updated for new version of catscan
[harrypotter-wikipedia-cdsw] / hpwp-trend.py
1 from csv import DictReader
2
3 # read in the input file and count by day
4 input_file = open("hp_wiki.tsv", 'r', encoding="utf-8")
5
6 edits_by_day = {}
7 for row in DictReader(input_file, delimiter="\t"):
8     day_string = row['timestamp'][0:10]
9
10     if day_string in edits_by_day:
11         edits_by_day[day_string] = edits_by_day[day_string] + 1
12     else:
13         edits_by_day[day_string] = 1
14
15 input_file.close()
16
17 # output the counts by day
18 output_file = open("hp_edits_by_day.tsv", "w", encoding='utf-8')
19
20 # write a header
21 output_file.write("date\tedits\n")
22
23 # iterate through every day and print out data into the file
24 for day_string in edits_by_day.keys():
25     output_file.write("\t".join([day_string, str(edits_by_day[day_string])]) + "\n")
26
27 output_file.close()

Benjamin Mako Hill || Want to submit a patch?