Commons:Picture of the Year/2015/R1/Results/Python code

From Wikimedia Commons, the free media repository
Jump to navigation Jump to search

Picture of the Year 2015
The results are in! View results »
end
1


POTY 2015 : IntroductionRulesDiscussionTranslationsCommitteeHelpR1 Candidates / GalleryR2 GalleryResults

code

//Extremely hacky and ugly code, just to get something up. Never code like this in real life
import json

with open("poty2015r1.json") as f:
    votes=json.loads(f.read())

//Note eligible voters that were marked in the json as ineligible

renamed_pairs=[[u'Zaphod',u'Jonnie Nord'],[u'Vikoula5',u'Reda Kerbouche'],[u'Ask27',u'SnapMeUp'],[u'Garik.Khachatryan',u'TonJ'],[u'Alifatehighahfarokhi',u'AliFatehi'],[u'জুলমাত আলাম',u'আজিজ'],[u'Scipio83',u'Scip.'],[u'Orkosiada',u'ים'],[u'محمد الفلسطيني',u'بدارين'],[u'JLanzer',u'Jacob Lanzer'],[u'Fsandlinux',u'Hatas'],[u'Piotrjutkiewicz',u'Ppiioottrr'],[u'Topshelvr',u'Topshelver'],[u'Marce79',u'Marcello Gianola'],[u'Theodor2001',u'Yuvalbab']]
eligible=[]
for pair in renamed_pairs:
    eligible+=pair


//gather votes for each file
results=dict()
for voter in votes:
    if votes[voter]['eligibility'] or voter in eligible:
        for v in votes[voter]['votes']['votesByCandidate'].keys():
            v=v.replace("_"," ")
            if v in results:
                results[v].append(voter)
            else:
                try:
                    results[v]=[voter,]
                except:
                    print voter, v
                    print 1/0 //d'oh... never get here


//make sure no renamed user voted for the same image under two usernames
for res in results.values():
    for p in renamed_pairs:
        if p[0] in res and p[1] in res:
            print p, "voted twice"

//put the wikitext of [[Commons:Picture_of_the_Year/2015/R1/Gallery]] here as a raw string
catstring=""""""

//split into chunks, luckily each has one gallery, thus one closing tag
cs=catstring.split("</gallery>")

//find the category names, populate dictionary with files and reverse dictionary to find cat of a file
categories=dict()
for cgroup in cs:
    cgroup=cgroup.split("\n")
    cat=""
    files=[]
    for line in cgroup:
        if "== [[" in line:
            if cat !="":
                print "ERROR: cat already populated",cat,line
                print 1/0
            cat=line.replace("==","").strip()
        else:
            if line.startswith("File:"):
                files.append(line.split("|")[0].replace("_"," "))
    if len(cat)!=0:
        categories[cat]=files[:]

catof=dict()
for cat in categories:
    for f in categories[cat]:
        catof[f]=cat

//Note file moves
filemoves={"File:Japanese beautyberry, October 2015 - Stacking.jpg":"File:Purple beautyberry, October 2015 - Stacking.jpg",
           "File:Eastern great egret 2015-06-17.jpg":"File:Egretta garzetta 2015-06-17.jpg",
           "File:2015.05.24.-15-Buchklingen--Pyramideneule-Raupe.jpg":"File:2015.05.24.-15-Buchklingen--Svenssons Pyramideneule-Raupe.jpg",
           "File:Southern armyworm, pupae, side 2014-06-04-21.10.13 ZS PMax (15750996370).jpg":"File:Spodoptera eridania (Southern armyworm) pupae lateral view.jpg",
           "File:Doña Isabel Cobos de Porc by Francisco Goya.jpg":"File:Portrait of Doña Isabel de Porcel by Francisco Goya.jpg",
           "File:Set design by Philippe Chaperon for Act4 sc2 of Aida by Verdi 1871 Cairo.jpg":"File:Set design by Philippe Chaperon for Act4 sc2 of Aida by Verdi 1880 Paris.jpg",
           "File:Black-faced impala from Etosha National Park.jpg":"File:Black-faced impala from Etosha National Park, Namibia, 2014.jpg",
           "File:Cervo do Pantano Perfil.jpg":"File:Femea Cervo do Pantanal Perfil.jpg",
           "File:Love padlocks at Butchers' Bridge (Ljubljana).JPG":"File:Love padlocks on the Butchers' Bridge (Ljubljana).jpg",
           "File:Pažaislis Monastery interior 1, Kaunas, Lithania - Diliff.jpg":"File:Pažaislis Monastery interior 1, Kaunas, Lithuania - Diliff.jpg",
           "File:San Cesareo de Appia (Rome) ,interior.jpg":"File:San Cesareo de Appia (Rome), interior.jpg",
           "File:Brown-eared bulbuls perching on the cables.jpg":"File:White-cheeked Starlings perching on the cables.jpg"
          }

//do per category
catres={}
for c in categories:
    tempres=[]
    for f in categories[c]:
        if f in filemoves:
            f=filemoves[f]
        try:
            tempres.append([f,len(results[f[5:].decode("utf-8")]),c])
        except:
            print f
    catres[c]=sorted(tempres,key=lambda x: -x[1])


//get top 30 overall
from itertools import chain
fullres=sorted(chain(*catres.values()),key=lambda x: -x[1])

rank=0
for r in fullres:
    rank+=1
    r+=[rank,[a[0] for a in catres[r[-1]]].index(r[0])+1]

outres=fullres[:30]

//print in table format
for line in outres:
    print "<tr>",
    for item in line:
        print "<td>",
        if type(item) is str and "File:" in item:
            print "[["+item+"|16px]] [[:"+item+"]]",
        else:
            print item,
        print "</td>",
    print "</tr>"


//note which files done so far
outnames=[a[0] for a in outres]

//do top two of each cat if not already done
for c in catres:
    for i in (0,1):
        if catres[c][i][0] not in outnames:
            for item in catres[c][i]:
                print "<td>",
                if type(item) is str and "File:" in item:
                    print "[["+item+"|16px]] [[:"+item+"]]",
                else:
                    print item,
                print "</td>",
            print "</tr>"

This code is writtern by Storkk.