def main():
# Evaluate model performance
# Get the "ideal" order of y_test by sorting in descending order.
args = parse.get_test_args()
X_train, X_test, X_val, y_train, y_test, y_val, group_vali, group_train = get_data(
args["data_path"])
gbm = lgb.Booster(model_file=args["model_path"])
true_relevance = y_test.sort_values(ascending=False)
# Get the actual order of y_test by sorting it according to our model's predictions.
test_pred = gbm.predict(X_test)
y_test = pd.DataFrame({
"relevance_score": y_test,
"predicted_ranking": test_pred
})
relevance_score = y_test.sort_values("predicted_ranking", ascending=False)
# Use computed variables to calculate the nDCG score
print(
"nDCG score: ",
ndcg_score([true_relevance.to_numpy()],
[relevance_score["relevance_score"].to_numpy()]),
)
def run(cfg: DictConfig, ):
cwd = hydra.utils.get_original_cwd()
# lag_win_pairs = [
# (28, 28),
# (28, 7),
# (7,7),
# (7, 3),
# (1, 3),
# ]
lag_win_pairs = cfg.feat.lag_win_pairs
writer.log_params_from_omegaconf_dict(cfg)
print(os.getcwd())
writer.log_artifact(os.path.join(os.getcwd(), '.hydra/config.yaml'))
# ----------------------------------------------------------------------
# load data
# ----------------------------------------------------------------------
PATH_PRICE_CSV = os.path.join(
cwd, "../input/m5-forecasting-accuracy/sell_prices.csv")
PATH_CALENDER_CSV = os.path.join(
cwd, "../input/m5-forecasting-accuracy/calendar.csv")
# PATH_SALES_CSV = os.path.join(cwd, "../input/m5-forecasting-accuracy/sales_train_validation.csv")
PATH_SALES_CSV = os.path.join(
cwd, "../input/m5-forecasting-accuracy/sales_train_evaluation.csv")
PATH_SAMPLE_SUB_CSV = os.path.join(
cwd, "../input/m5-forecasting-accuracy/sample_submission.csv")
load_start_time = time.time()
if cfg.data.path_basic_df == "":
print("making basic df from scratch...")
df = load_data.create_dt(
PATH_PRICE_CSV,
PATH_CALENDER_CSV,
PATH_SALES_CSV,
first_day=1500,
)
df = load_data.reduce_mem_usage(df)
else:
print("loading saved basic csv...")
path_df = cfg.data.path_basic_df
df = pd.read_csv(os.path.join(cwd, path_df), index_col=0)
df = load_data.reduce_mem_usage(df)
print(df.shape)
print(f"data loading time:{(time.time() - load_start_time)//60} min.")
df = df.query("date > @dev_firstdate")
gc.collect()
# ----------------------------------------------------------------------
# feature engineering
# ----------------------------------------------------------------------
# max_lags = max(list(map(lambda x:x[0], lag_win_pairs))) * 2
max_lags = 56 + 29
create_feature.create_fea(df, lag_win_pairs=lag_win_pairs)
# ----------------------------------------------------------------------
# Train model
# ----------------------------------------------------------------------
if cfg.lgbm.pretrained:
m_lgb = lgb.Booster(
model_file=os.path.join(cwd, cfg.lgbm.pretrained_model_path))
else:
model, _, train_cols = train_lgbm(df, cfg)
model_savepath = os.path.join(
cwd, f"../result/{writer.experiment_name}_{writer.run_id}.model")
model.save_model(model_savepath)
writer.log_param("model_path", model_savepath)
# ----------------------------------------------------------------------
# Inference on public lb
# ----------------------------------------------------------------------
public_pred_df = make_lb_predictions(model,
public_firstdate,
train_cols,
max_lags,
test_data_path=cfg.data.path_test_df,
lag_win_pairs=lag_win_pairs)
public_pred_wrmsse = eval_metrics.get_public_score(public_pred_df,
PATH_SALES_CSV,
PATH_PRICE_CSV,
PATH_CALENDER_CSV,
PATH_SAMPLE_SUB_CSV)
print(f"Public score: {public_pred_wrmsse}")
writer.log_metric("public_WRMSSE", public_pred_wrmsse)
# ----------------------------------------------------------------------
# Inference on private lb
# ----------------------------------------------------------------------
pass
parser = argparse.ArgumentParser(description='Process input')
parser.add_argument('tsv_path', type=str, help='tsv file path')
args = parser.parse_args()
# Reading input TSV
data_raw = pd.read_csv(args.tsv_path, sep="\t")
#####
with open('preprocessor.pkl', 'rb') as input:
prep = pickle.load(input)
data = prep.transform(data_raw)
# logtarget = np.log1p(data.revenue)
# data = data.drop(['revenue'],axis = 1)
bst_lgbm = lgb.Booster(model_file='lgbm_model.txt') # init model
preds_lgbm = bst_lgbm.predict(data)
bst_xgb = xgb.Booster()
bst_xgb.load_model("xgb_model.txt")
dtest = xgb.DMatrix(data)
preds_xgb = bst_xgb.predict(dtest)
preds = (preds_lgbm + preds_xgb) / 2
preds = np.expm1(preds)
prediction_df = pd.DataFrame(columns=['id', 'revenue'])
prediction_df['id'] = data_raw['id']
prediction_df['revenue'] = preds
prediction_df.to_csv("prediction.csv", index=False, header=False)