GitLab

Created by: bacalfa

I'm testing the AutoML approach with Fedot on a dataset with 11 rows and 66 columns (never mind the many more columns than rows in this case). The default parameters for the strategy (ransac_non_lin_reg) aren't being initialized. For example, min_samples is None. And I'm getting an error:

Traceback (most recent call last):
  ....
  File "C:\Users\username\Miniconda3\envs\myenv\lib\site-packages\fedot\api\main.py", line 206, in fit
    return self._obtain_model(is_composing_required)
  File "C:\Users\username\Miniconda3\envs\myenv\lib\site-packages\fedot\api\main.py", line 156, in _obtain_model
    self.current_model, self.best_models, self.history = compose_fedot_model(**execution_params)
  File "C:\Users\username\Miniconda3\envs\myenv\lib\site-packages\fedot\api\api_utils.py", line 190, in compose_fedot_model
    chain_gp_composed = gp_composer.compose_chain(data=train_data)
  File "C:\Users\username\Miniconda3\envs\myenv\lib\site-packages\fedot\core\composer\gp_composer\gp_composer.py", line 140, in compose_chain
    best_chain = self.optimiser.optimise(metric_function_for_nodes,
  File "C:\Users\username\Miniconda3\envs\myenv\lib\site-packages\fedot\core\composer\optimisers\gp_comp\param_free_gp_optimiser.py", line 123, in optimise
    self._evaluate_individuals(new_population, objective_function, timer=t)
  File "C:\Users\username\Miniconda3\envs\myenv\lib\site-packages\fedot\core\composer\optimisers\gp_comp\gp_optimiser.py", line 383, in _evaluate_individuals
    evaluate_individuals(individuals_set=individuals_set, objective_function=objective_function, timer=timer,
  File "C:\Users\username\Miniconda3\envs\myenv\lib\site-packages\fedot\core\composer\optimisers\gp_comp\gp_operators.py", line 85, in evaluate_individuals
    ind.fitness = calculate_objective(ind.chain, objective_function, is_multi_objective)
  File "C:\Users\username\Miniconda3\envs\myenv\lib\site-packages\fedot\core\composer\optimisers\gp_comp\gp_operators.py", line 100, in calculate_objective
    calculated_fitness = objective_function(ind)
  File "C:\Users\username\Miniconda3\envs\myenv\lib\site-packages\fedot\core\operations\cross_validation.py", line 20, in cross_validation
    chain.fit(train_data)
  File "C:\Users\username\Miniconda3\envs\myenv\lib\site-packages\fedot\core\chains\chain.py", line 173, in fit
    train_predicted = self._fit(input_data=copied_input_data, use_cache=use_cache)
  File "C:\Users\username\Miniconda3\envs\myenv\lib\site-packages\fedot\core\chains\chain.py", line 142, in _fit
    train_predicted = self.root_node.fit(input_data=input_data)
  File "C:\Users\username\Miniconda3\envs\myenv\lib\site-packages\fedot\core\chains\node.py", line 241, in fit
    secondary_input = self._input_from_parents(input_data=input_data, parent_operation='fit')
  File "C:\Users\username\Miniconda3\envs\myenv\lib\site-packages\fedot\core\chains\node.py", line 272, in _input_from_parents
    parent_results, target = _combine_parents(parent_nodes, input_data,
  File "C:\Users\username\Miniconda3\envs\myenv\lib\site-packages\fedot\core\chains\node.py", line 303, in _combine_parents
    prediction = parent.fit(input_data=input_data)
  File "C:\Users\username\Miniconda3\envs\myenv\lib\site-packages\fedot\core\chains\node.py", line 241, in fit
    secondary_input = self._input_from_parents(input_data=input_data, parent_operation='fit')
  File "C:\Users\username\Miniconda3\envs\myenv\lib\site-packages\fedot\core\chains\node.py", line 272, in _input_from_parents
    parent_results, target = _combine_parents(parent_nodes, input_data,
  File "C:\Users\username\Miniconda3\envs\myenv\lib\site-packages\fedot\core\chains\node.py", line 303, in _combine_parents
    prediction = parent.fit(input_data=input_data)
  File "C:\Users\username\Miniconda3\envs\myenv\lib\site-packages\fedot\core\chains\node.py", line 174, in fit
    return super().fit(input_data)
  File "C:\Users\username\Miniconda3\envs\myenv\lib\site-packages\fedot\core\chains\node.py", line 96, in fit
    self.fitted_operation, operation_predict = self.operation.fit(data=input_data,
  File "C:\Users\username\Miniconda3\envs\myenv\lib\site-packages\fedot\core\operations\operation.py", line 86, in fit
    fitted_operation = self._eval_strategy.fit(train_data=data)
  File "C:\Users\username\Miniconda3\envs\myenv\lib\site-packages\fedot\core\operations\evaluation\regression.py", line 65, in fit
    operation_implementation.fit(train_data)
  File "C:\Users\username\Miniconda3\envs\myenv\lib\site-packages\fedot\core\operations\evaluation\operation_implementations\data_operations\sklearn_filters.py", line 25, in fit
    self.operation.fit(input_data.features, input_data.target)
  File "C:\Users\username\Miniconda3\envs\myenv\lib\site-packages\sklearn\linear_model\_ransac.py", line 281, in fit
    raise ValueError("`min_samples` may not be larger than number "
ValueError: `min_samples` may not be larger than number of samples: n_samples = 11.

In this case, min_samples is much larger than the number of rows, and RANSACRegressor doesn't allow that. How do I make sure min_samples is properly initialized?