def DictionaryCreation(vocab_dict):
py_compile.compile('segmentmeta.py')
from segmentmeta import segmentamt
new_temp=[]
seg_list=[]
file =open(vocab_dict_file,'w')
for key in vocab_dict:
new_temp.append(key)
new_temp=sorted(new_temp)# sorted keys of the clustered word dictionary
final_dict = dict()
for x in xrange (1, len(new_temp)):
seg = (segmentamt(new_temp[x]))
seg_list.append(seg)
for y in xrange(len(seg)):
final_vo=[]
final_vo = MaxiMumInVocab(vocab_dict,seg[y].upper())
if(final_dict.has_key(final_vo[0])==False):
final_dict[final_vo[0]]=final_vo[1]
file.write(str(final_vo[0])+'\n')
file.close()
def DictionaryCreation(vocab_dict):
py_compile.compile('segmentmeta.py')
from segmentmeta import segmentamt
new_temp = []
seg_list = []
file = open(vocab_dict_file, 'w')
for key in vocab_dict:
new_temp.append(key)
new_temp = sorted(new_temp) # sorted keys of the clustered word dictionary
final_dict = dict()
for x in xrange(1, len(new_temp)):
seg = (segmentamt(new_temp[x]))
seg_list.append(seg)
for y in xrange(len(seg)):
final_vo = []
final_vo = MaxiMumInVocab(vocab_dict, seg[y].upper())
if (final_dict.has_key(final_vo[0]) == False):
final_dict[final_vo[0]] = final_vo[1]
file.write(str(final_vo[0]) + '\n')
file.close()
def PrepareFinalString(Address,cluster,wordlist,abb_list,vocab_dict):
from segmentmeta import segmentamt
from segment import segment
xyz_score=45
print(Address)
Address =Address.lower()
Address = (''.join( abb_list.get( word, word ) for word in re.split( '(\W+)', Address )) )
Address = re.sub('[^A-Za-z]+',' ', Address) #extracting on alphabets
Address= Address.split(' ') #removing all white spaces to make a single long query for segmentation i.e ahmedblockgardentown
I_do_not_have_anymore_names=[]
for k in xrange(len(Address)):
temp_segment = segment(Address[k])
print temp
if(len(temp_segment)>1):
for x in xrange(len(temp_segment)):
answer = doublemetaphone(temp_segment[x])
if (len(answer[0])>1):
metaph=answer[0]
if(cluster.has_key(metaph.upper())):
I_do_not_have_anymore_names.append(str(MaxiMumInVocab(cluster,metaph.upper())[0]))
else:
I_do_not_have_anymore_names.append(str(temp_segment[x]))
else:
metaph=answer[1]
if(cluster.has_key(metaph.upper())):
I_do_not_have_anymore_names.append(str(MaxiMumInVocab(cluster,metaph.upper())[0]))
else:
I_do_not_have_anymore_names.append(str(temp_segment[x]))
#if not metaph:
#I_do_not_have_anymore_names.append(temp_segment[x])
elif (len(temp_segment)==1):
if(len(temp_segment[0])==1):
I_do_not_have_anymore_names.append(temp_segment[0])
else:
Match_score = SpellCheck(temp_segment[0],wordlist)
xyz_score = (float(Match_score[0][1])*100)
if(xyz_score<85):
answer = doublemetaphone(temp_segment[0])
if (len(answer[0])>1):
metaph=answer[0]
else:
metaph=answer[1]
if not metaph:
I_do_not_have_anymore_names.append(str(temp_segment[0]))
segmented_meta=(segmentamt(metaph))
#print (segmented_meta)
for y in xrange(len(segmented_meta)):
if(cluster.has_key(segmented_meta[y].upper())):
I_do_not_have_anymore_names.append(str(MaxiMumInVocab(cluster,segmented_meta[y].upper())[0]))
else:
I_do_not_have_anymore_names.append(str(temp_segment))
else:
I_do_not_have_anymore_names.append(str(Match_score[0][0]))
#print(I_do_not_have_anymore_names)
Address =" ".join(I_do_not_have_anymore_names)
Address = (''.join( abb_list.get( word, word ) for word in re.split( '(\W+)', Address )) )
try:
remove_list = RemoveList(vocab_dict)
Address = (''.join( remove_list.get( word, word ) for word in re.split( '(\W+)', Address)))
except:
Address= re.sub(' +',' ',Address)
return Address.strip()
def PrepareFinalString(Address, cluster, wordlist, abb_list, vocab_dict):
from segmentmeta import segmentamt
from segment import segment
xyz_score = 45
print(Address)
Address = Address.lower()
Address = (''.join(
abb_list.get(word, word) for word in re.split('(\W+)', Address)))
Address = re.sub('[^A-Za-z]+', ' ', Address) #extracting on alphabets
Address = Address.split(
' '
) #removing all white spaces to make a single long query for segmentation i.e ahmedblockgardentown
I_do_not_have_anymore_names = []
for k in xrange(len(Address)):
temp_segment = segment(Address[k])
print temp
if (len(temp_segment) > 1):
for x in xrange(len(temp_segment)):
answer = doublemetaphone(temp_segment[x])
if (len(answer[0]) > 1):
metaph = answer[0]
if (cluster.has_key(metaph.upper())):
I_do_not_have_anymore_names.append(
str(MaxiMumInVocab(cluster, metaph.upper())[0]))
else:
I_do_not_have_anymore_names.append(str(
temp_segment[x]))
else:
metaph = answer[1]
if (cluster.has_key(metaph.upper())):
I_do_not_have_anymore_names.append(
str(MaxiMumInVocab(cluster, metaph.upper())[0]))
else:
I_do_not_have_anymore_names.append(str(
temp_segment[x]))
#if not metaph:
#I_do_not_have_anymore_names.append(temp_segment[x])
elif (len(temp_segment) == 1):
if (len(temp_segment[0]) == 1):
I_do_not_have_anymore_names.append(temp_segment[0])
else:
Match_score = SpellCheck(temp_segment[0], wordlist)
xyz_score = (float(Match_score[0][1]) * 100)
if (xyz_score < 85):
answer = doublemetaphone(temp_segment[0])
if (len(answer[0]) > 1):
metaph = answer[0]
else:
metaph = answer[1]
if not metaph:
I_do_not_have_anymore_names.append(str(
temp_segment[0]))
segmented_meta = (segmentamt(metaph))
#print (segmented_meta)
for y in xrange(len(segmented_meta)):
if (cluster.has_key(segmented_meta[y].upper())):
I_do_not_have_anymore_names.append(
str(
MaxiMumInVocab(
cluster,
segmented_meta[y].upper())[0]))
else:
I_do_not_have_anymore_names.append(
str(temp_segment))
else:
I_do_not_have_anymore_names.append(str(Match_score[0][0]))
#print(I_do_not_have_anymore_names)
Address = " ".join(I_do_not_have_anymore_names)
Address = (''.join(
abb_list.get(word, word) for word in re.split('(\W+)', Address)))
try:
remove_list = RemoveList(vocab_dict)
Address = (''.join(
remove_list.get(word, word)
for word in re.split('(\W+)', Address)))
except:
Address = re.sub(' +', ' ', Address)
return Address.strip()
