def create_matrix(self):
matrix = [] # List that will hold the matrix
threshold = float(
self.combobox.get()[:-1]) # Gets the thershold from the combobox
self.selected_districts = [
self.lb.get(i) for i in self.lb.curselection()
] # appends the districts that are selected in the listbox
if self.selected_districts == []: # if no disticts are selected in the listbox adds all districts to the list for clustering
self.selected_districts = self.data_center.list_of_districts
parties = self.data_center.list_of_parties # Gets all the political parties from DataCenter
for party_acr in parties:
list_for_party = [] # Holds one of the rows of the matrix
for district in self.selected_districts:
try:
if float(
self.data_center.parties_dict[party_acr].
election_results[district]
) >= threshold: # filters out parties from disttricts whose vote percentage are below threshold
list_for_party.append(
float(self.data_center.parties_dict[party_acr].
election_results[district]))
else:
list_for_party.append(0.0)
except KeyError:
list_for_party.append(
0.0
) # If the party isn't available in a certain district sets the vote percentage to 0
matrix.append(list_for_party)
matrix = clusters.rotatematrix(matrix)
return matrix
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 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_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
####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。
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 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
docs, words, data = clusters.readfile('titles_vectors.txt')
distance_func = clusters.pearson
print()
print("Pearson coefficient between words")
wordvectors = clusters.rotatematrix(data)
for i in range(len(wordvectors) - 1):
for j in range(i + 1, len(wordvectors)):
dist = distance_func(wordvectors[i], wordvectors[j])
sim = 1.0 - dist
print(
'distance between words <' + words[i - 1] + '> and <' +
words[j - 1] + '>=', dist, ', and similarity =', sim)
def getKClusterRotated(inputFile, k):
"""Do K-means Clustering"""
blognames, words, data = clusters.readfile(inputFile)
kclust = clusters.kcluster(clusters.rotatematrix(data), k=k)
return blognames, words, getNumbersToString(words, kclust)
def main(args):
def usage():
print >> sys.stderr, "Usage:"
print >> sys.stderr, "sctoolbox correlates common_tracks [user1] [user2]"
print >> sys.stderr, "sctoolbox correlates pearson_tastes [user1] [user2]"
print >> sys.stderr, "sctoolbox suggest [user] bestlikes [n]"
print >> sys.stderr, "sctoolbox suggest [user] following_tournament [n]"
print >> sys.stderr, "sctoolbox suggest [user] following_tournament_short [n]"
print >> sys.stderr, "sctoolbox suggest [user] following_tournament [n] --nomix"
print >> sys.stderr, "sctoolbox suggest [user] following_tournament_short [n] --nomix"
print >> sys.stderr, "sctoolbox suggest [user] following_tournament_playlimit [n] --nomix [playlimit]"
print >> sys.stderr, "sctoolbox suggest [user] following_tournament_playlimit [n] [playlimit]"
print >> sys.stderr, "sctoolbox searchUser [username]"
print >> sys.stderr, "sctoolbox searchTrack [trackname]"
print >> sys.stderr, "sctoolbox getTrackScore [trackname]"
print >> sys.stderr, "sctoolbox similar [trackname]"
print >> sys.stderr, "sctoolbox draw_style_galaxy [user] [jpg_path]"
paths = []
client = SCDB.register()
##############################################################################
if len(args
) == 5 and args[1] == 'correlates' and args[2] == 'pearson_tastes':
user1 = SCDB.searchForUser(client, args[3])
user2 = SCDB.searchForUser(client, args[4])
puser1 = SCDB.extractProfile(client, user1)
puser2 = SCDB.extractProfile(client, user2)
r = SCDB.comparePearson(puser1, puser2)
print 'Correlation score between users (pearson):', r
##############################################################################
##############################################################################
elif len(args
) == 5 and args[1] == 'correlates' and args[2] == 'common_tracks':
user1 = SCDB.searchForUser(client, args[3])
user2 = SCDB.searchForUser(client, args[4])
puser1 = SCDB.extractProfile(client, user1)
puser2 = SCDB.extractProfile(client, user2)
r = SCDB.compareCommonTracks(puser1, puser2)
print 'Correlation score between users (common tracks):', r
##############################################################################
##############################################################################
elif len(args) == 5 and args[1] == 'suggest' and args[
3] == 'following_tournament':
print(
'Launching tournament between tracks from followings, might take a while...'
)
user = SCDB.searchForUser(client, args[2])
profile = SCDB.profileFollowings(client, user)
suggestions = SCDB.getSuggestionsFromProfile(client, profile,
int(args[4]))
print(args[2] + " should like these tracks:")
for item in suggestions:
print item
##############################################################################
##############################################################################
elif len(args) == 5 and args[1] == 'suggest' and args[3] == 'bestlikes':
print(
'Rating tracks user liked, reposted, or commented, and playlisted, might take a while...'
)
user = SCDB.searchForUser(client, args[2])
profile = SCDB.sortProfileFromFollowings(client, user)
suggestions = SCDB.getSuggestionsFromProfile(client, profile,
int(args[4]))
print(args[2] + " best likes are:")
for item in suggestions:
print item
##############################################################################
##############################################################################
elif len(args) == 5 and args[1] == 'suggest' and args[
3] == 'following_tournament_short':
print('Launching short tournament between tracks from followings...')
user = SCDB.searchForUser(client, args[2])
profile = SCDB.profileFollowingsShort(client, user)
suggestions = SCDB.getSuggestionsFromProfile(client, profile,
int(args[4]))
print(args[2] + " should like these tracks:")
for item in suggestions:
print item
##############################################################################
##############################################################################
elif len(args) == 6 and args[1] == 'suggest' and args[
3] == 'following_tournament' and args[5] == '--nomix':
print(
'Launching tournament between tracks from followings, might take a while...'
)
user = SCDB.searchForUser(client, args[2])
profile = SCDB.profileFollowings(client, user)
suggestions = SCDB.getSuggestionsFromProfile(client,
profile,
int(args[4]),
no_mix=True)
print(args[2] + " should like these tracks:")
for item in suggestions:
print item
##############################################################################
##############################################################################
elif len(args) == 6 and args[1] == 'suggest' and args[
3] == 'following_tournament_short' and args[5] == '--nomix':
print('Launching short tournament between tracks from followings...')
user = SCDB.searchForUser(client, args[2])
profile = SCDB.profileFollowingsShort(client, user)
print('Generating big profile...')
suggestions = SCDB.getSuggestionsFromProfile(client,
profile,
int(args[4]),
no_mix=True)
print(args[2] + " should like these tracks:")
for item in suggestions:
print item
##############################################################################
##############################################################################
elif len(args) == 7 and args[1] == 'suggest' and args[
3] == 'following_tournament_playlimit' and args[5] == '--nomix':
print('Launching custom tournament between tracks from followings...')
user = SCDB.searchForUser(client, args[2])
profile = SCDB.profileFollowings(client, user)
suggestions = SCDB.getSuggestionsFromProfile(client,
profile,
int(args[4]),
no_mix=True,
played_limit=int(args[6]))
print(args[2] + " should like these tracks:")
for item in suggestions:
print item
##############################################################################
##############################################################################
elif len(args) == 6 and args[1] == 'suggest' and args[
3] == ' following_tournament_playlimit ':
print('Launching custom tournament between tracks from followings...')
user = SCDB.searchForUser(client, args[2])
profile = SCDB.profileFollowings(client, user)
suggestions = SCDB.getSuggestionsFromProfile(client,
profile,
int(args[4]),
no_mix=False,
played_limit=int(args[5]))
print(args[2] + " should like these tracks:")
for item in suggestions:
print item
##############################################################################
##############################################################################
elif len(args) == 3 and args[1] == 'searchUser':
container = client.get('/users', q=args[2])
n = 1
for item in container:
print('############################')
print('#' + str(n))
n += 1
print('username:'******'permalink:' + item.permalink)
print('############################')
##############################################################################
##############################################################################
elif len(args) == 4 and args[1] == 'draw_style_galaxy':
print('Identifying user...')
user = SCDB.searchForUser(client, args[2])
print('Downloading followers list...')
followers_list = SCDB.getFollowerList(client, user)
followers_list = SCDB.exctractsample(followers_list)
row, col, data = SCDB.getCommentsData(client, followers_list)
print('Generating clusters...')
rotdata = clusters.rotatematrix(data)
tagclust = clusters.hcluster(rotdata)
print("Generationg dendrogram drawing...")
clusters.drawdendrogram(tagclust, col, jpeg=args[3])
##############################################################################
##############################################################################
##############################################################################
##############################################################################
##############################################################################
##############################################################################
##############################################################################
##############################################################################
##############################################################################
else:
usage()
def getKClusterRotated(inputFile, k):
"""Do K-means Clustering"""
blognames, words, data = clusters.readfile(inputFile)
kclust = clusters.kcluster(clusters.rotatematrix(data), k=k)
return blognames, words, getNumbersToString(words, kclust)