Add forecasting length increasing for fit

Author: kasyanovse

fedot/api/api_utils/api_params_repository.py

@@ -6,7 +6,7 @@
 from golem.core.optimisers.genetic.operators.mutation import MutationTypesEnum
 
 from fedot.core.composer.gp_composer.specific_operators import parameter_change_mutation, boosting_mutation
-from fedot.core.constants import AUTO_PRESET_NAME
+from fedot.core.constants import AUTO_PRESET_NAME, DEFAULT_CV_FOLDS_BY_TASK
 from fedot.core.repository.tasks import TaskTypesEnum
 from fedot.core.utils import default_fedot_data_dir
 
@@ -32,12 +32,6 @@ def __init__(self, task_type: TaskTypesEnum):
     @staticmethod
     def default_params_for_task(task_type: TaskTypesEnum) -> dict:
         """ Returns a dict with default parameters"""
-        if task_type in [TaskTypesEnum.classification, TaskTypesEnum.regression]:
-            cv_folds = 5
-
-        elif task_type == TaskTypesEnum.ts_forecasting:
-            cv_folds = 3
-
         # Dict with allowed keyword attributes for Api and their default values. If None - default value set
         # in dataclasses ``PipelineComposerRequirements``, ``GPAlgorithmParameters``, ``GraphGenerationParams``
         # will be used.
@@ -51,7 +45,7 @@ def default_params_for_task(task_type: TaskTypesEnum) -> dict:
             keep_n_best=1,
             available_operations=None,
             metric=None,
-            cv_folds=cv_folds,
+            cv_folds=DEFAULT_CV_FOLDS_BY_TASK[task_type],
             genetic_scheme=None,
             early_stopping_iterations=None,
             early_stopping_timeout=10,

fedot/core/constants.py

@@ -15,8 +15,12 @@
 
 FRACTION_OF_UNIQUE_VALUES = 0.95
 
-default_data_split_ratio_by_task = {
+DEFAULT_DATA_SPLIT_RATIO_BY_TASK = {
     TaskTypesEnum.classification: 0.8,
     TaskTypesEnum.regression: 0.8,
     TaskTypesEnum.ts_forecasting: 0.5
 }
+
+DEFAULT_CV_FOLDS_BY_TASK = {TaskTypesEnum.classification: 5,
+                            TaskTypesEnum.regression: 5,
+                            TaskTypesEnum.ts_forecasting: 3}

fedot/core/optimisers/objective/data_source_splitter.py

@@ -1,9 +1,10 @@
 from functools import partial
 from typing import Optional
+from copy import deepcopy
 
 from golem.core.log import default_log
 
-from fedot.core.constants import default_data_split_ratio_by_task
+from fedot.core.constants import DEFAULT_DATA_SPLIT_RATIO_BY_TASK, DEFAULT_CV_FOLDS_BY_TASK
 from fedot.core.data.data import InputData
 from fedot.core.data.data_split import train_test_data_setup
 from fedot.core.data.multi_modal import MultiModalData
@@ -31,7 +32,7 @@ def __init__(self,
                  cv_folds: Optional[int] = None,
                  validation_blocks: Optional[int] = None,
                  split_ratio: Optional[float] = None,
-                 shuffle: bool = False):
+                 shuffle: bool = False,):
         self.cv_folds = cv_folds
         self.validation_blocks = validation_blocks
         self.split_ratio = split_ratio
@@ -45,13 +46,21 @@ def build(self, data: InputData) -> DataSource:
             data.shuffle()
 
         # Check split_ratio
-        split_ratio = self.split_ratio or default_data_split_ratio_by_task[data.task.task_type]
+        split_ratio = self.split_ratio or DEFAULT_DATA_SPLIT_RATIO_BY_TASK[data.task.task_type]
         if not (0 < split_ratio < 1):
             raise ValueError(f'split_ratio is {split_ratio} but should be between 0 and 1')
 
-        # Calculate the number of validation blocks
-        if self.validation_blocks is None and data.task.task_type is TaskTypesEnum.ts_forecasting:
-            self._propose_cv_folds_and_validation_blocks(data, split_ratio)
+        # Calculate the number of validation blocks and number of cv folds for ts forecasting
+        if data.task.task_type is TaskTypesEnum.ts_forecasting:
+            if self.validation_blocks is None:
+                self._propose_cv_folds_and_validation_blocks(data, split_ratio)
+            # when forecasting length is low and data length is high there are huge amount of validation blocks
+            # some model refit each step of forecasting that may be time consuming
+            # solution is set forecasting length to higher value and reduce validation blocks count
+            # without reducing validation data length which is equal to forecast_length * validation_blocks
+            max_validation_blocks = DEFAULT_CV_FOLDS_BY_TASK[data.task.task_type] if self.cv_folds is None else 1
+            if self.validation_blocks > max_validation_blocks:
+                data = self._propose_forecast_length(data, max_validation_blocks)
 
         # Split data
         if self.cv_folds is not None:
@@ -73,7 +82,7 @@ def _build_holdout_producer(self, data: InputData) -> DataSource:
         that always returns same data split. Equivalent to 1-fold validation.
         """
 
-        split_ratio = self.split_ratio or default_data_split_ratio_by_task[data.task.task_type]
+        split_ratio = self.split_ratio or DEFAULT_DATA_SPLIT_RATIO_BY_TASK[data.task.task_type]
         train_data, test_data = train_test_data_setup(data, split_ratio, validation_blocks=self.validation_blocks)
 
         if RemoteEvaluator().is_enabled:
@@ -129,3 +138,11 @@ def _propose_cv_folds_and_validation_blocks(self, data, split_ratio):
         else:
             test_share = 1 / (self.cv_folds + 1)
         self.validation_blocks = int(data_shape * test_share // forecast_length)
+
+    def _propose_forecast_length(self, data, max_validation_blocks):
+        horizon = self.validation_blocks * data.task.task_params.forecast_length
+        self.validation_blocks = max_validation_blocks
+        # TODO: make copy without copy all data, only with task copy
+        data = deepcopy(data)
+        data.task.task_params.forecast_length = int(horizon // self.validation_blocks)
+        return data