#####words Data Set####
words_data_set = pandas.DataFrame({'keywords':['wlmart womens book set','microsoft fish sauce','books from walmat store','mens login for facebook fools','mens login for facbook fools','login for twetter boy','apples from cook']})

#####Company Name List#####
company_name_list = ['walmart','microsoft','facebook','twitter','amazon','apple']

######Check for fuzzy match######
import pandas
from fuzzywuzzy import fuzz
from fuzzywuzzy import process
import time
print(len(words_data_set),'....rows')
start_time = time.time()


fuzzed_data_final = pandas.DataFrame()
for s in words_data_set.keywords.tolist():

#Flatten each word within the string
step1 = words_data_set[words_data_set.keywords == s]
step1['keywords2'] = step1.keywords.str.split()
step2 = step1.keywords2.values.tolist()
step3 = [item for sublist in step2 for item in sublist]
step3 = pandas.DataFrame(step3)
step3.columns = ['search_words']
step3['keywords'] = s

#For each word within the string, do a fuzzy match, where if the max score for the fuzzy match is >= 95 then replace the word with blank, else retain the word

fuzzed_data = pandas.DataFrame()
for w in step3.search_words.tolist():
    step4 = step3[step3.search_words == w]
    step5 = pandas.DataFrame(process.extract(w,keyword_list))
    step5.columns = ['w','score']
    if step5.score.max() >= 90:
        w = ''
    else:
        w

    step4['search_words'] = w
    fuzzed_data = fuzzed_data.append(step4)
fuzzed_data_final = fuzzed_data_final.append(fuzzed_data)

print("--- %s seconds ---" % (time.time() - start_time))