diff options
Diffstat (limited to 'scripts')
| -rw-r--r-- | scripts/fix_fav_counts.py | 24 | ||||
| -rwxr-xr-x | scripts/sort_faves.sh | 4 |
2 files changed, 21 insertions, 7 deletions
diff --git a/scripts/fix_fav_counts.py b/scripts/fix_fav_counts.py index 00e8d0f..0472488 100644 --- a/scripts/fix_fav_counts.py +++ b/scripts/fix_fav_counts.py @@ -3,13 +3,23 @@ before running this command, please run the following SQL, which tallies the faves per post: - COPY (SELECT messages.user_id, tags.message_id, COUNT(tags.message_id) AS mycount, TO_CHAR(messages.created_on, 'YYYYMMDD') + COPY (SELECT messages.user_id, tags.message_id, COUNT(tags.message_id) + AS mycount, TO_CHAR(messages.created_on, 'YYYYMMDD') FROM tags, messages WHERE tags.message_id = messages.message_id AND tags.tag = 'favorite' GROUP BY tags.message_id, messages.user_id, messages.created_on) - TO '/tmp/fav_counts2.csv' WITH CSV; + TO '/tmp/fav_counts69.csv' WITH CSV; - then run ./sort_faves.sh which will pre-sort the data for this script. + this file will be owned by the postgres user, + so change the 69 to some other number (janky i know) + + then run ./sort_faves.sh /tmp/fav_counts69.csv + ...which will pre-sort the data for this script. + + then run python3 fix_fav_counts.py + ...this script. + + if you run this twice, don't worry, data will not be duplicated. """ import re @@ -33,6 +43,7 @@ def fetch_users(): # field order: user_id, message_id, score, date def load_faves_by_user(): + print("fixing favscores...") nicks = load_nicks() counter = 0 user_counter = 0 @@ -59,6 +70,7 @@ def load_faves_by_user(): counter += 1 def load_faves_by_date(): + print("fixing daily halls...") date_counter = 0 counter = 0 date = "" @@ -79,6 +91,7 @@ def load_faves_by_date(): counter += 1 def load_hall(): + print("fixing hall...") with open('faves/hall.csv', 'r') as csvfile: reader = csv.reader(csvfile) for row in reader: @@ -93,7 +106,8 @@ def load_nicks(): return nicks if __name__ == "__main__": - # load_hall() - # load_faves_by_user() + load_hall() + load_faves_by_user() load_faves_by_date() + print("done!") diff --git a/scripts/sort_faves.sh b/scripts/sort_faves.sh index eb28a39..3daad0b 100755 --- a/scripts/sort_faves.sh +++ b/scripts/sort_faves.sh @@ -12,9 +12,9 @@ echo "Get the top 50 faves for the Hall of Fame" sort -t, -k3,3 -rn $1 | head -50 > faves/hall.csv echo "Group faves by user for popular pages, total fave scores" -sort -t, -k1,1 -r -k3,3 -n faves/counts_sorted.csv > faves/by_user.csv +sort -t, -k1,1 -r -k3,3 -n $1 > faves/by_user.csv echo "Group faves by date for daily tallies" -sort -t, -k4,4 -r -k3,3 -n faves/counts_sorted.csv > faves/by_date.csv +sort -t, -k4,4 -r -k3,3 -n $1 > faves/by_date.csv |