'boosting_type': 'gbdt',
'metric': METRIC,
'num_threads': N_THREADS,
'verbose': VERBOSE,
'seed': SEED,
'n_estimators': N_ESTIMATORS,
'early_stopping_rounds': EARLY_STOPPING_ROUNDS
}
logger = utility.get_logger(LOGGER_NAME, MODEL_NUMBER, run_id, LOG_DIR)
utility.set_seed(SEED)
logger.info(f'Running for Model Number {MODEL_NUMBER}')
utility.update_tracking(run_id,
"model_number",
MODEL_NUMBER,
drop_incomplete_rows=True)
utility.update_tracking(run_id, "model_type", MODEL_TYPE)
utility.update_tracking(run_id, "is_test", IS_TEST)
utility.update_tracking(run_id, "n_estimators", N_ESTIMATORS)
utility.update_tracking(run_id, "early_stopping_rounds", EARLY_STOPPING_ROUNDS)
utility.update_tracking(run_id, "random_state", SEED)
utility.update_tracking(run_id, "n_threads", N_THREADS)
#utility.update_tracking(run_id, "learning_rate", LEARNING_RATE)
utility.update_tracking(run_id, "n_fold", N_FOLDS)
############################################
# Preparaing Data
############################################
#Read the data file
SHUFFLE = True
# Parameters related to model
MODEL_TYPE = "LinearDiscriminantAnalysis"
N_THREADS = -1
SOLVER = 'eigen'
# Name of the target
TARGET = 'target'
logger = utility.get_logger(LOGGER_NAME, MODEL_NUMBER, run_id, LOG_DIR)
utility.set_seed(SEED)
logger.info(f'Running for Model Number {MODEL_NUMBER}')
utility.update_tracking(run_id, "model_number", MODEL_NUMBER, drop_incomplete_rows=True)
utility.update_tracking(run_id, "model_type", MODEL_TYPE)
utility.update_tracking(run_id, "is_test", IS_TEST)
utility.update_tracking(run_id, "random_state", SEED)
utility.update_tracking(run_id, "n_threads", N_THREADS)
utility.update_tracking(run_id, "n_fold", N_FOLDS)
utility.update_tracking(run_id, "solver", SOLVER)
############################################
# Preparaing Data
############################################
#Read the data file
train, test, submission = utility.read_files(logger=logger, dir_path=DATA_DIR, index_col='id')
combined_df = pd.concat([train.drop('target', axis=1), test])