remove duplicate rows in csv file python
# credit to the Stack Overflow user in the source link
with open('file_with_duplicates.csv','r') as in_file, open('ouput.csv','w') as out_file:
seen = set() # set for fast O(1) amortized lookup
for line in in_file:
if line in seen:
continue # skip duplicate
seen.add(line)
out_file.write(line)