코랩에서 베이스라인 다운로드 받으셔서

flow_validation 기준으로 작업하시면 됩니다

train만 바꾸시면 될 듯

Train.py

import numpy as np

import sys

import pickle

import xgboost as xgb

x_train_path = sys.argv[1]

y_train_path = sys.argv[2]

model_save_path = sys.argv[3]

x_train = np.load(x_train_path, allow_pickle=True)

y_train = np.load(y_train_path, allow_pickle=True)

# Convert to DMatrix

dtrain = xgb.DMatrix(x_train, label=y_train)

# Set parameters

params = {

'base_score': 0.5,

'booster': 'gbtree',

'objective': 'reg:squarederror',

'max_depth': 3,

'learning_rate': 0.05,

'subsample': 0.5, # Consider using subsample to reduce memory usage

'max_bin': 256, # Reduce number of bins

'device': 'cuda', # Use GPU accelerated algorithm

}

# Custom evaluation function for MAPE

def mape(preds, dtrain):

labels = dtrain.get_label()

return 'MAPE', np.mean(np.abs((labels - preds) / (labels + 1e-6))) * 100 # Avoid division by zero

# Train the XGBoost model with custom evaluation metric

model = xgb.train(params, dtrain, evals=[(dtrain, 'train')],

custom_metric=mape, # Use the custom evaluation function

verbose_eval=100, num_boost_round=400)

# save

pickle.dump(model, open(model_save_path, "wb")):)

model_inference.py

import numpy as np

import sys

import pickle

import xgboost as xgb

model_path = sys.argv[1]

x_test_path = sys.argv[2]

y_pred_save_path = sys.argv[3]

# 모델 로딩

with open(model_path, "rb") as f:

model = pickle.load(f)

x_test = np.load(x_test_path, allow_pickle=True)

# Convert numpy array to DMatrix

dtest = xgb.DMatrix(x_test)

y_pred = model.predict(dtest)

np.save(y_pred_save_path, y_pred)