dragon-ml-toolbox 19.8.2__py3-none-any.whl → 19.10.0__py3-none-any.whl

{dragon_ml_toolbox-19.8.2.dist-info → dragon_ml_toolbox-19.10.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 19.8.2
+Version: 19.10.0
 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
@@ -90,12 +90,6 @@ Provides-Extra: gui-torch
 Requires-Dist: numpy<2.0; extra == "gui-torch"
 Requires-Dist: torch; extra == "gui-torch"
 Requires-Dist: FreeSimpleGUI>=5.2; extra == "gui-torch"
-Provides-Extra: pyinstaller
-Requires-Dist: pyinstaller; extra == "pyinstaller"
-Provides-Extra: nuitka
-Requires-Dist: nuitka; extra == "nuitka"
-Requires-Dist: zstandard; extra == "nuitka"
-Requires-Dist: ordered-set; extra == "nuitka"
 Dynamic: license-file
 
 # dragon-ml-toolbox
@@ -137,7 +131,7 @@ conda install -c conda-forge dragon-ml-toolbox
 
 ## Modular Installation
 
-This toolbox is designed as a collection of mutually exclusive environments due to conflicting core dependencies, except APP bundlers (PyInstaller/Nuitka).
+This toolbox is designed as a collection of mutually exclusive environments due to conflicting core dependencies.
 
 - Rule: Create a fresh virtual environment for each module to use.
 
@@ -330,18 +324,6 @@ schema
 
 ---
 
-### ⚒️ APP bundlers
-
-Dependencies required to compile applications, inference scripts, or GUIs into standalone executables (`.exe` or binary) for distribution. Choose your preferred backend:
-
-```Bash
-pip install "dragon-ml-toolbox[pyinstaller]"
-```
-
-```Bash
-pip install "dragon-ml-toolbox[nuitka]"
-```
-
 ## Usage
 
 After installation, import modules like this:

{dragon_ml_toolbox-19.8.2.dist-info → dragon_ml_toolbox-19.10.0.dist-info}/RECORD

@@ -1,5 +1,5 @@
-dragon_ml_toolbox-19.8.2.dist-info/licenses/LICENSE,sha256=L35WDmmLZNTlJvxF6Vy7Uy4SYNi6rCfWUqlTHpoRMoU,1081
-dragon_ml_toolbox-19.8.2.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=XBLtvGjvBf-q93a5iylHj94Lm78UzInC-3Cii01jc6I,3127
+dragon_ml_toolbox-19.10.0.dist-info/licenses/LICENSE,sha256=L35WDmmLZNTlJvxF6Vy7Uy4SYNi6rCfWUqlTHpoRMoU,1081
+dragon_ml_toolbox-19.10.0.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=0-HBRMMgKuwtGy6nMJZvIn1fLxhx_ksyyVB2U_iyYZU,2818
 ml_tools/ETL_cleaning.py,sha256=cKXyRFaaFs_beAGDnQM54xnML671kq-yJEGjHafW-20,351
 ml_tools/ETL_engineering.py,sha256=cwh1FhtNdUHllUDvho-x3SIVj4KwG_rFQR6VYzWUg0U,898
 ml_tools/GUI_tools.py,sha256=O89rG8WQv6GY1DiphQjIsPzXFCQID6te7q_Sgt1iTkQ,294
@@ -45,7 +45,7 @@ ml_tools/ensemble_learning.py,sha256=BLPnpfJWCly-D75mkRP1FE5TExoWAAlAHR89KAzW9iU
 ml_tools/excel_handler.py,sha256=h35HMNnO44btxsTSfZXj2HiJtpRS4fdrJLbzru4heMs,453
 ml_tools/keys.py,sha256=s9HEIAJCRw4DO7ll0yjc8u5rrSI9MOmfkR_1fKpkfy8,263
 ml_tools/math_utilities.py,sha256=53nOXlhb5taUHj4CDHsXliArEfPkOlJD7G_dJa3_iOU,321
-ml_tools/optimization_tools.py,sha256=YQZiXT86kP28NEcyLDbowGeNXHgJDm9hzl-ClNgGQXU,389
+ml_tools/optimization_tools.py,sha256=rPG2VJ7hk9hv5wfKPq4zPJDXFWKioROOiJWmzXlXzVA,541
 ml_tools/path_manager.py,sha256=ion-x2W_rQjra3ChuOHwVtgXhv7LkpXP0lkBef730tk,350
 ml_tools/plot_fonts.py,sha256=6-WevfhDjbyWbSrFM6bqW-h5NC_mAO4XzdFR-oQ3DPE,110
 ml_tools/schema.py,sha256=AddXOa4P9HinlJ6SnICksHzBqRyi7MaichwVn-z_oVE,219
@@ -59,7 +59,7 @@ ml_tools/_core/_MICE_imputation.py,sha256=_juIymUnNDRWjSLepL8Ee_PncoShbxjR7YtqTt
 ml_tools/_core/_ML_callbacks.py,sha256=qtCrVFHTq-nk4NIsAdwIkfkKwFXX6I-6PoCgqZELp70,16734
 ml_tools/_core/_ML_chaining_inference.py,sha256=vXUPZzuQ2yKU71kkvUsE0xPo0hN-Yu6gfnL0JbXoRjI,7783
 ml_tools/_core/_ML_chaining_utilities.py,sha256=nsYowgRbkIYuzRiHlqsM3tnC3c-8O73CY8DHUF14XL0,19248
-ml_tools/_core/_ML_configuration.py,sha256=6lKod_NuXSj0ElYmkkwnRxZEiZctMlX1x4b0ByRKKhg,52281
+ml_tools/_core/_ML_configuration.py,sha256=hwnDCo9URsFqRCgLuFJhGTtoOqbE1XJreNY8B_3spTg,52693
 ml_tools/_core/_ML_configuration_pytab.py,sha256=C3e4iScqdRePVDoqnic6xXMOW7DNYqpgTCeaFDyMdL4,3286
 ml_tools/_core/_ML_datasetmaster.py,sha256=yU1BMtzz6XumMWCetVACrRLk7WJQwmYhaQ-VAWu9Ots,32043
 ml_tools/_core/_ML_evaluation.py,sha256=bu8qlYzhWSC1B7wNfCC5TSF-oed-uP8EF7TV45VTiBM,37325
@@ -70,8 +70,8 @@ ml_tools/_core/_ML_inference.py,sha256=5swm2lnsrDLalBnCm7gZPlDucX4yNCq5vn7ck3SW_
 ml_tools/_core/_ML_models.py,sha256=8FUx4-TVghlBF9srh1_5UxovrWPU7YEZ6XXLqwJei88,27974
 ml_tools/_core/_ML_models_advanced.py,sha256=oU6M5FEBMQ9yPp32cziWh3bz8SXRho07vFMC8ZDVcuU,45002
 ml_tools/_core/_ML_models_pytab.py,sha256=EHHnDG02ghcJORy2gipm3NcrlzL0qygD44o7QGmT1Zs,26297
-ml_tools/_core/_ML_optimization.py,sha256=b1qfHiGyvVoj-ENqDbHTf1jNx55niUWE9KEZJv3vg80,28253
-ml_tools/_core/_ML_optimization_pareto.py,sha256=fad4UjW5TDbCgIsVFk1qmkq8DnU5sahFFuC2DgKAQ3I,36889
+ml_tools/_core/_ML_optimization.py,sha256=mvG1joVS3U67lmSwzMgLgNGzh4H3Py3ttKeaTM3EUnU,28126
+ml_tools/_core/_ML_optimization_pareto.py,sha256=1PA8o5qbI13x5QusWhRIJMiPz3cMA2dUT1ZwU9NIZQM,37609
 ml_tools/_core/_ML_scaler.py,sha256=Nhu6qli_QezHQi5NKhRb8Z51bBJgzk2nEp_yW4B9H4U,8134
 ml_tools/_core/_ML_sequence_datasetmaster.py,sha256=0YVOPf-y4ZNdgUxropXUWrmInNyGYaUYprYvXf31n9U,17811
 ml_tools/_core/_ML_sequence_evaluation.py,sha256=AiPHtZ9DRpE6zL9n3Tp5eGGD9vrYRkLbZ0Nc274mL7I,8069
@@ -99,13 +99,13 @@ ml_tools/_core/_math_utilities.py,sha256=IlXAiZgTcLtus03jJOBOyF9ZCQDf8qLGjrCHu9M
 ml_tools/_core/_models_advanced_base.py,sha256=ceW0V_CcfOnSFqHlxUhVU8-5mtQq4tFyo8TX-xVexrY,4982
 ml_tools/_core/_models_advanced_helpers.py,sha256=yrAVgYdBsNYD6Vy-pYL5__wI9Z7inOvNUngMgyuypjo,38973
 ml_tools/_core/_optimization_tools.py,sha256=2LkntNRc19uGur9u0yI-KnNX56tc63sxaRNj6W440Og,20077
-ml_tools/_core/_path_manager.py,sha256=ty_tTUfOMiqKfB3fL_xerWhiJRZFgxvtzM-RHR-9U5E,18504
+ml_tools/_core/_path_manager.py,sha256=z4zqYqppKhgOj3ArfkKo4tieO8oNaHWUoshCQRNbd1w,20284
 ml_tools/_core/_plot_fonts.py,sha256=CjYXW2gZ9AUaGkyX8_WOXXNYs6d1PTK-nEJBrv_Zb2o,2287
 ml_tools/_core/_schema.py,sha256=TM5WVVMoKOvr_Bc2z34sU_gzKlM465PRKTgdZaEOkGY,14076
 ml_tools/_core/_script_info.py,sha256=21r83LV3RubsNZ_RTEUON6RbDf7Mh4_udweNcvdF_Fk,212
 ml_tools/_core/_serde.py,sha256=tsI4EO2Y7jrBMmbQ1pinDsPOrOg-SaPuB-Dt40q0taE,5609
 ml_tools/_core/_utilities.py,sha256=iA8fLWdhsIx4ut2Dp8M_OyU0Y3PPLgGdIklyl17x6xk,22560
-dragon_ml_toolbox-19.8.2.dist-info/METADATA,sha256=PBht866esAUBXiPNsjgNFLcwiTlWk0yNFa2RL1QoV8Y,8774
-dragon_ml_toolbox-19.8.2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-dragon_ml_toolbox-19.8.2.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
-dragon_ml_toolbox-19.8.2.dist-info/RECORD,,
+dragon_ml_toolbox-19.10.0.dist-info/METADATA,sha256=HNycos2k-C6KCjfj1g1pprR6APPYcst7HkoKylfgeR8,8193
+dragon_ml_toolbox-19.10.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+dragon_ml_toolbox-19.10.0.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
+dragon_ml_toolbox-19.10.0.dist-info/RECORD,,

{dragon_ml_toolbox-19.8.2.dist-info → dragon_ml_toolbox-19.10.0.dist-info}/licenses/LICENSE-THIRD-PARTY.md

@@ -31,13 +31,9 @@ This project depends on the following third-party packages. Each is governed by
 - [colorlog](https://github.com/borntyping/python-colorlog/blob/main/LICENSE)
 - [evotorch](https://github.com/nnaisense/evotorch/blob/master/LICENSE)
 - [FreeSimpleGUI](https://github.com/spyoungtech/FreeSimpleGUI/blob/main/license.txt)
-- [nuitka](https://github.com/Nuitka/Nuitka/blob/main/LICENSE.txt)
 - [omegaconf](https://github.com/omry/omegaconf/blob/master/LICENSE)
-- [ordered-set](https://github.com/rspeer/ordered-set/blob/master/MIT-LICENSE)
-- [pyinstaller](https://github.com/pyinstaller/pyinstaller/blob/develop/COPYING.txt)
 - [pytorch_tabular](https://github.com/manujosephv/pytorch_tabular/blob/main/LICENSE)
 - [torchmetrics](https://github.com/Lightning-AI/torchmetrics/blob/master/LICENSE)
-- [zstandard](https://github.com/indygreg/python-zstandard/blob/main/LICENSE)
 - [captum](https://github.com/meta-pytorch/captum/blob/master/LICENSE)
 - [node](https://github.com/Qwicen/node/blob/master/LICENSE.md)
 - [pytorch-widedeep](https://github.com/jrzaurin/pytorch-widedeep?tab=readme-ov-file#license)

ml_tools/_core/_ML_configuration.py

@@ -6,7 +6,7 @@ import numpy as np
 from ._schema import FeatureSchema
 from ._script_info import _script_info
 from ._logger import get_logger
-from ._path_manager import sanitize_filename
+from ._path_manager import sanitize_filename, make_fullpath
 from ._keys import MLTaskKeys
 
 
@@ -701,11 +701,11 @@ class DragonParetoConfig(_BaseModelParams):
     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]]],
+                 continuous_bounds_map: Union[Dict[str, Tuple[float, float]], Dict[str, List[float]], str, Path],
                  columns_to_round: Optional[List[str]] = None,
-                 population_size: int = 400,
+                 population_size: int = 500,
                  generations: int = 1000,
-                 solutions_filename: str = "ParetoSolutions",
+                 solutions_filename: str = "NonDominatedSolutions",
                  float_precision: int = 4,
                  log_interval: int = 10,
                  plot_size: Tuple[int, int] = (10, 7),
@@ -718,7 +718,7 @@ class DragonParetoConfig(_BaseModelParams):
             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)}.
+            continuous_bounds_map (Dict): Bounds for continuous features {name: (min, max)}. Or a path/str to a directory containing the "optimization_bounds.json" file.
             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.
@@ -729,7 +729,13 @@ class DragonParetoConfig(_BaseModelParams):
             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
+        # Validate string or Path
+        valid_save_dir = make_fullpath(save_directory, make=True, enforce="directory")
+        
+        if isinstance(continuous_bounds_map, (str, Path)):
+            continuous_bounds_map = make_fullpath(continuous_bounds_map, make=False, enforce="directory")
+        
+        self.save_directory = valid_save_dir
         self.target_objectives = target_objectives
         self.continuous_bounds_map = continuous_bounds_map
         self.columns_to_round = columns_to_round
@@ -742,7 +748,6 @@ class DragonParetoConfig(_BaseModelParams):
         self.plot_font_size = plot_font_size
         self.discretize_start_at_zero = discretize_start_at_zero
 
-
 # ----------------------------
 # Metrics Configurations
 # ----------------------------

ml_tools/_core/_ML_optimization.py

@@ -44,12 +44,10 @@ class DragonOptimizer:
     SNES and CEM algorithms do not accept bounds, the given bounds will be used as an initial starting point.
 
     Example:
-        >>> # 1. Get the final schema from data exploration
-        >>> schema = data_exploration.finalize_feature_schema(...)
-        >>> # 2. Define bounds for continuous features
+        >>> # 1. Define bounds for continuous features
         >>> cont_bounds = {'feature_A': (0, 100), 'feature_B': (-10, 10)}
         >>>
-        >>> # 3. Initialize the optimizer
+        >>> # 2. Initialize the optimizer
         >>> optimizer = DragonOptimizer(
         ...     inference_handler=my_handler,
         ...     schema=schema,
@@ -58,7 +56,7 @@ class DragonOptimizer:
         ...     task="max",
         ...     algorithm="Genetic",
         ... )
-        >>> # 4. Run the optimization
+        >>> # 3. Run the optimization
         >>> best_result = optimizer.run(
         ...     num_generations=100,
         ...     save_dir="/path/to/results",

ml_tools/_core/_ML_optimization_pareto.py

@@ -7,7 +7,7 @@ import matplotlib.cm as cm
 from matplotlib.collections import LineCollection
 import seaborn as sns
 from pathlib import Path
-from typing import Literal, Union, Tuple, List, Optional, Dict
+from typing import Literal, Union, List, Optional, Dict
 from tqdm import tqdm
 import plotly.express as px
 import plotly.graph_objects as go
@@ -21,7 +21,7 @@ from ._SQL import DragonSQL
 from ._ML_inference import DragonInferenceHandler
 from ._ML_chaining_inference import DragonChainInference
 from ._ML_configuration import DragonParetoConfig
-from ._optimization_tools import create_optimization_bounds, plot_optimal_feature_distributions_from_dataframe
+from ._optimization_tools import create_optimization_bounds, plot_optimal_feature_distributions_from_dataframe, load_continuous_bounds_template
 from ._math_utilities import discretize_categorical_values
 from ._utilities import save_dataframe_filename
 from ._IO_tools import save_json
@@ -107,6 +107,10 @@ class DragonParetoOptimizer:
                 _LOGGER.error(f"Target '{name}' not found in model targets: {available_targets}")
                 raise ValueError()
             
+            if direction not in ["min" , "max"]:
+                _LOGGER.error(f"Invalid optimization direction '{direction}' for target '{name}'. Use 'min' or 'max'.")
+                raise ValueError()
+            
             # For standard handlers, we need indices to slice the output tensor.
             # For chain handlers, we just rely on name matching, but we track index for consistency.
             idx = available_targets.index(name)
@@ -117,10 +121,20 @@ class DragonParetoOptimizer:
         _LOGGER.info(f"Pareto Optimization setup for: {self.ordered_target_names}")
 
         # --- 2. Bounds Setup ---
+        # check type
+        raw_bounds_map = config.continuous_bounds_map
+        if isinstance(raw_bounds_map, (str, Path)):
+            continuous_bounds = load_continuous_bounds_template(raw_bounds_map)
+        elif isinstance(raw_bounds_map, dict):
+            continuous_bounds = raw_bounds_map
+        else:
+            _LOGGER.error(f"Invalid type for 'continuous_bounds_map' in config. Expected dict or Path. Got {type(raw_bounds_map)}.")
+            raise ValueError()
+        
         # Uses the external tool which reads the schema to set correct bounds for both continuous and categorical
         bounds = create_optimization_bounds(
             schema=schema,
-            continuous_bounds_map=config.continuous_bounds_map,
+            continuous_bounds_map=continuous_bounds,
             start_at_zero=self.discretize_start_at_zero
         )
         self.lower_bounds = list(bounds[0])

ml_tools/_core/_path_manager.py

@@ -35,7 +35,8 @@ class DragonPathManager:
     def __init__(
         self,
         anchor_file: str,
-        base_directories: Optional[List[str]] = None
+        base_directories: Optional[List[str]] = None,
+        strict_to_root: bool = True
     ):
         """
         Sets up the core paths for a project by anchoring to a specific file.
@@ -53,14 +54,16 @@ class DragonPathManager:
                                                     where each string is the name
                                                     of a subdirectory to register
                                                     relative to the package root.
+            strict_to_root (bool): If True, checks that all registered paths are defined within the package ROOT.
         """
         resolved_anchor_path = Path(anchor_file).resolve()
         self._package_name = resolved_anchor_path.parent.name
         self._is_bundled, bundle_root = self._get_bundle_root()
         self._paths: Dict[str, Path] = {}
+        self._strict_to_root = strict_to_root
 
         if self._is_bundled:
-            # In a PyInstaller bundle, the package is inside the temp _MEIPASS dir
+            # In a PyInstaller/Nuitka bundle, the package is inside the temp _MEIPASS dir
             package_root = Path(bundle_root) / self._package_name # type: ignore
         else:
             # In dev mode, the package root is the directory containing the anchor file.
@@ -182,17 +185,44 @@ class DragonPathManager:
         """
         Checks the status of all registered paths on the filesystem and prints a formatted report.
         """
-        report = {}
-        for key, path in self.items():
+        # 1. Gather Data and determine max widths
+        rows = []
+        max_key_len = len("Key")  # Start with header width
+        
+        # Sort by key for readability
+        for key, path in sorted(self.items()):
             if path.is_dir():
-                report[key] = "📁 Directory"
+                stat_msg = "📁 Directory"
             elif path.is_file():
-                report[key] = "📄 File"
+                stat_msg = "📄 File"
+            elif not path.exists():
+                stat_msg = "❌ Not Found"
             else:
-                report[key] = "❌ Not Found"
+                stat_msg = "❓ Unknown"
+            
+            rows.append((key, stat_msg, str(path)))
+            max_key_len = max(max_key_len, len(key))
 
-        print("\n--- Path Status Report ---")
-        pprint(report)
+        # 2. Print Header
+        mode_icon = "📦" if self._is_bundled else "🛠️"
+        mode_text = "Bundled Mode" if self._is_bundled else "Development Mode"
+        
+        print(f"\n{'-'*80}")
+        print(f" 🐉 DragonPathManager Status Report")
+        print(f"    Context: {mode_icon} {mode_text}")
+        print(f"    Root:    {self.ROOT}")
+        print(f"{'-'*80}")
+
+        # 3. Print Table Header
+        # {variable:<width} aligns text to the left within the padding
+        print(f" {'Key':<{max_key_len}} | {'Status':<12} | Path")
+        print(f" {'-'*max_key_len} | {'-'*12} | {'-'*40}")
+
+        # 4. Print Rows
+        for key, stat, p_str in rows:
+            print(f" {key:<{max_key_len}} | {stat:<12} | {p_str}")
+        
+        print(f"{'-'*80}\n")
 
     def __repr__(self) -> str:
         """Provides a string representation of the stored paths."""
@@ -276,10 +306,22 @@ class DragonPathManager:
         
         if not isinstance(value, (str, Path)):
             _LOGGER.error(f"Cannot assign type '{type(value).__name__}' to a path. Must be str or Path.")
-            raise TypeError
-
-        # If all checks pass, treat it as a public path and store it in the _paths dictionary.
-        self._paths[sanitized_name] = Path(value)
+            raise TypeError()
+        
+        # Resolve the new path
+        new_path = Path(value).expanduser().absolute()
+
+        # --- STRICT CHECK ---
+        # Only check if strict mode is on
+        if self.__dict__.get("_strict_to_root", False) and sanitized_name != "ROOT":
+            root_path = self._paths.get("ROOT")
+            # Ensure ROOT exists and the new path is inside it
+            if root_path and not new_path.is_relative_to(root_path):
+                _LOGGER.error(f"Strict Mode Violation: '{name}' ({new_path}) is outside ROOT ({root_path})")
+                raise ValueError()
+
+        # Store absolute Path.
+        self._paths[sanitized_name] = new_path
 
 
 def make_fullpath(

ml_tools/optimization_tools.py

@@ -1,4 +1,6 @@
 from ._core._optimization_tools import (
+    make_continuous_bounds_template,
+    load_continuous_bounds_template,
     create_optimization_bounds,
     parse_lower_upper_bounds,
     plot_optimal_feature_distributions,
@@ -7,6 +9,8 @@ from ._core._optimization_tools import (
 )
 
 __all__ = [
+    "make_continuous_bounds_template",
+    "load_continuous_bounds_template",
     "create_optimization_bounds",
     "parse_lower_upper_bounds",
     "plot_optimal_feature_distributions",