def main():
cl = docclass.classifier(docclass.getwords)
cl.setdb('test1.db')
docclass.sampletrain(cl)
print cl.fprob('quick', 'good')
print cl.weighted_prob('money', 'good', cl.fprob)
docclass.sampletrain(cl)
print cl.weighted_prob('money', 'good', cl.fprob)
clnb = docclass.naivebayes(docclass.getwords)
clnb.setdb('test1.db')
docclass.sampletrain(clnb)
print clnb.prob('quick rabbit', 'good')
print clnb.prob('quick rabbit', 'bad')
print clnb.classify('quick rabbit', default='unknown')
print clnb.classify('quick money', default='unknown')
clnb.setthreshold('bad', 3.0)
print clnb.classify('quick money', default='unknown')
clfs = docclass.fisherclassifier(docclass.getwords)
clfs.setdb('test1.db')
docclass.sampletrain(clfs)
print clfs.cprob('quick', 'good')
print clfs.cprob('money', 'bad')
print clfs.weighted_prob('money', 'bad', clfs.cprob)
print clfs.fisherprob('quick rabbit', 'good')
print clfs.fisherprob('quick rabbit', 'bad')
print clfs.classify('quick rabbit')
print clfs.classify('quick money')
clfs2 = docclass.fisherclassifier(docclass.getwords)
clfs2.setdb('test1.db')
feedclassifier('feed_sample2.rss', clfs2)
print clfs2.cprob('Pandas', 'python')
print clfs2.cprob('python', 'python')
def train1():
import docclass as docclass
cl = docclass.classifier(docclass.getwords)
cl.setdb('test1.db')
for a in range(2000):
docclass.sampletrain(cl)
cl.con.commit()
def test_fprob():
sys.stderr.write("testing sampletrain and computation of feature probability...\n")
reload(docclass)
cl=docclass.classifier(docclass.getwords)
docclass.sampletrain(cl)
fprob = cl.fprob('quick', 'good')
sys.stdout.write("%f\n" %(fprob)) # 0.6666...
def test_train():
sys.stderr.write("testing training...\n")
cl=docclass.classifier(docclass.getwords)
cl.train('the quick brown fox jumps over the lazy dog', 'good')
cl.train('make quick money in the online casino', 'bad')
fcount1 = cl.fcount('quick', 'good')
sys.stdout.write("%f\n" %(fcount1)) # 1.0
fcount2 = cl.fcount('quick', 'bad')
sys.stdout.write("%f\n" %(fcount2)) # 1.0
def test_weightedprob():
sys.stderr.write("testing computation of weightedprob (probability for unseen words)...\n")
reload(docclass)
cl=docclass.classifier(docclass.getwords)
docclass.sampletrain(cl)
wp1 = cl.weightedprob('money', 'good', cl.fprob)
sys.stdout.write("%f\n" %(wp1)) # 0.25
docclass.sampletrain(cl)
wp2 = cl.weightedprob('money', 'good', cl.fprob)
sys.stdout.write("%f\n" %(wp2)) # 0.1666...
def upload_csv_button(self):
self.file_path = tkFileDialog.askopenfilename(
initialdir='/',
title='Select file',
filetypes=(('csv files', '*.csv'), ('all files', '*.*')))
with open(self.file_path) as f:
s = f.read()
my_d = repr(s)
docclass.getwords(my_d)
c1 = docclass.classifier(docclass.getwords)
docclass.sampletrain(c1)
def FisherClassifier(fn):
cl=docclass.classifier(docclass.getwords)
cl.setdb('A10.db')
stig = {}
#get ratings into dictionary to be used later with entries
with open('rated.txt') as rated:
rated = rated.readlines()
for entry in rated:
entry = str(entry).split(" ")
key = entry[0]
val = entry[1].encode('utf-8').strip('\n')
stig[key]=val
#get all words for each title
with open(fn) as entries:
doc = entries.readlines()
i = 0
for line in doc:
title = line.split(" ")
a = title[0]
title.pop(0)
title.pop(0)
if a in stig.keys():
#train classifier using first 50 manually rated entries
if i < 50:
titlestr =''
for word in title:
word = word + ' '
titlestr= titlestr + word
category = stig[a]
cl.train(titlestr,category)
i+=1
else:
for word in title:
word = word + ' '
titlestr = titlestr + word
print "\n"
print cl.fprob(titlestr, 'A')
print "\n"
def FisherClassifier(fn):
cl = docclass.classifier(docclass.getwords)
cl.setdb('A10.db')
stig = {}
#get ratings into dictionary to be used later with entries
with open('rated.txt') as rated:
rated = rated.readlines()
for entry in rated:
entry = str(entry).split(" ")
key = entry[0]
val = entry[1].encode('utf-8').strip('\n')
stig[key] = val
#get all words for each title
with open(fn) as entries:
doc = entries.readlines()
i = 0
for line in doc:
title = line.split(" ")
a = title[0]
title.pop(0)
title.pop(0)
if a in stig.keys():
#train classifier using first 50 manually rated entries
if i < 50:
titlestr = ''
for word in title:
word = word + ' '
titlestr = titlestr + word
category = stig[a]
cl.train(titlestr, category)
i += 1
else:
for word in title:
word = word + ' '
titlestr = titlestr + word
print "\n"
print cl.fprob(titlestr, 'A')
print "\n"
#!/usr/bin/env python
# -*- coding: utf-8 -*-
import docclass
cl = docclass.classifier(docclass.getwords)
docclass.sampletrain(cl)
print(cl.weightedprob('money', 'good', cl.fprob))
docclass.sampletrain(cl)
print(cl.weightedprob('money', 'good', cl.fprob))
import docclass
reload(docclass)
cl = docclass.classifier(docclass.getwords)
docclass.sampledata(cl)
print(cl.weightedprob("money", "good", cl.fprob))
def testBasic(self):
cl = docclass.classifier(docclass.getwords)
cl.setdb('test.db')
cl.train('spam spam spam', 'bad')
self.assertEquals(1.0, cl.fprob('spam', 'bad'))
def data_Fetch_Train(self):
self.parent.geometry("780x595+200+50")
# GUI For Fetching and Training
self.frame3 = Frame(self.parent, bg='wheat2')
self.frame3.grid(row=2, column=0, sticky=W, stick=W)
self.label6 = Label(self.frame3,
text="Individual Books",
fg='black',
font=("Helvetica", 12),
bg="wheat2")
self.label6.grid(row=0, column=0, padx=5, stick=S, sticky=S)
self.label7 = Label(self.frame3,
text="Top 3 Estimates ",
fg='black',
font=("Helvetica", 12),
bg="wheat2")
self.label7.grid(row=0, column=1, padx=5, stick=S, sticky=S)
self.listBox1 = Listbox(self.frame3,
width=50,
height=10,
font=("Helvetica", 8))
self.listBox1.grid(row=1, rowspan=5, column=0, pady=5, padx=140)
self.listBox1.bind('<<ListboxSelect>>', self.listClicked)
self.labelp1 = Label(self.frame3, text="one ", font=("Helvetica", 10))
self.labelp1.grid(row=2, column=1, padx=5)
self.labelp2 = Label(self.frame3, text=" Two", font=("Helvetica", 10))
self.labelp2.grid(row=3, column=1, padx=5)
self.labelp3 = Label(self.frame3,
text=" Three",
font=("Helvetica", 10))
self.labelp3.grid(row=4, column=1, padx=5)
################# Analysis part GUI
self.frame4 = Frame(self.parent, bg='wheat2')
self.frame4.grid(row=3, column=0)
self.l8 = Label(self.frame4,
text='Accuracy analysis based \n on Genres: ',
font=("Helvetica", 10),
bg='wheat2')
self.l8.grid(row=0, column=0)
self.listbox2 = Listbox(self.frame4, height=8)
self.listbox2.grid(row=1, column=0)
self.listbox2.bind('<<ListboxSelect>>', self.analysis)
self.text = Text(self.frame4, height=8, width=30)
self.text.grid(row=1, column=1)
# Fetching part
self.clasifier = docclass.classifier(docclass.getwords)
data = self.GetgenresFromFile()
data = [data[0], data[1]]
self.BooksDATA = self.Crawler(data)
print self.BooksDATA
# Training Part
self.listboxinfo = []
for key, value in self.BooksDATA.items():
# print key
self.listbox2.insert(END, key)
for val in value:
print key, " --> ", val[1]
self.listboxinfo.append(val[0] + '- ' + val[1] + '-' + key)
self.clasifier.train(val[1], key)
random.shuffle(self.listboxinfo, random.random)
for i in self.listboxinfo:
self.listBox1.insert(END, i)
self.label5.config(text="< Trained >", fg='black', bg='Gold')
def test_incf(self):
clas = docclass.classifier(docclass.getwords)
origin_str = 'the quick brown for jumps over the lazy dog'
clas.train('the quick brown for jumps over the lazy dog', 'good')
str_tobe = docclass.getwords(origin_str)
self.assertDictEqual(clas.fc, str_tobe)
#!/usr/bin/env python
import docclass
classifier = docclass.classifier()
classifier.train('the quick brown fox jumps over the lazy dog', 'good')
classifier.train('make quick money in the online casino', 'bad')
print classifier.get_word_count_per_tag('quick', 'good')
print classifier.get_word_count_per_tag('quick', 'bad')
def test_incf(self):
clas = docclass.classifier(docclass.getwords)
origin_str = 'the quick brown for jumps over the lazy dog'
clas.train('the quick brown for jumps over the lazy dog', 'good')
str_tobe = docclass.getwords(origin_str)
self.assertDictEqual(clas.fc, str_tobe)