dragon-ml-toolbox 20.0.1__py3-none-any.whl → 20.1.0__py3-none-any.whl

{dragon_ml_toolbox-20.0.1.dist-info → dragon_ml_toolbox-20.1.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 20.0.1
+Version: 20.1.0
 Summary: Complete pipelines and helper tools for data science and machine learning projects.
 Author-email: Karl Luigi Loza Vidaurre <luigiloza@gmail.com>
 License-Expression: MIT

{dragon_ml_toolbox-20.0.1.dist-info → dragon_ml_toolbox-20.1.0.dist-info}/RECORD

@@ -1,5 +1,5 @@
-dragon_ml_toolbox-20.0.1.dist-info/licenses/LICENSE,sha256=L35WDmmLZNTlJvxF6Vy7Uy4SYNi6rCfWUqlTHpoRMoU,1081
-dragon_ml_toolbox-20.0.1.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=0-HBRMMgKuwtGy6nMJZvIn1fLxhx_ksyyVB2U_iyYZU,2818
+dragon_ml_toolbox-20.1.0.dist-info/licenses/LICENSE,sha256=L35WDmmLZNTlJvxF6Vy7Uy4SYNi6rCfWUqlTHpoRMoU,1081
+dragon_ml_toolbox-20.1.0.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=0-HBRMMgKuwtGy6nMJZvIn1fLxhx_ksyyVB2U_iyYZU,2818
 ml_tools/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 ml_tools/constants.py,sha256=3br5Rk9cL2IUo638eJuMOGdbGQaWssaUecYEvSeRBLM,3322
 ml_tools/ETL_cleaning/__init__.py,sha256=TytE8RKmtW4KQlkaTxpYKlJAbCu-VAc82eDdHwVD3Jo,427
@@ -29,10 +29,11 @@ ml_tools/ML_callbacks/_checkpoint.py,sha256=Ioj9wn8XlsR_S1NnmWbyT9lkO8o2_DcHVMrF
 ml_tools/ML_callbacks/_early_stop.py,sha256=qzTzxfDCDim0qj7QQ7ykJNIOBWbXtviDptMCczXXy_k,8073
 ml_tools/ML_callbacks/_imprimir.py,sha256=Wz6NXhiCFSJsAZh3JnQ4qt7tj2_qhu14DTwu-gkkzZs,257
 ml_tools/ML_callbacks/_scheduler.py,sha256=mn97_VH8Lp37KH3zSgmPemGQV8g-K8GfhRNHTftaNcg,7390
-ml_tools/ML_chain/__init__.py,sha256=rUBVwB96fAoq-Q9zY3s0fL_TFU5W2axlg7XZzrCXrSU,399
-ml_tools/ML_chain/_chaining_tools.py,sha256=ASi0Zr9WBVA7wd-pYVN69VIZFOIuB4QpGlrSl9Ob-90,13788
-ml_tools/ML_chain/_dragon_chain.py,sha256=wFlknv0rlL8P3K0ls8kj_oup4SvPNFqSxDmiBdPfGt4,5737
-ml_tools/ML_chain/_imprimir.py,sha256=JCVslxnrmvJ_LJOmexL2u5-OYykHFe1H49EkrJPpAIg,254
+ml_tools/ML_chain/__init__.py,sha256=UVD1xaJ59pft_ysg8z_ihqjEDQqPRQwmhui_zNRFp7I,491
+ml_tools/ML_chain/_chaining_tools.py,sha256=BDwTvgJFbJ-wgy3IkP6_SNpNaWpHGXV3PhAM7sYmHeU,13675
+ml_tools/ML_chain/_dragon_chain.py,sha256=x3fN136C5N9WcXJJW9zkNrBzP8QoBaXpxz7SPF3txjg,5601
+ml_tools/ML_chain/_imprimir.py,sha256=tHVXoGhMlbpkpcoGKwtkYVFlHFEllRCsYdpiAFI1aZk,285
+ml_tools/ML_chain/_update_schema.py,sha256=z1Us7lv6hy6GwSu1mcid50Jmqq3sh91hMQ0LnQjhte8,3806
 ml_tools/ML_configuration/__init__.py,sha256=wSpfk8bHRSoYjcKJmjd5ivB4Fw8UFjyOZL4hct9rJT0,2637
 ml_tools/ML_configuration/_base_model_config.py,sha256=95L3IfobNFMtnNr79zYpDGerC1q1v7M05tWZvTS2cwE,2247
 ml_tools/ML_configuration/_finalize.py,sha256=l_n13bLu0avMdJ8hNRrH8V_wOBQZM1UGsTydKBkTysM,15047
@@ -146,7 +147,7 @@ ml_tools/excel_handler/_excel_handler.py,sha256=TODudmeQgDSdxUKzLfAzizs--VL-g8Wx
 ml_tools/excel_handler/_imprimir.py,sha256=QHazgqjRMzthRbDt33EVpvR7GqufSzng6jHw7IVCdtI,306
 ml_tools/keys/__init__.py,sha256=DV52KLOY5GfpLwJdDAHlFVz0qAmyh-KWg3gZorFdMSk,336
 ml_tools/keys/_imprimir.py,sha256=4qmwdia16DPq3OtlWGMkgLPT5R3lcM-ka3tQdCLx5qk,197
-ml_tools/keys/_keys.py,sha256=wyUpNY7iZIGIqvnT2BSahnkkNkK_vvZALOtRWZ7h50A,8800
+ml_tools/keys/_keys.py,sha256=fArSyT_UGGSH4PHjG-R0kefFznAtAxSAasDCQ7-89a8,8899
 ml_tools/math_utilities/__init__.py,sha256=NuTcb_Ogdwx5x-oDieBt1EAqCoZRnXbkZbUrwB6ItH0,337
 ml_tools/math_utilities/_imprimir.py,sha256=kk5DQb_BV9g767uTdXQiRjEEHgQwJpEXU3jxO3QV2Fw,238
 ml_tools/math_utilities/_math_utilities.py,sha256=BYHIVcM9tuKIhVrkgLLiM5QalJ39zx7dXYy_M9aGgiM,9012
@@ -172,7 +173,7 @@ ml_tools/utilities/__init__.py,sha256=pkR2HxUIlKZMDderP2awYXVIFxkU2Xt3FkJmcmuRIp
 ml_tools/utilities/_imprimir.py,sha256=sV3ASBOsTdVYvGojOTIpZYFyrnd4panS5h_4HcMzob4,432
 ml_tools/utilities/_utility_save_load.py,sha256=7skiiuYGVLVMK_nU9uLfUZw16ePvF3i9ub7G7LMyUgs,16085
 ml_tools/utilities/_utility_tools.py,sha256=bN0J9d1S0W5wNzNntBWqDsJcEAK7-1OgQg3X2fwXns0,6918
-dragon_ml_toolbox-20.0.1.dist-info/METADATA,sha256=ApSFj2vI7jdgUYtlYgjBpAXFQw9OKcd6em0ssSVZvGg,7866
-dragon_ml_toolbox-20.0.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-dragon_ml_toolbox-20.0.1.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
-dragon_ml_toolbox-20.0.1.dist-info/RECORD,,
+dragon_ml_toolbox-20.1.0.dist-info/METADATA,sha256=g8BdKr-giBfa-J0TWjinoX1W4lzGaTFZEovm_Fv_43w,7866
+dragon_ml_toolbox-20.1.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+dragon_ml_toolbox-20.1.0.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
+dragon_ml_toolbox-20.1.0.dist-info/RECORD,,

ml_tools/ML_chain/__init__.py

@@ -8,11 +8,16 @@ from ._chaining_tools import (
     prepare_chaining_dataset,
 )
 
+from ._update_schema import (
+    derive_next_step_schema
+)
+
 from ._imprimir import info
 
 
 __all__ = [
     "DragonChainOrchestrator",
+    "derive_next_step_schema",
     "augment_dataset_with_predictions",
     "augment_dataset_with_predictions_multi",
     "prepare_chaining_dataset",

ml_tools/ML_chain/_chaining_tools.py

@@ -5,7 +5,7 @@ from typing import Optional, Literal
 
 from ..ML_inference import DragonInferenceHandler
 
-from ..keys._keys import MLTaskKeys, PyTorchInferenceKeys
+from ..keys._keys import MLTaskKeys, PyTorchInferenceKeys, ChainKeys
 from .._core import get_logger
 
 
@@ -23,11 +23,10 @@ def augment_dataset_with_predictions(
     handler: DragonInferenceHandler,
     dataset: pd.DataFrame,
     ground_truth_targets: list[str],
-    prediction_col_prefix: str = "pred_",
     batch_size: int = 4096
 ) -> pd.DataFrame:
     """
-    Uses a DragonInferenceHandler to generate predictions for a dataset and appends them as new feature columns.
+    Uses a DragonInferenceHandler to generate predictions for a dataset and appends them as new feature columns with a standardized prefix.
     
     This function splits the features from the ground truth targets, runs inference in batches to ensure
     memory efficiency, and returns a unified DataFrame containing:
@@ -38,8 +37,6 @@ def augment_dataset_with_predictions(
         dataset (pd.DataFrame): The input pandas DataFrame containing features and ground truth targets.
         ground_truth_targets (List[str]): A list of column names in `dataset` representing the actual targets.
             These are removed from the input features during inference and appended to the end of the result.
-        prediction_col_prefix (str, optional): A string to prepend when creating the
-            new prediction columns.
         batch_size (int, optional): The number of samples to process in a single inference step. 
             Prevents OOM errors on large datasets. Defaults to 4096.
 
@@ -107,7 +104,7 @@ def augment_dataset_with_predictions(
     full_prediction_array = np.vstack(all_predictions)
     
     # Generate new column names
-    new_col_names = [f"{prediction_col_prefix}{tid}" for tid in handler.target_ids]
+    new_col_names = [f"{ChainKeys.CHAIN_PREDICTION_PREFIX}{tid}" for tid in handler.target_ids]
     
     # Verify dimensions match
     if full_prediction_array.shape[1] != len(new_col_names):

ml_tools/ML_chain/_dragon_chain.py

@@ -77,18 +77,16 @@ class DragonChainOrchestrator:
     def update_with_inference(
         self, 
         handler: DragonInferenceHandler, 
-        prefix: str = "pred_", 
         batch_size: int = 4096
     ) -> None:
         """
         Runs inference using the provided handler on the full internal dataset and appends the results as new features.
         
         This updates the internal state of the Orchestrator. Subsequent calls to `get_training_data` 
-        will include these new prediction columns as features.
+        will include these new prediction columns as features with a standardized prefix.
 
         Args:
             handler (DragonInferenceHandler): The trained model handler.
-            prefix (str): Prefix for the new prediction columns (e.g., "m1_", "step2_").
             batch_size (int): Batch size for inference.
         """
         _LOGGER.info(f"Orchestrator: Updating internal state with predictions from handler (Targets: {handler.target_ids})...")
@@ -99,7 +97,6 @@ class DragonChainOrchestrator:
             handler=handler,
             dataset=self.current_dataset,
             ground_truth_targets=self.all_targets,
-            prediction_col_prefix=prefix,
             batch_size=batch_size
         )
         

ml_tools/ML_chain/_imprimir.py

@@ -2,6 +2,7 @@ from .._core import _imprimir_disponibles
 
 _GRUPOS = [
     "DragonChainOrchestrator",
+    "derive_next_step_schema",
     "augment_dataset_with_predictions",
     "augment_dataset_with_predictions_multi",
     "prepare_chaining_dataset",

ml_tools/ML_chain/_update_schema.py

@@ -0,0 +1,96 @@
+from ..schema import FeatureSchema
+from ..ML_inference import DragonInferenceHandler
+
+from ..keys._keys import MLTaskKeys, ChainKeys
+from .._core import get_logger
+
+
+_LOGGER = get_logger("Schema Updater")
+
+
+__all__ = [
+    "derive_next_step_schema",
+]
+
+
+def derive_next_step_schema(
+    current_schema: FeatureSchema, 
+    handler: DragonInferenceHandler, 
+    verbose: bool = True
+) -> FeatureSchema:
+    """
+    Creates the FeatureSchema for the NEXT step in the chain by appending the current handler's predictions as new features.
+    
+    Args:
+        current_schema (FeatureSchema): The current FeatureSchema.
+        handler (DragonInferenceHandler): The inference handler of the model trained using the current schema.
+    
+    Returns:
+        FeatureSchema: An updated schema including new predicted features.
+    """
+    # 1. Determine New Column Names
+    # Match logic from _chaining_tools.py
+    if handler.target_ids is None:
+        _LOGGER.error("Handler target_ids is None; cannot derive schema.")
+        raise ValueError()
+        
+    new_cols = [f"{ChainKeys.CHAIN_PREDICTION_PREFIX}{tid}" for tid in handler.target_ids]
+    
+    # 2. Base Lists (Convert tuples to lists for mutation)
+    new_feature_names = list(current_schema.feature_names) + new_cols
+    new_cont_names = list(current_schema.continuous_feature_names)
+    new_cat_names = list(current_schema.categorical_feature_names)
+    
+    # Copy existing maps (handle None case)
+    new_cat_index_map = dict(current_schema.categorical_index_map) if current_schema.categorical_index_map else {}
+    new_cat_mappings = dict(current_schema.categorical_mappings) if current_schema.categorical_mappings else {}
+
+    # 3. Determine Feature Type based on Task
+    is_categorical = False
+    cardinality = 0
+    
+    if handler.task in [MLTaskKeys.BINARY_CLASSIFICATION, MLTaskKeys.MULTILABEL_BINARY_CLASSIFICATION]:
+        is_categorical = True
+        cardinality = 2
+        
+    elif handler.task == MLTaskKeys.MULTICLASS_CLASSIFICATION:
+        is_categorical = True
+        # We rely on the class map to know the 'vocabulary' size
+        if handler._class_map is None:
+            _LOGGER.error("Handler class_map is None, cannot determine cardinality for multiclass classification model.")
+            raise ValueError()
+        cardinality = len(handler._class_map)
+        
+    # 4. Append New Metadata
+    current_total_feats = len(current_schema.feature_names)
+    
+    for i, col_name in enumerate(new_cols):
+        # Calculate the absolute index of this new column
+        # If we had 10 features (0-9), the new one is at index 10 + i
+        new_index = current_total_feats + i
+        
+        if is_categorical:
+            new_cat_names.append(col_name)
+            
+            # A. Update Cardinality for Embeddings
+            new_cat_index_map[new_index] = cardinality
+            
+            # B. Create Identity Mapping (Dummy Encoding)
+            # Maps string representation of int back to the int. 
+            identity_map = {str(k): k for k in range(cardinality)}
+            new_cat_mappings[col_name] = identity_map
+        else:
+            # Regression / Multitarget Regression
+            new_cont_names.append(col_name)
+    
+    if verbose:
+        _LOGGER.info(f"Derived next step schema with {len(new_feature_names)} features:\n    {len(new_cont_names)} continuous\n    {len(new_cat_names)} categorical")
+
+    # 5. Return New Immutable Schema
+    return FeatureSchema(
+        feature_names=tuple(new_feature_names),
+        continuous_feature_names=tuple(new_cont_names),
+        categorical_feature_names=tuple(new_cat_names),
+        categorical_index_map=new_cat_index_map if new_cat_index_map else None,
+        categorical_mappings=new_cat_mappings if new_cat_mappings else None
+    )

ml_tools/keys/_keys.py

@@ -278,6 +278,11 @@ class SchemaKeys:
     OPTIONAL_LABELS = "optional_labels"
 
 
+class ChainKeys:
+    """Used by the ML chaining module."""
+    CHAIN_PREDICTION_PREFIX = "pred_"
+
+
 class _EvaluationConfig:
     """Set config values for evaluation modules."""
     DPI = 400