def stemreplacer(reader):
line=reader.readline()
replacer = SpellingReplacer()
fo=open("stemreplacer.txt","a+" )
while line:
fo.write(replacer.replace(line))
line=reader.readline()
fo.close()
def spell_correction(tweet):
replacer=SpellingReplacer()
length=len(tweet)
i=0
dGB=enchant.Dict('en_GB')
while i<length:
if not dGB.check(tweet[i]):
tweet[i]=replacer.replace(tweet[i])
i=i+1
return str(tweet)
def spelling_replacer(document): from replacers import SpellingReplacer replacer = SpellingReplacer() return replacer.replace(document)
<br class="spacer" />
</div>
<!--body end -->
<!--footer start --><!--footer end -->
</body>
</html>
"""
# open and read the csv file into memory
file = open(saibaba.csv)
reader = csv.reader(file)
# iterate through the lines and print them to stdout
# the csv module returns us a list of lists and we
# simply iterate through it
replacer = SpellingReplacer()
fo1 = open("c-expansion.txt", "a+")
fo6 = open("h-synset.txt", "a+")
fo5 = open("g-spellcheck.txt", "a+")
fo4 = open("f-stemmingwords.txt", "a+")
fo3 = open("e-wordswithoutstopwords.txt", "a+")
fo2 = open("d-words.txt", "a+")
fo = open("a-sentence.txt", "a+")
for line in reader:
a = PunktSentenceTokenizer().tokenize(line[2])
fo.write('\n'.join(a))
review = '\n'.join(a)
review = review.lower()
#Convert www.* or https?://* to URL
review = re.sub('((www\.[\s]+)|(https?://[^\s]+))', 'URL', review)
from replacers import SpellingReplacer
import enchant
input = "i ahve nt done"
input_list = input.split(" ")
replacer = SpellingReplacer()
length = len(input_list)
print length
i = 0
dGB = enchant.Dict('en_GB')
while i < length:
if not dGB.check(input_list[i]):
input_list[i] = replacer.replace(input_list[i])
i = i + 1
print str(input_list)
import enchant
from replacers import SpellingReplacer
replacer = SpellingReplacer()
print(replacer.replace('cookbok'))
# enchant
print(enchant.list_languages())
print(replacer.replace('goose') == 'goose')
# 1_34
print(edit_distance("relate", "relation"))
print(edit_distance("suggestion", "calculation"))
# 1_35
X = {10, 20, 30, 40}
Y = {20, 30, 60}
print(jaccard_distance(X, Y))
print('================================')
print('Spelling Correction with Enchant')
print('================================')
replacer = SpellingReplacer()
print(replacer.replace('cookbok') == 'cookbook')
d = enchant.Dict('en')
print(d.suggest(
'languege')) # == ['language', 'languages', 'languor', "language's"]
print(edit_distance('language', 'languege') == 1)
print(edit_distance('language', 'languor') == 3)
print(enchant.list_languages()) # == ['en', 'en_CA', 'en_GB', 'en_US']
dUS = enchant.Dict('en_US')
dGB = enchant.Dict('en_GB')
us_replacer = SpellingReplacer('en_US')
gb_replacer = SpellingReplacer('en_GB')
import re
import pprint
from replacers import SpellingReplacer
def my_range(start, end, step):
while start <= end:
yield start
start += step
f = open("separate_text.py", 'r')
lines = f.readlines()
f.close()
f = open("separate_text.py", 'w')
l = ' '
for line in lines:
if len(line.split()) > 4:
g = line.split()
for x in my_range(0, len(line.split()) - 1, 1):
replacer = SpellingReplacer()
l += (replacer.replace(g[x]) + ' ')
f.write(l + '\n')
l = ' '
if len(line.split()) == 0:
f.write(line)