in range(
len(
clusters.clust2str(clust, labels=prof_names).split(
'\n')) - 1):
#split method is used for proper showing of cluster.
self.All_Results_Part.insert(
END,
clusters.clust2str(clust,
labels=prof_names).split('\n')[i])
#Last line of list will be empty string so it is neglected.
elif type_of_clustering == "K-Means":
clust = clusters.kcluster(data, k=int(self.Value_of_k.get()))
#k is getting from the entry.
prof_names = database.keys()
new_list_with_length_of_elements = [(len(i), i) for i in clust]
new_list_with_length_of_elements.sort(reverse=True)
counter = 0
self.All_Results_Part.delete(0, END)
for i, j in new_list_with_length_of_elements:
new_proper_list = [prof_names[k] for k in range(len(j))]
new_str = ""
for i in new_proper_list:
new_str += str(i) + " "
self.All_Results_Part.insert(
END, "Cluster %d:{" % (counter + 1) + new_str + "}" + "\n")
counter += 1
def do_non_stem():
# generate the blog file
generate_blogfile()
# read the data in
blognames, words, data = clusters.readfile('datafiles/blogtop500.txt')
# do clustering
clust = clusters.hcluster(data)
# write out asci denogram
with open("datafiles/blogtop500_asciideno.txt", "w+") as out:
clusters.printclust2file(clust, out, labels=blognames)
# generate jpg version of same denogram
clusters.drawdendrogram(clust, blognames, jpeg='datafiles/blogtop500_deno.jpg')
# do kmeans and log to file
with open("datafiles/kmeans_blogtop500.txt", "w+") as kout:
for k in [5, 10, 20]:
print("For k=%d" % k)
kout.write("K=%d\n" % k)
kout.write("Iterations\n")
# kmeans for value k
centriods = clusters.kcluster_toFile(data, k=k, out=kout)
kout.write("Centroid Values\n-------------------------\n")
# log centroid values
for count, centriod in enumerate(centriods, 1):
print("Centroid #%d" % count)
kout.write("Centroid #%d\n" % count)
values = []
for idx in centriod:
print(blognames[idx])
values.append(blognames[idx])
kout.write("%s\n" % ', '.join(values))
kout.write("=================================\n")
print("-------")
# do the dimensionality reduction
with open("datafiles/dimensionReductionNonStemmed.txt","w+") as dout:
scaled = clusters.scaledown_logiter(data,out=dout)
# generated the similar blog jpg
clusters.draw2d(scaled, blognames, jpg='datafiles/blogtop500_clust2d.jpg')
#!/usr/bin/env python
import clusters
import question2b_conference_truth
import question2b_policy_truth
import question2b_race_truth
import question2b_review_truth
import question2b_story_truth
from svm import *
import svmutil
datafile = '../data/blog_entries_word_data.tsv';
training = 50
blognames,words,data=clusters.readfile(datafile)
def calculate_conference():
correct = 0
answers = []
input = []
count = 0
for d in data:
answers.append(question2b_conference_truth.truth[count])
input.append(d)
if count == 49:
break
count += 1
prob = svmutil.svm_problem(answers, input)
param = svmutil.svm_parameter('-t 2 -c 4')
param.cross_validation = 1
#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')
# Take the average of the top k results
for i in range(k):
idx=dlist[i][1]
avg+=data[idx]['result']
avg=avg/k
return avg
def exclude(data, idx):
new_data = []
for i in range(len(data)):
if i!=idx:
new_data.append(data[i])
return new_data
if __name__ == '__main__':
blognames, terms, data = clusters.readfile('blog_term_matrix.csv')
rows = []
for i in range(len(data)):
int_d = [int(c) for c in data[i]]
rows.append({
'input' : tuple(data[i]),
'result' : i
})
for k in [1,2,5,10,20]:
print('Using k=%s' % k)
print('=' * len('Using k=%s' % k))
# Nearest blog for 99th blog : F-Measure
# Exclude 99th row from rows
####54页调用generatefeedvector生成blogdata文件失败。是因为feedlist里面的网址无法打开吗？
###downloadzebodata生成zebo.txt也失败。sigh
import clusters
blognames,words,data = clusters.readfile('blogdatadown.txt')#1
#clust = clusters.hcluster(data)
#print (clust)#果然函数中这个值输出也都不一样呢。
#print(blognames)
#clusters.printclust(clust, labels = blognames)#2
#clusters.drawdendrogram(clust, blognames, jpeg = 'blogclust.jpg')#3
rdata = clusters.rotatematrix(data)#4
wordclust = clusters.hcluster(rdata)
clusters.drawdendrogram(wordclust, labels = words, jpeg = 'wordclust.jpg')
'''
kclust = clusters.kcluster(data, k = 4)#5
print ([blognames[r] for r in kclust[0]])
print ([blognames[r] for r in kclust[1]])
import urllib.request#6
from bs4 import BeautifulSoup
c = urllib.request.urlopen('https://en.wikipedia.org/wiki/Jon_Snow')
soup = BeautifulSoup(c.read(),"lxml")#这里非常有趣！ 感觉有空需要看下这个源代码库呀。
links = soup('a')#所以我还是不懂beautiful soup 的用法呀。
print(links[10])
print(links[10]['href'])
#这一段是教BS的。
def countword():
blognames,words,data=clusters.readfile('blogdata1.txt')
clust=clusters.hcluster(data)
def prefer():
reload(clusters)
wants,people,data=clusters.readfile('zebo.txt')
clust=clusters.hcluster(data,distance=clusters.tanamoto)
clusters.drawdendrogram(clust,wants)
def ColumnClustering():
reload(clusters)
blognames,words,data=clusters.readfile('blogdata1.txt')
rdata=clusters.rotatematrix(data)
wordclust=clusters.hcluster(rdata)
clusters.drawdendrogram(wordclust,labels=words,jpeg='wordclust.jpg')
#!/usr/bin/env python # -*- coding: utf-8 -*- import clusters blognames,words,data = clusters.readfile( './../data/feed_list.csv' ) coords = clusters.scaledown(data) clusters.draw2d(coords, blognames, jpeg="2d.jpg")
import clusters
blognames, words, data = clusters.readfile('blogVectorResult.txt')
clust = clusters.hcluster(data)
#clusters.printclust(clust,labels=blognames)
reload(clusters)
#clusters.drawdendrogram(clust,blognames,jpeg='blogclust.jpg')
#kclust=clusters.kcluster(data,k=20)
coords = clusters.scaledown(data)
clusters.draw2d(coords, blognames, jpeg='blogs2d.jpg')
import clusters
blognames,words,data=clusters.readfile('blogList500-matrix.txt')
clust = clusters.hcluster(data)
# print ASCII dendrogram
clusters.printclust(clust, labels=blognames)
# save JPEG dendrogram
clusters.drawdendrogram(clust, blognames, jpeg='blogclust-q5.jpg')
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
# 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 draw_dendogram():
jobnames,projects,data=clusters.readfile('job_projects')
clust=clusters.hcluster(data)
#clusters.printclust(clust,labels=jobnames)
clusters.drawdendrogram(clust,jobnames,jpeg='jobclust.jpg')
import clusters
import numpredict
def findNearestNeighbour(i, data, k):
testing = data[i]
neighbors = numpredict.knnestimate(data, testing, k)
for i in neighbors:
print(blogs[i[1]])
blogs, text, data = clusters.readfile("blogDataForknn.txt")
for name in "F-Measure", "Web Science and Digital Libraries Research Group":
for k in 1, 2, 5, 10, 20:
print("Blog Name", name)
print("For K", k)
findNearestNeighbour(blogs.index(name), data, k)
print("\n\n")
def kmean():
reload(clusters)
rownames,words,data=clusters.readfile('blogdata.txt')
kclust=clusters.kcluster(data,k=2)
[rownames[r] for r in kclust[0]]
[rownames[r] for r in kclust[1]]
import codecs
import clusters, random
import shelve
sh = shelve.open("melone_data")
standnames, words, data = clusters.readfile("jojodata.txt")
datasize = len(data)
sh["standnames"] = standnames
sh["words"] = words
sh["data"] = data
tmpvec = []
def geneticoptimize(costf,popsize=50,\
mutprob=0.3,elite=0.3,maxiter=100):
def mutate(vec):
j = random.randint(1, len(vec) - 1)
except_vec = [
y for y in filter(lambda x: x not in vec,
[x for x in range(datasize)])
]
new_dna = random.sample(except_vec, j)
return new_dna + vec[j:]
def crossover(r1, r2):
i = random.randint(1, datasize - 2)
result = r1[0:i] + r2[i:]
while len(set(result)) != 5:
result = r1[0:i] + r2[i:]
return result
def prefer2d():
reload(clusters)
blognames,words,data=clusters.readfile('blogdata.txt')
coords=clusters.scaledown(data)
clusters.draw2d(coords,blognames,jpeg='blogs2d.jpg')
def printwords(list, data, words):
vecsum = zeros(len(data[0]))
for l in list:
vecsum = add(data[l],vecsum)
topwrds = sorted(range(len(vecsum)), key=lambda x: vecsum[x])[-5:]
for r in topwrds:
print vecsum[r]
print "The top words of this cluster are: \n"
for r in topwrds:
print words[r]
moviename, words, data = clusters.readfile('res/blogdata2.txt')
print 'Processing......'
kclust = clusters.kcluster( data, k = 5)
print "\t\t******* CLUSTER 1 *******"
printwords( kclust[0], data, words)
print '\n'
print [moviename[r] for r in kclust[0]]
print '\n\n\n'
print "\t\t******* CLUSTER 2 *******"
printwords( kclust[1], data, words)
print '\n'
print [moviename[r] for r in kclust[1]]
print '\n\n\n'
# Valentina Neblitt-Jones
# CS 595 Introduction to Web Science
# Fall 2013
# Assignment 9 Question 2
import sys
sys.path.insert(0, '/Users/vneblitt/Documents/cs595-f13/assignment09/library')
import clusters
# Create clusters
blognames,words,data=clusters.readfile('/Users/vneblitt/Documents/cs595-f13/assignment09/q01/blogdata1.txt')
clust=clusters.hcluster(data)
# Create ASCII dendrogram
clusters.printclust(clust,labels=blognames)
# Create Nicer dendrogram with PIL
clusters.drawdendrogram(clust,blognames,jpeg='blogclust.jpg')
import clusters
blognames,words,data=clusters.readfile('blogVectorResult.txt')
clust=clusters.hcluster(data)
#clusters.printclust(clust,labels=blognames)
reload(clusters)
#clusters.drawdendrogram(clust,blognames,jpeg='blogclust.jpg')
#kclust=clusters.kcluster(data,k=20)
coords=clusters.scaledown(data)
clusters.draw2d(coords,blognames,jpeg='blogs2d.jpg')
import clusters
docs, words, data = clusters.readfile('titles_vectors.txt')
distance_func = clusters.euclidean
similarity_matrix = []
similarity_matrix.append([])
similarity_matrix[0].append(" ")
padded_docs = ["{:<5}".format(d) for d in docs]
similarity_matrix[0].extend(padded_docs)
for i in range(1, len(data) + 1):
similarity_matrix.append([])
similarity_matrix[i].append(docs[i - 1])
similarity_matrix[i].extend([' ' * 5] * len(data))
print("Euclidean distance - for documents")
for i in range(len(data) - 1):
for j in range(i + 1, len(data)):
dist = distance_func(data[i], data[j])
similarity_matrix[i + 1][j + 1] = "{:<5}".format("{:.2f}".format(
1.0 / (1.0 + dist)))
clusters.print_2d_array(similarity_matrix)
rows.append(row)
except:
skip -= 1
size = size + skip
print(skip, size)
#print(rows)
f = open("newsdata.txt", "w")
f.write("|||".join(word_list) + "\n")
for i in range(size):
row = rows[i]
last_row = []
last_row.append(row["TITLE"])
for word in word_list:
if word in row:
last_row.append(str(row[word]))
else:
last_row.append(str(0))
f.write("|||".join(last_row) + "\n")
f.close()
# what's data :data.append([float(x) for x in p[1:]]) p:row
blognames, words, data = clusters.readfile("newsdata.txt")
clust = clusters.hcluster(data)
clusters.printclust(clust, labels=blognames)
#!/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
# all code here stolen shamelessly from
# "Programming Collective Intelligence, Chapter 3"
import sys
import argparse
sys.path.insert(0, '../libs')
import clusters
blognames,words,data=clusters.readfile('../producedFiles/blogtermmatrix.txt')
coords = clusters.scaledown(data)
clusters.draw2d(coords, blognames, jpeg='../producedFiles/2dBlogSpace.jpg')
#!/usr/bin/env python # -*- coding: utf-8 -*- import clusters blognames,words,data=clusters.readfile( './../data/banpaku_utf8.csv' ) clust=clusters.hcluster(data) # CUIで結果を表示 #clusters.printclust( clust, labels=blognames) # 画像で結果を表示 reload(clusters) clusters.drawdendrogram(clust, blognames, jpeg="banpaku_reg.jpg")
import clusters
blognames,words,data=clusters.readfile('blogsdata.txt')
kclust=clusters.kcluster(data,k=20)
print([blognames[r] for r in kclust[0]])
print([blognames[r] for r in kclust[1]])
print([blognames[r] for r in kclust[2]])
print([blognames[r] for r in kclust[3]])
print([blognames[r] for r in kclust[4]])
print([blognames[r] for r in kclust[5]])
print([blognames[r] for r in kclust[6]])
print([blognames[r] for r in kclust[7]])
print([blognames[r] for r in kclust[8]])
print([blognames[r] for r in kclust[9]])
print([blognames[r] for r in kclust[10]])
print([blognames[r] for r in kclust[11]])
print([blognames[r] for r in kclust[12]])
print([blognames[r] for r in kclust[13]])
print([blognames[r] for r in kclust[14]])
print([blognames[r] for r in kclust[15]])
print([blognames[r] for r in kclust[16]])
print([blognames[r] for r in kclust[17]])
print([blognames[r] for r in kclust[18]])
print([blognames[r] for r in kclust[19]])
distancelist.sort()
return distancelist
def euclidean(v1, v2): #NEED TO REIMPLEMENT.
d = 0.0
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)
def drawingtheDendrogram():
blognames,words,data=clusters.readfile('blogdata1.txt')
clust=clusters.hcluster(data)
reload(clusters)
clusters.drawdendrogram(clust,blognames,jpeg='blogclust.jpg')
import clusters
blognames, words, data = clusters.readfile('blogdataascii.txt')
clust = clusters.hcluster(data)
clusters.drawdendrogram(clust, blognames, jpeg='blogcluster.jpg')
import clusters
def printCentroid(name, kcluster, n):
for x in range(n):
print("Centroid ", str(x + 1), ":")
print([name[r] for r in kcluster[x]])
print("Centroid ", str(x + 1), ":", file=open("kcluster" + str(n) + ".txt", 'a+'))
print([name[r] for r in kcluster[x]], file=open("kcluster" + str(n) + ".txt", 'a+'))
name, word, data = clusters.readfile('blogdata1 (copy).txt')
kcluster =clusters.kcluster(data,k=5)
printCentroid(name,kcluster,5)
kcluster =clusters.kcluster(data,k=10)
printCentroid(name,kcluster,10)
kcluster =clusters.kcluster(data,k=20)
printCentroid(name,kcluster,20)