dragon-ml-toolbox 19.6.0__tar.gz → 19.8.0__tar.gz

{dragon_ml_toolbox-19.6.0/dragon_ml_toolbox.egg-info → dragon_ml_toolbox-19.8.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 19.6.0
+Version: 19.8.0
 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-19.6.0 → dragon_ml_toolbox-19.8.0/dragon_ml_toolbox.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 19.6.0
+Version: 19.8.0
 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-19.6.0 → dragon_ml_toolbox-19.8.0}/ml_tools/ML_configuration.py

@@ -37,7 +37,8 @@ from ._core._ML_configuration import (
     DragonAutoIntParams,
     
     # --- Training Config ---  
-    DragonTrainingConfig,  
+    DragonTrainingConfig,
+    DragonParetoConfig,
     info
 )
 
@@ -80,5 +81,6 @@ __all__ = [
     "DragonAutoIntParams",
     
     # --- Training Config ---
-    "DragonTrainingConfig"
+    "DragonTrainingConfig",
+    "DragonParetoConfig",
 ]

{dragon_ml_toolbox-19.6.0 → dragon_ml_toolbox-19.8.0}/ml_tools/_core/_ML_configuration.py

@@ -1,4 +1,5 @@
-from typing import Union, Optional, List, Any, Dict, Literal
+from typing import Union, Optional, List, Any, Dict, Literal, Tuple
+from pathlib import Path
 from collections.abc import Mapping
 import numpy as np
 
@@ -51,7 +52,8 @@ __all__ = [
     "DragonAutoIntParams",
     
     # --- Training Config ---
-    "DragonTrainingConfig"
+    "DragonTrainingConfig",
+    "DragonParetoConfig"
 ]
 
 
@@ -65,7 +67,11 @@ class _BaseClassificationFormat:
                  cmap: str="BuGn",
                  ROC_PR_line: str='darkorange',
                  calibration_bins: int=15, 
-                 font_size: int=16) -> None:
+                 xtick_size: int=22,
+                 ytick_size: int=22,
+                 legend_size: int=26,
+                 font_size: int=26,
+                 cm_font_size: int=26) -> None:
         """
         Initializes the formatting configuration for single-label classification metrics.
 
@@ -84,6 +90,14 @@ class _BaseClassificationFormat:
                 creating the calibration (reliability) plot.
             
             font_size (int): The base font size to apply to the plots.
+            
+            xtick_size (int): Font size for x-axis tick labels.
+            
+            ytick_size (int): Font size for y-axis tick labels.
+            
+            legend_size (int): Font size for plot legends.
+            
+            cm_font_size (int): Font size for the confusion matrix.
         
         <br>
         
@@ -97,13 +111,21 @@ class _BaseClassificationFormat:
         self.ROC_PR_line = ROC_PR_line
         self.calibration_bins = calibration_bins
         self.font_size = font_size
+        self.xtick_size = xtick_size
+        self.ytick_size = ytick_size
+        self.legend_size = legend_size
+        self.cm_font_size = cm_font_size
         
     def __repr__(self) -> str:
         parts = [
             f"cmap='{self.cmap}'",
             f"ROC_PR_line='{self.ROC_PR_line}'",
             f"calibration_bins={self.calibration_bins}",
-            f"font_size={self.font_size}"
+            f"font_size={self.font_size}",
+            f"xtick_size={self.xtick_size}",
+            f"ytick_size={self.ytick_size}",
+            f"legend_size={self.legend_size}",
+            f"cm_font_size={self.cm_font_size}"
         ]
         return f"{self.__class__.__name__}({', '.join(parts)})"
 
@@ -115,7 +137,10 @@ class _BaseMultiLabelFormat:
     def __init__(self,
                  cmap: str = "BuGn",
                  ROC_PR_line: str='darkorange',
-                 font_size: int = 16) -> None:
+                 font_size: int = 25,
+                 xtick_size: int=20,
+                 ytick_size: int=20,
+                 legend_size: int=23) -> None:
         """
         Initializes the formatting configuration for multi-label classification metrics.
 
@@ -132,6 +157,12 @@ class _BaseMultiLabelFormat:
             
             font_size (int): The base font size to apply to the plots.
             
+            xtick_size (int): Font size for x-axis tick labels.
+            
+            ytick_size (int): Font size for y-axis tick labels.
+            
+            legend_size (int): Font size for plot legends.
+            
         <br>
         
         ### [Matplotlib Colormaps](https://matplotlib.org/stable/users/explain/colors/colormaps.html)
@@ -143,12 +174,18 @@ class _BaseMultiLabelFormat:
         self.cmap = cmap
         self.ROC_PR_line = ROC_PR_line
         self.font_size = font_size
+        self.xtick_size = xtick_size
+        self.ytick_size = ytick_size
+        self.legend_size = legend_size
         
     def __repr__(self) -> str:
         parts = [
             f"cmap='{self.cmap}'",
             f"ROC_PR_line='{self.ROC_PR_line}'",
-            f"font_size={self.font_size}"
+            f"font_size={self.font_size}",
+            f"xtick_size={self.xtick_size}",
+            f"ytick_size={self.ytick_size}",
+            f"legend_size={self.legend_size}"
         ]
         return f"{self.__class__.__name__}({', '.join(parts)})"
 
@@ -158,12 +195,14 @@ class _BaseRegressionFormat:
     [PRIVATE] Base configuration for regression metrics.
     """
     def __init__(self, 
-                 font_size: int=16,
+                 font_size: int=26,
                  scatter_color: str='tab:blue',
                  scatter_alpha: float=0.6,
                  ideal_line_color: str='k',
                  residual_line_color: str='red',
-                 hist_bins: Union[int, str] = 'auto') -> None:
+                 hist_bins: Union[int, str] = 'auto',
+                 xtick_size: int=22,
+                 ytick_size: int=22) -> None:
         """
         Initializes the formatting configuration for regression metrics.
 
@@ -181,6 +220,8 @@ class _BaseRegressionFormat:
             hist_bins (int | str): The number of bins for the residuals histogram. 
                 Defaults to 'auto' to use seaborn's automatic bin selection.
                 - Options: 'auto', 'sqrt', 10, 20
+            xtick_size (int): Font size for x-axis tick labels.
+            ytick_size (int): Font size for y-axis tick labels.
         
         <br>
         
@@ -192,6 +233,8 @@ class _BaseRegressionFormat:
         self.ideal_line_color = ideal_line_color
         self.residual_line_color = residual_line_color
         self.hist_bins = hist_bins
+        self.xtick_size = xtick_size
+        self.ytick_size = ytick_size
         
     def __repr__(self) -> str:
         parts = [
@@ -200,7 +243,9 @@ class _BaseRegressionFormat:
             f"scatter_alpha={self.scatter_alpha}",
             f"ideal_line_color='{self.ideal_line_color}'",
             f"residual_line_color='{self.residual_line_color}'",
-            f"hist_bins='{self.hist_bins}'"
+            f"hist_bins='{self.hist_bins}'",
+            f"xtick_size={self.xtick_size}",
+            f"ytick_size={self.ytick_size}"
         ]
         return f"{self.__class__.__name__}({', '.join(parts)})"
 
@@ -248,7 +293,7 @@ class _BaseSequenceValueFormat:
     [PRIVATE] Base configuration for sequence to value metrics.
     """
     def __init__(self, 
-                 font_size: int=16,
+                 font_size: int=25,
                  scatter_color: str='tab:blue',
                  scatter_alpha: float=0.6,
                  ideal_line_color: str='k',
@@ -300,8 +345,7 @@ class _BaseSequenceSequenceFormat:
     [PRIVATE] Base configuration for sequence-to-sequence metrics.
     """
     def __init__(self,
-                 font_size: int = 16,
-                 plot_figsize: tuple[int, int] = (10, 6),
+                 font_size: int = 25,
                  grid_style: str = '--',
                  rmse_color: str = 'tab:blue',
                  rmse_marker: str = 'o-',
@@ -312,7 +356,6 @@ class _BaseSequenceSequenceFormat:
 
         Args:
             font_size (int): The base font size to apply to the plots.
-            plot_figsize (Tuple[int, int]): Figure size for the plot.
             grid_style (str): Matplotlib linestyle for the plot grid.
                 - Options: '--' (dashed), ':' (dotted), '-.' (dash-dot), '-' (solid)
             rmse_color (str): Matplotlib color for the RMSE line.
@@ -337,7 +380,6 @@ class _BaseSequenceSequenceFormat:
         ### [Matplotlib Markers](https://matplotlib.org/stable/api/markers_api.html)
         """
         self.font_size = font_size
-        self.plot_figsize = plot_figsize
         self.grid_style = grid_style
         self.rmse_color = rmse_color
         self.rmse_marker = rmse_marker
@@ -347,7 +389,6 @@ class _BaseSequenceSequenceFormat:
     def __repr__(self) -> str:
         parts = [
             f"font_size={self.font_size}",
-            f"plot_figsize={self.plot_figsize}",
             f"grid_style='{self.grid_style}'",
             f"rmse_color='{self.rmse_color}'",
             f"mae_color='{self.mae_color}'"
@@ -406,6 +447,9 @@ class _BaseModelParams(Mapping):
             if isinstance(v, FeatureSchema):
                 # Force the repr() string, otherwise json.dump treats it as a list
                 clean_dict[k] = repr(v)
+            elif isinstance(v, Path):
+                # JSON cannot serialize Path objects, convert to string
+                clean_dict[k] = str(v)
             else:
                 clean_dict[k] = v
         return clean_dict
@@ -607,6 +651,8 @@ class DragonTrainingConfig(_BaseModelParams):
     Configuration object for the training process.
     
     Can be unpacked as a dictionary for logging or accessed as an object.
+    
+    Accepts arbitrary keyword arguments which are set as instance attributes.
     """
     def __init__(self,
                  validation_size: float,
@@ -617,7 +663,7 @@ class DragonTrainingConfig(_BaseModelParams):
                  early_stop_patience: Optional[int] = None,
                  scheduler_patience: Optional[int] = None,
                  scheduler_lr_factor: Optional[float] = None,
-                 scheduler_threshold: Optional[float] = None) -> None:
+                 **kwargs: Any) -> None:
         self.validation_size = validation_size
         self.test_size = test_size
         self.initial_learning_rate = initial_learning_rate
@@ -626,7 +672,75 @@ class DragonTrainingConfig(_BaseModelParams):
         self.early_stop_patience = early_stop_patience
         self.scheduler_patience = scheduler_patience
         self.scheduler_lr_factor = scheduler_lr_factor
-        self.scheduler_threshold = scheduler_threshold
+        
+        # Process kwargs with validation
+        for key, value in kwargs.items():
+            # Python guarantees 'key' is a string for **kwargs
+            
+            # Allow None in value
+            if value is None:
+                setattr(self, key, value)
+                continue
+            
+            if isinstance(value, dict):
+                _LOGGER.error("Nested dictionaries are not supported, unpack them first.")
+                raise TypeError()
+            
+            # Check if value is a number or a string or a JSON supported type, except dict
+            if not isinstance(value, (str, int, float, bool, list, tuple)):
+                _LOGGER.error(f"Invalid type for configuration '{key}': {type(value).__name__}")
+                raise TypeError()
+            
+            setattr(self, key, value)
+
+
+class DragonParetoConfig(_BaseModelParams):
+    """
+    Configuration object for the Pareto Optimization process.
+    """
+    def __init__(self,
+                 save_directory: Union[str, Path],
+                 target_objectives: Dict[str, Literal["min", "max"]],
+                 continuous_bounds_map: Union[Dict[str, Tuple[float, float]], Dict[str, List[float]]],
+                 columns_to_round: Optional[List[str]] = None,
+                 population_size: int = 400,
+                 generations: int = 1000,
+                 solutions_filename: str = "ParetoSolutions",
+                 float_precision: int = 4,
+                 log_interval: int = 10,
+                 plot_size: Tuple[int, int] = (10, 7),
+                 plot_font_size: int = 16,
+                 discretize_start_at_zero: bool = True):
+        """  
+        Configure the Pareto Optimizer.
+
+        Args:
+            save_directory (str | Path): Directory to save artifacts.
+            target_objectives (Dict[str, "min"|"max"]): Dictionary mapping target names to optimization direction.
+                Example: {"price": "max", "error": "min"}
+            continuous_bounds_map (Dict): Bounds for continuous features {name: (min, max)}.
+            columns_to_round (List[str] | None): List of continuous column names that should be rounded to the nearest integer.
+            population_size (int): Size of the genetic population.
+            generations (int): Number of generations to run.
+            solutions_filename (str): Filename for saving Pareto solutions.
+            float_precision (int): Number of decimal places to round standard float columns.
+            log_interval (int): Interval for logging progress.
+            plot_size (Tuple[int, int]): Size of the 2D plots.
+            plot_font_size (int): Font size for plot text.
+            discretize_start_at_zero (bool): Categorical encoding start index. True=0, False=1.
+        """
+        self.save_directory = save_directory
+        self.target_objectives = target_objectives
+        self.continuous_bounds_map = continuous_bounds_map
+        self.columns_to_round = columns_to_round
+        self.population_size = population_size
+        self.generations = generations
+        self.solutions_filename = solutions_filename
+        self.float_precision = float_precision
+        self.log_interval = log_interval
+        self.plot_size = plot_size
+        self.plot_font_size = plot_font_size
+        self.discretize_start_at_zero = discretize_start_at_zero
 
 
 # ----------------------------
@@ -639,18 +753,22 @@ class RegressionMetricsFormat(_BaseRegressionFormat):
     Configuration for single-target regression.
     """
     def __init__(self, 
-                 font_size: int=16,
+                 font_size: int=26,
                  scatter_color: str='tab:blue',
                  scatter_alpha: float=0.6,
                  ideal_line_color: str='k',
                  residual_line_color: str='red',
-                 hist_bins: Union[int, str] = 'auto') -> None:
+                 hist_bins: Union[int, str] = 'auto',
+                 xtick_size: int=22,
+                 ytick_size: int=22) -> None:
         super().__init__(font_size=font_size, 
                          scatter_color=scatter_color, 
                          scatter_alpha=scatter_alpha, 
                          ideal_line_color=ideal_line_color, 
                          residual_line_color=residual_line_color, 
-                         hist_bins=hist_bins)
+                         hist_bins=hist_bins,
+                         xtick_size=xtick_size,
+                         ytick_size=ytick_size)
 
 
 # Multitarget regression
@@ -659,18 +777,22 @@ class MultiTargetRegressionMetricsFormat(_BaseRegressionFormat):
     Configuration for multi-target regression.
     """
     def __init__(self, 
-                 font_size: int=16,
+                 font_size: int=26,
                  scatter_color: str='tab:blue',
                  scatter_alpha: float=0.6,
                  ideal_line_color: str='k',
                  residual_line_color: str='red',
-                 hist_bins: Union[int, str] = 'auto') -> None:
+                 hist_bins: Union[int, str] = 'auto',
+                 xtick_size: int=22,
+                 ytick_size: int=22) -> None:
         super().__init__(font_size=font_size, 
                          scatter_color=scatter_color, 
                          scatter_alpha=scatter_alpha, 
                          ideal_line_color=ideal_line_color, 
                          residual_line_color=residual_line_color, 
-                         hist_bins=hist_bins)
+                         hist_bins=hist_bins,
+                         xtick_size=xtick_size,
+                         ytick_size=ytick_size)
 
 
 # Classification
@@ -682,11 +804,20 @@ class BinaryClassificationMetricsFormat(_BaseClassificationFormat):
                  cmap: str="BuGn",
                  ROC_PR_line: str='darkorange',
                  calibration_bins: int=15, 
-                 font_size: int=16) -> None:
+                 font_size: int=26,
+                 xtick_size: int=22,
+                 ytick_size: int=22,
+                 legend_size: int=26,
+                 cm_font_size: int=26
+                 ) -> None:
         super().__init__(cmap=cmap, 
                          ROC_PR_line=ROC_PR_line, 
                          calibration_bins=calibration_bins, 
-                         font_size=font_size)
+                         font_size=font_size,
+                         xtick_size=xtick_size,
+                         ytick_size=ytick_size,
+                         legend_size=legend_size,
+                         cm_font_size=cm_font_size)
 
 
 class MultiClassClassificationMetricsFormat(_BaseClassificationFormat):
@@ -697,12 +828,20 @@ class MultiClassClassificationMetricsFormat(_BaseClassificationFormat):
                  cmap: str="BuGn",
                  ROC_PR_line: str='darkorange',
                  calibration_bins: int=15, 
-                 font_size: int=16) -> None:
+                 font_size: int=26,
+                 xtick_size: int=22,
+                 ytick_size: int=22,
+                 legend_size: int=26,
+                 cm_font_size: int=26
+                 ) -> None:
         super().__init__(cmap=cmap, 
                          ROC_PR_line=ROC_PR_line, 
                          calibration_bins=calibration_bins, 
-                         font_size=font_size)
-
+                         font_size=font_size,
+                         xtick_size=xtick_size,
+                         ytick_size=ytick_size,
+                         legend_size=legend_size,
+                         cm_font_size=cm_font_size)
 
 class BinaryImageClassificationMetricsFormat(_BaseClassificationFormat):
     """
@@ -712,12 +851,20 @@ class BinaryImageClassificationMetricsFormat(_BaseClassificationFormat):
                  cmap: str="BuGn",
                  ROC_PR_line: str='darkorange',
                  calibration_bins: int=15, 
-                 font_size: int=16) -> None:
+                 font_size: int=26,
+                 xtick_size: int=22,
+                 ytick_size: int=22,
+                 legend_size: int=26,
+                 cm_font_size: int=26
+                 ) -> None:
         super().__init__(cmap=cmap, 
                          ROC_PR_line=ROC_PR_line, 
                          calibration_bins=calibration_bins, 
-                         font_size=font_size)
-
+                         font_size=font_size,
+                         xtick_size=xtick_size,
+                         ytick_size=ytick_size,
+                         legend_size=legend_size,
+                         cm_font_size=cm_font_size)
 
 class MultiClassImageClassificationMetricsFormat(_BaseClassificationFormat):
     """
@@ -727,12 +874,20 @@ class MultiClassImageClassificationMetricsFormat(_BaseClassificationFormat):
                  cmap: str="BuGn",
                  ROC_PR_line: str='darkorange',
                  calibration_bins: int=15, 
-                 font_size: int=16) -> None:
+                 font_size: int=26,
+                 xtick_size: int=22,
+                 ytick_size: int=22,
+                 legend_size: int=26,
+                 cm_font_size: int=26
+                 ) -> None:
         super().__init__(cmap=cmap, 
                          ROC_PR_line=ROC_PR_line, 
                          calibration_bins=calibration_bins, 
-                         font_size=font_size)
-
+                         font_size=font_size,
+                         xtick_size=xtick_size,
+                         ytick_size=ytick_size,
+                         legend_size=legend_size,
+                         cm_font_size=cm_font_size)
 
 # Multi-Label classification
 class MultiLabelBinaryClassificationMetricsFormat(_BaseMultiLabelFormat):
@@ -742,11 +897,17 @@ class MultiLabelBinaryClassificationMetricsFormat(_BaseMultiLabelFormat):
     def __init__(self,
                  cmap: str = "BuGn",
                  ROC_PR_line: str='darkorange',
-                 font_size: int = 16) -> None:
+                 font_size: int = 25,
+                 xtick_size: int=20,
+                 ytick_size: int=20,
+                 legend_size: int=23
+                 ) -> None:
         super().__init__(cmap=cmap,
                          ROC_PR_line=ROC_PR_line, 
-                         font_size=font_size)
-
+                         font_size=font_size,
+                         xtick_size=xtick_size,
+                         ytick_size=ytick_size,
+                         legend_size=legend_size)
 
 # Segmentation
 class BinarySegmentationMetricsFormat(_BaseSegmentationFormat):
@@ -781,7 +942,7 @@ class SequenceValueMetricsFormat(_BaseSequenceValueFormat):
     Configuration for sequence-to-value prediction.
     """
     def __init__(self, 
-                 font_size: int=16,
+                 font_size: int=25,
                  scatter_color: str='tab:blue',
                  scatter_alpha: float=0.6,
                  ideal_line_color: str='k',
@@ -800,15 +961,13 @@ class SequenceSequenceMetricsFormat(_BaseSequenceSequenceFormat):
     Configuration for sequence-to-sequence prediction.
     """
     def __init__(self,
-                 font_size: int = 16,
-                 plot_figsize: tuple[int, int] = (10, 6),
+                 font_size: int = 25,
                  grid_style: str = '--',
                  rmse_color: str = 'tab:blue',
                  rmse_marker: str = 'o-',
                  mae_color: str = 'tab:orange',
                  mae_marker: str = 's--'):
         super().__init__(font_size=font_size, 
-                         plot_figsize=plot_figsize, 
                          grid_style=grid_style, 
                          rmse_color=rmse_color, 
                          rmse_marker=rmse_marker,