dragon-ml-toolbox 12.9.0__py3-none-any.whl → 12.9.2__py3-none-any.whl

{dragon_ml_toolbox-12.9.0.dist-info → dragon_ml_toolbox-12.9.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 12.9.0
+Version: 12.9.2
 Summary: A collection of tools for data science and machine learning projects.
 Author-email: "Karl L. Loza Vidaurre" <luigiloza@gmail.com>
 License-Expression: MIT

{dragon_ml_toolbox-12.9.0.dist-info → dragon_ml_toolbox-12.9.2.dist-info}/RECORD

@@ -1,5 +1,5 @@
-dragon_ml_toolbox-12.9.0.dist-info/licenses/LICENSE,sha256=L35WDmmLZNTlJvxF6Vy7Uy4SYNi6rCfWUqlTHpoRMoU,1081
-dragon_ml_toolbox-12.9.0.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=iy2r_R7wjzsCbz_Q_jMsp_jfZ6oP8XW9QhwzRBH0mGY,1904
+dragon_ml_toolbox-12.9.2.dist-info/licenses/LICENSE,sha256=L35WDmmLZNTlJvxF6Vy7Uy4SYNi6rCfWUqlTHpoRMoU,1081
+dragon_ml_toolbox-12.9.2.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=iy2r_R7wjzsCbz_Q_jMsp_jfZ6oP8XW9QhwzRBH0mGY,1904
 ml_tools/ETL_cleaning.py,sha256=2VBRllV8F-ZiPylPp8Az2gwn5ztgazN0BH5OKnRUhV0,20402
 ml_tools/ETL_engineering.py,sha256=KfYqgsxupAx6e_TxwO1LZXeu5mFkIhVXJrNjP3CzIZc,54927
 ml_tools/GUI_tools.py,sha256=Va6ig-dHULPVRwQYYtH3fvY5XPIoqRcJpRW8oXC55Hw,45413
@@ -24,7 +24,7 @@ ml_tools/_logger.py,sha256=dlp5cGbzooK9YSNSZYB4yjZrOaQUGW8PTrM411AOvL8,4717
 ml_tools/_script_info.py,sha256=21r83LV3RubsNZ_RTEUON6RbDf7Mh4_udweNcvdF_Fk,212
 ml_tools/constants.py,sha256=3br5Rk9cL2IUo638eJuMOGdbGQaWssaUecYEvSeRBLM,3322
 ml_tools/custom_logger.py,sha256=xot-VeZFigKjcVxADgzvI54vZO_MqMMejo7JmDED8Xo,5892
-ml_tools/data_exploration.py,sha256=bERsPSmV8h5YtJEzkVVYXkOyvdq60g-3cvJRhFjnI_A,50270
+ml_tools/data_exploration.py,sha256=haddQFsXAWzuf84NLItcZ4Q7vzN3YWjFoh7lPlWUczo,50679
 ml_tools/ensemble_evaluation.py,sha256=FGHSe8LBI8_w8LjNeJWOcYQ1UK_mc6fVah8gmSvNVGg,26853
 ml_tools/ensemble_inference.py,sha256=0yLmLNj45RVVoSCLH1ZYJG9IoAhTkWUqEZmLOQTFGTY,9348
 ml_tools/ensemble_learning.py,sha256=vsIED7nlheYI4w2SBzP6SC1AnNeMfn-2A1Gqw5EfxsM,21964
@@ -35,7 +35,7 @@ ml_tools/optimization_tools.py,sha256=P074YCuZzkqkONnAsM-Zb9DTX_i8cRkkJLpwAWz6CR
 ml_tools/path_manager.py,sha256=CyDU16pOKmC82jPubqJPT6EBt-u-3rGVbxyPIZCvDDY,18432
 ml_tools/serde.py,sha256=UIshIesHRFmxr8F6B3LxGG8bYc1HHK-nlE3kENSZL18,5288
 ml_tools/utilities.py,sha256=OcAyV1tEcYAfOWlGjRgopsjDLxU3DcI5EynzvWV4q3A,15754
-dragon_ml_toolbox-12.9.0.dist-info/METADATA,sha256=AAbJFe1QFwEU3uFZV9mUOhXubpSBSRXAHO6zOtJiX10,6166
-dragon_ml_toolbox-12.9.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-dragon_ml_toolbox-12.9.0.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
-dragon_ml_toolbox-12.9.0.dist-info/RECORD,,
+dragon_ml_toolbox-12.9.2.dist-info/METADATA,sha256=vwKDioQfPVheuLmZasMsZGFynib5C8FMc52Tn1Ql7k0,6166
+dragon_ml_toolbox-12.9.2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+dragon_ml_toolbox-12.9.2.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
+dragon_ml_toolbox-12.9.2.dist-info/RECORD,,

ml_tools/data_exploration.py

@@ -364,7 +364,6 @@ def encode_categorical_features(
             - If True, encodes Null values as a distinct category 'null_label' with a value of 0. Other categories start from 1. 
             - If False, Nulls are ignored and categories start from 0. 
             
-        
         null_label (str): Category to encode Nulls to if `encode_nulls` is True. If a name collision with `null_label` occurs, the fallback key will be "__NULL__".
         split_resulting_dataset (bool): 
             - If True, returns two separate DataFrames, one with non-categorical columns and one with the encoded columns.
@@ -1025,6 +1024,7 @@ def reconstruct_one_hot(
     df: pd.DataFrame,
     features_to_reconstruct: List[Union[str, Tuple[str, Optional[str]]]],
     separator: str = '_',
+    baseline_category_name: Optional[str] = "Other",
     drop_original: bool = True,
     verbose: bool = True
 ) -> pd.DataFrame:
@@ -1042,19 +1042,22 @@ def reconstruct_one_hot(
             A list defining the features to reconstruct. This list can contain:
             
             - A string: (e.g., "Color")
-              This reconstructs the feature 'Color' and assumes all-zero rows represent missing data NaN.
+              This reconstructs the feature 'Color' and assumes all-zero rows represent the baseline category ("Other" by default).
             - A tuple: (e.g., ("Pet", "Dog"))
-              This reconstructs 'Pet' and maps all-zero rows to the baseline category "Dog" (handling 'drop_first=True' scenarios).
+              This reconstructs 'Pet' and maps all-zero rows to the baseline category "Dog".
             - A tuple with None: (e.g., ("Size", None))
-              This is explicit and behaves identically to just passing "Size". All-zero rows will be mapped to NaN.
+              This reconstructs 'Size' and maps all-zero rows to the NaN value.
             Example:
             [
-                "Mood",                      # All-zeros -> NaN
+                "Mood",                      # All-zeros -> "Other"
                 ("Color", "Red"),            # All-zeros -> "Red"
+                ("Size", None)               # All-zeros -> NaN
             ]
         separator (str): 
             The character separating the base name from the categorical value in 
             the column names (e.g., '_' in 'B_a').
+        baseline_category_name (str | None):
+            The baseline category name to use by default if it is not explicitly provided.
         drop_original (bool): 
             If True, the original one-hot encoded columns will be dropped from 
             the returned DataFrame.
@@ -1077,6 +1080,10 @@ def reconstruct_one_hot(
     if not isinstance(df, pd.DataFrame):
         _LOGGER.error("Input must be a pandas DataFrame.")
         raise TypeError()
+    
+    if not (baseline_category_name is None or isinstance(baseline_category_name, str)):
+        _LOGGER.error("The baseline_category must be None or a string.")
+        raise TypeError()
 
     new_df = df.copy()
     all_ohe_cols_to_drop = []
@@ -1090,7 +1097,7 @@ def reconstruct_one_hot(
             if isinstance(item, str):
                 # Case 1: "Color"
                 base_name = item
-                baseline_val = None
+                baseline_val = baseline_category_name
             elif isinstance(item, tuple) and len(item) == 2:
                 # Case 2: ("Pet", "dog") or ("Size", None)
                 base_name, baseline_val = item