def find(word):
if (eng.eng_search(word)):
return ("English word")
elif (beng.beng_word(word)):
return ("Bengali word")
else:
return ("Not a word")
def find(word):
if (eng.eng_search(word)):
return ("English word")
elif (beng.beng_word(word)):
return ("Bengali word")
else:
return ("Not a word")
def main():
lno = 1
word_tot = 0
corr = 0
init_corr = 0
fin = open("./beng_corpus.txt", 'r')
fout_pred = open("./predicted_tags_eng.txt", 'w')
fout_corr = open("./corrected_tags_eng.txt", 'w')
sent = fin.readline()
while (sent):
sent = re.sub(r'[^\w\s]', '', sent)
words = []
sent = sent.split()
for elem in sent:
elem.strip()
words.append(elem)
type_map = defaultdict(str)
type_count = defaultdict(int)
word_count = 0
for word in words:
word = word.strip(" ")
word_count += 1
type_word = finder.find(word)
type_map[word] = type_word
type_count[type_word] += 1
#print(str(word)+"(Detect:"+str(type_map[word])+")")
if (type_word == "English word"):
fout_pred.write(word + "\\" + "E ")
elif (type_word == "Bengali word"):
fout_pred.write(word + "\\" + "B ")
else:
fout_pred.write(word + "\\" + "N ")
'''
for word in words:
print (word+": "+type_map[word])
print("Type count of English: "+str(type_count["English word"]))
print("Type count of Bengali: "+str(type_count["Bengali word"]))
'''
if ((type_count["English word"]) > (type_count["Bengali word"])):
default = "e"
else:
default = "b"
print(str(lno) + default)
lno += 1
for i in range(len(words)):
word_count = 0
type_count["English word"] = 0
type_count["Bengali word"] = 0
if (default == "e"):
if (beng.beng_word(words[i]) == 1
and type_map[words[i]] == "English word"):
if (i > 1 and i < (len(words) - 2)):
word_count = 4
for j in range(i - 2, min((len(words) - 1), (i + 3))):
if (j != i):
type_count[type_map[words[j]]] += 1
if (type_count["Bengali word"] >
type_count["English word"]):
type_map[words[i]] = "Bengali word"
elif (i <= 1):
word_count = min(i + 2, len(words) - 1)
for j in range(min((len(words) - 1), (i + 3))):
if (j != i):
type_count[type_map[words[j]]] += 1
if (type_count["Bengali word"] >
type_count["English word"]):
type_map[words[i]] = "Bengali word"
elif (i >= (len(words) - 2)):
word_count = (len(words) - i) + 1
for j in range(i - 2, len(words)):
if (j != i):
type_count[type_map[words[j]]] += 1
if (type_count["Bengali word"] >
type_count["English word"]):
type_map[words[i]] = "Bengali word"
elif (default == "b"):
if (beng.beng_word(words[i]) == 1
and type_map[words[i]] == "English word"):
if (i > 1 and i < (len(words) - 2)):
word_count = 4
for j in range(i - 2, min((len(words) - 1), (i + 3))):
if (j != i):
type_count[type_map[words[j]]] += 1
if (type_count["Bengali word"] >=
type_count["English word"]):
type_map[words[i]] = "Bengali word"
elif (i <= 1):
word_count = min(i + 2, len(words) - 1)
for j in range(min((len(words) - 1), (i + 3))):
if (j != i):
type_count[type_map[words[j]]] += 1
if (type_count["Bengali word"] >=
type_count["English word"]):
type_map[words[i]] = "Bengali word"
elif (i >= (len(words) - 2)):
word_count = (len(words) - i) + 1
for j in range(i - 2, len(words)):
if (j != i):
type_count[type_map[words[j]]] += 1
if (type_count["Bengali word"] >=
type_count["English word"]):
type_map[words[i]] = "Bengali word"
if (type_map[words[i]] == "Bengali word"):
fout_corr.write(words[i] + "\\" + "B ")
elif (type_map[words[i]] == "English word"):
fout_corr.write(words[i] + "\\" + "E ")
else:
fout_corr.write(words[i] + "\\" + "N ")
#for word in words:
# print (word+": "+type_map[word])
sent = fin.readline()
fin.close()
fout_pred.close()
fout_corr.close()
def main():
type_map = defaultdict(str)
type_count = defaultdict(int)
word_count=0
sentence=input("Please enter your sentence: ")
words=sentence.split()
for word in words:
word=word.strip(" ")
word_count+=1
type_word=finder.find(word)
type_map[word]=type_word
type_count[type_word]+=1
for word in words:
print (word+": "+type_map[word])
print("Type count of English: "+str(type_count["English word"]))
print("Type count of Bengali: "+str(type_count["Bengali word"]))
if((type_count["English word"])>(type_count["Bengali word"])):
default="e"
else:
default="b"
print(default)
for i in range(len(words)):
word_count=0
type_count["English word"]=0
type_count["Bengali word"]=0
if(default=="e"):
if(beng.beng_word(words[i])==1 and type_map[words[i]]=="English word"):
if(i>1 and i<(len(words)-2)):
word_count=4
for j in range(i-2,i+3):
if(j!=i):
type_count[type_map[words[j]]]+=1
if(type_count["Bengali word"]>type_count["English word"]):
type_map[words[i]]="Bengali word"
elif (i<=1):
word_count=i+2
for j in range(i+3):
if(j!=i):
type_count[type_map[words[j]]]+=1
if(type_count["Bengali word"]>type_count["English word"]):
type_map[words[i]]="Bengali word"
elif(i>=(len(words)-2)):
word_count= (len(words)-i)+1
for j in range(i-2,len(words)):
if(j!=i):
type_count[type_map[words[j]]]+=1
if(type_count["Bengali word"]>type_count["English word"]):
type_map[words[i]]="Bengali word"
elif(default=="b"):
if(beng.beng_word(words[i])==1 and type_map[words[i]]=="English word"):
if(i>1 and i<(len(words)-2)):
word_count=4
for j in range(i-2,i+3):
if(j!=i):
type_count[type_map[words[j]]]+=1
if(type_count["Bengali word"]>=type_count["English word"]):
type_map[words[i]]="Bengali word"
elif (i<=1):
word_count=i+2
for j in range(i+3):
if(j!=i):
type_count[type_map[words[j]]]+=1
if(type_count["Bengali word"]>=type_count["English word"]):
type_map[words[i]]="Bengali word"
elif(i>=(len(words)-2)):
word_count= (len(words)-i)+1
for j in range(i-2,len(words)):
if(j!=i):
type_count[type_map[words[j]]]+=1
if(type_count["Bengali word"]>=type_count["English word"]):
type_map[words[i]]="Bengali word"
for word in words:
print (word+": "+type_map[word])
def main():
lno = 1
word_tot = 0
corr = 0
init_corr = 0
fin = open("./BanglaEnglish_FIRE2013_AnnotatedDev.txt", 'r')
sent = fin.readline()
while (sent):
words = []
lang = []
sent = sent.split()
for elem in sent:
elem = elem.split('\\')
lang.append(elem[1][0])
words.append(elem[0])
type_map = defaultdict(str)
type_count = defaultdict(int)
word_count = 0
for word in words:
word = word.strip(" ")
word_count += 1
type_word = finder.find(word)
type_map[word] = type_word
type_count[type_word] += 1
print(str(word) + "(Detect:" + str(type_map[word]) + ")")
if ((type_map[word] == "Bengali word"
and lang[words.index(word)] == 'B')
or (type_map[word] == "English word"
and lang[words.index(word)] == 'E')):
init_corr += 1
'''
for word in words:
print (word+": "+type_map[word])
print("Type count of English: "+str(type_count["English word"]))
print("Type count of Bengali: "+str(type_count["Bengali word"]))
'''
if ((type_count["English word"]) > (type_count["Bengali word"])):
default = "e"
else:
default = "b"
print(str(lno) + default)
lno += 1
for i in range(len(words)):
word_count = 0
type_count["English word"] = 0
type_count["Bengali word"] = 0
if (default == "e"):
if (beng.beng_word(words[i]) == 1
and type_map[words[i]] == "English word"):
if (i > 1 and i < (len(words) - 2)):
word_count = 4
for j in range(i - 2, min((len(words) - 1), (i + 3))):
if (j != i):
type_count[type_map[words[j]]] += 1
if (type_count["Bengali word"] >
type_count["English word"]):
type_map[words[i]] = "Bengali word"
elif (i <= 1):
word_count = min(i + 2, len(words) - 1)
for j in range(min((len(words) - 1), (i + 3))):
if (j != i):
type_count[type_map[words[j]]] += 1
if (type_count["Bengali word"] >
type_count["English word"]):
type_map[words[i]] = "Bengali word"
elif (i >= (len(words) - 2)):
word_count = (len(words) - i) + 1
for j in range(i - 2, len(words)):
if (j != i):
type_count[type_map[words[j]]] += 1
if (type_count["Bengali word"] >
type_count["English word"]):
type_map[words[i]] = "Bengali word"
elif (default == "b"):
if (beng.beng_word(words[i]) == 1
and type_map[words[i]] == "English word"):
if (i > 1 and i < (len(words) - 2)):
word_count = 4
for j in range(i - 2, min((len(words) - 1), (i + 3))):
if (j != i):
type_count[type_map[words[j]]] += 1
if (type_count["Bengali word"] >=
type_count["English word"]):
type_map[words[i]] = "Bengali word"
elif (i <= 1):
word_count = min(i + 2, len(words) - 1)
for j in range(min((len(words) - 1), (i + 3))):
if (j != i):
type_count[type_map[words[j]]] += 1
if (type_count["Bengali word"] >=
type_count["English word"]):
type_map[words[i]] = "Bengali word"
elif (i >= (len(words) - 2)):
word_count = (len(words) - i) + 1
for j in range(i - 2, len(words)):
if (j != i):
type_count[type_map[words[j]]] += 1
if (type_count["Bengali word"] >=
type_count["English word"]):
type_map[words[i]] = "Bengali word"
if (type_map[words[i]] == "Bengali word"):
det = "B"
elif (type_map[words[i]] == "English word"):
det = "E"
else:
det = "N"
print(
str(words[i]) + "(Orig:" + str(lang[i]) + " Detect:" +
str(det) + ")")
if ((type_map[words[i]] == "Bengali word" and lang[i] == 'B') or
(type_map[words[i]] == "English word" and lang[i] == 'E')):
corr += 1
word_tot += 1
#for word in words:
# print (word+": "+type_map[word])
sent = fin.readline()
print("The uncorrected accuracy is: " + str(init_corr * 100 / word_tot) +
"%")
print("The accuracy is: " + str(corr * 100 / word_tot) + "%")
word_cnt = 0
b2e_count = 0
e2b_count = 0
sent = fin.readline()
while (sent):
############ Only for Facebook corpus (COMMENT for FIRE)
#sent = re.sub(r'[^\w\s]','',sent)
##########################################
words = []
sent = sent.split()
for elem in sent:
word_cnt += 1
############ Only for FIRE CORPUS (COMMENT for Facebook)
elem = elem.split('\\')
#lang = (elem[1][0])
lang = elem[1]
word = elem[0]
#################################
word = word.strip()
if (lang == 'B' and eng.eng_search(word)):
# print(word)
b2e_count += 1
elif (lang == 'E' and beng.beng_word(word)):
print(word)
e2b_count += 1
sent = fin.readline()
print("Ambiguous words (Beng could be Eng): " + str(b2e_count))
print("Ambiguous words (Eng could be Beng): " + str(e2b_count))
print("Total words: " + str(word_cnt))
def main():
lno=1
word_tot=0
corr=0
init_corr=0
fin=open("./beng_corpus.txt",'r')
fout_pred=open("./predicted_tags_eng.txt",'w')
fout_corr=open("./corrected_tags_eng.txt",'w')
sent=fin.readline()
while(sent):
sent = re.sub(r'[^\w\s]','',sent)
words=[]
sent=sent.split()
for elem in sent:
elem.strip()
words.append(elem)
type_map = defaultdict(str)
type_count = defaultdict(int)
word_count=0
for word in words:
word=word.strip(" ")
word_count+=1
type_word=finder.find(word)
type_map[word]=type_word
type_count[type_word]+=1
#print(str(word)+"(Detect:"+str(type_map[word])+")")
if(type_word=="English word"):
fout_pred.write(word+"\\"+"E ")
elif(type_word=="Bengali word"):
fout_pred.write(word+"\\"+"B ")
else:
fout_pred.write(word+"\\"+"N ")
'''
for word in words:
print (word+": "+type_map[word])
print("Type count of English: "+str(type_count["English word"]))
print("Type count of Bengali: "+str(type_count["Bengali word"]))
'''
if((type_count["English word"])>(type_count["Bengali word"])):
default="e"
else:
default="b"
print(str(lno)+default)
lno+=1
for i in range(len(words)):
word_count=0
type_count["English word"]=0
type_count["Bengali word"]=0
if(default=="e"):
if(beng.beng_word(words[i])==1 and type_map[words[i]]=="English word"):
if(i>1 and i<(len(words)-2)):
word_count=4
for j in range(i-2,min((len(words)-1),(i+3))):
if(j!=i):
type_count[type_map[words[j]]]+=1
if(type_count["Bengali word"]>type_count["English word"]):
type_map[words[i]]="Bengali word"
elif (i<=1):
word_count=min(i+2,len(words)-1)
for j in range(min((len(words)-1),(i+3))):
if(j!=i):
type_count[type_map[words[j]]]+=1
if(type_count["Bengali word"]>type_count["English word"]):
type_map[words[i]]="Bengali word"
elif(i>=(len(words)-2)):
word_count= (len(words)-i)+1
for j in range(i-2,len(words)):
if(j!=i):
type_count[type_map[words[j]]]+=1
if(type_count["Bengali word"]>type_count["English word"]):
type_map[words[i]]="Bengali word"
elif(default=="b"):
if(beng.beng_word(words[i])==1 and type_map[words[i]]=="English word"):
if(i>1 and i<(len(words)-2)):
word_count=4
for j in range(i-2,min((len(words)-1),(i+3))):
if(j!=i):
type_count[type_map[words[j]]]+=1
if(type_count["Bengali word"]>=type_count["English word"]):
type_map[words[i]]="Bengali word"
elif (i<=1):
word_count=min(i+2,len(words)-1)
for j in range(min((len(words)-1),(i+3))):
if(j!=i):
type_count[type_map[words[j]]]+=1
if(type_count["Bengali word"]>=type_count["English word"]):
type_map[words[i]]="Bengali word"
elif(i>=(len(words)-2)):
word_count= (len(words)-i)+1
for j in range(i-2,len(words)):
if(j!=i):
type_count[type_map[words[j]]]+=1
if(type_count["Bengali word"]>=type_count["English word"]):
type_map[words[i]]="Bengali word"
if(type_map[words[i]]=="Bengali word"):
fout_corr.write(words[i]+"\\"+"B ")
elif(type_map[words[i]]=="English word"):
fout_corr.write(words[i]+"\\"+"E ")
else:
fout_corr.write(words[i]+"\\"+"N ")
#for word in words:
# print (word+": "+type_map[word])
sent=fin.readline()
fin.close()
fout_pred.close()
fout_corr.close()
def main():
lno=1
word_tot=0
corr=0
init_corr=0
beng_statistics = {}
beng_statistics = ng.ngram_prof("./beng_train.txt",beng_statistics)
eng_statistics = {}
'''
text = " ".join(brown.words())
tokenizer = RegexpTokenizer("[a-zA-Z'`]+")
text = tokenizer.tokenize(text)
text = " ".join(text)
brown_words=open("./brown_words.txt",'w')
brown_words.write(text)
brown_words.close()
'''
eng_statistics = ng.ngram_prof("./brown_words.txt",eng_statistics)
lang_stats={}
lang_stats.update({'e':eng_statistics})
lang_stats.update({'b':beng_statistics})
#fin=open("./beng_corpus.txt",'r')
fin=open("./BanglaEnglish_FIRE2013_AnnotatedDev.txt",'r')
#fout_pred=open("./predicted_tags_arff.txt",'w')
#fout_corr=open("./corrected_tags_arff.txt",'w')
word_list=[]
eng_dic=[]
beng_dic=[]
ngram=[]
surround=[]
corr_tag=[]
data=[]
sent=fin.readline()
while(sent):
############ Only for Facebook corpus (COMMENT for FIRE)
#sent = re.sub(r'[^\w\s]','',sent)
##########################################
words=[]
sent=sent.split()
for elem in sent:
############ Only for FIRE CORPUS (COMMENT for Facebook)
elem=elem.split('\\')
corr_tag.append(elem[1][0])
elem=elem[0]
#################################
elem.strip()
words.append(elem)
type_map = defaultdict(str)
type_count = defaultdict(int)
word_count=0
for word in words:
word=word.strip(" ")
word_list.append(word)
word_count+=1
beng_rat=0
eng_rat=0
if(beng.beng_word(word)):
beng_rat=1
if(eng.eng_search(word)):
eng_rat=1
############ REVERT 1/6
#eng_dic.append(eng_rat)
#beng_dic.append(beng_rat)
##############
word_statistics={}
lang_ratio = {}
grams = ngrams(word,4,pad_left=True,pad_right=True,left_pad_symbol=' ',right_pad_symbol=' ')
grams=list(grams)
ng_list=[]
for j in range (len(grams)):
ng_list.append(''.join(grams[j]))
word_statistics = ng.ngram_hash(ng_list,word_statistics)
word_statistics = sorted(word_statistics.items(), key=operator.itemgetter(1), reverse=True)
for lang, ngrams_statistics in lang_stats.items():
distance = ng.compare_ng_prof(ngrams_statistics,word_statistics)
lang_ratio.update({lang:distance})
ng_lang_result = min(lang_ratio, key = lang_ratio.get).upper()
ngram.append(ng_lang_result)
if(beng_rat and not eng_rat):
############# REVERT 2/6
beng_dic.append('2')
###################
type_word="Bengali word"
elif(eng_rat and not beng_rat):
############# REVERT 3/6
beng_dic.append('0')
###################
type_word="English word"
else:
############# REVERT 4/6
beng_dic.append('1')
###################
if(ng_lang_result=='B'):
type_word="Bengali word"
else:
type_word="English word"
type_map[word]=type_word
type_count[type_word]+=1
#print(str(word)+"(Detect:"+str(type_map[word])+")")
if((type_count["English word"])>(type_count["Bengali word"])):
default="e"
else:
default="b"
print(str(lno)+default)
lno+=1
for i in range(len(words)):
word_count=0
type_count["English word"]=0
type_count["Bengali word"]=0
if(i>1 and i<(len(words)-2)):
word_count=4
for j in range(i-2,min((len(words)-1),(i+3))):
if(j!=i):
type_count[type_map[words[j]]]+=1
elif (i<=1):
word_count=min(i+2,len(words)-1)
for j in range(min((len(words)-1),(i+3))):
if(j!=i):
type_count[type_map[words[j]]]+=1
elif(i>=(len(words)-2)):
word_count= (len(words)-i)+1
for j in range(i-2,len(words)):
if(j!=i):
type_count[type_map[words[j]]]+=1
if(word_count):
surround.append(str(type_count["Bengali word"]/word_count))
#if((type_count["Bengali word"]/word_count)>=0.5):
# surround.append('1')
#else:
# surround.append('0')
else:
surround.append('0')
sent=fin.readline()
############ Only for Facebook corpus (COMMENT for FIRE)
#real_tag = open("./real_tags.txt",'r')
#line = real_tag.readline().split()
#for word in line:
# tags=word.split('\\')
# corr_tag.append(tags[1])
#real_tag.close()
######################################
for i in range(len(word_list)):
vector=[]
# vector.append(word_list[i])
########REVERT 5/6
#vector.append(int(eng_dic[i]))
##############
vector.append(int(beng_dic[i]))
vector.append(ngram[i])
vector.append(float(surround[i]))
vector.append(corr_tag[i])
data.append(vector)
obj={
'description': u'',
'relation': 'langid',
'attributes': [
#############REVERT 6/6
#('eng_dict','NUMERIC'),
####################
('beng_dict','NUMERIC'),
('ngram','STRING'),
('beng_surr','REAL'),
('real_tag','STRING')
],
'data':data,
}
final = arff.dumps(obj)
#FIRE
final_file=open("./lang_id_fire.arff",'w')
#
#Facebook
#final_file=open("./lang_id.arff",'w')
#
final_file.write(final)
final_file.close()
fin.close()
def main():
lno=1
word_tot=0
corr=0
init_corr=0
fin=open("./BanglaEnglish_FIRE2013_AnnotatedDev.txt",'r')
sent=fin.readline()
while(sent):
words=[]
lang=[]
sent=sent.split()
for elem in sent:
elem=elem.split('\\')
lang.append(elem[1][0])
words.append(elem[0])
type_map = defaultdict(str)
type_count = defaultdict(int)
word_count=0
for word in words:
word=word.strip(" ")
word_count+=1
type_word=finder.find(word)
type_map[word]=type_word
type_count[type_word]+=1
print(str(word)+"(Detect:"+str(type_map[word])+")")
if((type_map[word]=="Bengali word" and lang[words.index(word)]=='B') or (type_map[word]=="English word" and lang[words.index(word)]=='E')):
init_corr+=1
'''
for word in words:
print (word+": "+type_map[word])
print("Type count of English: "+str(type_count["English word"]))
print("Type count of Bengali: "+str(type_count["Bengali word"]))
'''
if((type_count["English word"])>(type_count["Bengali word"])):
default="e"
else:
default="b"
print(str(lno)+default)
lno+=1
for i in range(len(words)):
word_count=0
type_count["English word"]=0
type_count["Bengali word"]=0
if(default=="e"):
if(beng.beng_word(words[i])==1 and type_map[words[i]]=="English word"):
if(i>1 and i<(len(words)-2)):
word_count=4
for j in range(i-2,min((len(words)-1),(i+3))):
if(j!=i):
type_count[type_map[words[j]]]+=1
if(type_count["Bengali word"]>type_count["English word"]):
type_map[words[i]]="Bengali word"
elif (i<=1):
word_count=min(i+2,len(words)-1)
for j in range(min((len(words)-1),(i+3))):
if(j!=i):
type_count[type_map[words[j]]]+=1
if(type_count["Bengali word"]>type_count["English word"]):
type_map[words[i]]="Bengali word"
elif(i>=(len(words)-2)):
word_count= (len(words)-i)+1
for j in range(i-2,len(words)):
if(j!=i):
type_count[type_map[words[j]]]+=1
if(type_count["Bengali word"]>type_count["English word"]):
type_map[words[i]]="Bengali word"
elif(default=="b"):
if(beng.beng_word(words[i])==1 and type_map[words[i]]=="English word"):
if(i>1 and i<(len(words)-2)):
word_count=4
for j in range(i-2,min((len(words)-1),(i+3))):
if(j!=i):
type_count[type_map[words[j]]]+=1
if(type_count["Bengali word"]>=type_count["English word"]):
type_map[words[i]]="Bengali word"
elif (i<=1):
word_count=min(i+2,len(words)-1)
for j in range(min((len(words)-1),(i+3))):
if(j!=i):
type_count[type_map[words[j]]]+=1
if(type_count["Bengali word"]>=type_count["English word"]):
type_map[words[i]]="Bengali word"
elif(i>=(len(words)-2)):
word_count= (len(words)-i)+1
for j in range(i-2,len(words)):
if(j!=i):
type_count[type_map[words[j]]]+=1
if(type_count["Bengali word"]>=type_count["English word"]):
type_map[words[i]]="Bengali word"
if(type_map[words[i]]=="Bengali word"):
det="B"
elif(type_map[words[i]]=="English word"):
det="E"
else:
det="N"
print(str(words[i])+"(Orig:"+str(lang[i])+" Detect:"+str(det)+")")
if((type_map[words[i]]=="Bengali word" and lang[i]=='B') or (type_map[words[i]]=="English word" and lang[i]=='E')):
corr+=1
word_tot+=1
#for word in words:
# print (word+": "+type_map[word])
sent=fin.readline()
print("The uncorrected accuracy is: "+str(init_corr*100/word_tot)+"%")
print("The accuracy is: "+str(corr*100/word_tot)+"%")
word_cnt = 0
b2e_count=0
e2b_count=0
sent=fin.readline()
while(sent):
############ Only for Facebook corpus (COMMENT for FIRE)
#sent = re.sub(r'[^\w\s]','',sent)
##########################################
words=[]
sent=sent.split()
for elem in sent:
word_cnt+=1
############ Only for FIRE CORPUS (COMMENT for Facebook)
elem=elem.split('\\')
#lang = (elem[1][0])
lang=elem[1]
word = elem[0]
#################################
word=word.strip()
if (lang=='B' and eng.eng_search(word)):
# print(word)
b2e_count+=1
elif (lang=='E' and beng.beng_word(word)):
print(word)
e2b_count+=1
sent=fin.readline()
print("Ambiguous words (Beng could be Eng): "+str(b2e_count))
print("Ambiguous words (Eng could be Beng): "+str(e2b_count))
print("Total words: "+str(word_cnt))
def main():
type_map = defaultdict(str)
type_count = defaultdict(int)
word_count = 0
sentence = input("Please enter your sentence: ")
words = sentence.split()
for word in words:
word = word.strip(" ")
word_count += 1
type_word = finder.find(word)
type_map[word] = type_word
type_count[type_word] += 1
for word in words:
print(word + ": " + type_map[word])
print("Type count of English: " + str(type_count["English word"]))
print("Type count of Bengali: " + str(type_count["Bengali word"]))
if ((type_count["English word"]) > (type_count["Bengali word"])):
default = "e"
else:
default = "b"
print(default)
for i in range(len(words)):
word_count = 0
type_count["English word"] = 0
type_count["Bengali word"] = 0
if (default == "e"):
if (beng.beng_word(words[i]) == 1
and type_map[words[i]] == "English word"):
if (i > 1 and i < (len(words) - 2)):
word_count = 4
for j in range(i - 2, i + 3):
if (j != i):
type_count[type_map[words[j]]] += 1
if (type_count["Bengali word"] >
type_count["English word"]):
type_map[words[i]] = "Bengali word"
elif (i <= 1):
word_count = i + 2
for j in range(i + 3):
if (j != i):
type_count[type_map[words[j]]] += 1
if (type_count["Bengali word"] >
type_count["English word"]):
type_map[words[i]] = "Bengali word"
elif (i >= (len(words) - 2)):
word_count = (len(words) - i) + 1
for j in range(i - 2, len(words)):
if (j != i):
type_count[type_map[words[j]]] += 1
if (type_count["Bengali word"] >
type_count["English word"]):
type_map[words[i]] = "Bengali word"
elif (default == "b"):
if (beng.beng_word(words[i]) == 1
and type_map[words[i]] == "English word"):
if (i > 1 and i < (len(words) - 2)):
word_count = 4
for j in range(i - 2, i + 3):
if (j != i):
type_count[type_map[words[j]]] += 1
if (type_count["Bengali word"] >=
type_count["English word"]):
type_map[words[i]] = "Bengali word"
elif (i <= 1):
word_count = i + 2
for j in range(i + 3):
if (j != i):
type_count[type_map[words[j]]] += 1
if (type_count["Bengali word"] >=
type_count["English word"]):
type_map[words[i]] = "Bengali word"
elif (i >= (len(words) - 2)):
word_count = (len(words) - i) + 1
for j in range(i - 2, len(words)):
if (j != i):
type_count[type_map[words[j]]] += 1
if (type_count["Bengali word"] >=
type_count["English word"]):
type_map[words[i]] = "Bengali word"
for word in words:
print(word + ": " + type_map[word])