Fix inplace modification of data during data definition (resolves #943)…

… (#950)

* some name/move refactorings

* Fix inplace modification of input data during data define

* fixup! some name/move refactorings

fedot/api/api_utils/api_data.py

@@ -2,9 +2,8 @@
 from typing import Optional
 
 import numpy as np
-import pandas as pd
 
-from fedot.api.api_utils.data_definition import data_strategy_selector
+from fedot.api.api_utils.data_definition import data_strategy_selector, FeaturesType, TargetType
 from fedot.core.data.data import InputData, OutputData, data_type_is_table
 from fedot.core.data.data_preprocessing import convert_into_column
 from fedot.core.data.multi_modal import MultiModalData
@@ -35,8 +34,8 @@ def __init__(self, task: Task):
                                 'label_encoded': self.preprocessor.label_encoding_for_fit}
 
     def define_data(self,
-                    features: Union[str, np.ndarray, pd.DataFrame, InputData, dict],
-                    target: Union[str, np.ndarray, pd.Series] = None,
+                    features: FeaturesType,
+                    target: Optional[TargetType] = None,
                     is_predict=False):
         """ Prepare data for FEDOT pipeline composing.
         Obligatory preprocessing steps are applying also. If features is dictionary

fedot/api/api_utils/data_definition.py

@@ -1,6 +1,6 @@
 from abc import ABC, abstractmethod
 from copy import deepcopy
-from typing import Union
+from typing import Union, Optional
 
 import numpy as np
 import pandas as pd
@@ -10,6 +10,9 @@
 from fedot.core.repository.dataset_types import DataTypesEnum
 from fedot.core.repository.tasks import Task, TaskTypesEnum
 
+FeaturesType = Union[str, np.ndarray, pd.DataFrame, InputData, dict, tuple]
+TargetType = Union[str, np.ndarray, pd.Series, dict]
+
 
 class DataDefiner:
 
@@ -24,9 +27,9 @@ def strategy(self):
     def strategy(self, strategy) -> None:
         self._strategy = strategy
 
-    def define_data(self, features: Union[tuple, str, np.ndarray, pd.DataFrame, InputData],
+    def define_data(self, features: FeaturesType,
                     ml_task: Task,
-                    target: str = None,
+                    target: Optional[str] = None,
                     is_predict: bool = False) -> None:
         return self._strategy.define_data(features,
                                           ml_task,
@@ -77,7 +80,7 @@ def define_data(self, features: pd.DataFrame,
 
         if isinstance(target, str) and target in features.columns:
             target_array = features[target]
-            del features[target]
+            features = features.drop(columns=[target])
         else:
             target_array = target
 
@@ -90,15 +93,15 @@ def define_data(self, features: pd.DataFrame,
 class NumpyStrategy(StrategyDefineData):
     def define_data(self, features: np.ndarray,
                     ml_task: Task,
-                    target: str = None,
+                    target: Optional[int] = None,
                     is_predict: bool = False) -> InputData:
         # numpy format for input data
         if target is None:
             target = np.array([])
 
-        if isinstance(target, str):
+        if isinstance(target, int):
             target_array = features[target]
-            del features[target]
+            features = np.delete(features, target, axis=1)
         else:
             target_array = target
 
@@ -163,13 +166,15 @@ def define_data(self, features: dict,
 
 def data_strategy_selector(features, target, ml_task: Task = None, is_predict: bool = None):
     data_type = type(features)
-    strategy_dict = {InputData: FedotStrategy(),
-                     MultiModalData: FedotStrategy(),
-                     tuple: TupleStrategy(),
-                     pd.DataFrame: PandasStrategy(),
-                     np.ndarray: NumpyStrategy(),
-                     str: CsvStrategy(),
-                     dict: MultimodalStrategy()}
-
-    data = DataDefiner(strategy_dict[data_type])
+
+    data = DataDefiner(_strategy_dispatch[data_type]())
     return data.define_data(features, ml_task, target, is_predict)
+
+
+_strategy_dispatch = {InputData: FedotStrategy,
+                      MultiModalData: FedotStrategy,
+                      tuple: TupleStrategy,
+                      pd.DataFrame: PandasStrategy,
+                      np.ndarray: NumpyStrategy,
+                      str: CsvStrategy,
+                      dict: MultimodalStrategy}

fedot/api/main.py

@@ -7,6 +7,7 @@
 
 from fedot.api.api_utils.api_composer import ApiComposer
 from fedot.api.api_utils.api_data import ApiDataProcessor
+from fedot.api.api_utils.data_definition import FeaturesType, TargetType
 from fedot.api.api_utils.api_data_analyser import DataAnalyser
 from fedot.api.api_utils.metrics import ApiMetrics
 from fedot.api.api_utils.params import ApiParams
@@ -30,9 +31,6 @@
 
 NOT_FITTED_ERR_MSG = 'Model not fitted yet'
 
-FeaturesType = Union[str, np.ndarray, pd.DataFrame, InputData, dict]
-TargetType = Union[str, np.ndarray, pd.Series, dict]
-
 
 class Fedot:
     """Main class for FEDOT API.
@@ -142,7 +140,7 @@ def __init__(self,
         self.history: Optional[OptHistory] = None
 
     def fit(self,
-            features: Union[str, np.ndarray, pd.DataFrame, InputData, dict],
+            features: FeaturesType,
             target: TargetType = 'target',
             predefined_model: Union[str, Pipeline] = None) -> Pipeline:
         """Fits the graph with a predefined structure or compose and fit the new graph