gistfile1.txt

#Purpose: Removes all duplicate strings from a csv
#Author:  Jake Gaylor
#Written: June 8th, 2012
import csv

#initiate the csv reader
reader = csv.reader(open('words.csv','rU'), delimiter=",", quotechar='|')

#open the target file
target = open('trimmed_list.txt', 'w+')

#create an empty list to feed the csv into
list_of_words = []

#combine the csv into one list
for row in reader:
	for word in row:
		list_of_words.append(word)

#copy the list
trimmed_list = list_of_words

#remove duplicates
set = set(trimmed_list)
trimmed_list = list(set)		

#print the size of each list
print len(list_of_words)
print len(trimmed_list)

#sort the new list
trimmed_list.sort()

for w in trimmed_list:
	target.write(w+"\n")