Created
April 9, 2020 04:08
-
-
Save evmcheb/c50df022fcafc4f49a59445156f2c67f to your computer and use it in GitHub Desktop.
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
| import os | |
| import numpy as np | |
| from tqdm import tqdm | |
| from pymongo import MongoClient | |
| bookies = { | |
| "44":"Betfair", | |
| "16":"bet365", | |
| "18":"Pinnacle", | |
| "5":"Unibet" | |
| } | |
| client = MongoClient() | |
| db = client.nba | |
| games = db.games | |
| seasons = [f"002{str(i).zfill(2)}" for i in range(8, 20)] | |
| # load the samples into memory | |
| x, y = [], [] | |
| def normalize_sample(nparr): | |
| for feature in range(nparr.shape[-1]): # iterate over the features | |
| f = np.nan_to_num(nparr[:, :, feature]) | |
| nparr[:, :, feature] = (f-f.min())/(f.max()-f.min()) | |
| return nparr | |
| for season in seasons: | |
| for filename in tqdm(os.listdir(f"samples/{season}")[120:]): | |
| if ".npy" in filename: | |
| game = list(games.find({"GAME_ID":filename.strip(".npy"), "bet365":{"$exists":"True"}})) | |
| if not game: | |
| continue | |
| game = game[0] | |
| closing_odds = 1/float(game["bet365"].split()[1].split("v")[0]) | |
| home_win = int(game["HOME"] == game["WINNER"]) | |
| sample = np.load(f"samples/{season}/{filename}") | |
| x.append((normalize_sample(sample), closing_odds)) | |
| y.append(home_win) | |
| x = np.array(x) | |
| y = np.array(y) | |
| import random | |
| print(x.shape, y.shape) | |
| diff = len(y)//2 - np.count_nonzero(y == 0) | |
| for i in tqdm(range(diff)): | |
| while True: | |
| a = random.randint(1, len(y)-1) | |
| if y[a] == 1: | |
| x = np.delete(x, a, 0) | |
| y = np.delete(y, a, 0) | |
| break | |
| print(len(x), len(y)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment