dragon-ml-toolbox 2.4.0__tar.gz → 3.1.0__tar.gz

{dragon_ml_toolbox-2.4.0/dragon_ml_toolbox.egg-info → dragon_ml_toolbox-3.1.0}/PKG-INFO

@@ -1,7 +1,7 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 2.4.0
-Summary: A collection of tools for data science and machine learning projects
+Version: 3.1.0
+Summary: A collection of tools for data science and machine learning projects.
 Author-email: Karl Loza <luigiloza@gmail.com>
 License-Expression: MIT
 Project-URL: Homepage, https://github.com/DrAg0n-BoRn/ML_tools
@@ -125,9 +125,12 @@ GUI_tools
 handle_excel
 logger
 MICE_imputation
+ML_callbacks
+ML_evaluation
+ML_trainer
+ML_tutorial
 PSO_optimization
-trainer
+RNN_forecast
 utilities
 VIF_factor
-vision_helpers
 ```

{dragon_ml_toolbox-2.4.0 → dragon_ml_toolbox-3.1.0}/README.md

@@ -82,9 +82,12 @@ GUI_tools
 handle_excel
 logger
 MICE_imputation
+ML_callbacks
+ML_evaluation
+ML_trainer
+ML_tutorial
 PSO_optimization
-trainer
+RNN_forecast
 utilities
 VIF_factor
-vision_helpers
 ```

{dragon_ml_toolbox-2.4.0 → dragon_ml_toolbox-3.1.0/dragon_ml_toolbox.egg-info}/PKG-INFO

@@ -1,7 +1,7 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 2.4.0
-Summary: A collection of tools for data science and machine learning projects
+Version: 3.1.0
+Summary: A collection of tools for data science and machine learning projects.
 Author-email: Karl Loza <luigiloza@gmail.com>
 License-Expression: MIT
 Project-URL: Homepage, https://github.com/DrAg0n-BoRn/ML_tools
@@ -125,9 +125,12 @@ GUI_tools
 handle_excel
 logger
 MICE_imputation
+ML_callbacks
+ML_evaluation
+ML_trainer
+ML_tutorial
 PSO_optimization
-trainer
+RNN_forecast
 utilities
 VIF_factor
-vision_helpers
 ```

{dragon_ml_toolbox-2.4.0 → dragon_ml_toolbox-3.1.0}/dragon_ml_toolbox.egg-info/SOURCES.txt

@@ -10,16 +10,19 @@ dragon_ml_toolbox.egg-info/top_level.txt
 ml_tools/ETL_engineering.py
 ml_tools/GUI_tools.py
 ml_tools/MICE_imputation.py
+ml_tools/ML_callbacks.py
+ml_tools/ML_evaluation.py
+ml_tools/ML_trainer.py
+ml_tools/ML_tutorial.py
 ml_tools/PSO_optimization.py
+ml_tools/RNN_forecast.py
 ml_tools/VIF_factor.py
 ml_tools/__init__.py
 ml_tools/_particle_swarm_optimization.py
+ml_tools/_pytorch_models.py
 ml_tools/data_exploration.py
 ml_tools/datasetmaster.py
 ml_tools/ensemble_learning.py
 ml_tools/handle_excel.py
 ml_tools/logger.py
-ml_tools/pytorch_models.py
-ml_tools/trainer.py
-ml_tools/utilities.py
-ml_tools/vision_helpers.py
+ml_tools/utilities.py

{dragon_ml_toolbox-2.4.0 → dragon_ml_toolbox-3.1.0}/ml_tools/ETL_engineering.py

@@ -3,17 +3,18 @@ import re
 from typing import Literal, Union, Optional, Any, Callable, List, Dict
 from .utilities import _script_info
 import pandas as pd
+from .logger import _LOGGER
 
 
 __all__ = [
     "ColumnCleaner",
-    "DataFrameCleaner"
+    "DataFrameCleaner",
     "TransformationRecipe",
     "DataProcessor",
     "KeywordDummifier",
     "NumberExtractor",
     "MultiNumberExtractor",
-    "RatioCalculator"
+    "RatioCalculator",
     "CategoryMapper",
     "RegexMapper",
     "ValueBinner",
@@ -24,18 +25,26 @@ __all__ = [
 
 class ColumnCleaner:
     """
-    Cleans and standardizes a single pandas Series based on a dictionary of regex-to-value replacement rules.
+    Cleans and standardizes a pandas Series by applying regex-to-replacement rules.
+    Supports sub-string replacements and case-insensitivity.
+    
+    Notes:
+    - Write separate, specific rules for each case. Don't combine patterns with an "OR".
+    - Define rules from most specific to more general to create a fallback system.
+    - Beware of chain replacements (rules matching strings that have already been changed by a previous rule).
     
     Args:
         rules (Dict[str, str]):
-            A dictionary where each key is a regular expression pattern and
-            each value is the standardized string to replace matches with.
+            A dictionary of regex patterns to replacement strings. Can use
+            backreferences in the replacement statement (e.g., r'\\1 \\2 \\3 \\4 \\5') for captured groups.
+        case_insensitive (bool):
+            If True, regex matching ignores case.
     """
-    def __init__(self, rules: Dict[str, str]):
+    def __init__(self, rules: Dict[str, str], case_insensitive: bool = True):
         if not isinstance(rules, dict):
             raise TypeError("The 'rules' argument must be a dictionary.")
 
-        # Validate that all keys are valid regular expressions
+        # Validate regex patterns
         for pattern in rules.keys():
             try:
                 re.compile(pattern)
@@ -43,32 +52,52 @@ class ColumnCleaner:
                 raise ValueError(f"Invalid regex pattern '{pattern}': {e}") from e
 
         self.rules = rules
+        self.case_insensitive = case_insensitive
 
     def clean(self, series: pd.Series) -> pd.Series:
         """
-        Applies the standardization rules to the provided Series (requires string data).
+        Applies the standardization rules sequentially to the provided Series.
         
-        Non-matching values are kept as they are.
-
         Args:
             series (pd.Series): The pandas Series to clean.
 
         Returns:
-            pd.Series: A new Series with the values cleaned and standardized.
+            pd.Series: A new Series with the regex replacements applied.
         """
-        return series.astype(str).replace(self.rules, regex=True)
+        cleaned_series = series.astype(str)
+        
+        # Set the regex flags based on the case_insensitive setting
+        flags = re.IGNORECASE if self.case_insensitive else 0
+        
+        # Sequentially apply each regex rule
+        for pattern, replacement in self.rules.items():
+            cleaned_series = cleaned_series.str.replace(
+                pattern, 
+                replacement, 
+                regex=True,
+                flags=flags
+            )
+            
+        return cleaned_series
 
 
 class DataFrameCleaner:
     """
     Orchestrates the cleaning of multiple columns in a pandas DataFrame using a nested dictionary of rules and `ColumnCleaner` objects.
+    
+    Chosen case-sensitivity is applied to all columns.
+    
+    Notes:
+    - Write separate, specific rules for each case. Don't combine patterns with an "OR".
+    - Define rules from most specific to more general to create a fallback system.
+    - Beware of chain replacements (rules matching strings that have already been changed by a previous rule).
 
     Args:
         rules (Dict[str, Dict[str, str]]):
             A nested dictionary where each top-level key is a column name,
             and its value is a dictionary of regex rules for that column, as expected by `ColumnCleaner`.
     """
-    def __init__(self, rules: Dict[str, Dict[str, str]]):
+    def __init__(self, rules: Dict[str, Dict[str, str]], case_insensitive: bool = True):
         if not isinstance(rules, dict):
             raise TypeError("The 'rules' argument must be a nested dictionary.")
         
@@ -80,6 +109,7 @@ class DataFrameCleaner:
                 )
         
         self.rules = rules
+        self.case_insensitive = case_insensitive
 
     def clean(self, df: pd.DataFrame) -> pd.DataFrame:
         """
@@ -108,7 +138,7 @@ class DataFrameCleaner:
         
         for column_name, column_rules in self.rules.items():
             # Create and apply the specific cleaner for the column
-            cleaner = ColumnCleaner(rules=column_rules)
+            cleaner = ColumnCleaner(rules=column_rules, case_insensitive=self.case_insensitive)
             df_cleaned[column_name] = cleaner.clean(df_cleaned[column_name])
             
         return df_cleaned
@@ -251,7 +281,7 @@ class DataProcessor:
                 raise TypeError(f"Invalid 'transform' action for '{input_col_name}': {transform_action}")
 
         if not processed_columns:
-            print("Warning: The transformation resulted in an empty DataFrame.")
+            _LOGGER.warning("The transformation resulted in an empty DataFrame.")
             return pl.DataFrame()
             
         return pl.DataFrame(processed_columns)
@@ -403,7 +433,7 @@ class NumberExtractor:
             if not isinstance(round_digits, int):
                 raise TypeError("round_digits must be an integer.")
             if dtype == "int":
-                print(f"Warning: 'round_digits' is specified but dtype is 'int'. Rounding will be ignored.")
+                _LOGGER.warning(f"'round_digits' is specified but dtype is 'int'. Rounding will be ignored.")
 
         self.regex_pattern = regex_pattern
         self.dtype = dtype
@@ -561,9 +591,9 @@ class RatioCalculator:
         denominator = groups.struct.field("group_2").cast(pl.Float64, strict=False)
 
         # Safely perform division, returning null if denominator is 0
-        return pl.when(denominator != 0).then(
-            numerator / denominator
-        ).otherwise(None)
+        final_expr = pl.when(denominator != 0).then(numerator / denominator).otherwise(None)
+        
+        return pl.select(final_expr).to_series()
 
 
 class CategoryMapper:

{dragon_ml_toolbox-2.4.0 → dragon_ml_toolbox-3.1.0}/ml_tools/GUI_tools.py

@@ -7,6 +7,7 @@ from functools import wraps
 from typing import Any, Dict, Tuple, List
 from .utilities import _script_info
 import numpy as np
+from .logger import _LOGGER
 
 
 __all__ = [
@@ -46,7 +47,7 @@ class PathManager:
         if self._is_bundled:
             # In a Briefcase bundle, resource_path gives an absolute path
             # to the resource directory.
-            self.package_root = self._resource_path_func(self.package_name, "")
+            self.package_root = self._resource_path_func(self.package_name, "") # type: ignore
         else:
             # In development mode, the package root is the directory
             # containing the anchor file.
@@ -56,7 +57,7 @@ class PathManager:
         """Checks if the app is running in a bundled environment."""
         try:
             # This is the function Briefcase provides in a bundled app
-            from briefcase.platforms.base import resource_path
+            from briefcase.platforms.base import resource_path # type: ignore
             return True, resource_path
         except ImportError:
             return False, None
@@ -147,7 +148,7 @@ class ConfigManager:
         """
         path = Path(file_path)
         if path.exists() and not force_overwrite:
-            print(f"Configuration file already exists at {path}. Aborting.")
+            _LOGGER.warning(f"Configuration file already exists at {path}. Aborting.")
             return
 
         config = configparser.ConfigParser()
@@ -205,7 +206,7 @@ class ConfigManager:
 
         with open(path, 'w') as configfile:
             config.write(configfile)
-        print(f"Successfully generated config template at: '{path}'")
+        _LOGGER.info(f"Successfully generated config template at: '{path}'")
 
 
 # --- GUI Factory ---
@@ -219,8 +220,8 @@ class GUIFactory:
         Initializes the factory with a configuration object.
         """
         self.config = config
-        sg.theme(self.config.general.theme)
-        sg.set_options(font=(self.config.general.font_family, 12))
+        sg.theme(self.config.general.theme) # type: ignore
+        sg.set_options(font=(self.config.general.font_family, 12)) # type: ignore
 
     # --- Atomic Element Generators ---
     def make_button(self, text: str, key: str, **kwargs) -> sg.Button:
@@ -234,13 +235,13 @@ class GUIFactory:
                       (e.g., `tooltip='Click me'`, `disabled=True`).
         """
         cfg = self.config
-        font = (cfg.fonts.font_family, cfg.fonts.button_size, cfg.fonts.button_style)
+        font = (cfg.fonts.font_family, cfg.fonts.button_size, cfg.fonts.button_style) # type: ignore
         
         style_args = {
-            "size": cfg.layout.button_size,
+            "size": cfg.layout.button_size, # type: ignore
             "font": font,
-            "button_color": (cfg.colors.button_text, cfg.colors.button_background),
-            "mouseover_colors": (cfg.colors.button_text, cfg.colors.button_background_hover),
+            "button_color": (cfg.colors.button_text, cfg.colors.button_background), # type: ignore
+            "mouseover_colors": (cfg.colors.button_text, cfg.colors.button_background_hover), # type: ignore
             "border_width": 0,
             **kwargs
         }
@@ -257,7 +258,7 @@ class GUIFactory:
                       (e.g., `title_color='red'`, `relief=sg.RELIEF_SUNKEN`).
         """
         cfg = self.config
-        font = (cfg.fonts.font_family, cfg.fonts.frame_size)
+        font = (cfg.fonts.font_family, cfg.fonts.frame_size) # type: ignore
         
         style_args = {
             "font": font,
@@ -289,7 +290,7 @@ class GUIFactory:
         """
         cfg = self.config
         bg_color = sg.theme_background_color()
-        label_font = (cfg.fonts.font_family, cfg.fonts.label_size, cfg.fonts.label_style)
+        label_font = (cfg.fonts.font_family, cfg.fonts.label_size, cfg.fonts.label_style) # type: ignore
         
         columns = []
         for name, (val_min, val_max) in data_dict.items():
@@ -298,21 +299,21 @@ class GUIFactory:
             
             label = sg.Text(name, font=label_font, background_color=bg_color, key=f"_text_{name}")
             
-            input_style = {"size": cfg.layout.input_size_cont, "justification": "center"}
+            input_style = {"size": cfg.layout.input_size_cont, "justification": "center"} # type: ignore
             if is_target:
-                input_style["text_color"] = cfg.colors.target_text
-                input_style["disabled_readonly_background_color"] = cfg.colors.target_background
+                input_style["text_color"] = cfg.colors.target_text # type: ignore
+                input_style["disabled_readonly_background_color"] = cfg.colors.target_background # type: ignore
             
             element = sg.Input(default_text, key=key, disabled=is_target, **input_style)
             
             if is_target:
                 layout = [[label], [element]]
             else:
-                range_font = (cfg.fonts.font_family, cfg.fonts.range_size)
+                range_font = (cfg.fonts.font_family, cfg.fonts.range_size) # type: ignore
                 range_text = sg.Text(f"Range: {int(val_min)}-{int(val_max)}", font=range_font, background_color=bg_color)
                 layout = [[label], [element], [range_text]]
             
-            layout.append([sg.Text(" ", font=(cfg.fonts.font_family, 2), background_color=bg_color)])
+            layout.append([sg.Text(" ", font=(cfg.fonts.font_family, 2), background_color=bg_color)]) # type: ignore
             columns.append(sg.Column(layout, background_color=bg_color))
 
         if layout_mode == 'row':
@@ -340,17 +341,17 @@ class GUIFactory:
         """
         cfg = self.config
         bg_color = sg.theme_background_color()
-        label_font = (cfg.fonts.font_family, cfg.fonts.label_size, cfg.fonts.label_style)
+        label_font = (cfg.fonts.font_family, cfg.fonts.label_size, cfg.fonts.label_style) # type: ignore
 
         columns = []
         for name, values in data_dict.items():
             label = sg.Text(name, font=label_font, background_color=bg_color, key=f"_text_{name}")
             element = sg.Combo(
                 values, default_value=values[0], key=name,
-                size=cfg.layout.input_size_binary, readonly=True
+                size=cfg.layout.input_size_binary, readonly=True # type: ignore
             )
             layout = [[label], [element]]
-            layout.append([sg.Text(" ", font=(cfg.fonts.font_family, 2), background_color=bg_color)])
+            layout.append([sg.Text(" ", font=(cfg.fonts.font_family, 2), background_color=bg_color)]) # type: ignore
             columns.append(sg.Column(layout, background_color=bg_color))
 
         if layout_mode == 'row':
@@ -370,8 +371,8 @@ class GUIFactory:
             **kwargs: Additional arguments to pass to the sg.Window constructor
                       (e.g., `location=(100, 100)`, `keep_on_top=True`).
         """
-        cfg = self.config.general
-        version = getattr(self.config.meta, 'version', None)
+        cfg = self.config.general # type: ignore
+        version = getattr(self.config.meta, 'version', None) # type: ignore
         full_title = f"{title} v{version}" if version else title
 
         window_args = {
@@ -406,9 +407,7 @@ def catch_exceptions(show_popup: bool = True):
                     sg.popup_error("An error occurred:", error_msg, title="Error")
                 else:
                     # Fallback for non-GUI contexts or if popup is disabled
-                    print("--- An exception occurred ---")
-                    print(error_msg)
-                    print("-----------------------------")
+                    _LOGGER.error(error_msg)
         return wrapper
     return decorator
 

{dragon_ml_toolbox-2.4.0 → dragon_ml_toolbox-3.1.0}/ml_tools/MICE_imputation.py

@@ -6,6 +6,7 @@ import numpy as np
 from .utilities import load_dataframe, list_csv_paths, sanitize_filename, _script_info, merge_dataframes, save_dataframe, threshold_binary_values, make_fullpath
 from plotnine import ggplot, labs, theme, element_blank # type: ignore
 from typing import Optional, Union
+from .logger import _LOGGER
 
 
 __all__ = [
@@ -40,7 +41,9 @@ def apply_mice(df: pd.DataFrame, df_name: str, binary_columns: Optional[list[str
     if binary_columns is not None:
         invalid_binary_columns = set(binary_columns) - set(df.columns)
         if invalid_binary_columns:
-            print(f"⚠️ These 'binary columns' are not in the dataset: {invalid_binary_columns}")
+            _LOGGER.warning(f"⚠️ These 'binary columns' are not in the dataset:")
+            for invalid_binary_col in invalid_binary_columns:
+                print(f"  - {invalid_binary_col}")
         valid_binary_columns = [col for col in binary_columns if col not in invalid_binary_columns]
         for imputed_df in imputed_datasets:
             for binary_column_name in valid_binary_columns:
@@ -125,7 +128,7 @@ def get_convergence_diagnostic(kernel: mf.ImputationKernel, imputed_dataset_name
             plt.savefig(save_path, bbox_inches='tight', format="svg")
             plt.close()
             
-        print(f"{dataset_file_dir} completed.")
+        _LOGGER.info(f"{dataset_file_dir} completed.")
 
 
 # Imputed distributions
@@ -210,7 +213,7 @@ def get_imputed_distributions(kernel: mf.ImputationKernel, df_name: str, root_di
             fig = kernel.plot_imputed_distributions(variables=[feature])
             _process_figure(fig, feature)
 
-    print(f"{local_dir_name} completed.")
+    _LOGGER.info(f"{local_dir_name} completed.")
 
 
 def run_mice_pipeline(df_path_or_dir: Union[str,Path], target_columns: list[str], 
@@ -240,7 +243,8 @@ def run_mice_pipeline(df_path_or_dir: Union[str,Path], target_columns: list[str]
         all_file_paths = list(list_csv_paths(input_path).values())
     
     for df_path in all_file_paths:
-        df, df_name = load_dataframe(df_path=df_path)
+        df: pd.DataFrame
+        df, df_name = load_dataframe(df_path=df_path, kind="pandas") # type: ignore
         
         df, df_targets = _skip_targets(df, target_columns)