def contentDensity(pylinguistObj):
if (pylinguistObj.postag == []):
pylinguistObj.postag= tools.getPosTag(pylinguistObj)
nVerb=0
nNoun=0
nAdjective=0
nAdverb=0
for tag in pylinguistObj.postag:
word = tag[0]
word_clas = tag[1]
#if word_clas == "VB" or word_clas == "VBD" or word_clas == "VBG" or word_clas == "VBN" or word_clas == "VBP" or word_clas == "VBZ" :
if word_clas == "VERB" :
nVerb +=1
#elif word_clas == "NN" or word_clas == "NNS" or word_clas == "NNP" or word_clas == "NNPS" :
elif word_clas == "NOUN" :
nNoun +=1
#elif word_clas == "JJ" or word_clas == "JJR" or word_clas == "JJS" :
elif word_clas == "ADJ" :
nAdjective +=1
#elif word_clas == "RB" or word_clas == "RBR" or word_clas == "RBS":
elif word_clas == "ADV" :
nAdverb +=1
contentDensity=10
#print ('somatorio %i'%(nVerb+nNoun+nAdjective+nAdverb))
#print ('dividido por %i'%len(postag))
content_words = nVerb+nNoun+nAdjective+nAdverb
function_words = float(len(pylinguistObj.postag)-content_words)
content_density = content_words / function_words if function_words else 0
return content_density
def adpPronRatio(pylinguistObj):
#Counting pronouns
if (pylinguistObj.postag == []):
pylinguistObj.postag= tools.getPosTag(pylinguistObj)
nPRON=0
for tag in pylinguistObj.postag:
word = tag[0]
word_clas = tag[1]
#if word_clas == "VB" or word_clas == "VBD" or word_clas == "VBG" or word_clas == "VBN" or word_clas == "VBP" or word_clas == "VBZ" :
if word_clas == "PRON" or word_clas == "PRO-KS" or word_clas == "PRO-KS-REL":
nPRON +=1
#print('adjective %i' %nAdjective)
pronIncidence=0
try:
pronIncidence = nPRON / (float(len(pylinguistObj.postag))/1000)
except:
pronIncidence = 0
#counting adpositions
if (pylinguistObj.postag == []):
pylinguistObj.postag= tools.getPosTag(pylinguistObj)
nADP=0
for tag in pylinguistObj.postag:
word = tag[0]
word_clas = tag[1]
#if word_clas == "VB" or word_clas == "VBD" or word_clas == "VBG" or word_clas == "VBN" or word_clas == "VBP" or word_clas == "VBZ" :
if word_clas == "ADP":
nADP +=1
#print('adjective %i' %nAdjective)
adpIncidence=0
try:
adpIncidence = nADP / (float(len(pylinguistObj.postag))/1000)
except:
adpIncidence = 0
try:
ratio = pronIncidence / float(adpIncidence)
except:
ratio = 0
return ratio
def adpPronRatio(pylinguistObj):
#Counting pronouns
if (pylinguistObj.postag == []):
pylinguistObj.postag = tools.getPosTag(pylinguistObj)
nPRON = 0
for tag in pylinguistObj.postag:
word = tag[0]
word_clas = tag[1]
#if word_clas == "VB" or word_clas == "VBD" or word_clas == "VBG" or word_clas == "VBN" or word_clas == "VBP" or word_clas == "VBZ" :
if word_clas == "PRON" or word_clas == "PRO-KS" or word_clas == "PRO-KS-REL":
nPRON += 1
#print('adjective %i' %nAdjective)
pronIncidence = 0
try:
pronIncidence = nPRON / (float(len(pylinguistObj.postag)) / 1000)
except:
pronIncidence = 0
#counting adpositions
if (pylinguistObj.postag == []):
pylinguistObj.postag = tools.getPosTag(pylinguistObj)
nADP = 0
for tag in pylinguistObj.postag:
word = tag[0]
word_clas = tag[1]
#if word_clas == "VB" or word_clas == "VBD" or word_clas == "VBG" or word_clas == "VBN" or word_clas == "VBP" or word_clas == "VBZ" :
if word_clas == "ADP":
nADP += 1
#print('adjective %i' %nAdjective)
adpIncidence = 0
try:
adpIncidence = nADP / (float(len(pylinguistObj.postag)) / 1000)
except:
adpIncidence = 0
try:
ratio = pronIncidence / float(adpIncidence)
except:
ratio = 0
return ratio
def calcAmbiquity(pylinguistObj):
if (pylinguistObj.postag == []):
pylinguistObj.postag= tools.getPosTag(pylinguistObj)
nVerb=0
nNoun=0
nAdjective=0
nAdverb=0
mVerb=0
mNoun=0
mAdjective=0
mAdverb=0
avgMVerb = 0
avgMNoun = 0
avgMAdjective = 0
avgMAdverb = 0
AvgAmbiquity = 0
#Tag Meaning
#https://www.ling.upenn.edu/courses/Fall_2003/ling001/penn_treebank_pos.html
for tag in pylinguistObj.postag:
word = tag[0]
word_clas = tag[1]
#print(word_clas)
if word_clas == "VB" or word_clas == "VBD" or word_clas == "VBG" or word_clas == "VBN" or word_clas == "VBP" or word_clas == "VBZ" :
nVerb +=1
mVerb += len(wn.synsets(word))
elif word_clas == "NN" or word_clas == "NNS" or word_clas == "NNP" or word_clas == "NNPS" :
nNoun +=1
mNoun += len(wn.synsets(word))
elif word_clas == "JJ" or word_clas == "JJR" or word_clas == "JJS" :
nAdjective +=1
mAdjective += len(wn.synsets(word))
elif word_clas == "RB" or word_clas == "RBR" or word_clas == "RBS":
nAdverb +=1
mAdverb += len(wn.synsets(word))
if nVerb > 0: avgMVerb = mVerb / float(nVerb)
if nNoun > 0: avgMNoun = mNoun / float(nNoun)
if nAdjective > 0: avgMAdjective = mAdjective / float(nAdjective)
if nAdverb > 0: avgMAdverb = mAdverb / float(nAdverb)
if (nVerb+nNoun+nAdjective+nAdverb) > 0: AvgAmbiquity = (mVerb+mNoun+mAdjective+mAdverb) / float(nVerb+nNoun+nAdjective+nAdverb)
return AvgAmbiquity
def calcAmbiquity(pylinguistObj):
if (pylinguistObj.postag == []):
pylinguistObj.postag = tools.getPosTag(pylinguistObj)
nVerb = 0
nNoun = 0
nAdjective = 0
nAdverb = 0
mVerb = 0
mNoun = 0
mAdjective = 0
mAdverb = 0
avgMVerb = 0
avgMNoun = 0
avgMAdjective = 0
avgMAdverb = 0
AvgAmbiquity = 0
#Tag Meaning
#https://www.ling.upenn.edu/courses/Fall_2003/ling001/penn_treebank_pos.html
for tag in pylinguistObj.postag:
word = tag[0]
word_clas = tag[1]
#print(word_clas)
if word_clas == "VB" or word_clas == "VBD" or word_clas == "VBG" or word_clas == "VBN" or word_clas == "VBP" or word_clas == "VBZ":
nVerb += 1
mVerb += len(wn.synsets(word))
elif word_clas == "NN" or word_clas == "NNS" or word_clas == "NNP" or word_clas == "NNPS":
nNoun += 1
mNoun += len(wn.synsets(word))
elif word_clas == "JJ" or word_clas == "JJR" or word_clas == "JJS":
nAdjective += 1
mAdjective += len(wn.synsets(word))
elif word_clas == "RB" or word_clas == "RBR" or word_clas == "RBS":
nAdverb += 1
mAdverb += len(wn.synsets(word))
if nVerb > 0: avgMVerb = mVerb / float(nVerb)
if nNoun > 0: avgMNoun = mNoun / float(nNoun)
if nAdjective > 0: avgMAdjective = mAdjective / float(nAdjective)
if nAdverb > 0: avgMAdverb = mAdverb / float(nAdverb)
if (nVerb + nNoun + nAdjective + nAdverb) > 0:
AvgAmbiquity = (mVerb + mNoun + mAdjective +
mAdverb) / float(nVerb + nNoun + nAdjective + nAdverb)
return AvgAmbiquity
def nounIncidence(pylinguistObj):
if (pylinguistObj.postag == []):
pylinguistObj.postag= tools.getPosTag(pylinguistObj)
nNoun=0
for tag in pylinguistObj.postag:
word = tag[0]
word_clas = tag[1]
#if word_clas == "NN" or word_clas == "NNS" or word_clas == "NNP" or word_clas == "NNPS" :
if word_clas == "NOUN" :
nNoun +=1
#print('adjective %i' %nAdjective)
noumIncidence=0
try:
noumIncidence = nNoun / (float(pylinguistObj.word_count)/1000)
except:
noumIncidence = 0
return noumIncidence
def nounIncidence(pylinguistObj):
if (pylinguistObj.postag == []):
pylinguistObj.postag = tools.getPosTag(pylinguistObj)
nNoun = 0
for tag in pylinguistObj.postag:
word = tag[0]
word_clas = tag[1]
#if word_clas == "NN" or word_clas == "NNS" or word_clas == "NNP" or word_clas == "NNPS" :
if word_clas == "NOUN":
nNoun += 1
#print('adjective %i' %nAdjective)
noumIncidence = 0
try:
noumIncidence = nNoun / (float(pylinguistObj.word_count) / 1000)
except:
noumIncidence = 0
return noumIncidence
def verbIncidence(pylinguistObj):
if (pylinguistObj.postag == []):
pylinguistObj.postag= tools.getPosTag(pylinguistObj)
nVerb=0
for tag in pylinguistObj.postag:
word = tag[0]
word_clas = tag[1]
#if word_clas == "VB" or word_clas == "VBD" or word_clas == "VBG" or word_clas == "VBN" or word_clas == "VBP" or word_clas == "VBZ" :
if word_clas == "VERB":
nVerb +=1
#print('adjective %i' %nAdjective)
verbIncidence=0
try:
verbIncidence = nVerb / (float(pylinguistObj.word_count)/1000)
except:
verbIncidence = 0
return verbIncidence
def functionalIncidence(pylinguistObj):
if (pylinguistObj.postag == []):
pylinguistObj.postag= tools.getPosTag(pylinguistObj)
count=0
for tag in pylinguistObj.postag:
word = tag[0]
word_clas = tag[1]
#if word_clas == "VB" or word_clas == "VBD" or word_clas == "VBG" or word_clas == "VBN" or word_clas == "VBP" or word_clas == "VBZ" :
if word_clas == "DET" or word_clas == "ADP" or word_clas == "PRON" or word_clas == "CONJ" or word_clas == "IN" :
count +=1
#print('adjective %i' %nAdjective)
incidence=0
try:
incidence = count / (float(pylinguistObj.word_count)/1000)
except:
incidence = 0
return incidence
def contentIncidence(pylinguistObj):
if (pylinguistObj.postag == []):
pylinguistObj.postag= tools.getPosTag(pylinguistObj)
count=0
for tag in pylinguistObj.postag:
word = tag[0]
word_clas = tag[1]
#if word_clas == "VB" or word_clas == "VBD" or word_clas == "VBG" or word_clas == "VBN" or word_clas == "VBP" or word_clas == "VBZ" :
if word_clas == "VERB" or word_clas == "NOUN" or word_clas == "ADJ" or word_clas == "ADV" :
count +=1
#print('adjective %i' %nAdjective)
incidence=0
try:
incidence = count / (float(pylinguistObj.word_count)/1000)
except:
incidence = 0
return incidence
def pronIncidence(pylinguistObj):
if (pylinguistObj.postag == []):
pylinguistObj.postag = tools.getPosTag(pylinguistObj)
nPRON = 0
for tag in pylinguistObj.postag:
word = tag[0]
word_clas = tag[1]
#if word_clas == "VB" or word_clas == "VBD" or word_clas == "VBG" or word_clas == "VBN" or word_clas == "VBP" or word_clas == "VBZ" :
if word_clas == "PRON" or word_clas == "PRO-KS" or word_clas == "PRO-KS-REL":
nPRON += 1
#print('adjective %i' %nAdjective)
pronIncidence = 0
try:
pronIncidence = nPRON / (float(len(pylinguistObj.postag)) / 1000)
except:
pronIncidence = 0
return pronIncidence
def pronIncidence(pylinguistObj):
if (pylinguistObj.postag == []):
pylinguistObj.postag= tools.getPosTag(pylinguistObj)
nPRON=0
for tag in pylinguistObj.postag:
word = tag[0]
word_clas = tag[1]
#if word_clas == "VB" or word_clas == "VBD" or word_clas == "VBG" or word_clas == "VBN" or word_clas == "VBP" or word_clas == "VBZ" :
if word_clas == "PRON" or word_clas == "PRO-KS" or word_clas == "PRO-KS-REL":
nPRON +=1
#print('adjective %i' %nAdjective)
pronIncidence=0
try:
pronIncidence = nPRON / (float(len(pylinguistObj.postag))/1000)
except:
pronIncidence = 0
return pronIncidence
def advIncidence(pylinguistObj):
if (pylinguistObj.postag == []):
pylinguistObj.postag= tools.getPosTag(pylinguistObj)
nADV=0
for tag in pylinguistObj.postag:
word = tag[0]
word_clas = tag[1]
#if word_clas == "VB" or word_clas == "VBD" or word_clas == "VBG" or word_clas == "VBN" or word_clas == "VBP" or word_clas == "VBZ" :
if word_clas == "ADV" or word_clas == "ADV-KS":
nADV +=1
#print('adjective %i' %nAdjective)
advIncidence=0
try:
advIncidence = nADV / (float(pylinguistObj.word_count)/1000)
except:
advIncidence = 0
return advIncidence
def contentIncidence(pylinguistObj):
if (pylinguistObj.postag == []):
pylinguistObj.postag = tools.getPosTag(pylinguistObj)
count = 0
for tag in pylinguistObj.postag:
word = tag[0]
word_clas = tag[1]
#if word_clas == "VB" or word_clas == "VBD" or word_clas == "VBG" or word_clas == "VBN" or word_clas == "VBP" or word_clas == "VBZ" :
if word_clas == "VERB" or word_clas == "NOUN" or word_clas == "ADJ" or word_clas == "ADV":
count += 1
#print('adjective %i' %nAdjective)
incidence = 0
try:
incidence = count / (float(pylinguistObj.word_count) / 1000)
except:
incidence = 0
return incidence
def advIncidence(pylinguistObj):
if (pylinguistObj.postag == []):
pylinguistObj.postag = tools.getPosTag(pylinguistObj)
nADV = 0
for tag in pylinguistObj.postag:
word = tag[0]
word_clas = tag[1]
#if word_clas == "VB" or word_clas == "VBD" or word_clas == "VBG" or word_clas == "VBN" or word_clas == "VBP" or word_clas == "VBZ" :
if word_clas == "ADV" or word_clas == "ADV-KS":
nADV += 1
#print('adjective %i' %nAdjective)
advIncidence = 0
try:
advIncidence = nADV / (float(pylinguistObj.word_count) / 1000)
except:
advIncidence = 0
return advIncidence
def verbIncidence(pylinguistObj):
if (pylinguistObj.postag == []):
pylinguistObj.postag = tools.getPosTag(pylinguistObj)
nVerb = 0
for tag in pylinguistObj.postag:
word = tag[0]
word_clas = tag[1]
#if word_clas == "VB" or word_clas == "VBD" or word_clas == "VBG" or word_clas == "VBN" or word_clas == "VBP" or word_clas == "VBZ" :
if word_clas == "VERB":
nVerb += 1
#print('adjective %i' %nAdjective)
verbIncidence = 0
try:
verbIncidence = nVerb / (float(pylinguistObj.word_count) / 1000)
except:
verbIncidence = 0
return verbIncidence
def functionalIncidence(pylinguistObj):
if (pylinguistObj.postag == []):
pylinguistObj.postag = tools.getPosTag(pylinguistObj)
count = 0
for tag in pylinguistObj.postag:
word = tag[0]
word_clas = tag[1]
#if word_clas == "VB" or word_clas == "VBD" or word_clas == "VBG" or word_clas == "VBN" or word_clas == "VBP" or word_clas == "VBZ" :
if word_clas == "DET" or word_clas == "ADP" or word_clas == "PRON" or word_clas == "CONJ" or word_clas == "IN":
count += 1
#print('adjective %i' %nAdjective)
incidence = 0
try:
incidence = count / (float(pylinguistObj.word_count) / 1000)
except:
incidence = 0
return incidence
def adjectiveIncidence(pylinguistObj): if (pylinguistObj.postag == []): pylinguistObj.postag = tools.getPosTag(pylinguistObj) nAdjective=0 for tag in pylinguistObj.postag: word = tag[0] word_clas = tag[1] #if word_clas == "JJ" or word_clas == "JJR" or word_clas == "JJS" : if word_clas == "ADJ": nAdjective +=1 adjectiveIncidence=0 try: adjectiveIncidence = nAdjective / (float(pylinguistObj.word_count)/1000) except: adjectiveIncidence = 0 return adjectiveIncidence
def adjectiveIncidence(pylinguistObj):
if (pylinguistObj.postag == []):
pylinguistObj.postag = tools.getPosTag(pylinguistObj)
nAdjective = 0
for tag in pylinguistObj.postag:
word = tag[0]
word_clas = tag[1]
#if word_clas == "JJ" or word_clas == "JJR" or word_clas == "JJS" :
if word_clas == "ADJ":
nAdjective += 1
adjectiveIncidence = 0
try:
adjectiveIncidence = nAdjective / (float(pylinguistObj.word_count) /
1000)
except:
adjectiveIncidence = 0
return adjectiveIncidence
def text(self, text):
self.types = []
self.tokens = []
self.postag = []
self.text = text
#.decode('utf-8','ignore')
self.tokens = tools.getTokens(self)
#optimization
self.postag = tools.getPosTag(self)
#Descriptive counts
self.tokenized_sentences = descriptive.tokenized_sentences(self)
self.word_count = descriptive.word_count(self)
self.sentence_count = descriptive.sentence_count(self)
self.avg_word_per_sentence = descriptive.avg_word_per_sentence(self)
#self.word_length = descriptive.word_length(self) #Doesn't work, for some reason
#self.syllable_count = descriptive.syllable_count(self)
#self.avg_syllables_per_word = descriptive.avg_syllables_per_word(self)
return self
def text(self, text):
self.types=[]
self.tokens=[]
self.postag=[]
self.text = text
#.decode('utf-8','ignore')
self.tokens = tools.getTokens(self)
#optimization
self.postag = tools.getPosTag(self)
#Descriptive counts
self.tokenized_sentences = descriptive.tokenized_sentences(self)
self.word_count = descriptive.word_count(self)
self.sentence_count = descriptive.sentence_count(self)
self.avg_word_per_sentence = descriptive.avg_word_per_sentence(self)
#self.word_length = descriptive.word_length(self) #Doesn't work, for some reason
#self.syllable_count = descriptive.syllable_count(self)
#self.avg_syllables_per_word = descriptive.avg_syllables_per_word(self)
return self
