dragon-ml-toolbox 3.12.1__py3-none-any.whl → 3.12.2__py3-none-any.whl

{dragon_ml_toolbox-3.12.1.dist-info → dragon_ml_toolbox-3.12.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 3.12.1
+Version: 3.12.2
 Summary: A collection of tools for data science and machine learning projects.
 Author-email: Karl Loza <luigiloza@gmail.com>
 License-Expression: MIT

{dragon_ml_toolbox-3.12.1.dist-info → dragon_ml_toolbox-3.12.2.dist-info}/RECORD

@@ -1,7 +1,7 @@
-dragon_ml_toolbox-3.12.1.dist-info/licenses/LICENSE,sha256=2uUFNy7D0TLgHim1K5s3DIJ4q_KvxEXVilnU20cWliY,1066
-dragon_ml_toolbox-3.12.1.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=lY4_rJPnLnMu7YBQaY-_iz1JRDcLdQzNCyeLAF1glJY,1837
+dragon_ml_toolbox-3.12.2.dist-info/licenses/LICENSE,sha256=2uUFNy7D0TLgHim1K5s3DIJ4q_KvxEXVilnU20cWliY,1066
+dragon_ml_toolbox-3.12.2.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=lY4_rJPnLnMu7YBQaY-_iz1JRDcLdQzNCyeLAF1glJY,1837
 ml_tools/ETL_engineering.py,sha256=yeZsW_7zRvEcuMZbM4E2GV1dxwBoWIeJAcFFk2AK0fY,39502
-ml_tools/GUI_tools.py,sha256=VonZEizPS0ncm8HWU-ik-SgcXKryJU8eSG7NN0QN9cc,42222
+ml_tools/GUI_tools.py,sha256=SkPqqY0xdxVq3C0hpcMVxEseVXzW3eT9jN1RUlP6qbA,43105
 ml_tools/MICE_imputation.py,sha256=7CDsIQxx5Jb_DwPAmWmz3FXcn85sUyH7g9UcZ1_E07s,11412
 ml_tools/ML_callbacks.py,sha256=g_9nSzoA22UJOQZCPKeDz-Ayh0ECFZLzRd6rZ8SokrE,13080
 ml_tools/ML_evaluation.py,sha256=oiDV6HItQloUUKCUpltV-2pogubWLBieGpc-VUwosAQ,10106
@@ -16,11 +16,11 @@ ml_tools/data_exploration.py,sha256=ZpjK_lN5mDhjf9iQpvyYNA2SF7M5q4D5m09saln7YFI,
 ml_tools/datasetmaster.py,sha256=S3PKHNQZ9cyAOck8xQltVLZhaD1gFLfgHFL-aRjz4JU,30077
 ml_tools/ensemble_learning.py,sha256=D-9IbOKtCvyAB-LbPu3sdSRtdp0RZIcQEZcyMnarHmQ,45758
 ml_tools/handle_excel.py,sha256=2Q_MBArss4emPQ8p-Uj9x_e7wGg3OoYM2AU_HG59UCY,12978
-ml_tools/keys.py,sha256=A3mLrtLZrxL27whAs2F1GPqZ1KzJpxBp6QbhxY5ioPI,636
+ml_tools/keys.py,sha256=3YVbcYARSjE3vKr_6PavJSf7vXvlos7szu3qva4T3Ts,781
 ml_tools/logger.py,sha256=UkbiU9ihBhw9VKyn3rZzisdClWV94EBV6B09_D0iUU0,6026
 ml_tools/path_manager.py,sha256=1LD9JFzqVyJQl2kTA7tK930_IV3qxfiV4cMIBzItytY,8309
 ml_tools/utilities.py,sha256=Vh4ZdI03g8EpgQL7KDwnAw2vtBlHtx6KxCuAATxLvT4,24208
-dragon_ml_toolbox-3.12.1.dist-info/METADATA,sha256=vwEN95BhK71LrhuuTuZbxdyfdq_X5VljuP89uXNguok,3274
-dragon_ml_toolbox-3.12.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-dragon_ml_toolbox-3.12.1.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
-dragon_ml_toolbox-3.12.1.dist-info/RECORD,,
+dragon_ml_toolbox-3.12.2.dist-info/METADATA,sha256=JyL5AgD0yfz5tZL8bT0w4EYlKwDwU5DbabfWQl77vNs,3274
+dragon_ml_toolbox-3.12.2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+dragon_ml_toolbox-3.12.2.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
+dragon_ml_toolbox-3.12.2.dist-info/RECORD,,

ml_tools/GUI_tools.py

@@ -7,6 +7,7 @@ from typing import Any, Dict, Tuple, List, Literal, Union, Optional, Callable
 from .utilities import _script_info
 import numpy as np
 from .logger import _LOGGER
+from .keys import _OneHotOtherPlaceholder
 
 
 __all__ = [
@@ -416,7 +417,7 @@ class FeatureMaster:
 
     This class serves as a centralized registry for all features and targets 
     used by a model. It is designed to bridge the gap between a user-facing 
-    application (like a GUI) and the underlying model's data representation.
+    application (GUI) and the underlying model's data representation.
 
     It takes various types of features (continuous, binary, one-hot encoded, 
     categorical) and targets, processing them into two key formats:
@@ -439,7 +440,8 @@ class FeatureMaster:
                  binary_features: Optional[Dict[str, str]] = None,
                  multi_binary_features: Optional[Dict[str, Dict[str, str]]] = None,
                  one_hot_features: Optional[Dict[str, Dict[str, str]]] = None,
-                 categorical_features: Optional[List[Tuple[str, str, Dict[str, int]]]] = None) -> None:
+                 categorical_features: Optional[List[Tuple[str, str, Dict[str, int]]]] = None,
+                 add_one_hot_other_placeholder: bool = True) -> None:
         """
         Initializes the FeatureMaster instance by processing feature and target definitions.
 
@@ -490,6 +492,9 @@ class FeatureMaster:
                     -   `[1]` (str): The model's internal feature name.
                     -   `[2]` (Dict[str, int]): A dictionary mapping the user-selectable 
                         options to their corresponding integer values.
+                
+            add_one_hot_other_placeholder (bool):
+                Add a placeholder for the "Other" option. Used if `drop_first` was used when making the one-hot-encoding to prevent multicollinearity.
         """
         # Validation
         if continuous_features is None and binary_features is None and one_hot_features is None and categorical_features is None and multi_binary_features is None:
@@ -526,7 +531,15 @@ class FeatureMaster:
             self.has_multi_binary = False
         
         # one-hot features
+        self._has_one_hot_other = False
         if one_hot_features is not None:
+            # Check for add_other
+            if add_one_hot_other_placeholder:
+                self._has_one_hot_other = True
+                # update OTHER value in-place
+                for _gui_name, one_hot_dict in one_hot_features.items():
+                    one_hot_dict.update(_OneHotOtherPlaceholder.OTHER_DICT)
+
             self._one_hot_values = self._handle_one_hot_features(one_hot_features)
             self._one_hot_mapping = one_hot_features
             self.has_one_hot = True
@@ -861,11 +874,17 @@ class GUIHandler:
             _LOGGER.error(f"No matching name for '{gui_feature}' defined as one-hot.")
             raise e
         else:
-            mapped_chosen_value = one_hot_mapping[chosen_value]
             # base results mapped to 0
             results = {model_key: 0 for model_key in one_hot_mapping.values()}
+            # get mapped key
+            mapped_chosen_value = one_hot_mapping[chosen_value]
             # update chosen value
             results[mapped_chosen_value] = 1
+            
+            # check if OTHER was added
+            if self.master._has_one_hot_other:
+                results.pop(_OneHotOtherPlaceholder.OTHER_MODEL)
+            
             return results
         
     def _process_categorical(self, gui_feature: str, chosen_value: str) -> Tuple[str,int]:

ml_tools/keys.py

@@ -26,3 +26,9 @@ class ModelSaveKeys:
     # Classification keys
     CLASSIFICATION_LABEL = "label"
     CLASSIFICATION_PROBABILITIES = "probabilities"
+
+
+class _OneHotOtherPlaceholder:
+    OTHER_GUI = "OTHER"
+    OTHER_MODEL = "one hot OTHER placeholder"
+    OTHER_DICT = {OTHER_GUI: OTHER_MODEL}