def test_find_with_letter_pattern_in_string(self):
string = 'onetwothreefourfive'
assert find(string, 'one') is True
assert find(string, 'two') is True
assert find(string, 'three') is True
assert find(string, 'four') is True
assert find(string, 'five') is True
def test_find_with_number_pattern_in_string(self):
string = '12345'
assert find(string, '1') is True
assert find(string, '12') is True
assert find(string, '123') is True
assert find(string, '1234') is True
assert find(string, '12345') is True
def test_find_with_empty_pattern(self):
string = 'a'
pattern = ''
assert find(string, pattern) is False
string = ''
pattern = ''
assert find(string, pattern) is False
def location(bot, update):
lang = get_lang(update)
bot.send_message(chat_id=update.message.chat_id,
text=rand_str(lang, "try-find-close-hospital"))
poi = finder.find(lat=update.message.location.latitude,
lng=update.message.location.longitude)
results = [
finder.get_details(poi[i].attrib["id"]) for i in range(0, len(poi))
]
bot.send_message(chat_id=update.message.chat_id,
parse_mode=telegram.ParseMode.MARKDOWN,
text=i18n.t("strings.{}.closest-hospital-is".format(
get_lang(update)),
name=results[0]["name"]))
bot.send_location(chat_id=update.message.chat_id,
latitude=poi[0].attrib["lat"],
longitude=poi[0].attrib["lon"])
if len(results) > 1:
time.sleep(1.5 + 0.5 * (len(results) - 1))
other_options = rand_str(get_lang(update),
"other-hospital-options") + "\n"
for i in results[1:]:
other_options += "∙ *{}*\n".format(i["name"])
bot.send_message(chat_id=update.message.chat_id,
text=other_options,
parse_mode=telegram.ParseMode.MARKDOWN)
def query_text(query):
try:
data = {}
choice = query.query
data = finder.find(choice)
desc = 'Поиск: ' + data["name"]
text = 'Поиск по: ' + query.query + '\n\n*' + str(
data["name"]
) + ' (' + str(
data["num"]
) + ' номер в таблице)\n' + '*' + 'Русское название: ' + '*' + data[
"Rname"] + '*' + '\nЛатинское название: ' + '*' + data[
"Lname"] + '*' + '\nАнглийское название: ' + '*' + data[
"Ename"] + '*' + '\nДата открытия: ' + '*' + str(
data["Birth"]
) + '*' + '\nЭлектронная оболочка: ' + '*' + data[
"Eshell"] + '*' + '\nСтепень окисления: ' + '*' + data[
"Doxi"] + '*' + '\nАтомная масса: ' + '*' + data[
"Amass"] + ' (г/моль)' + '*' + '\nПлотность: ' + '*' + data[
"density"] + ' (г/см³)' + '*' + '\nТемпература плавления: ' + '*' + data[
"Tmelting"] + '°C' + '*' + '\nТемпература кипения: ' + '*' + data[
"boil"] + '°C' + '*'
r = types.InlineQueryResultArticle(
'1', desc,
types.InputTextMessageContent(text, parse_mode="MARKDOWN"))
bot.answer_inline_query(query.id, [r])
rate.append(data["name"])
except:
er = 'Поиск по: ' + query.query + '\n\nЭлемент не найден!'
r2 = types.InlineQueryResultArticle(
'2',
title='Ошибка!',
description='Элемент не найден!',
input_message_content=types.InputTextMessageContent(er))
bot.answer_inline_query(query.id, [r2])
def getAvailableSwap(self):
result = find(
'SwapAvailable',
subprocess.check_output(['cat', '/proc/meminfo'
]).decode('utf-8').split('\n'))
if not result == '':
return result
else:
return 'SwapAvailable: 0 kB'
def find_files(args):
"""
Reads data from files and outputs to files
"""
for name in find(args.glob):
basename, _ = os.path.splitext(name)
new_name = basename + "_parsed.csv"
if args.save:
output = open(new_name, WRITEABLE)
else:
output = None
pipe(args, open(name), output)
return
def analyze(args):
"""
Reads data from files and outputs to files
"""
for name in find(args.glob):
basename, _ = os.path.splitext(name)
new_name = basename + "_parsed.csv"
if args.save:
output = open(new_name, WRITEABLE)
else:
output = None
pipe(args, open(name), output)
return
def rater(message):
if message.from_user.id in admin:
x = message.text.split(' ')[1]
if x == 777:
bot.send_message(message.chat.id, rate)
data = finder.find(x)
if data == None:
bot.send_message(message.chat.id, 'Такого элемента нет')
else:
y = rate.count(data["name"])
text = data["name"] + ' - искалось ' + str(y) + ' раз'
bot.send_message(message.chat.id, text)
else:
bot.send_message(message.chat.id, 'Вы не уполномочены!')
def finds(message):
keyboard = types.InlineKeyboardMarkup()
rateMe = types.InlineKeyboardButton(
text="Оценить!",
url="https://telegram.me/storebot?start=zChemistryBot")
joinG = types.InlineKeyboardButton(text='Группа!',
url="t.me/zChemistryGroup")
joinB = types.InlineKeyboardButton(text='Канал!',
url="t.me/zChemistryBlog")
keyboard.add(rateMe, joinG, joinB)
choice = message.text
data = finder.find(choice)
if data == None:
text = 'Такого не существует!'
bot.send_message(message.chat.id, text)
else:
rate.append(data["name"])
try:
photo = open(
elements_1[choice]['/home/zchemistry/Chem/' + data["link"]],
'rb')
bot.send_photo(message.chat.id, photo)
photo.close()
except Exception as error:
print(error)
text = '*' + str(data["name"]) + ' (' + str(
data["num"]
) + ' номер в таблице)\n' + '*' + 'Русское название: ' + '*' + data[
"Rname"] + '*' + '\nЛатинское название: ' + '*' + data[
"Lname"] + '*' + '\nАнглийское название: ' + '*' + data[
"Ename"] + '*' + '\nДата открытия: ' + '*' + str(
data["Birth"]
) + '*' + '\nЭлектронная оболочка: ' + '*' + data[
"Eshell"] + '*' + '\nСтепень окисления: ' + '*' + data[
"Doxi"] + '*' + '\nАтомная масса: ' + '*' + data[
"Amass"] + ' (г/моль)' + '*' + '\nПлотность: ' + '*' + data[
"density"] + ' (г/см³)' + '*' + '\nТемпература плавления: ' + '*' + data[
"Tmelting"] + '°C' + '*' + '\nТемпература кипения: ' + '*' + data[
"boil"] + '°C' + '*'
bot.send_message(message.chat.id, text, parse_mode="MARKDOWN")
bot.send_message(
message.chat.id,
'Понравилось? ставь самую высокую оценку.\nА также присоединяйся к нам!',
reply_markup=keyboard,
disable_web_page_preview=True)
def main():
lno = 1
word_tot = 0
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
'''
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 ((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 accuracy is: " + str(corr * 100 / word_tot) + "%")
def main():
lno=1
word_tot=0
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
'''
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((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 accuracy is: "+str(corr*100/word_tot)+"%")
def output(input_json):
'''
Find the module to calculate the output, 'ask4' should be the module name.
'''
if 'ask4' not in input_json:
#input_json['error'] = "no ask4 no done anything"
return {error : "no ask4 no done anything"}
asked = input_json['ask4'].replace('.', '_')
try:
main = finder.find(Path_of_Workers, asked)
output = main(input_json) or {}
return output
except (Exception) as e:
print('except exception:')
print(e)
# noop: no operation
return noop_service(input_json)
def getModelName(self):
return find(
'Model name',
subprocess.check_output(['lscpu']).decode('utf-8').split('\n'))
def getFreeSwap(self):
return find(
'SwapFree',
subprocess.check_output(['cat', '/proc/meminfo'
]).decode('utf-8').split('\n'))
def location(bot, update):
print(update.message.location)
bot.send_message(chat_id=update.message.chat_id, text="")
poi = finder.find(lat=update.message.location.latitude,
lng=update.message.location.longitude)
def getTotalMemory(self):
return find(
'MemTotal',
subprocess.check_output(['cat', '/proc/meminfo'
]).decode('utf-8').split('\n'))
def test_find_with_none_pattern(self):
string = ''
pattern = None
assert find(string, pattern) is False
def test_find_with_empty_string(self):
string = ''
pattern = 'one'
assert find(string, pattern) is False
def test_find_with_none_string(self):
string = None
pattern = 'one'
assert find(string, pattern) is False
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("./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
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) + "%")
def select(self, query_=None, table=None, limit=0):
data_, error = find(self.__name, self.__data, table, query_, limit)
if error:
raise Exception(error)
return data_
def getArchitecture(self):
return find(
'Architecture',
subprocess.check_output(['lscpu']).decode('utf-8').split('\n'))
def find():
term = request.args.get('term')
files_found = finder.find(indexed_files, term)
return json.dumps(files_found)
def test_find_with_letter_pattern_not_in_string(self):
string = 'onetwothreefourfive'
assert find(string, 'six') is False
assert find(string, 'seven') is False
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 test_find_with_number_pattern_not_in_string(self):
string = '12345'
assert find(string, '6') is False
assert find(string, '67') is False
def example_handler(bot, update):
nametext = update.message.text
name = nametext
bot.send_message(update.message.chat_id, text=finder.find(nametext))
def test_find_with_any_pattern_in_string(self):
string = 'asdn\y of23h01148n+)&^%#@xc'
assert find(string, '8n+)&') is True
assert find(string, '8n+)&A') is False
assert find(string, 'A8n+)&') is False
assert find(string, '\y ') is True
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
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)+"%")
