WCA 4BLD > 12 min to 5BLD < 12 min

# Software by Alexandre Campos
# [email protected]
# 12/30/2018
# Software made for WDC purpose. It compares when a competitor got a 4BLD result > 12 min to when s/he got a 5BLD < 12 min.

# Place this program.py alongside with the tsv export of WCA db
# https://www.worldcubeassociation.org/results/misc/export.html
# and execute it with
# python program.py

import csv
from datetime import date

def get_competition_date(competition_id):

    with open('WCA_export_Competitions.tsv','rb') as tsvin:
        tsvin = csv.reader(tsvin, delimiter='\t')

        for line in tsvin:
            if competition_id == line[0]:

                year = int(line[5])
                month = int(line[6])
                day = int(line[7])

                return date(year, month, day)

        return None

def show_results(labels, results_list, list_of_lists, limit = float("inf"), direction = "asc"):
    """Labels is intuitive. Results_list is the main order list and list_of_lists are other lists that are gonna be ordered as well (eg.: country, name, etc). You can set limit if you wish. Direction = 'asc' if you wanna the lower results first; direction = 'des' if you wanna bigger results first."""

    pos = 1

    prev = None

    out = "Pos"
    for x in labels:
        out += "\t"+x
    print out

    temp = []
    if direction == "asc":
        temp = sorted(zip(results_list, range(len(results_list))))
    elif direction == "des":
        temp = sorted(zip(results_list, range(len(results_list))))[::-1]

    for a, b in temp:
        out = ""
        if a != prev:
            if pos > limit:
                break
            out+="%s)\t"%pos
        else:
            out += "---\t"
        out += str(a)+"\t"
        for x in list_of_lists:
            out += str(x[b])+"\t"
        print out.strip()
        prev = a
        pos += 1

def time_format(time):
    m = int(time/60)
    time -= m*60

    s = int(time)
    time -= s

    d = int(time*100)

    return "%s:%s.%s"%(str(m).zfill(2), str(s).zfill(2), str(d).zfill(2))

def get_results(ev):

    results = []
    id_list = []
    competition_id = []
    competition_date = []

    with open('WCA_export_Results.tsv','rb') as tsvin:
        tsvin = csv.reader(tsvin, delimiter='\t')

        prev_competition = None
        date = None

        for line in tsvin:

            event = line[1]

            if event == ev:

                best = line[4]
                if best == -1: # competitor got at least one right
                    continue

                person_id = line[7]
                i = -1
                try:
                    i = id_list.index(person_id)
                except:
                    id_list.append(person_id)
                    results.append([])
                    competition_id.append([])
                    competition_date.append([])

                competition = line[0]

                # this saves time since looking for competition date is expensive
                if competition != prev_competition:
                    date = get_competition_date(competition)
                prev_competition = competition

                for x in line[10:13]:
                    if x not in ["0", "-1", "-2"]:
                        results[i].append(float(x)/100)
                        competition_date[i].append(date)
                        competition_id[i].append(competition)

    return (id_list, results, competition_id, competition_date)

def main():

    LIMIT = 1000000

    id_list_4, results_4, competition_id_4, bld_date_4 = get_results("444bf")
    id_list_5, results_5, competition_id_5, bld_date_5 = get_results("555bf")

    days = []
    id_list = []
    result4 = []
    comp4 = []
    date4 = []
    result5 = []
    comp5 = []
    date5 = []

    prev_comp_4 = None
    prev_comp_5 = None
    prev_id = None

    for i in range(len(id_list_4)):

        j = None
        try:
            j = id_list_5.index(id_list_4[i])
        except:
            continue

        for k in range(len(results_4[i])):
            if results_4[i][k] < 12*60:
                continue
            for l in range(len(results_5[j])):
                if results_5[j][l] > 12*60:
                    continue

                delta = bld_date_5[j][l] - bld_date_4[i][k]
                d = delta.days

                this_comp_4 = competition_id_4[i][k]
                this_comp_5 = competition_id_5[j][l]
                this_id = id_list_5[j]

                # people who got multiple results at same comps
                if this_comp_4 == prev_comp_4 and this_comp_5 == prev_comp_5 and this_id == prev_id:
                    continue

                days.append(d)
                id_list.append(this_id)
                result4.append(time_format(results_4[i][k]))
                comp4.append(this_comp_4)
                date4.append(bld_date_4[i][k])
                result5.append(time_format(results_5[j][l]))
                comp5.append(this_comp_5)
                date5.append(bld_date_5[j][l])

                prev_comp_4 = this_comp_4
                prev_comp_5 = this_comp_5
                prev_id = this_id

    list_of_lists = [id_list, result4, comp4, date4, result5, comp5, date5]
    labels = ["Days", "ID", "Result4", "Comp of 4", "Date of 4", "Result5", "Comp of 5", "Date of 5"]

    show_results(labels, days, list_of_lists, LIMIT)

main()