def lgb_predict(lgb_model, X_test, submission_file):
bst = lgb.Booster(model_file=lgb_model)
y_pred = bst.predict(X_test)
y_pred = inverse_transform_y(y_pred)
df = pd.DataFrame({'Id': range(1, len(y_pred) + 1), 'Sales': y_pred})
df.to_csv(submission_file, index=False)
def xgb_predict(model_file, submission_file):
bst = xgb.Booster(model_file=model_file)
train, test = load_data()
X_test = extract_X(test)
dtest = xgb.DMatrix(X_test)
y_pred = bst.predict(dtest)
y_pred = inverse_transform_y(y_pred)
pred_df = pd.DataFrame({'Id': range(1, len(y_pred) + 1), 'Sales': y_pred})
pred_df.to_csv(submission_file, index=False)
submit_to_kaggle(submission_file)
def xgb_train():
train_embed, train_sales, test_embed = get_embed_features()
train_sales = train_sales.reshape(-1)
feature_names = get_embed_fea_names()
assert len(feature_names) == train_embed.shape[1]
if DO_EVAL:
X_train, X_val, y_train, y_val = train_test_split(train_embed, train_sales, test_size=0.048, shuffle=False)
else:
X_train = train_embed
y_train = train_sales
X_test = test_embed
print('X_train:', X_train.shape)
print('y_train:', y_train.shape)
dtrain = xgb.DMatrix(X_train, y_train, feature_names=feature_names)
watchlist = [(dtrain, 'train')]
if DO_EVAL:
dval = xgb.DMatrix(X_val, y_val, feature_names=feature_names)
watchlist.append((dval, 'eval'))
#dtest = xgb.DMatrix(X_test)
param = {
'objective': 'reg:linear',
'eval_metric': 'mae',
'max_depth': 10,
'gamma': 0,
'min_child_weight': 1,
'eta': 0.02,
'subsample': 0.8,
'colsample_bytree': 0.95,
'tree_method': 'hist'
}
nrounds = 5000
bst = xgb.train(param, dtrain, nrounds, watchlist,
early_stopping_rounds=100,
feval=rmspe_xgb,
#model_file='xgb_1.model'
)
#bst = xgb.Booster(model_file='xgb_1.model')
bst.save_model('xgb_1.model')
if not DO_EVAL:
dtest = xgb.DMatrix(X_test)
y_pred = bst.predict(dtest)
y_pred = inverse_transform_y(y_pred)
df = pd.DataFrame({'Id': range(1, len(y_pred) + 1), 'Sales': y_pred})
df.to_csv('./output/xgb_pred1.csv', index=False)
submit_to_kaggle('./output/xgb_pred1.csv')
def evaluate(self, X, y):
y_pred = self.predict(X)
y_true = inverse_transform_y(y)
err = rmspe(y_true, y_pred)
return err
def predict(self, X):
y_pred = self.predict_raw(X)
y_pred = inverse_transform_y(y_pred)
return y_pred # (len(X),)