def post(request):
if request.method == 'POST':
form = PostForm(request.POST)
new_post = form.save(commit=False)
new_post.user = request.user
new_post.pub_date = timezone.now()
new_post.save()
text = new_post.text
sentenceList = rake.split_sentences(text)
for sentence in sentenceList:
print("Sentence:", sentence)
# generate candidate keywords
stopwords = rake.load_stop_words(stoppath)
stopwordpattern = rake.build_stop_word_regex(stoppath)
phraseList = rake.generate_candidate_keywords(sentenceList,
stopwordpattern,
stopwords)
print("Phrases:", phraseList)
# calculate individual word scores
wordscores = rake.calculate_word_scores(phraseList)
# generate candidate keyword scores
keywordcandidates = rake.generate_candidate_keyword_scores(
phraseList, wordscores)
for candidate in keywordcandidates.keys():
print("Candidate: ", candidate, ", score: ",
keywordcandidates.get(candidate))
# sort candidates by score to determine top-scoring keywords
sortedKeywords = sorted(six.iteritems(keywordcandidates),
key=operator.itemgetter(1),
reverse=True)
for keywords in sortedKeywords:
print("Keyword: " + str(keywords) + "\n")
print(rake_object.run(text))
x = rake_object.run(text)
if len(x) == 0:
x = sortedKeywords[0][0]
else:
x = x[0][0]
# if topic is already in topics table, just add to posts object
if len(Topic.objects.filter(topic=x)) > 0:
topics = Topic.objects.get(topic=x)
topics.posts.add(new_post)
# if topic is not in topics table, create it and add the new post
else:
newTopic = Topic(topic=x)
newTopic.save()
newTopic.posts.add(new_post)
return home(request)
else:
form = PostForm
return render(request, 'micro/post.html', {'form': form})
def keywordExtract(filename):
# EXAMPLE ONE - SIMPLE
stoppath = "SmartStoplist.txt"
print("---------------------------------------------")
# EXAMPLE TWO - BEHIND THE SCENES (from https://github.com/aneesha/RAKE/rake.py)
# 1. initialize RAKE by providing a path to a stopwords file
# rake_object = rake.Rake(stoppath)
sample_file = io.open(filename, 'r',encoding="iso-8859-1")
text = sample_file.read()
# 1. Split text into sentences
sentenceList = rake.split_sentences(text)
# generate candidate keywords
stopwordpattern = rake.build_stop_word_regex(stoppath)
phraseList = rake.generate_candidate_keywords(sentenceList, stopwordpattern)
# print("Phrases:", phraseList)
# print("---------------------------------------------")
# calculate individual word scores
wordscores = rake.calculate_word_scores(phraseList)
# generate candidate keyword scores
keywordcandidates = rake.generate_candidate_keyword_scores(phraseList, wordscores)
# sort candidates by score to determine top-scoring keywords
sortedKeywords = sorted(six.iteritems(keywordcandidates), key=operator.itemgetter(1), reverse=True)
# totalKeywords = len(sortedKeywords)
return sortedKeywords
def extract_key(text):
#text = "The index had gained 68.22 points in the previous session on Thursday.Nifty acted very range bound facing a strong resistance at 8750 level and found immediate support at 8680 level which we mentioned earlier.Nifty still holds the immediate support placed at 8680 level.Prominent losers among the 30 sensex stocks were TCS, Axis Bank, Bharti Airtel, BHEL, GAIL, HDFC, HDFC Bank, Hero MotoCorp, Infosys, M&M, Maruti Suzuki, NTPC, ONGC, SBI, Sesa Sterlite, Sun Pharma and Tata Motors.These payments amount to around Rs 26 crore, the company said in a release here.Dabur India Ltd: The Burman Family Office, the investment arm of the Burman family, promoters of fast-moving consumer group conglomerate Dabur India, is in the final stages of negotiations to invest an undisclosed amount in online insurance policy aggregator EasyPolicy.com."
# Split text into sentences
sentenceList = rake.split_sentences(text)
# generate candidate keywords
stopwordpattern = rake.build_stop_word_regex(stoppath)
phraseList = rake.generate_candidate_keywords(sentenceList,
stopwordpattern)
# calculate individual word scores
wordscores = rake.calculate_word_scores(phraseList)
# generate candidate keyword scores
keywordcandidates = rake.generate_candidate_keyword_scores(
phraseList, wordscores)
# sort candidates by score to determine top-scoring keywords
sortedKeywords = sorted(keywordcandidates.iteritems(),
key=operator.itemgetter(1),
reverse=True)
totalKeywords = len(sortedKeywords)
return_words = []
# take the top four as the final keywords
for keyword in sortedKeywords[0:4]:
return_words.append(keyword[0])
return return_words
#Example call
#print extract_key("The index had gained 68.22 points in the previous session on Thursday.Nifty acted very range bound facing a strong resistance at 8750 level and found immediate support at 8680 level which we mentioned earlier.Nifty still holds the immediate support placed at 8680 level.Prominent losers among the 30 sensex stocks were TCS, Axis Bank, Bharti Airtel, BHEL, GAIL, HDFC, HDFC Bank, Hero MotoCorp, Infosys, M&M, Maruti Suzuki, NTPC, ONGC, SBI, Sesa Sterlite, Sun Pharma and Tata Motors.These payments amount to around Rs 26 crore, the company said in a release here.Dabur India Ltd: The Burman Family Office, the investment arm of the Burman family, promoters of fast-moving consumer group conglomerate Dabur India, is in the final stages of negotiations to invest an undisclosed amount in online insurance policy aggregator EasyPolicy.com.")
def RakeExtract(text, stoppath="SmartStoplist.txt"):
"""
:param text: string type
:param stoppath: stopword list
:return: a list of tuples where the 1st index is the keyword and the second index the score
"""
# Each word has at least 5 characters, each phrase has at most 3 words
rake_object = rake.Rake(stoppath, 2, 2, 1)
# Splits the text into sentences
sentenceList = rake.split_sentences(text)
stopwordpattern = rake.build_stop_word_regex(stoppath)
# Generate Candidates
phraseList = rake.generate_candidate_keywords(sentenceList,
stopwordpattern)
# print "Candidate Keywords: ", phraseList
wordscores = rake.calculate_word_scores(phraseList)
keywordcandidates = rake.generate_candidate_keyword_scores(
phraseList, wordscores)
sortedKeywords = sorted(keywordcandidates.iteritems(),
key=operator.itemgetter(1),
reverse=True)
totalKeywords = len(sortedKeywords)
keywords = sortedKeywords[0:(totalKeywords / 3)]
return keywords
def Analyse_Text(self):
text = self.bodyOfText.toPlainText()
self.sentenceList = rake.split_sentences(text)
# print(sentenceList)
# #stoppath = "FoxStoplist.txt" #Fox stoplist contains "numbers", so it will not find "natural numbers" like in Table 1.1
self.stoppath = 'C:\\Users\\EmmaAdeiza\\PycharmProjects\\needed_project_main\\Ok_keyword-rake-master\\SmartStoplist.txt' # SMART stoplist misses some of the lower-scoring keywords in Figure 1.5, which means that the top 1/3 cuts off one of the 4.0 score words in Table 1.1
self.stopwordpattern = rake.build_stop_word_regex(self.stoppath)
#
# generate candidate keywords
self.phraseList = rake.generate_candidate_keywords(
self.sentenceList, self.stopwordpattern)
#
# # calculate individual word scores
self.wordscores = rake.calculate_word_scores(self.phraseList)
# generate candidate keyword scores
self.keywordcandidates = rake.generate_candidate_keyword_scores(
self.phraseList, self.wordscores)
if debug: print(self.keywordcandidates)
self.sortedKeywords = sorted(self.keywordcandidates.items(),
key=operator.itemgetter(1),
reverse=True)
if debug: print(self.sortedKeywords)
totalKeywords = len(self.sortedKeywords)
if debug: print(self.totalKeywords)
self.keyterms = ''
for i in range(len(self.sortedKeywords[0:20])):
self.keyterms = self.keyterms + '\n' + self.sortedKeywords[0:20][
i][0]
self.keywordField.setText(self.keyterms)
def keyword_tokenize(text):
'''
INPUT: String
OUTPUT: Tokenized String
'''
stoppath = 'RAKE-tutorial/SmartStoplist.txt'
rake_object = rake.Rake(stoppath, 5, 3, 4)
sentenceList = rake.split_sentences(text)
stopwordpattern = rake.build_stop_word_regex(stoppath)
phraseList = rake.generate_candidate_keywords(sentenceList,
stopwordpattern)
wordscores = rake.calculate_word_scores(phraseList)
return phraseList
def extract_phrase(sentence):
# 1. initialize RAKE by providing a path to a stopwords file
stoppath = "SmartStoplist_mod.txt"
rake_object = rake.Rake(stoppath)
text = "I would like to order 2 mnchurien and rice. Send me a mechnic"
# 2. Split text into sentences
txt = spellcheck.sentence_correct(sentence)
sentenceList = rake.split_sentences(txt)
# 3. generate candidate keywords
stopwordpattern = rake.build_stop_word_regex(stoppath)
phraseList = rake.generate_candidate_keywords(sentenceList, stopwordpattern)
return phraseList
#print(extract_phrase("Haa got you"))
def label(sentenceList):
# EXAMPLE ONE - SIMPLE
stoppath = "SmartStoplist.txt"
__author__ = 'jiangenhe'
rake_object = rake.Rake(stoppath)
# generate candidate keywords
stopwordpattern = rake.build_stop_word_regex(stoppath)
phraseList = rake.generate_candidate_keywords(sentenceList, stopwordpattern)
# calculate individual word scores
wordscores = rake.calculate_word_scores(phraseList)
# generate candidate keyword scores
keywordcandidates = rake.generate_candidate_keyword_scores(phraseList, wordscores)
# sort candidates by score to determine top-scoring keywords
sortedKeywords = sorted(keywordcandidates.iteritems(), key=operator.itemgetter(1), reverse=True)
return sortedKeywords
def get_keywords_of_single_abstract_RAKE(abstract):
sentence_list = rake.split_sentences(abstract)
stopword_pattern = rake.build_stop_word_regex(STOPPATH)
phrase_list = rake.generate_candidate_keywords(sentence_list,
stopword_pattern)
word_scores = rake.calculate_word_scores(phrase_list)
keyword_candidates = rake.generate_candidate_keyword_scores(
phrase_list, word_scores)
keywords = keyword_candidates.iteritems()
keywords = list(keywords)
stemmer = PorterStemmer()
keywords = [(' '.join(stemmer.stem(w) for w in k.split(' ')), score)
for k, score in keywords]
sorted_keywords = sorted(keywords,
key=operator.itemgetter(1),
reverse=True)
total_keywords = len(sorted_keywords)
return [k[0] for k in sorted_keywords[0:total_keywords / 3]]
def main(args):
atexit.register(quit_repl)
rake_instance = rake.Rake()
while True:
print '-' * 80
try:
text = raw_input('Enter text to analyze\n%s' % PROMPT_STR)
except EOFError:
# Exit gracefully on Ctrl-D
break
# Split text into sentences
sentenceList = rake.split_sentences(text)
stopwordpattern = rake.build_stop_word_regex()
# generate candidate keywords
phraseList = rake.generate_candidate_keywords(sentenceList,
stopwordpattern)
# calculate individual word scores
wordscores = rake.calculate_word_scores(phraseList)
# generate candidate keyword scores
keywordcandidates = rake.generate_candidate_keyword_scores(
phraseList, wordscores)
if args.verbose:
print keywordcandidates
sortedKeywords = sorted(keywordcandidates.iteritems(),
key=itemgetter(1),
reverse=True)
if args.verbose:
print sortedKeywords
totalKeywords = len(sortedKeywords)
if args.verbose:
print totalKeywords
print sortedKeywords[0:(totalKeywords / 3)]
keywords = rake_instance.run(text)
print keywords
def extract_phrase(sentence):
"""for the purpose of phrase extraction this function is employed
:param name: sentence
:type name: str.
:param state: free from slangs and spell errors
:type state: str
:returns: list -- extracted phrases.
:raises: AttributeError, KeyError
"""
# 1. initialize RAKE by providing a path to a stopwords file
stoppath = "SmartStoplist_mod.txt"
rake_object = rake.Rake(stoppath)
text = "I would like to order 2 mnchurien and rice. Send me a mechnic"
# 2. Split text into sentences
txt = spellcheck.sentence_correct(sentence)
sentenceList = rake.split_sentences(txt)
# 3. generate candidate keywords
stopwordpattern = rake.build_stop_word_regex(stoppath)
phraseList = rake.generate_candidate_keywords(sentenceList, stopwordpattern)
return phraseList
def findKeywords(company_news):
stoppath = "../Data/data/stoplists/SmartStoplist.txt"
rake_obj = rake.Rake(stoppath, 5, 3, 4)
sample_file = io.open("../Data/data/docs/fao_test/w2167e.txt",
'r',
encoding="iso-8859-1")
text = sample_file.read()
keywords = rake_obj.run(text)
rake_obj = rake.Rake(stoppath)
text = company_news
sentences = rake.split_sentences(text)
stop_words = rake.load_stop_words(stoppath)
stop_pattern = rake.build_stop_word_regex(stoppath)
phraseList = rake.generate_candidate_keywords(sentences, stop_pattern,
stop_words)
wscores = rake.calculate_word_scores(phraseList)
keywordcandidates = rake.generate_candidate_keyword_scores(
phraseList, wscores)
keywords = sorted(six.iteritems(keywordcandidates),
key=operator.itemgetter(1),
reverse=True)
totalKeywords = len(keywords)
keyword_list = rake_obj.run(text)[0:10]
keyword_list1 = []
for i in keyword_list:
keyword_list1.append(i[0])
return keyword_list1
def extract_phrase(sentence):
"""for the purpose of phrase extraction this function is employed
:param name: sentence
:type name: str.
:param state: free from slangs and spell errors
:type state: str
:returns: list -- extracted phrases.
:raises: AttributeError, KeyError
"""
# 1. initialize RAKE by providing a path to a stopwords file
stoppath = "SmartStoplist_mod.txt"
rake_object = rake.Rake(stoppath)
text = "I would like to order 2 mnchurien and rice. Send me a mechnic"
# 2. Split text into sentences
txt = spellcheck.sentence_correct(sentence)
sentenceList = rake.split_sentences(txt)
# 3. generate candidate keywords
stopwordpattern = rake.build_stop_word_regex(stoppath)
phraseList = rake.generate_candidate_keywords(sentenceList,
stopwordpattern)
return phraseList
def keywordExtract(filename):
# EXAMPLE ONE - SIMPLE
stoppath = "SmartStoplist.txt"
print("---------------------------------------------")
# EXAMPLE TWO - BEHIND THE SCENES (from https://github.com/aneesha/RAKE/rake.py)
# 1. initialize RAKE by providing a path to a stopwords file
# rake_object = rake.Rake(stoppath)
sample_file = io.open(filename, 'r', encoding="iso-8859-1")
text = sample_file.read()
# 1. Split text into sentences
sentenceList = rake.split_sentences(text)
# generate candidate keywords
stopwordpattern = rake.build_stop_word_regex(stoppath)
phraseList = rake.generate_candidate_keywords(sentenceList,
stopwordpattern)
# print("Phrases:", phraseList)
# print("---------------------------------------------")
# calculate individual word scores
wordscores = rake.calculate_word_scores(phraseList)
# generate candidate keyword scores
keywordcandidates = rake.generate_candidate_keyword_scores(
phraseList, wordscores)
# sort candidates by score to determine top-scoring keywords
sortedKeywords = sorted(six.iteritems(keywordcandidates),
key=operator.itemgetter(1),
reverse=True)
# totalKeywords = len(sortedKeywords)
return sortedKeywords
def keyphrase_extract(text):
stoppath = "SmartStoplist.txt"
# generate candidate keywords
sentenceList = []
sentenceList.append(text)
stopwordpattern = rake.build_stop_word_regex(stoppath)
phraseList = rake.generate_candidate_keywords(sentenceList,
stopwordpattern)
# print("Phrases:", phraseList)
# calculate individual word scores
wordscores = rake.calculate_word_scores(phraseList)
# generate candidate keyword scores
keywordcandidates = rake.generate_candidate_keyword_scores(
phraseList, wordscores)
# for candidate in keywordcandidates.keys():
# print("Candidate: ", candidate, ", score: ", keywordcandidates.get(candidate))
# sort candidates by score to determine top-scoring keywords
sortedKeywords = sorted(six.iteritems(keywordcandidates),
key=operator.itemgetter(1),
reverse=True)
return sortedKeywords
def enFunc():
ans = entry.get('1.0', 'end')
n = 0
for line in ans:
words = line.split()
n = len(words)
if (n >= 200):
marks1 = 10
else:
marks1 = 5
print("Marks obtained for word length", marks1, "/10")
a = marks1
stoppath = "data/stoplists/SmartStoplist.txt"
rake_object = rake.Rake(stoppath)
sample_file = io.open("data/docs/mp.txt", 'r', encoding="iso-8859-1")
text = ans
sentenceList = rake.split_sentences(text)
for sentence in sentenceList:
print("Sentence:", sentence)
stopwords = rake.load_stop_words(stoppath)
stopwordpattern = rake.build_stop_word_regex(stoppath)
phraseList = rake.generate_candidate_keywords(sentenceList,
stopwordpattern, stopwords)
print("Phrases:", phraseList)
wordscores = rake.calculate_word_scores(phraseList)
keywordcandidates = rake.generate_candidate_keyword_scores(
phraseList, wordscores)
for candidate in keywordcandidates.keys():
print("Candidate: ", candidate, ", score: ",
keywordcandidates.get(candidate))
sortedKeywords = sorted(six.iteritems(keywordcandidates),
key=operator.itemgetter(1),
reverse=True)
totalKeywords = len(sortedKeywords)
for keyword in sortedKeywords[0:int(totalKeywords / 3)]:
print("Keyword: ", keyword[0], ", score: ", keyword[1])
keyw = dict(rake_object.run(text))
print(keyw)
f1 = io.open("data/docs/mpques1.txt", 'r', encoding="iso-8859-1")
text1 = f1.read()
l = text1.split("\n\n")
kw = l[2].split("\n")
print("keyword in original file:", kw)
c = 0
for i in keyw:
for j in kw:
if (i == j):
c = c + 1
print("count:", c)
total = len(kw)
percentage = (c / total) * 100
if (percentage >= 90):
marks2 = 20
message = "Marks obtained for keyword:" + str(marks2) + "/20"
elif (percentage >= 80 or percentage < 90):
marks2 = 18
message = "Marks obtained for keyword:" + str(marks2) + "/20"
elif (percentage >= 70 or percentage < 80):
marks2 = 16
message = "Marks obtained for keyword:" + str(marks2) + "/20"
elif (percentage >= 60 or percentage < 80):
marks2 = 14
message = "Marks obtained for keyword:" + str(marks2) + "/20"
elif (percentage >= 50 or percentage < 60):
marks2 = 12
message = "Marks obtained for keyword:" + str(marks2) + "/20"
else:
marks2 = 10
message = "Score:" + str(marks2) + "/20"
mes = Message(root, text=message, width=50)
mes.grid(row=150)
b = marks2
tool = language_check.LanguageTool('en-US')
#input=open("mp.txt","r")
count = 0
text = str(ans)
txtlen = len(text.split())
setxt = set(text.split())
setlen = len(setxt)
matches = tool.check(text)
#print("Error:",matches)
print("No. of Errors:", len(matches))
noOfError = len(matches)
if noOfError <= 5:
marks3 = 10
elif noOfError <= 10:
marks3 = 8
elif noOfError <= 15:
marks3 = 5
else:
marks3 = 3
if setlen > (txtlen / 2):
marks3 += 10
else:
marks3 += 5
print("Marks obtained after parsing:", marks3, "/20")
mes2 = Message(root,
text="Marks obtained after parsing:" + str(marks3) + "/20",
width=500)
mes2.grid(row=200, column=50)
c = marks3
print("Marks obtained out of 50 is:", a + b + c, "/50")
mes3 = Message(root,
text="Marks obtained out of 50 is:" + a + b + c + "/50",
width=500)
mes3.grid(row=250, column=50)
import rake
import six
#r.extract_keywords_from_text("The Beta Blocker Heart Attack Trial (BHAT) is a multicenter, randomized, double-blind, placebo control clinical trial sponsored by the National Heart, Lung, and Blood Institute designed to test the effectiveness of regular propranolol administration in reducing total mortality in patients who have survived a recent acute myocardial infarction., A number of other fatal and nonfatal response variables are also being monitored., Three thousand eight hundred thirty-seven patients, ages 30-69, are being followed at 31 clinical centers for a minimum of about 2 and a maximum of 4 years after the infarction., A number of design features of BHAT are discussed., These include maintenance of patient logs, guidelines for obtaining informed consent of patients, assessment of patient knowledge about BHAT, adjustment of study drug dose based on serum levels, and comparison of 1-hr and 24-hr ambulatory electrocardiogram readings., © 1981.")
#print(r.get_ranked_phrases()) # To get keyword phrases ranked highest to lowest.
r = Rake()
filename = '/Users/iqra/Downloads/testing-data.csv'
stop_words_file = '/Users/iqra/Documents/Rake Examples/RAKE-tutorial/data/stoplists/SmartStoplist.txt'
rake_object = rake.Rake(stop_words_file)
data_frame = pd.read_csv(filename, encoding='latin1', engine='c')
# generate candidate keywords
stopwords = rake.load_stop_words(stop_words_file)
stopwordpattern = rake.build_stop_word_regex(stop_words_file)
def rake_implement(x, r):
r.extract_keywords_from_text(x)
return r.get_ranked_phrases()
data_frame['phrases'] = data_frame['abstract'].apply(
lambda x: rake_implement(x, r))
print(data_frame['phrases'])
def make_prediction():
if request.method == 'POST':
#get uploaded document
file = request.files['uploaded_file']
if not file:
return render_template('index.html', label="No file uploaded")
test = pd.read_csv(file)
line = list()
for i in test[test.columns.tolist()]:
line.append(i)
X_test = ''
X_test = X_test.join(line)
text = word_tokenize(X_test)
#text = ''.join(text)
cleaned_text = clean_text(text)
joined_text = " ".join(cleaned_text)
rake_object = rake.Rake('stopwords.txt')
sentenceList = rake.split_sentences(joined_text)
stopwords = rake.load_stop_words('stopwords.txt')
stopwordpattern = rake.build_stop_word_regex('stopwords.txt')
phraseList = rake.generate_candidate_keywords(sentenceList,
stopwordpattern,
stopwords)
wordscores = rake.calculate_word_scores(phraseList)
keywordcandidates = rake.generate_candidate_keyword_scores(
phraseList, wordscores)
sortedKeywords = sorted(six.iteritems(keywordcandidates),
key=operator.itemgetter(1),
reverse=True)
totalKeywords = len(sortedKeywords)
for keyword in sortedKeywords[0:int(5)]:
print("Keyword: ", keyword[0], ", score: ", keyword[1])
x_test_mat = weight_model.transform(joined_text.split('.'))
predict = model.predict(x_test_mat)
print(predict)
label = str(np.squeeze(predict[0]))
print(label)
#read_dict = np.load('final.npy').item()
#id = read_dict[label]["doi"]
#title = read_dict[label]["title"]
#recommend = zip(id, title)
browser = mechanicalsoup.StatefulBrowser()
q = label
browser.open("https://www.scimagojr.com/journalsearch.php?q=" + q)
soup = browser.get_current_page()
#print(soup.prettify())
#soup = BeautifulSoup(open("C:/Users/divya/Desktop/crawl.txt").read())
divTag = soup.find_all("div", {"class": "search_results"})
l = len(divTag)
divTag = str(divTag)
#print((divTag.split('</a>\n')[0]))
recommend = []
for i in range(1, 6):
s = divTag.split('</a>\n')[i]
a = s.split('>')
#print(a)
b = a[0].split('"')
link = b[1]
c = a[2].split('<')
#print(c)
title = c[0]
recommend.append((title, "https://www.scimagojr.com/" + link))
recommend = [(y, x.replace('amp;', '')) for y, x in recommend]
print(recommend)
return render_template('index.html',
label=label,
keyword=sortedKeywords[0:int(5)],
recommendations=recommend)
def enFunc():
global counter
ans = entry.get('1.0','end')
n=0
for line in ans:
words=[line.split(' ') for line in ans]
n=len(words)
if(counter==1 or counter==2):
if(n>=850):
marks1=10
elif(n>=400):
marks1=5
else:
marks1=3
else:
if(n>=250):
marks1=10
elif(n>=100):
marks1=5
else:
marks1=3
a=marks1
fname="data/docs/mp"+str(counter)+".txt"
stoppath = "data/stoplists/SmartStoplist.txt"
rake_object = rake.Rake(stoppath)
sample_file = io.open(fname, 'r',encoding="iso-8859-1")
text = ans
sentenceList = rake.split_sentences(text)
#for sentence in sentenceList:
# print("Sentence:", sentence)
stopwords = rake.load_stop_words(stoppath)
stopwordpattern = rake.build_stop_word_regex(stoppath)
phraseList = rake.generate_candidate_keywords(sentenceList, stopwordpattern, stopwords)
#print("Phrases:", phraseList)
wordscores = rake.calculate_word_scores(phraseList)
keywordcandidates = rake.generate_candidate_keyword_scores(phraseList, wordscores)
"""for candidate in keywordcandidates.keys():
print("Candidate: ", candidate, ", score: ", keywordcandidates.get(candidate))
sortedKeywords = sorted(six.iteritems(keywordcandidates), key=operator.itemgetter(1), reverse=True)
totalKeywords = len(sortedKeywords)
for keyword in sortedKeywords[0:int(totalKeywords/3)]:
print("Keyword: ", keyword[0], ", score: ", keyword[1])"""
keyw=dict(rake_object.run(text))
print(keyw)
#l1=len(keyw)
print(fname)
f1=io.open(fname, 'r',encoding="iso-8859-1")
text1=f1.read()
que=text1.split("\n")
print(que[0])
l=text1.split("\n\n")
kw=l[2].split("\n")
print("keyword in original file=",kw)
total=len(kw)
print("No of keywords in original file=",total)
c=0
for i in keyw:
for j in range(0,total):
if(kw[j].lower() in i.lower()):
print("Detected= " +str(i))
c=c+1
print("count=",c)
percentage=(c/total)*100
if(percentage>=90):
marks2=30
message = "Marks obtained for keyword:" + str(marks2) + "/30"
elif(percentage>=80 and percentage<90):
marks2=28
message = "Marks obtained for keyword:"+ str(marks2) + "/30"
elif(percentage>=70 and percentage<80):
marks2=26
message = "Marks obtained for keyword:" + str(marks2) + "/30"
elif(percentage>=60 and percentage<80):
marks2=24
message = "Marks obtained for keyword:" + str(marks2) + "/30"
elif(percentage>=50 and percentage<60):
marks2=28
message = "Marks obtained for keyword:" + str(marks2) + "/30"
elif(percentage>=40 and percentage<50):
marks2=25
message = "Marks obtained for keyword:" + str(marks2) + "/30"
else:
marks2 = 0
message = "Marks obtained for keyword:" + str(marks2) + "/30"
mes2text = "\nMarks for length = " + str(a) + "/10" + "\nLength = " + str(n)
print(mes2text)
print(message)
b=marks2
tool=language_check.LanguageTool('en-US')
count=0
text=str(ans)
txtlen=len(text.split())
setxt = set(text.split())
setlen = len(setxt)
matches=tool.check(text)
#print("Error:",matches)
print("No. of Errors=",len(matches))
noOfError=len(matches)
for i in range (0,noOfError):
print(matches[i].msg)
if (noOfError<=3 and n>0):
marks3=10
elif (noOfError<=5):
marks3=8
elif (noOfError<=8):
marks3=5
else:
marks3=3
print("Marks obtained after parsing=",marks3,"/10")
c=marks3
d=a+b+c
print("Marks obtained out of 50 is=",d,"/50")
if(counter==1 or counter==2):
tot=(d/50)*12
else:
tot=(d/50)*4
m="\nMarks obtained for this question is"+str(tot)
messagebox.showinfo("Result",m)
global totmark
totmark[counter-1]=tot
flag = False
reftext = text.split(' ')
# for x in
# print text
sentence = " "
for x in reftext:
# print x
if (flag == True):
sentence = sentence + " " + x
if "EFERENCES" in x:
flag = True
referencesentencelist = rake.split_sentences(sentence)
stopwordpattern = rake.build_stop_word_regex(stoppath)
refphraseList = rake.generate_candidate_keywords(referencesentencelist,
stopwordpattern)
# print sentence
'''
'''
# 1. Split text into sentences
sentenceList = rake.split_sentences(text)
# for sentence in sentenceList:
# print "Sentence:", sentence
# generate candidate keywords
# stopwordpattern = rake.build_stop_word_regex(stoppath)
import rake
import operator
# EXAMPLE ONE - SIMPLE
stoppath = "SmartStoplist.txt"
rake_object = rake.Rake(stoppath)
text = "Compatibility of systems of linear constraints over the set of natural numbers. Criteria of compatibility " \
"of a system of linear Diophantine equations, strict inequations, and nonstrict inequations are considered. " \
"Upper bounds for components of a minimal set of solutions and algorithms of construction of minimal generating"\
" sets of solutions for all types of systems are given. These criteria and the corresponding algorithms " \
"for constructing a minimal supporting set of solutions can be used in solving all the considered types of " \
"systems and systems of mixed types."
sentenceList = rake.split_sentences(text)
stopwordpattern = rake.build_stop_word_regex(stoppath)
phraseList = rake.generate_candidate_keywords(sentenceList, stopwordpattern)
print "Phrases:", phraseList
# coding: utf-8
# In[16]:
import rake
import pandas as pd
import numpy as np
import re
# In[20]:
filename = '../data/survey_unilever.xlsx'
nb_kp = 10
stopword_pattern = rake.build_stop_word_regex("SmartStoplist.txt")
min_char_length = 1
max_words_length = 3
headers = ''
groupby = ''
# In[21]:
nb_kp = float(nb_kp)
srv_raw = pd.ExcelFile(filename)
srv = srv_raw.parse()
if len(headers) == 0:
del srv[list(srv)[0]]
qst = list(srv)
qst = [str(q).split("\n")[0] for q in list(srv)]
srv.columns = qst
else: