Most DNF Ratio on WCA, excluding BLDs and FM

# acampos@worldcubeassociation.org

# program made for the WCA Statistics
# place this program alongside with the tsv (unziped) export from
# https://www.worldcubeassociation.org/results/misc/WCA_export.tsv.zip
# and run it with
# python program.py
# it takes about 24 min on my PC

import csv
from datetime import date

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 main():

    with open("WCA_export_Results.tsv") as tsvfile:

        tsvreader = csv.reader(tsvfile, delimiter="\t")

        ids = []
        names = []
        countries = []
        results_count = []
        attempts_count = []
        dnf_count = []
        dns_count = []
        no_results = []
        exclude = ["333bf", "444bf", "555bf", "333fm", "333mbf", "333mbo"]

        header = True

        for line in tsvreader:

            if header:
                header = False
                continue

            event = line[1]
            if event in exclude:
                continue

            this_id = line[7]

            i = -1
            try:
                i = ids.index(this_id)
            except:
                name = line[6]
                country = line[8]

                ids.append(this_id)
                names.append(name)
                countries.append(country)

                results_count.append(0)
                dnf_count.append(0)
                dns_count.append(0)
                no_results.append(0)
                attempts_count.append(0)

            for x in line[10:15]:

                if x == "-1":
                    dnf_count[i] += 1
                    attempts_count[i] += 1
                elif x == "-2":
                    dns_count[i] += 1
                elif x == "0":
                    no_results[i] += 1
                else:
                    results_count[i] += 1
                    attempts_count[i] += 1

        ratio = []
        out_names = []
        out_countries = []
        out_results = []
        out_dnf = []
        out_attempt = []

        hold = 100

        for i in range(len(ids)):
            attempts = attempts_count[i]
            if attempts < hold:
                continue
            result = results_count[i]
            if result == 0:
                continue

            name = names[i]
            country = countries[i]
            dnf = dnf_count[i]

            out_names.append(name)
            out_countries.append(country)
            out_results.append(result)
            out_dnf.append(dnf)
            out_attempt.append(attempts)
            ratio.append(1.0*dnf/attempts)

        labels = ["DNF Ratio", "Name", "Country", "DNF", "Attempts"]
        list_of_lists = [out_names, out_countries, out_dnf, out_attempt]

        assert len(labels) == len(list_of_lists)+1

        limit = 100
        show_results(labels, ratio, list_of_lists, limit, "des")

main()