Last active
March 16, 2021 03:01
-
-
Save jkukul/f02d239936a74f3db273bd02c17c1de1 to your computer and use it in GitHub Desktop.
Script to calculate your current score in Kaggle's March madness competition.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# python3 | |
# | |
# Example usage: | |
# python get_score.py --gender M --submissions-file SampleSubmissionStage2.csv | |
# | |
# TeamSpellings.csv and/or WTeamSpellings.csv file must be present in the current directory | |
import argparse | |
from math import log | |
import pandas as pd | |
import requests | |
parser = argparse.ArgumentParser(description=''' | |
This script calculates your current score in Kaggle's March madness competition. | |
''') | |
parser.add_argument('--submission-file', type=str) | |
parser.add_argument('--gender', type=str, help='W or M') | |
args = parser.parse_args() | |
df_submissions = pd.read_csv(args.submission_file) | |
df_spellings = pd.read_csv(f'{"W" if args.gender == "W" else ""}TeamSpellings.csv', encoding='latin1') | |
# FETCH RESULTS FROM NCAA API: | |
gender = 'women' if args.gender == 'W' else 'men' | |
results = requests.get( | |
f"https://data.ncaa.com/casablanca/carmen/brackets/championships/basketball-{gender}/d1/2019/data.json") | |
json_results = results.json() | |
games = map(lambda x: x['game'], results.json()['games']) | |
scores = [] | |
for game in games: | |
if game['bracketRound'].startswith('First Four') or game['gameState'] == 'pre': | |
# Filter out First Four games and games which haven't started yet | |
continue | |
score = dict() | |
score['isLive'] = game['gameState'] != 'final' | |
score['homeTeamName'] = game['home']['names']['seo'] | |
score['awayTeamName'] = game['away']['names']['seo'] | |
home_team_score = int(game['home']['score']) | |
away_team_score = int(game['away']['score']) | |
score['winnerTeamName'] = score['homeTeamName'] if home_team_score > away_team_score else score['awayTeamName'] | |
scores.append(score) | |
df_results = pd.DataFrame(scores) | |
df_results = pd.merge(left=df_results, right=df_spellings, how='left', left_on='homeTeamName', right_on='TeamNameSpelling') | |
df_results = df_results.rename(index=str, columns={"TeamID": "homeTeamID", "TeamNameSpelling": "homeTeamSpelling"}) | |
df_results = pd.merge(left=df_results, right=df_spellings, how='left', left_on='awayTeamName', right_on='TeamNameSpelling') | |
df_results = df_results.rename(index=str, columns={"TeamID": "awayTeamID", "TeamNameSpelling": "awayTeamSpelling"}) | |
df_results['team1_name'] = df_results[['homeTeamID', 'awayTeamID', 'homeTeamName', 'awayTeamName']].apply(lambda x: x[2] if x[0] < x[1] else x[3], axis=1) | |
df_results['team2_name'] = df_results[['homeTeamID', 'awayTeamID', 'homeTeamName', 'awayTeamName']].apply(lambda x: x[2] if x[0] > x[1] else x[3], axis=1) | |
df_results['ID'] = df_results[['homeTeamID', 'awayTeamID']].apply(lambda x: f'2019_{min(x)}_{max(x)}', axis=1) | |
df_results['True'] = df_results[['winnerTeamName', 'team1_name']].apply(lambda x: 1 if x[0] == x[1] else 0, axis=1) | |
df_results = pd.merge(left=df_results, right=df_submissions, how='left', on='ID') | |
df_results = df_results[['ID', 'isLive', 'team1_name', 'team2_name', 'Pred', 'True']] | |
df_results['log_loss'] = df_results[['Pred', 'True']].apply(lambda x: -1*(x[1]*log(x[0] or 1e-15)+(1-x[1])*log((1-x[0]) or 1e-15)), axis=1) | |
print(df_results.to_string(index=False)) | |
print(f'Your score: {round(df_results["log_loss"].mean(), 5)}') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment