("rfe_features", rfe_feature),
("no_elo_features", no_elo_features)]
file_name = "outcome_report_full.txt"
reports = []
for (name, feature_set) in feature_sets:
write_log(file_name, str(datetime.datetime.now()))
write_log(file_name,
f"Running test for feature set: {name}",
print_text=True)
data_loader = DataLoader(feature_set)
X, y = data_loader.get_all_data("home_win")
params = get_default_parameters()
arguments = get_cv_grid_search_arguments(params, X)
results = run_grid_search_for_outcome(arguments, X, y)
results.to_csv(f"outcome_hyperparam_optimization_{name}.csv")
best_params_dict = get_best_params(results)
write_log(file_name, str(best_params_dict), print_text=True)
optimal_params = params.copy()
optimal_params["max_depth"] = best_params_dict["max_depth"]
optimal_params["min_samples_leaf"] = best_params_dict["min_samples_leaf"]
optimal_params["max_features"] = best_params_dict["max_features"]
for (tt_file, bet_file, filter_start) in tournament_parameters:
data_loader.set_filter_start(filter_start)
simulations, units, kellys = iterate_simulations(
data_loader, tt_file, bet_file, run_outcome_model_for_features,
tt_file = 'data/original/wc_2010_games_real.csv'
mb_file = 'data/original/wc_2010_bets.csv'
filter_start = "2010-06-11"
elif args.y == 2014:
tt_file = 'data/original/wc_2014_games_real.csv'
mb_file = 'data/original/wc_2014_bets.csv'
filter_start = "2014-06-12"
else:
tt_file = 'data/original/wc_2018_games_real.csv'
mb_file = 'data/original/wc_2018_bets.csv'
filter_start = "2018-06-13"
prefix = f"{args.f}_{args.y}"
dl = DataLoader(all_features, filter_start=filter_start)
model_parameters = get_default_parameters()
model_parameters["max_depth"] = 8
model_parameters["max_features"] = "sqrt"
model_parameters["min_samples_leaf"] = 1
af_data = simulate(tt_file, mb_file, dl, model_parameters,
f"{prefix}_all_features")
dl = DataLoader(other_features, filter_start=filter_start)
model_parameters["max_depth"] = 8
model_parameters["max_features"] = "log2"
model_parameters["min_samples_leaf"] = 10
gf_data = simulate(tt_file, mb_file, dl, model_parameters,
f"{prefix}_general_features")
dl = DataLoader(player_features, filter_start=filter_start)
model_parameters["max_depth"] = None