projects.mako.cc - harrypotter-wikipedia-cdsw-solutions/blob - solution2-alternative.py

   1 # Q: Who are the 5 most active editors on articles in Harry Potter? How may edits have they made?
   2
   3 from csv import DictReader
   4
   5 # read in the input file and count by day
   6 input_file = open("hp_wiki.tsv", 'r', encoding="utf-8")
   7
   8 edits_by_editor = {}
   9 for row in DictReader(input_file, delimiter="\t"):
  10     user = row['user']
  11
  12     if user in edits_by_editor:
  13         edits_by_editor[user] = edits_by_editor[user] + 1
  14     else:
  15         edits_by_editor[user] = 1
  16
  17 input_file.close()
  18
  19 # output the counts by day
  20 output_file = open("hp_edits_by_user.tsv", "w", encoding='utf-8')
  21
  22 # write a header
  23 output_file.write("user\tedits\n")
  24
  25 # iterate through every day and print out data into the file
  26 for user in edits_by_editor:
  27     output_file.write("\t".join([user, str(edits_by_editor[user])]) + "\n")
  28
  29 output_file.close()
  30