source

​
mlforecast_objective

 mlforecast_objective
                       (df:Union[pandas.core.frame.DataFrame,polars.datafr
                       ame.frame.DataFrame], config_fn:Callable[[optuna.tr
                       ial._trial.Trial],Dict[str,Any]], loss:Callable,
                       model:sklearn.base.BaseEstimator,
                       freq:Union[int,str], n_windows:int, h:int,
                       step_size:Optional[int]=None,
                       input_size:Optional[int]=None,
                       refit:Union[bool,int]=False,
                       id_col:str='unique_id', time_col:str='ds',
                       target_col:str='y')

optuna objective function for the MLForecast class

TypeDefaultDetails
dfUnion
config_fnCallableFunction that takes an optuna trial and produces a configuration with the following keys:
- model_params
- mlf_init_params
- mlf_fit_params
lossCallableFunction that takes the validation and train dataframes and produces a float.
modelBaseEstimatorscikit-learn compatible model to be trained
freqUnionpandas’ or polars’ offset alias or integer denoting the frequency of the series.
n_windowsintNumber of windows to evaluate.
hintForecast horizon.
step_sizeOptionalNoneStep size between each cross validation window. If None it will be equal to h.
input_sizeOptionalNoneMaximum training samples per serie in each window. If None, will use an expanding window.
refitUnionFalseRetrain model for each cross validation window.
If False, the models are trained at the beginning and then used to predict each window.
If positive int, the models are retrained every refit windows.
id_colstrunique_idColumn that identifies each serie.
time_colstrdsColumn that identifies each timestep, its values can be timestamps or integers.
target_colstryColumn that contains the target.
ReturnsCallable
import lightgbm as lgb
from datasetsforecast.m4 import M4, M4Evaluation, M4Info
from utilsforecast.losses import smape

from mlforecast.lag_transforms import ExpandingMean, RollingMean
from mlforecast.target_transforms import Differences, LocalBoxCox, LocalStandardScaler

def train_valid_split(group):
    df, *_ = M4.load(directory='data', group=group)
    df['ds'] = df['ds'].astype('int')
    horizon = M4Info[group].horizon
    valid = df.groupby('unique_id').tail(horizon)
    train = df.drop(valid.index)
    return train, valid

h = M4Info['Weekly'].horizon
weekly_train, weekly_valid = train_valid_split('Weekly')
weekly_train['unique_id'] = weekly_train['unique_id'].astype('category')
weekly_valid['unique_id'] = weekly_valid['unique_id'].astype(weekly_train['unique_id'].dtype)

def config_fn(trial):
    candidate_lags = [
        [1],
        [13],
        [1, 13],
        range(1, 33),
    ]
    lag_idx = trial.suggest_categorical('lag_idx', range(len(candidate_lags)))
    candidate_lag_tfms = [
        {
            1: [RollingMean(window_size=13)]
        },
        {
            1: [RollingMean(window_size=13)],
            13: [RollingMean(window_size=13)],
        },
        {
            13: [RollingMean(window_size=13)],
        },
        {
            4: [ExpandingMean(), RollingMean(window_size=4)],
            8: [ExpandingMean(), RollingMean(window_size=4)],
        }
    ]
    lag_tfms_idx = trial.suggest_categorical('lag_tfms_idx', range(len(candidate_lag_tfms)))
    candidate_targ_tfms = [
        [Differences([1])],
        [LocalBoxCox()],
        [LocalStandardScaler()],        
        [LocalBoxCox(), Differences([1])],
        [LocalBoxCox(), LocalStandardScaler()],
        [LocalBoxCox(), Differences([1]), LocalStandardScaler()],
    ]
    targ_tfms_idx = trial.suggest_categorical('targ_tfms_idx', range(len(candidate_targ_tfms)))
    return {
        'model_params': {
            'learning_rate': 0.05,
            'objective': 'l1',
            'bagging_freq': 1,
            'num_threads': 2,
            'verbose': -1,
            'force_col_wise': True,
            'n_estimators': trial.suggest_int('n_estimators', 10, 1000, log=True),            
            'num_leaves': trial.suggest_int('num_leaves', 31, 1024, log=True),
            'lambda_l1': trial.suggest_float('lambda_l1', 0.01, 10, log=True),
            'lambda_l2': trial.suggest_float('lambda_l2', 0.01, 10, log=True),
            'bagging_fraction': trial.suggest_float('bagging_fraction', 0.75, 1.0),
            'feature_fraction': trial.suggest_float('feature_fraction', 0.75, 1.0),
        },
        'mlf_init_params': {
            'lags': candidate_lags[lag_idx],
            'lag_transforms': candidate_lag_tfms[lag_tfms_idx],
            'target_transforms': candidate_targ_tfms[targ_tfms_idx],
        },
        'mlf_fit_params': {
            'static_features': ['unique_id'],
        }
    }

def loss(df, train_df):
    return smape(df, models=['model'])['model'].mean()

optuna.logging.set_verbosity(optuna.logging.WARNING)
objective = mlforecast_objective(
    df=weekly_train,
    config_fn=config_fn,
    loss=loss,    
    model=lgb.LGBMRegressor(),
    freq=1,
    n_windows=2,
    h=h,
)
study = optuna.create_study(
    direction='minimize', sampler=optuna.samplers.TPESampler(seed=0)
)
study.optimize(objective, n_trials=2)
best_cfg = study.best_trial.user_attrs['config']
final_model = MLForecast(
    models=[lgb.LGBMRegressor(**best_cfg['model_params'])],
    freq=1,
    **best_cfg['mlf_init_params'],
)
final_model.fit(weekly_train, **best_cfg['mlf_fit_params'])
preds = final_model.predict(h)
M4Evaluation.evaluate('data', 'Weekly', preds['LGBMRegressor'].values.reshape(-1, 13))
SMAPEMASEOWA
Weekly9.2615382.6144730.976158
LightGBMCVUtils