From f97526bad8c73956542d8592bda4f19e01936778 Mon Sep 17 00:00:00 2001
From: valer1435 <valp998@gmail.com>
Date: Mon, 7 Aug 2023 14:34:22 +0300
Subject: [PATCH 1/8] fix pep8

---
 fedot/core/pipelines/random_pipeline_factory.py | 2 +-
 fedot/core/pipelines/verification_rules.py      | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/fedot/core/pipelines/random_pipeline_factory.py b/fedot/core/pipelines/random_pipeline_factory.py
index 1210af75c4..f964f0f54e 100644
--- a/fedot/core/pipelines/random_pipeline_factory.py
+++ b/fedot/core/pipelines/random_pipeline_factory.py
@@ -85,4 +85,4 @@ def graph_growth(graph: OptGraph,
             secondary_node = node_factory.get_node(is_primary=False)
             graph.add_node(secondary_node)
             node_parent.nodes_from.append(secondary_node)
-            graph_growth(graph, secondary_node, node_factory, requirements, max_depth)
\ No newline at end of file
+            graph_growth(graph, secondary_node, node_factory, requirements, max_depth)
diff --git a/fedot/core/pipelines/verification_rules.py b/fedot/core/pipelines/verification_rules.py
index cfb02f480f..eebede3594 100644
--- a/fedot/core/pipelines/verification_rules.py
+++ b/fedot/core/pipelines/verification_rules.py
@@ -12,7 +12,7 @@
 
 
 def has_correct_operations_for_task(pipeline: Pipeline, task_type: Optional[TaskTypesEnum] = None):
-    if task_type and not task_type in pipeline.root_node.operation.acceptable_task_types:
+    if task_type and task_type not in pipeline.root_node.operation.acceptable_task_types:
         raise ValueError(f'{ERROR_PREFIX} Pipeline has incorrect operations positions')
     return True
 

From 124f327bfd2fee329f6deb00ab1cb9dfca8254d2 Mon Sep 17 00:00:00 2001
From: valer1435 <valp998@gmail.com>
Date: Wed, 2 Aug 2023 14:10:06 +0300
Subject: [PATCH 2/8] fix pos_label

---
 fedot/core/composer/metrics.py                | 18 +++++++++++++++---
 test/integration/models/test_model.py         | 14 ++++++++++++++
 test/unit/composer/test_quality_metrics.py    |  2 --
 test/unit/data/test_data.py                   |  2 --
 .../optimizer/test_pipeline_objective_eval.py | 19 ++++++++++++++++++-
 5 files changed, 47 insertions(+), 8 deletions(-)

diff --git a/fedot/core/composer/metrics.py b/fedot/core/composer/metrics.py
index 505c356be9..d3d9e42c3e 100644
--- a/fedot/core/composer/metrics.py
+++ b/fedot/core/composer/metrics.py
@@ -88,7 +88,7 @@ def get_value(cls, pipeline: 'Pipeline', reference_data: InputData,
                               save_path=Path(save_path, 'forecast.png'))
 
         except Exception as ex:
-            pipeline.log.info(f'Metric can not be evaluated because of: {ex}')
+            pipeline.log.info(f'Metric can not be evaluated because of: {ex}', raise_if_test=True)
 
         return metric
 
@@ -216,7 +216,10 @@ def metric(reference: InputData, predicted: OutputData) -> float:
         if n_classes > 2:
             additional_params = {'average': F1.multiclass_averaging_mode}
         else:
-            additional_params = {'average': F1.binary_averaging_mode}
+            u, count = np.unique(np.ravel(reference.target), return_counts=True)
+            count_sort_ind = np.argsort(count)
+            pos_label = u[count_sort_ind[0]].item()
+            additional_params = {'average': F1.binary_averaging_mode, 'pos_label': pos_label}
         return f1_score(y_true=reference.target, y_pred=predicted.predict,
                         **additional_params)
 
@@ -271,7 +274,16 @@ class Precision(QualityMetric):
     @staticmethod
     @from_maximised_metric
     def metric(reference: InputData, predicted: OutputData) -> float:
-        return precision_score(y_true=reference.target, y_pred=predicted.predict)
+        n_classes = reference.num_classes
+        if n_classes > 2:
+            return precision_score(y_true=reference.target, y_pred=predicted.predict)
+        else:
+            u, count = np.unique(np.ravel(reference.target), return_counts=True)
+            count_sort_ind = np.argsort(count)
+            pos_label = u[count_sort_ind[0]].item()
+            additional_params = {'pos_label': pos_label}
+            return precision_score(y_true=reference.target, y_pred=predicted.predict,
+                                   **additional_params)
 
 
 class Logloss(QualityMetric):
diff --git a/test/integration/models/test_model.py b/test/integration/models/test_model.py
index 5fdc72b52f..171acb23ad 100644
--- a/test/integration/models/test_model.py
+++ b/test/integration/models/test_model.py
@@ -98,6 +98,20 @@ def classification_dataset():
     threshold = 0.5
     classes = np.array([0.0 if val <= threshold else 1.0 for val in y])
     classes = np.expand_dims(classes, axis=1)
+    data = InputData(features=MinMaxScaler().fit_transform(x), target=classes, idx=np.arange(0, len(x)),
+                     task=Task(TaskTypesEnum.classification),
+                     data_type=DataTypesEnum.table)
+    return data
+
+
+def classification_dataset_with_str_labels():
+    samples = 1000
+    x = 10.0 * np.random.rand(samples, ) - 5.0
+    x = np.expand_dims(x, axis=1)
+    y = 1.0 / (1.0 + np.exp(np.power(x, -1.0)))
+    threshold = 0.5
+    classes = np.array(['a' if val <= threshold else 'b' for val in y])
+    classes = np.expand_dims(classes, axis=1)
     data = InputData(features=MinMaxScaler().fit_transform(x), target=classes, idx=np.arange(0, len(x)),
                      task=Task(TaskTypesEnum.classification),
                      data_type=DataTypesEnum.table)
diff --git a/test/unit/composer/test_quality_metrics.py b/test/unit/composer/test_quality_metrics.py
index bb9e1786f6..426faef66d 100644
--- a/test/unit/composer/test_quality_metrics.py
+++ b/test/unit/composer/test_quality_metrics.py
@@ -22,8 +22,6 @@
 @pytest.fixture()
 def data_setup():
     predictors, response = load_breast_cancer(return_X_y=True)
-    np.random.shuffle(predictors)
-    np.random.shuffle(response)
     response = response[:100]
     predictors = predictors[:100]
 
diff --git a/test/unit/data/test_data.py b/test/unit/data/test_data.py
index 7d987dc3c9..a3eb55bfaa 100644
--- a/test/unit/data/test_data.py
+++ b/test/unit/data/test_data.py
@@ -18,8 +18,6 @@
 @pytest.fixture()
 def data_setup() -> InputData:
     predictors, response = load_iris(return_X_y=True)
-    np.random.shuffle(predictors)
-    np.random.shuffle(response)
     predictors = predictors[:100]
     response = response[:100]
     data = InputData(features=predictors, target=response, idx=np.arange(0, 100),
diff --git a/test/unit/optimizer/test_pipeline_objective_eval.py b/test/unit/optimizer/test_pipeline_objective_eval.py
index cfb3f86444..657b7a201e 100644
--- a/test/unit/optimizer/test_pipeline_objective_eval.py
+++ b/test/unit/optimizer/test_pipeline_objective_eval.py
@@ -18,7 +18,7 @@
     RegressionMetricsEnum
 from fedot.core.repository.tasks import Task, TaskTypesEnum
 from fedot.core.validation.split import tabular_cv_generator, OneFoldInputDataSplit
-from test.integration.models.test_model import classification_dataset
+from test.integration.models.test_model import classification_dataset, classification_dataset_with_str_labels
 from test.unit.tasks.test_forecasting import get_simple_ts_pipeline
 from test.unit.validation.test_table_cv import sample_pipeline
 from test.unit.validation.test_time_series_cv import configure_experiment
@@ -86,6 +86,23 @@ def test_pipeline_objective_evaluate_with_different_metrics(classification_datas
         assert np.isclose(fitness.value, act_fitness.value, atol=1e-8), metric.name
 
 
+@pytest.mark.parametrize(
+    'pipeline',
+    [pipeline_first_test(), pipeline_second_test(), pipeline_third_test()]
+)
+def test_pipeline_objective_evaluate_with_different_metrics_with_str_labes(pipeline):
+    for metric in ClassificationMetricsEnum:
+        one_fold_split = OneFoldInputDataSplit()
+        data_split = partial(one_fold_split.input_split, input_data=classification_dataset_with_str_labels())
+        check_pipeline = deepcopy(pipeline)
+        objective_eval = PipelineObjectiveEvaluate(MetricsObjective(metric), data_split)
+        fitness = objective_eval(pipeline)
+        act_fitness = actual_fitness(data_split, check_pipeline, metric)
+        assert fitness.valid
+        assert fitness.value is not None
+        assert np.isclose(fitness.value, act_fitness.value, atol=1e-8), metric.name
+
+
 def test_pipeline_objective_evaluate_with_empty_pipeline(classification_dataset):
     pipeline = empty_pipeline()
 

From 8fcdae4199521e93adeb9439a2d28644493f48da Mon Sep 17 00:00:00 2001
From: valer1435 <valp998@gmail.com>
Date: Thu, 3 Aug 2023 17:54:44 +0300
Subject: [PATCH 3/8] fix resample

---
 .../core/pipelines/random_pipeline_factory.py |  3 ++-
 fedot/core/pipelines/verification.py          |  5 +++--
 fedot/core/pipelines/verification_rules.py    | 22 +++++++++++++++++++
 .../repository/data/model_repository.json     |  6 ++++-
 test/unit/validation/test_table_cv.py         |  2 ++
 5 files changed, 34 insertions(+), 4 deletions(-)

diff --git a/fedot/core/pipelines/random_pipeline_factory.py b/fedot/core/pipelines/random_pipeline_factory.py
index f964f0f54e..d48e305b53 100644
--- a/fedot/core/pipelines/random_pipeline_factory.py
+++ b/fedot/core/pipelines/random_pipeline_factory.py
@@ -1,3 +1,4 @@
+import random
 from copy import deepcopy
 from random import randint
 from typing import Optional
@@ -76,7 +77,7 @@ def graph_growth(graph: OptGraph,
     for offspring_node in range(offspring_size):
         height = distance_to_root_level(graph, node_parent)
         is_max_depth_exceeded = height >= max_depth - 2
-        is_primary_node_selected = height < max_depth - 1 and randint(0, 1)
+        is_primary_node_selected = height < max_depth - 1 and random.random() > 0.3
         if is_max_depth_exceeded or is_primary_node_selected:
             primary_node = node_factory.get_node(is_primary=True)
             node_parent.nodes_from.append(primary_node)
diff --git a/fedot/core/pipelines/verification.py b/fedot/core/pipelines/verification.py
index 6e619ba38c..6a5ff7d5a7 100644
--- a/fedot/core/pipelines/verification.py
+++ b/fedot/core/pipelines/verification.py
@@ -26,7 +26,7 @@
     has_no_data_flow_conflicts_in_ts_pipeline,
     has_primary_nodes,
     is_pipeline_contains_ts_operations,
-    only_non_lagged_operations_are_primary
+    only_non_lagged_operations_are_primary, has_correct_location_of_resample
 )
 from fedot.core.repository.tasks import TaskTypesEnum
 
@@ -40,7 +40,8 @@
                 has_no_conflicts_with_data_flow,
                 has_no_conflicts_in_decompose,
                 has_correct_data_connections,
-                has_correct_data_sources]
+                has_correct_data_sources,
+                has_correct_location_of_resample]
 
 ts_rules = [is_pipeline_contains_ts_operations,
             only_non_lagged_operations_are_primary,
diff --git a/fedot/core/pipelines/verification_rules.py b/fedot/core/pipelines/verification_rules.py
index eebede3594..8b5610580c 100644
--- a/fedot/core/pipelines/verification_rules.py
+++ b/fedot/core/pipelines/verification_rules.py
@@ -152,6 +152,28 @@ def has_no_data_flow_conflicts_in_ts_pipeline(pipeline: Pipeline):
     return True
 
 
+def has_correct_location_of_resample(pipeline: Pipeline):
+    """
+    Pipeline can have only one resample operation located in start of the pipeline
+
+    :param pipeline: pipeline for checking
+    """
+    is_resample_primary = False
+    is_not_resample_primary = False
+    for node in pipeline.nodes:
+        if not node.nodes_from:
+            if node.name == 'resample':
+                is_resample_primary = True
+            else:
+                is_not_resample_primary = True
+        if node.name == 'resample':
+            raise ValueError(
+                f'{ERROR_PREFIX} Pipeline can have only one resample operation located in start of the pipeline')
+    if is_resample_primary and is_not_resample_primary:
+        raise ValueError(
+            f'{ERROR_PREFIX} Pipeline can have only one resample operation located in start of the pipeline')
+
+
 def get_wrong_links(ts_to_table_operations: list, ts_data_operations: list, non_ts_data_operations: list,
                     ts_models: list, non_ts_models: list) -> dict:
     """
diff --git a/fedot/core/repository/data/model_repository.json b/fedot/core/repository/data/model_repository.json
index 47d1be30c6..0ef86535fa 100644
--- a/fedot/core/repository/data/model_repository.json
+++ b/fedot/core/repository/data/model_repository.json
@@ -165,7 +165,10 @@
       "meta": "sklearn_class",
       "presets": ["fast_train"],
       "tags": [
-        "bayesian", "non_multi", "linear"
+        "simple",
+        "bayesian",
+        "non_multi",
+        "linear"
       ]
     },
     "catboost": {
@@ -186,6 +189,7 @@
       "meta": "sklearn_class",
       "presets": ["fast_train", "*tree"],
       "tags": [
+        "simple",
         "tree",
         "interpretable",
         "non_linear"
diff --git a/test/unit/validation/test_table_cv.py b/test/unit/validation/test_table_cv.py
index fe67c0ab34..e63ee9c5f3 100644
--- a/test/unit/validation/test_table_cv.py
+++ b/test/unit/validation/test_table_cv.py
@@ -4,9 +4,11 @@
 
 import pytest
 from golem.core.tuning.simultaneous import SimultaneousTuner
+from sklearn.metrics import roc_auc_score as roc_auc
 from sklearn.model_selection import KFold, StratifiedKFold
 
 from fedot.api.main import Fedot
+from fedot.core.composer.composer_builder import ComposerBuilder
 from fedot.core.data.data import InputData
 from fedot.core.data.data_split import train_test_data_setup
 from fedot.core.optimisers.objective import PipelineObjectiveEvaluate

From 293c4532d77e88261c173d87763af13ba814ace2 Mon Sep 17 00:00:00 2001
From: valer1435 <valp998@gmail.com>
Date: Mon, 7 Aug 2023 11:59:52 +0300
Subject: [PATCH 4/8] fix resample

---
 fedot/api/api_utils/api_params_repository.py      |  5 ++++-
 .../composer/gp_composer/specific_operators.py    | 11 +++++++++++
 fedot/core/pipelines/pipeline.py                  | 15 ++++++++++++++-
 fedot/core/pipelines/verification_rules.py        |  8 +++++---
 4 files changed, 34 insertions(+), 5 deletions(-)

diff --git a/fedot/api/api_utils/api_params_repository.py b/fedot/api/api_utils/api_params_repository.py
index ed90d03d8b..9a6e76f4ef 100644
--- a/fedot/api/api_utils/api_params_repository.py
+++ b/fedot/api/api_utils/api_params_repository.py
@@ -5,7 +5,8 @@
 from golem.core.optimisers.genetic.operators.inheritance import GeneticSchemeTypesEnum
 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.composer.gp_composer.specific_operators import parameter_change_mutation, boosting_mutation, \
+    add_resample_mutation
 from fedot.core.constants import AUTO_PRESET_NAME
 from fedot.core.repository.tasks import TaskTypesEnum
 from fedot.core.utils import default_fedot_data_dir
@@ -131,5 +132,7 @@ def _get_default_mutations(task_type: TaskTypesEnum, params) -> Sequence[Mutatio
         # TODO remove workaround after boosting mutation fix
         if task_type == TaskTypesEnum.ts_forecasting:
             mutations.append(partial(boosting_mutation, params=params))
+        else:
+            mutations.append(add_resample_mutation)
 
         return mutations
diff --git a/fedot/core/composer/gp_composer/specific_operators.py b/fedot/core/composer/gp_composer/specific_operators.py
index 439bd89fad..2e53c8ae50 100644
--- a/fedot/core/composer/gp_composer/specific_operators.py
+++ b/fedot/core/composer/gp_composer/specific_operators.py
@@ -90,6 +90,17 @@ def boosting_mutation(pipeline: Pipeline, requirements, graph_gen_params, **kwar
     return pipeline
 
 
+def add_resample_mutation(pipeline: Pipeline, **kwargs):
+    resample_node = PipelineNode('resample')
+
+    p_nodes = [p_node for p_node in pipeline.primary_nodes]
+    pipeline.add_node(resample_node)
+
+    for node in p_nodes:
+        pipeline.connect_nodes(resample_node, node)
+    return pipeline
+
+
 def choose_new_model(boosting_model_candidates: List[str]) -> str:
     """ Since 'linear' and 'dtreg' operations are suitable for solving the problem
     and they are simpler than others, they are preferred """
diff --git a/fedot/core/pipelines/pipeline.py b/fedot/core/pipelines/pipeline.py
index 220984b206..3778f27934 100644
--- a/fedot/core/pipelines/pipeline.py
+++ b/fedot/core/pipelines/pipeline.py
@@ -1,7 +1,7 @@
 from copy import deepcopy
 from datetime import timedelta
 from os import PathLike
-from typing import Optional, Tuple, Union, Sequence, Dict
+from typing import Optional, Tuple, Union, Sequence, List, Dict
 
 import func_timeout
 from golem.core.dag.graph import Graph
@@ -327,6 +327,19 @@ def root_node(self) -> Optional[PipelineNode]:
             raise ValueError(f'{ERROR_PREFIX} More than 1 root_nodes in pipeline')
         return root[0]
 
+    @property
+    def primary_nodes(self) -> List[PipelineNode]:
+        """Finds pipelines sink-node
+
+        Returns:
+            the final predictor-node
+        """
+        if not self.nodes:
+            return []
+        primary_nodes = [node for node in self.nodes
+                         if not node.nodes_from]
+        return primary_nodes
+
     def pipeline_for_side_task(self, task_type: TaskTypesEnum) -> 'Pipeline':
         """Returns pipeline formed from the last node solving the given problem and all its parents
 
diff --git a/fedot/core/pipelines/verification_rules.py b/fedot/core/pipelines/verification_rules.py
index 8b5610580c..fbc1c13ea8 100644
--- a/fedot/core/pipelines/verification_rules.py
+++ b/fedot/core/pipelines/verification_rules.py
@@ -166,12 +166,14 @@ def has_correct_location_of_resample(pipeline: Pipeline):
                 is_resample_primary = True
             else:
                 is_not_resample_primary = True
-        if node.name == 'resample':
-            raise ValueError(
-                f'{ERROR_PREFIX} Pipeline can have only one resample operation located in start of the pipeline')
+        else:
+            if node.name == 'resample':
+                raise ValueError(
+                    f'{ERROR_PREFIX} Pipeline can have only one resample operation located in start of the pipeline')
     if is_resample_primary and is_not_resample_primary:
         raise ValueError(
             f'{ERROR_PREFIX} Pipeline can have only one resample operation located in start of the pipeline')
+    return True
 
 
 def get_wrong_links(ts_to_table_operations: list, ts_data_operations: list, non_ts_data_operations: list,

From b9be1d8eb9ee0cdd91bcbebaaf25e683fc125024 Mon Sep 17 00:00:00 2001
From: valer1435 <valp998@gmail.com>
Date: Mon, 7 Aug 2023 18:04:22 +0300
Subject: [PATCH 5/8] fix unexpected inplace operations

---
 fedot/core/operations/operation.py | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/fedot/core/operations/operation.py b/fedot/core/operations/operation.py
index 23314407e1..deed03a172 100644
--- a/fedot/core/operations/operation.py
+++ b/fedot/core/operations/operation.py
@@ -1,4 +1,5 @@
 from abc import abstractmethod
+from copy import deepcopy
 from typing import Optional, Union, Dict, Any
 
 from golem.core.log import default_log
@@ -80,6 +81,7 @@ def fit(self, params: Optional[Union[OperationParameters, dict]], data: InputDat
         Returns:
             tuple: trained operation and prediction on train data
         """
+        data = deepcopy(data)
         self._init(data.task, params=params, n_samples_data=data.features.shape[0])
 
         self.fitted_operation = self._eval_strategy.fit(train_data=data)
@@ -119,6 +121,7 @@ def predict_for_fit(self, fitted_operation, data: InputData, params: Optional[Op
     def _predict(self, fitted_operation, data: InputData, params: Optional[OperationParameters] = None,
                  output_mode: str = 'default', is_fit_stage: bool = False):
 
+        data = deepcopy(data)
         is_main_target = data.supplementary_data.is_main_target
         data_flow_length = data.supplementary_data.data_flow_length
         self._init(data.task, output_mode=output_mode, params=params, n_samples_data=data.features.shape[0])

From 4ae55dbd4ce99c8d59fa4e993053aa0a1116e096 Mon Sep 17 00:00:00 2001
From: valer1435 <valp998@gmail.com>
Date: Wed, 9 Aug 2023 17:44:54 +0300
Subject: [PATCH 6/8] review fixes

---
 fedot/core/composer/gp_composer/specific_operators.py | 7 +++++++
 fedot/core/pipelines/pipeline.py                      | 8 ++++----
 fedot/core/pipelines/random_pipeline_factory.py       | 6 ++++--
 fedot/core/pipelines/verification_rules.py            | 2 +-
 4 files changed, 16 insertions(+), 7 deletions(-)

diff --git a/fedot/core/composer/gp_composer/specific_operators.py b/fedot/core/composer/gp_composer/specific_operators.py
index 2e53c8ae50..7799fe432f 100644
--- a/fedot/core/composer/gp_composer/specific_operators.py
+++ b/fedot/core/composer/gp_composer/specific_operators.py
@@ -91,6 +91,13 @@ def boosting_mutation(pipeline: Pipeline, requirements, graph_gen_params, **kwar
 
 
 def add_resample_mutation(pipeline: Pipeline, **kwargs):
+    """
+    Add resample operation before all primary operations in pipeline
+
+    :param pipeline: pipeline to insert resample
+
+    :return: mutated pipeline
+    """
     resample_node = PipelineNode('resample')
 
     p_nodes = [p_node for p_node in pipeline.primary_nodes]
diff --git a/fedot/core/pipelines/pipeline.py b/fedot/core/pipelines/pipeline.py
index 3778f27934..a9a608c2c9 100644
--- a/fedot/core/pipelines/pipeline.py
+++ b/fedot/core/pipelines/pipeline.py
@@ -307,7 +307,7 @@ def load(self, source: Union[str, dict], dict_fitted_operations: Optional[dict]
             dict_fitted_operations: dictionary of the fitted operations
         """
 
-        self.nodes = []
+        self.nodes: Optional[List[PipelineNode]] = []
         template = PipelineTemplate(self)
         template.import_pipeline(source, dict_fitted_operations)
         return self
@@ -329,15 +329,15 @@ def root_node(self) -> Optional[PipelineNode]:
 
     @property
     def primary_nodes(self) -> List[PipelineNode]:
-        """Finds pipelines sink-node
+        """Finds pipeline's primary nodes
 
         Returns:
-            the final predictor-node
+            list of primary nodes
         """
         if not self.nodes:
             return []
         primary_nodes = [node for node in self.nodes
-                         if not node.nodes_from]
+                         if node.is_primary]
         return primary_nodes
 
     def pipeline_for_side_task(self, task_type: TaskTypesEnum) -> 'Pipeline':
diff --git a/fedot/core/pipelines/random_pipeline_factory.py b/fedot/core/pipelines/random_pipeline_factory.py
index d48e305b53..d08f180c58 100644
--- a/fedot/core/pipelines/random_pipeline_factory.py
+++ b/fedot/core/pipelines/random_pipeline_factory.py
@@ -15,6 +15,7 @@
 
 class RandomPipelineFactory(RandomGraphFactory):
     """ Default realisation of random graph factory. Generates DAG graph using random growth. """
+    PROBABILITY_OF_GROWTH = 0.3
 
     def __init__(self,
                  verifier: GraphVerifier,
@@ -77,8 +78,9 @@ def graph_growth(graph: OptGraph,
     for offspring_node in range(offspring_size):
         height = distance_to_root_level(graph, node_parent)
         is_max_depth_exceeded = height >= max_depth - 2
-        is_primary_node_selected = height < max_depth - 1 and random.random() > 0.3
-        if is_max_depth_exceeded or is_primary_node_selected:
+        is_primary_node_selected = height < max_depth - 1
+        is_growth_should_stopped = random.random() > RandomPipelineFactory.PROBABILITY_OF_GROWTH
+        if is_max_depth_exceeded or is_primary_node_selected or is_growth_should_stopped:
             primary_node = node_factory.get_node(is_primary=True)
             node_parent.nodes_from.append(primary_node)
             graph.add_node(primary_node)
diff --git a/fedot/core/pipelines/verification_rules.py b/fedot/core/pipelines/verification_rules.py
index fbc1c13ea8..7c40d53280 100644
--- a/fedot/core/pipelines/verification_rules.py
+++ b/fedot/core/pipelines/verification_rules.py
@@ -161,7 +161,7 @@ def has_correct_location_of_resample(pipeline: Pipeline):
     is_resample_primary = False
     is_not_resample_primary = False
     for node in pipeline.nodes:
-        if not node.nodes_from:
+        if node.is_primary:
             if node.name == 'resample':
                 is_resample_primary = True
             else:

From 1d4959079afdc89bc0cca418be09735db24809b1 Mon Sep 17 00:00:00 2001
From: valer1435 <valp998@gmail.com>
Date: Mon, 14 Aug 2023 11:17:05 +0300
Subject: [PATCH 7/8] remove deepcopy

---
 fedot/core/operations/operation.py | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/fedot/core/operations/operation.py b/fedot/core/operations/operation.py
index deed03a172..1b34ebacde 100644
--- a/fedot/core/operations/operation.py
+++ b/fedot/core/operations/operation.py
@@ -1,5 +1,4 @@
 from abc import abstractmethod
-from copy import deepcopy
 from typing import Optional, Union, Dict, Any
 
 from golem.core.log import default_log
@@ -81,7 +80,6 @@ def fit(self, params: Optional[Union[OperationParameters, dict]], data: InputDat
         Returns:
             tuple: trained operation and prediction on train data
         """
-        data = deepcopy(data)
         self._init(data.task, params=params, n_samples_data=data.features.shape[0])
 
         self.fitted_operation = self._eval_strategy.fit(train_data=data)
@@ -121,7 +119,7 @@ def predict_for_fit(self, fitted_operation, data: InputData, params: Optional[Op
     def _predict(self, fitted_operation, data: InputData, params: Optional[OperationParameters] = None,
                  output_mode: str = 'default', is_fit_stage: bool = False):
 
-        data = deepcopy(data)
+
         is_main_target = data.supplementary_data.is_main_target
         data_flow_length = data.supplementary_data.data_flow_length
         self._init(data.task, output_mode=output_mode, params=params, n_samples_data=data.features.shape[0])
@@ -136,11 +134,11 @@ def _predict(self, fitted_operation, data: InputData, params: Optional[Operation
                 predict_data=data)
         prediction = self.assign_tabular_column_types(prediction, output_mode)
 
+        # any inplace operations here are dangerous!
         if is_main_target is False:
             prediction.supplementary_data.is_main_target = is_main_target
 
         prediction.supplementary_data.data_flow_length = data_flow_length
-        prediction.supplementary_data.obligatorily_preprocessed = True
         return prediction
 
     @staticmethod

From b7af0ed7c296c4e2621b7c5e83c179ec2e429172 Mon Sep 17 00:00:00 2001
From: valer1435 <valp998@gmail.com>
Date: Mon, 14 Aug 2023 12:08:17 +0300
Subject: [PATCH 8/8] pep8

---
 test/unit/validation/test_table_cv.py | 2 --
 1 file changed, 2 deletions(-)

diff --git a/test/unit/validation/test_table_cv.py b/test/unit/validation/test_table_cv.py
index e63ee9c5f3..fe67c0ab34 100644
--- a/test/unit/validation/test_table_cv.py
+++ b/test/unit/validation/test_table_cv.py
@@ -4,11 +4,9 @@
 
 import pytest
 from golem.core.tuning.simultaneous import SimultaneousTuner
-from sklearn.metrics import roc_auc_score as roc_auc
 from sklearn.model_selection import KFold, StratifiedKFold
 
 from fedot.api.main import Fedot
-from fedot.core.composer.composer_builder import ComposerBuilder
 from fedot.core.data.data import InputData
 from fedot.core.data.data_split import train_test_data_setup
 from fedot.core.optimisers.objective import PipelineObjectiveEvaluate