def home(request):
text_list = Text.objects.all()
template = loader.get_template('home.html')
context = Context({
'text_list': text_list,
})
if request.method == 'GET':
id = request.GET.get('id', '')
analyse = request.GET.get('analyse', '')
if id:
text = Text.objects.get(id=id)
context['text_object'] = text;
if analyse and len(text.words.all()) == 0:
token=Tokenizer(text.id)
token.analyzeWords()
if len(text.words.all()) == 0:
context['analyse'] = 1
else:
words = text.words.all()
wordcount = []
for w in words:
texthaswords = TextHasWords.objects.get(text=text,word=w)
wordcount.append(WordCount(w.name,texthaswords.count))
if not len(wordcount) == 0:
sorted(wordcount, key=lambda WordCount: WordCount.count, reverse=True)
wordrange = 15
if len(wordcount) < wordrange:
wordrange = len(wordcount)
wordname = ''
wordcounted = ''
for w in range(wordrange):
wordname += "'%s',"%(wordcount[w].name)
for w in range(wordrange):
wordcounted += "%i, "%(int(wordcount[w].count))
context['word_name'] = mark_safe(wordname)
context['word_count'] = wordcounted
context['word_range'] = wordrange
return HttpResponse(template.render(context))
def home(request):
text_list = Text.objects.all()
template = loader.get_template('home.html')
context = Context({
'text_list': text_list,
})
if request.method == 'GET':
id = request.GET.get('id', '')
analyse = request.GET.get('analyse', '')
if id:
text = Text.objects.get(id=id)
context['text_object'] = text;
if analyse and len(text.words.all()) == 0:
token=Tokenizer(text.id)
token.analyzeWords()
if len(text.words.all()) == 0:
context['analyse'] = 1
else:
words = text.words.all()
wordcount = []
for w in words:
texthaswords = TextHasWords.objects.get(text=text,word=w)
wordcount.append(WordCount(w.name,texthaswords.count))
if not len(wordcount) == 0:
sorted(wordcount, key=lambda WordCount: WordCount.count, reverse=True)
wordrange = 15
if len(wordcount) < wordrange:
wordrange = len(wordcount)
wordname = ''
wordcounted = ''
for w in range(wordrange):
wordname += "'%s',"%(wordcount[w].name)
for w in range(wordrange):
wordcounted += "%i, "%(int(wordcount[w].count))
context['word_name'] = mark_safe(wordname)
context['word_count'] = wordcounted
context['word_range'] = wordrange
domains = Domain.objects.all()
for domain in domains:
terms = domain.terms.all()
if domain.name == 'IT':
itterms = terms
if domain.name == 'MEDICAL':
medterms = terms
itlist=[]
medlist=[]
for term in itterms:
itlist.append(term.name)
for term in medterms:
medlist.append(term.name)
it_words = 0
med_words = 0
print itlist
for w in range(wordrange):
if wordcount[w].name in itlist:
it_words += 1
if wordcount[w].name in medlist:
med_words += 1
context['it_words'] = it_words
context['med_words'] = med_words
return HttpResponse(template.render(context))
def home(request):
text_list = Text.objects.all()
template = loader.get_template('home.html')
context = Context({
'text_list': text_list,
})
if request.method == 'GET':
id = request.GET.get('id', '')
analyse = request.GET.get('analyse', '')
if id:
text = Text.objects.get(id=id)
context['analyse'] = 1
context['text_object'] = text;
if analyse:
token=Tokenizer(text.id)
token.analyzeWords()
if len(text.words.all()) > 0:
words = text.words.all()
wordcount = []
for w in words:
texthaswords = TextHasWords.objects.get(text=text,word=w)
wordcount.append(WordCount(w.name,texthaswords.count))
if not len(wordcount) == 0:
sorted(wordcount, key=lambda WordCount: WordCount.count, reverse=True)
wordrange = 15
if len(wordcount) < wordrange:
wordrange = len(wordcount)
wordname = ''
wordcounted = ''
for w in range(wordrange):
wordname += "'%s',"%(wordcount[w].name)
for w in range(wordrange):
wordcounted += "%i, "%(int(wordcount[w].count))
context['word_name'] = mark_safe(wordname)
context['word_count'] = wordcounted
context['word_range'] = wordrange
domains = Domain.objects.all()
blacklist = Blacklist.objects.all()
counted = []
for domain in domains:
terms = domain.terms.all()
termlist=[]
counter = 0
for term in terms:
termlist.append(term.name)
for w in range(wordrange):
if wordcount[w].name in termlist:
counter += 1
counted.append(WordCount(domain.name,counter))
context['domains'] = counted
# Pie Charts Work Starts Here.
paragraph_tokens = re.findall(r'\w+', text.text)
total_tokens = len(paragraph_tokens)
itTerms = []
medTerms = []
for domain in domains:
#STUB FOR FREQUENCY CHARTS STARTS
if domain.name == "IT":
#print "Yes IT"
itTerms = domain.terms.all()
if domain.name == "MEDICAL":
#print "Yes Medical"
medTerms = domain.terms.all()
#STUB FOR FREQUENCY CHARTS ENDS
terms = domain.terms.all()
termlist=[]
counter = 0
for term in terms:
termlist.append(term.name.upper())
for token in paragraph_tokens:
if token.upper() in termlist:
#print "Token Found: " + token
counter += 1
#print str(domain.name) + " count: " + str(counter) + " Total : " + str(len(termlist))
context[domain.name] = str(counter)
blacklist_count = 0
for token in paragraph_tokens:
for blacklist_terms in blacklist:
if token.upper() == str(blacklist_terms).upper():
blacklist_count += 1
#print "Blacklist Items: " + str(blacklist_count)
context['blacklist_count'] = str(blacklist_count)
context['general_domain'] = str(total_tokens - int(context['MEDICAL']) - int(context['IT']) - blacklist_count)
print str(total_tokens) + " " + context['IT'] + " " + context['blacklist_count']
# Pie Charts Work Ends Here.
# Frequency Distribution Work Starts Here
wordrange = total_tokens
if len(wordcount) < wordrange:
wordrange = len(wordcount)
itTermList = []
medTermList = []
blackTermList = []
for term in itTerms:
itTermList.append(term.name.upper())
for term in medTerms:
medTermList.append(term.name.upper())
for term in blacklist:
blackTermList.append(str(term).upper())
itData = ''
medData = ''
genData = ''
blackData = ''
#print range(wordrange)
for w in range(wordrange):
#wordname += "'%s',"%(wordcount[w].name)
if wordcount[w].name.upper() in itTermList:
itData += "%i, "%(int(wordcount[w].count))
#print "IT" + " " +(wordcount[w].name) + " " + str(wordcount[w].count)
elif wordcount[w].name.upper() in medTermList:
#print "MED" + " " +(wordcount[w].name) + " " + str(wordcount[w].count)
medData += "%i, "%(int(wordcount[w].count))
elif wordcount[w].name.upper() in blackTermList:
blackData += "%i, "%(int(wordcount[w].count))
else:
#print "GEN" + " " +(wordcount[w].name) + " " + str(wordcount[w].count)
genData += "%i, "%(int(wordcount[w].count))
context['itData'] = itData
context['medData'] = medData
context['genData'] = genData
context['blackData'] = blackData
# Frequency Distribution Work Ends Here
return HttpResponse(template.render(context))