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 main(nameof_file):
(countries, vectors) = kmeans.readfile(nameof_file)
clusters = utils.hcluster(vectors, distance=choice_dist)
utils.drawdendrogram(
clusters,
list(map(lambda x: x[1], countries)),
jpeg="C:/Users/akars/clustering_lab/processedhierarchical.jpg")
opt_clust = [
clusters.left, clusters.right.left, clusters.right.right.left.left,
clusters.right.right.left.right.left,
clusters.right.right.left.right.right,
clusters.right.right.right.right, clusters.right.right.right.left
]
cluster_level = []
for cluster in opt_clust:
country_ids = []
get(cluster, country_ids)
cluster_level.append(country_ids)
for i in range(clusternum):
print('cluster {}:'.format(i + 1))
print([countries[r] for r in cluster_level[i]])
print("SSE: " + str(kmeans.sse(cluster_level, vectors)))
if __name__ == "__main__":
main("C:/Users/akars/clustering_lab/processed/preprocessed.csv")
def main(input_f):
(countries, vectors) = k_means.read_file(input_f)
clusters = utils.hcluster(vectors, distance=distance_function)
utils.drawdendrogram(clusters,
list(map(lambda x: x[1], countries)),
jpeg='data/hierarchical.jpg')
# Self-picked clusters from the graph which I considered good
good_clusters = [
clusters.left, clusters.right.left, clusters.right.right.left.left,
clusters.right.right.left.right.left,
clusters.right.right.left.right.right,
clusters.right.right.right.right, clusters.right.right.right.left
]
cluster_level = []
for cluster in good_clusters:
country_ids = []
get_all(cluster, country_ids)
cluster_level.append(country_ids)
for i in range(num_clusters):
print('cluster {}:'.format(i + 1))
print([countries[r] for r in cluster_level[i]])
print("SSE: " + str(k_means.sse(cluster_level, vectors)))
def __main__():
blognames, words, data = clusters.read_file("blogdata.txt")
clust = clusters.hcluster(data, distance=euclidean_distance)
clusters.draw_dendogram(clust, blognames, jpeg="ex3dendrogram.jpg")
# I think this weights against groupings that have similar word use rates but different word use counts.
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 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 hierarchical(self):
self.clst = 1
if len(self.data) != 0:
clust = clusters.hcluster(self.data)
names = self.authors
output = clusters.clust2str(clust, names)
self.t3.get("1.0", END)
self.t3.delete("1.0", END)
self.t3.insert(END, output)
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 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 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 testNormal(self):
rows = [[6, 4, 2],
[2, 4, 6],
[1, 2, 3],
[3, 2, 1.01]]
clust = [clusters.bicluster(rows[i], id=i) for i in range(len(rows))]
c0 = clusters.bicluster(clusters.mergevecs(rows[1], rows[2]),
left=clust[1], right=clust[2], id=-1, distance=0.0)
c1 = clusters.bicluster(clusters.mergevecs(rows[0], rows[3]),
left=clust[0], right=clust[3], id=-2,
distance=clusters.pearson_dist(rows[0], rows[3]))
c2 = clusters.bicluster(clusters.mergevecs(c0.vec, c1.vec),
left=c0, right=c1, id=-3,
distance=clusters.pearson_dist(c0.vec, c1.vec))
self.assertEquals(c2, clusters.hcluster(rows))
def cluster_poli(self, event): # function to cluster according to parties
if self.run == 0: # checks if it is the first time that clustering has been made
self.create_rest_of_gui()
self.run += 1
self.update_idletasks()
self.var.set(
"party") # sets the variable for usage in refined analysis
clust = clusters.hcluster(
clusters.rotatematrix(self.create_matrix()), distance=sim_distance
) # calls a function from clusters.py to do the clustering
clusters.drawdendrogram(
clust, self.data_center.list_of_parties
) # calls a function from clusters.py to draw the dendogram
self.create_rest_of_gui(
) # recreates the 2. GUI part so everything is reset
self.img = ImageTk.PhotoImage(Image.open("clusters.jpg"))
self.canvas.create_image(
0, 0, anchor=NW,
image=self.img) # Inserts the dendogram to the canvas
def testNormal(self):
rows = [[6, 4, 2], [2, 4, 6], [1, 2, 3], [3, 2, 1.01]]
clust = [clusters.bicluster(rows[i], id=i) for i in range(len(rows))]
c0 = clusters.bicluster(clusters.mergevecs(rows[1], rows[2]),
left=clust[1],
right=clust[2],
id=-1,
distance=0.0)
c1 = clusters.bicluster(clusters.mergevecs(rows[0], rows[3]),
left=clust[0],
right=clust[3],
id=-2,
distance=clusters.pearson_dist(
rows[0], rows[3]))
c2 = clusters.bicluster(clusters.mergevecs(c0.vec, c1.vec),
left=c0,
right=c1,
id=-3,
distance=clusters.pearson_dist(c0.vec, c1.vec))
self.assertEquals(c2, clusters.hcluster(rows))
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')
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 __main__():
blognames, words, data = clusters.read_file("blogdata.txt")
clust = clusters.hcluster(data, distance=euclidean_distance)
clusters.draw_dendogram(clust, blognames, jpeg="ex3dendrogram.jpg")
# I think this weights against groupings that have similar word use rates but different word use counts.
import clusters
docs, words, data = clusters.readfile('titles_vectors.txt')
rdata = clusters.rotatematrix(data)
clust = clusters.hcluster(rdata, distance=clusters.pearson)
print('clusters by pearson correlation')
clusters.printhclust(clust, labels=words)
clusters.drawdendrogram(clust, words, jpeg='wordsclustpearson.jpg')
clust = clusters.hcluster(rdata, distance=clusters.tanimoto)
print('clusters by tanimoto coefficient')
clusters.printhclust(clust, labels=words)
clusters.drawdendrogram(clust, words, jpeg='wordsclusttanimoto.jpg')
clust = clusters.hcluster(rdata, distance=clusters.euclidean)
print('clusters by euclidean distance')
clusters.printhclust(clust, labels=words)
clusters.drawdendrogram(clust, words, jpeg='wordsclusteuclidean.jpg')
def __main__():
entries, words, data = clusters.read_file('entrydata.txt')
clust = clusters.hcluster(data)
clusters.draw_dendogram(clust, entries, jpeg="ex2dend.jpg")
def drawingtheDendrogram():
blognames,words,data=clusters.readfile('blogdata1.txt')
clust=clusters.hcluster(data)
reload(clusters)
clusters.drawdendrogram(clust,blognames,jpeg='blogclust.jpg')
import clusters
row_names, column_names, data = clusters.readfile('dataset_vectors.txt')
clust = clusters.hcluster(data)
print('clusters by euclidean distance')
clusters.printhclust(clust, labels=row_names)
clusters.drawdendrogram(clust,
row_names,
jpeg='hcluster_euclidean_centroid.jpg')
print()
clust = clusters.hcluster(data, clusters.find_by_min)
print('clusters by euclidean distance')
clusters.printhclust(clust, labels=row_names)
clusters.drawdendrogram(clust, row_names, jpeg='hcluster_euclidean_min.jpg')
print()
clust = clusters.hcluster(data, clusters.find_by_max)
print('clusters by euclidean distance')
clusters.printhclust(clust, labels=row_names)
clusters.drawdendrogram(clust, row_names, jpeg='hcluster_euclidean_max.jpg')
import kmcluster
import clusters
import word_cloud
country, data = kmcluster.read_file("processed_data.csv")
#for i in ['min', 'max']:
clust = clusters.hcluster(data, distance=clusters.cosine, inter_dis=max)
print(clust)
print('cosine similarity')
def getHCluster(inputFile):
"""Do Hierarchical Clustering"""
blognames, words, data = clusters.readfile(inputFile)
return blognames, words, clusters.hcluster(data)
####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。
#!/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")
def createAsciiDendogram():
blognames,words,data=clusters.readfile('blogVector.txt')
clust=clusters.hcluster(data)
clusters.printclust(clust,labels=blognames)
def drawDendogram():
blognames,words,data=clusters.readfile('blogdata.txt')
clust=clusters.hcluster(data)
clusters.drawdendrogram(clust,blognames,jpeg='blogclust.jpg')
import clusters
blogname, words, data = clusters.readfile('blogdata2.txt')
coords = clusters.scaledown(data)
clusters.draw2d(coords, blogname, jpeg='blog2d.jpg')
rdata = clusters.rotatematrix(data)
wordclust = clusters.hcluster(rdata)
clusters.drawdendrogram(wordclust, labels=words, jpeg='wordclust.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')
def draw_dendogram():
blognames, words, data = clusters.readfile('Outputs/blogdata.txt')
clust = clusters.hcluster(data)
clusters.drawdendrogram(clust, blognames, jpeg='blogclust.jpg')
except IndexError:
outfile.close()
return
outfile.write('\n')
if __name__ == "__main__":
allw, articlew, artt = getarticlewords()
wordmatrix, wordvec = makematrix(allw, articlew)
# print wordvec[0:10]
# print artt[1]
# print wordmatrix[1][0:10]
# hierarchical clustering
import clusters
clust = clusters.hcluster(wordmatrix)
clusters.drawdendrogram(clust, artt, jpeg='news.jpg')
# non-negative matrix factorization
import nmf
# m1 = np.matrix([[1, 2, 3], [4, 5, 6]])
# m2 = np.matrix([[1, 2], [3, 4], [5, 6]])
# w, h = nmf.factorize(m1 * m2, pc = 3, iter = 100)
# print w * h
v = np.matrix(wordmatrix)
weights, feats = nmf.factorize(v, pc=20, iter=50)
topp, pn = showfeatures(weights, feats, artt, wordvec)
showarticles(artt, topp, pn)
def __main__():
tag_list = build_tag_list("programming")
tags, urls, data = build_tag_matrix(tag_list)
cluster = hcluster(data)
draw_dendogram(cluster, urls, jpeg="delicious.jpg")
import clusters
import json
if __name__ == "__main__":
docs, words, data = clusters.readfile('data/grocery_vectors.txt')
clust = clusters.hcluster(data, distance=clusters.tanimoto)
print('clusters by tanimoto coefficient')
clusters.drawdendrogram(clust, docs, jpeg='img/groceries_tanimoto.jpg')
json_obj = {}
clusters.jsonify(clust, json_obj)
with open("json/tanimoto.json", "w") as output:
json.dump(json_obj, output)
#clust=clusters.hcluster(data,distance=clusters.pearson)
#print('clusters by pearson correlation')
#clusters.drawdendrogram(clust,docs,jpeg='groceries_pearson.jpg')
#clust = clusters.hcluster(data, distance=clusters.cosine)
#print('clusters by cosine similarity')
#clusters.drawdendrogram(clust,docs,jpeg='groceries_cosine.jpg')
#clust=clusters.hcluster(data,distance=clusters.euclidean)
#print('clusters by euclidean distance')
#clusters.drawdendrogram(clust,docs,jpeg='groceries_euclidean.jpg')
def prefer():
reload(clusters)
wants,people,data=clusters.readfile('zebo.txt')
clust=clusters.hcluster(data,distance=clusters.tanamoto)
clusters.drawdendrogram(clust,wants)
def clustering(): print '## Clustering' import clusters allw,artw,artt,wordmatrix,wordvec=readpickle() clust=clusters.hcluster(wordmatrix) clusters.drawdendrogram(clust,artt,jpeg='cluster.jpg')
def getHCluster(inputFile):
"""Do Hierarchical Clustering"""
blognames, words, data = clusters.readfile(inputFile)
return blognames, words, clusters.hcluster(data)
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')
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 countword():
blognames,words,data=clusters.readfile('blogdata1.txt')
clust=clusters.hcluster(data)
def __main__():
tag_list = build_tag_list("programming")
tags, urls, data = build_tag_matrix(tag_list)
cluster = hcluster(data)
draw_dendogram(cluster, urls, jpeg="delicious.jpg")
def __main__():
wants, people, data = clusters.read_file('zebo.txt')
clust = clusters.hcluster(data, distance=manhattan_distance)
clusters.draw_dendogram(clust, wants, jpeg="ex4dend.jpg")
def __main__():
wants, people, data = clusters.read_file('zebo.txt')
clust = clusters.hcluster(data, distance=manhattan_distance)
clusters.draw_dendogram(clust, wants, jpeg="ex4dend.jpg")
except IndexError:
outfile.close()
return
outfile.write('\n')
if __name__ == "__main__":
allw, articlew, artt = getarticlewords()
wordmatrix, wordvec = makematrix(allw, articlew)
# print wordvec[0:10]
# print artt[1]
# print wordmatrix[1][0:10]
# hierarchical clustering
import clusters
clust = clusters.hcluster(wordmatrix)
clusters.drawdendrogram(clust, artt, jpeg = 'news.jpg')
# non-negative matrix factorization
import nmf
# m1 = np.matrix([[1, 2, 3], [4, 5, 6]])
# m2 = np.matrix([[1, 2], [3, 4], [5, 6]])
# w, h = nmf.factorize(m1 * m2, pc = 3, iter = 100)
# print w * h
v = np.matrix(wordmatrix)
weights, feats = nmf.factorize(v, pc = 20, iter = 50)
topp, pn = showfeatures(weights, feats, artt, wordvec)
showarticles(artt, topp, pn)
def generateAscii():
blognames,words,data=clusters.readfile('blogdata.txt')
clust=clusters.hcluster(data)
clusters.printclust(clust,labels=blognames)
def __main__():
entries, words, data = clusters.read_file('entrydata.txt')
clust = clusters.hcluster(data)
clusters.draw_dendogram(clust, entries, jpeg="ex2dend.jpg")
__author__ = 'feng'
import clusters
sessionIds, data = clusters.readSessionFile('session.csv')
clust = clusters.hcluster(data, distance=clusters.session_dissimilarity)
#clusters.printclust(clust, labels=sessionIds)
clusters.drawdendrogram(clust, sessionIds, jpeg='sessionclust.jpg')
import clusters
blognames, words, data = clusters.readfile('blogdataascii.txt')
clust = clusters.hcluster(data)
clusters.drawdendrogram(clust, blognames, jpeg='blogcluster.jpg')
import clusters
# pprint(clusters.readfile('blogdata.txt'))
blognames, words, data = clusters.readfile('blogdata.txt')
clust = clusters.hcluster(data)
# clusters.printclust(clust, labels=blognames)
# k-means
kclust1 = clusters.kcluster(data, k=10)
# pprint([[blognames[i] for i in kclust[j]] for j in range(10)])
kclust2, clusters_pos = clusters.kcluster_exercise(data, k=10)
# pprint(clusters_pos)
# clusters on preferences
wants, people, data = clusters.readfile('zebo.txt')
clust = clusters.hcluster(data, distance=clusters.tanamoto)
clusters.drawdendrogram(clust, wants)