def fit(self, source_df, y, experiment: ExperimentBackend) -> pd.DataFrame:
X, y = source_df.values, y
default_params = self.generate_default_model_parameter(
X, y, experiment)
with experiment.mark_time(prefix='fit'):
models, oof = self.run_oof_train(X,
y,
default_params,
experiment=experiment)
self._fitted_models = models
experiment.mark('n_cv', len(models))
return pd.DataFrame(oof)
def _fit_model(self, X: np.ndarray, y: np.ndarray, default_params: dict,
validation_set: tuple, indexes_set: tuple,
experiment: ExperimentBackend) -> PrePostProcessModel:
"""
fit a new model class.
Notes:
in model_params, add scaling parameters for target / input (ex. target_scaling = False)
Args:
X: training feature. numpy array. shape = (n_train, n_features)
y: target. shape = (n_train, n_classes)
default_params: parameters pass into model constructor
validation_set:
indexes_set:
experiment:
Returns:
trained model
"""
model_params = self.get_model_params_on_each_fold(
default_params, indexes_set)
model = self.create_model(model_params)
# MEMO: validation data are not transform so validation score is invalid (in boosting model, eval_set)
model._before_fit(X, y)
x_valid, y_valid = validation_set
x_valid = model.input_transformer.transform(x_valid)
y_valid = model.target_transformer.transform(y_valid)
fit_params = self.get_fit_params_on_each_fold(model_params,
training_set=(X, y),
validation_set=(x_valid,
y_valid),
indexes_set=indexes_set,
experiment=experiment)
if fit_params is None:
fit_params = {}
with experiment.mark_time('fit'):
model.fit(X, y, **fit_params)
return model