dragon-ml-toolbox 12.5.0__tar.gz → 12.7.0__tar.gz

{dragon_ml_toolbox-12.5.0/dragon_ml_toolbox.egg-info → dragon_ml_toolbox-12.7.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 12.5.0
+Version: 12.7.0
 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-12.5.0 → dragon_ml_toolbox-12.7.0/dragon_ml_toolbox.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 12.5.0
+Version: 12.7.0
 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-12.5.0 → dragon_ml_toolbox-12.7.0}/ml_tools/ETL_cleaning.py

@@ -5,7 +5,7 @@ from typing import Union, List, Dict
 
 from .path_manager import sanitize_filename, make_fullpath
 from .data_exploration import drop_macro
-from .utilities import save_dataframe, load_dataframe
+from .utilities import save_dataframe_filename, load_dataframe
 from ._script_info import _script_info
 from ._logger import _LOGGER
 
@@ -263,7 +263,7 @@ def basic_clean(input_filepath: Union[str,Path], output_filepath: Union[str,Path
     df_final = _cleaner_core(df_in=df, all_lowercase=all_lowercase)
     
     # Save cleaned dataframe
-    save_dataframe(df=df_final, save_dir=output_path.parent, filename=output_path.name)
+    save_dataframe_filename(df=df_final, save_dir=output_path.parent, filename=output_path.name)
     
     _LOGGER.info(f"Data successfully cleaned.")
     
@@ -329,7 +329,7 @@ def basic_clean_drop(input_filepath: Union[str,Path], output_filepath: Union[str
                           threshold=threshold)
     
     # Save cleaned dataframe
-    save_dataframe(df=df_final, save_dir=output_path.parent, filename=output_path.name)
+    save_dataframe_filename(df=df_final, save_dir=output_path.parent, filename=output_path.name)
     
     _LOGGER.info(f"Data successfully cleaned.")
 
@@ -494,7 +494,7 @@ class DataFrameCleaner:
         if isinstance(output_filepath, str):
             output_filepath = make_fullpath(input_path=output_filepath, enforce="file")
         
-        save_dataframe(df=df_clean, save_dir=output_filepath.parent, filename=output_filepath.name)
+        save_dataframe_filename(df=df_clean, save_dir=output_filepath.parent, filename=output_filepath.name)
         
         return None
 

{dragon_ml_toolbox-12.5.0 → dragon_ml_toolbox-12.7.0}/ml_tools/ETL_engineering.py

@@ -3,7 +3,7 @@ import re
 from pathlib import Path
 from typing import Literal, Union, Optional, Any, Callable, List, Dict, Tuple
 
-from .utilities import load_dataframe, save_dataframe
+from .utilities import load_dataframe, save_dataframe_filename
 from .path_manager import make_fullpath
 from ._script_info import _script_info
 from ._logger import _LOGGER
@@ -230,7 +230,7 @@ class DataProcessor:
         df_processed = self.transform(df)
         
         # save processed df
-        save_dataframe(df=df_processed, save_dir=out_path.parent, filename=out_path.name)
+        save_dataframe_filename(df=df_processed, save_dir=out_path.parent, filename=out_path.name)
         
     def __str__(self) -> str:
         """

{dragon_ml_toolbox-12.5.0 → dragon_ml_toolbox-12.7.0}/ml_tools/MICE_imputation.py

@@ -6,7 +6,7 @@ import numpy as np
 from plotnine import ggplot, labs, theme, element_blank # type: ignore
 from typing import Optional, Union
 
-from .utilities import load_dataframe, merge_dataframes, save_dataframe
+from .utilities import load_dataframe, merge_dataframes, save_dataframe_filename
 from .math_utilities import threshold_binary_values
 from .path_manager import sanitize_filename, make_fullpath, list_csv_paths
 from ._logger import _LOGGER
@@ -75,7 +75,7 @@ def apply_mice(df: pd.DataFrame, df_name: str, binary_columns: Optional[list[str
 def save_imputed_datasets(save_dir: Union[str, Path], imputed_datasets: list, df_targets: pd.DataFrame, imputed_dataset_names: list[str]):
     for imputed_df, subname in zip(imputed_datasets, imputed_dataset_names):
         merged_df = merge_dataframes(imputed_df, df_targets, direction="horizontal", verbose=False)
-        save_dataframe(df=merged_df, save_dir=save_dir, filename=subname)
+        save_dataframe_filename(df=merged_df, save_dir=save_dir, filename=subname)
 
 
 #Get names of features that had missing values before imputation

{dragon_ml_toolbox-12.5.0 → dragon_ml_toolbox-12.7.0}/ml_tools/ML_optimization.py

@@ -18,7 +18,7 @@ from .ML_inference import PyTorchInferenceHandler
 from .keys import PyTorchInferenceKeys
 from .SQL import DatabaseManager
 from .optimization_tools import _save_result
-from .utilities import save_dataframe
+from .utilities import save_dataframe_filename
 from .math_utilities import discretize_categorical_values
 
 
@@ -513,7 +513,7 @@ def _run_single_optimization_rep(
 
 def _handle_pandas_log(logger: PandasLogger, save_path: Path, target_name: str):
     log_dataframe = logger.to_dataframe()
-    save_dataframe(df=log_dataframe, save_dir=save_path / "EvolutionLogs", filename=target_name)
+    save_dataframe_filename(df=log_dataframe, save_dir=save_path / "EvolutionLogs", filename=target_name)
 
 
 def info():

{dragon_ml_toolbox-12.5.0 → dragon_ml_toolbox-12.7.0}/ml_tools/ML_simple_optimization.py

@@ -18,7 +18,7 @@ from .ML_inference import PyTorchInferenceHandler
 from .keys import PyTorchInferenceKeys
 from .SQL import DatabaseManager
 from .optimization_tools import _save_result
-from .utilities import save_dataframe
+from .utilities import save_dataframe_filename
 from .math_utilities import threshold_binary_values
 
 """
@@ -406,7 +406,7 @@ def s_run_optimization(
 
 def _handle_pandas_log(logger: PandasLogger, save_path: Path, target_name: str):
     log_dataframe = logger.to_dataframe()
-    save_dataframe(df=log_dataframe, save_dir=save_path / "EvolutionLogs", filename=target_name)
+    save_dataframe_filename(df=log_dataframe, save_dir=save_path / "EvolutionLogs", filename=target_name)
 
 
 def info():

{dragon_ml_toolbox-12.5.0 → dragon_ml_toolbox-12.7.0}/ml_tools/VIF_factor.py

@@ -7,7 +7,7 @@ from statsmodels.tools.tools import add_constant
 import warnings
 from pathlib import Path
 
-from .utilities import yield_dataframes_from_dir, save_dataframe
+from .utilities import yield_dataframes_from_dir, save_dataframe_filename
 from .path_manager import sanitize_filename, make_fullpath
 from ._logger import _LOGGER
 from ._script_info import _script_info
@@ -229,7 +229,7 @@ def compute_vif_multi(input_directory: Union[str, Path],
             result_df, dropped_cols = drop_vif_based(df=df, vif_df=vif_dataframe)
             
             if len(dropped_cols) > 0:
-                save_dataframe(df=result_df, save_dir=output_dataset_path, filename=new_filename)
+                save_dataframe_filename(df=result_df, save_dir=output_dataset_path, filename=new_filename)
 
 
 def info():

{dragon_ml_toolbox-12.5.0 → dragon_ml_toolbox-12.7.0}/ml_tools/data_exploration.py

@@ -10,7 +10,7 @@ import re
 from .path_manager import sanitize_filename, make_fullpath
 from ._script_info import _script_info
 from ._logger import _LOGGER
-from .utilities import save_dataframe
+from .utilities import save_dataframe_filename
 
 
 # Keep track of all available tools, show using `info()`
@@ -269,7 +269,7 @@ def drop_macro(df: pd.DataFrame,
     
     # Log initial state
     missing_data = show_null_columns(df=df_clean)
-    save_dataframe(df=missing_data.reset_index(drop=False),
+    save_dataframe_filename(df=missing_data.reset_index(drop=False),
                    save_dir=log_directory,
                    filename="Missing_Data_start")
     
@@ -298,7 +298,7 @@ def drop_macro(df: pd.DataFrame,
     
     # log final state
     missing_data = show_null_columns(df=df_clean)
-    save_dataframe(df=missing_data.reset_index(drop=False),
+    save_dataframe_filename(df=missing_data.reset_index(drop=False),
                    save_dir=log_directory,
                    filename="Missing_Data_final")
     

{dragon_ml_toolbox-12.5.0 → dragon_ml_toolbox-12.7.0}/ml_tools/ensemble_learning.py

@@ -14,7 +14,7 @@ from sklearn.model_selection import train_test_split
 from sklearn.base import clone
 
 from .utilities import yield_dataframes_from_dir, train_dataset_yielder
-from .serde import serialize_object
+from .serde import serialize_object_filename
 from .path_manager import sanitize_filename, make_fullpath
 from ._script_info import _script_info
 from .keys import EnsembleKeys
@@ -411,7 +411,7 @@ def _save_model(trained_model, model_name: str, target_name:str, feature_names:
                EnsembleKeys.FEATURES: feature_names,
                EnsembleKeys.TARGET: target_name}
 
-    serialize_object(obj=to_save, save_dir=save_directory, filename=filename, verbose=False, raise_on_error=True)
+    serialize_object_filename(obj=to_save, save_dir=save_directory, filename=filename, verbose=False, raise_on_error=True)
 
 
 # TRAIN EVALUATE PIPELINE

{dragon_ml_toolbox-12.5.0 → dragon_ml_toolbox-12.7.0}/ml_tools/utilities.py

@@ -12,10 +12,11 @@ from ._logger import _LOGGER
 # Keep track of available tools
 __all__ = [
     "load_dataframe",
+    "load_dataframe_greedy",
     "yield_dataframes_from_dir",
     "merge_dataframes",
+    "save_dataframe_filename",
     "save_dataframe",
-    "save_dataframe_path",
     "distribute_dataset_by_target",
     "train_dataset_orchestrator",
     "train_dataset_yielder"
@@ -124,6 +125,54 @@ def load_dataframe(
     return df, df_name # type: ignore
 
 
+def load_dataframe_greedy(directory: Union[str, Path],
+                          use_columns: Optional[list[str]] = None,
+                          all_strings: bool = False,
+                          verbose: bool = True) -> pd.DataFrame:
+    """
+    Greedily loads the first found CSV file from a directory into a Pandas DataFrame.
+
+    This function scans the specified directory for any CSV files. It will
+    attempt to load the *first* CSV file it finds using the `load_dataframe`
+    function as a Pandas DataFrame.
+
+    Args:
+        directory (str, Path): 
+            The path to the directory to search for a CSV file.
+        use_columns (list[str] | None):
+            A list of column names to load. If None, all columns are loaded.
+        all_strings (bool): 
+            If True, loads all columns as string data types.
+
+    Returns:
+        pd.DataFrame: 
+            A pandas DataFrame loaded from the first CSV file found.
+
+    Raises:
+        FileNotFoundError: 
+            If the specified directory does not exist or the CSV file path
+            found is invalid.
+        ValueError: 
+            If the loaded DataFrame is empty or `use_columns` contains
+            invalid column names.
+    """
+    # validate directory
+    dir_path = make_fullpath(directory, enforce="directory")
+    
+    # list all csv files and grab one (should be the only one)
+    csv_dict = list_csv_paths(directory=dir_path, verbose=False)
+    
+    for df_path in csv_dict.values():
+        df , _df_name = load_dataframe(df_path=df_path,
+                                    use_columns=use_columns,
+                                    kind="pandas",
+                                    all_strings=all_strings,
+                                    verbose=verbose)
+        break
+    
+    return df
+
+
 def yield_dataframes_from_dir(datasets_dir: Union[str,Path], verbose: bool=True):
     """
     Iterates over all CSV files in a given directory, loading each into a Pandas DataFrame.
@@ -210,7 +259,7 @@ def merge_dataframes(
     return merged_df
 
 
-def save_dataframe(df: Union[pd.DataFrame, pl.DataFrame], save_dir: Union[str,Path], filename: str) -> None:
+def save_dataframe_filename(df: Union[pd.DataFrame, pl.DataFrame], save_dir: Union[str,Path], filename: str) -> None:
     """
     Saves a pandas or polars DataFrame to a CSV file.
 
@@ -250,11 +299,11 @@ def save_dataframe(df: Union[pd.DataFrame, pl.DataFrame], save_dir: Union[str,Pa
     _LOGGER.info(f"Saved dataset: '{filename}' with shape: {df.shape}")
 
 
-def save_dataframe_path(df: Union[pd.DataFrame, pl.DataFrame], full_path: Path):
+def save_dataframe(df: Union[pd.DataFrame, pl.DataFrame], full_path: Path):
     """
     Saves a DataFrame to a specified full path.
 
-    This function is a convenience wrapper for `save_dataframe()`. It takes a
+    This function is a wrapper for `save_dataframe_filename()`. It takes a
     single `pathlib.Path` object pointing to a `.csv` file.
 
     Args:
@@ -265,9 +314,9 @@ def save_dataframe_path(df: Union[pd.DataFrame, pl.DataFrame], full_path: Path):
         _LOGGER.error('A path object pointing to a .csv file must be provided.')
         raise ValueError()
         
-    save_dataframe(df=df, 
-                   save_dir=full_path.parent,
-                   filename=full_path.name)
+    save_dataframe_filename(df=df, 
+                            save_dir=full_path.parent,
+                            filename=full_path.name)
 
 
 def distribute_dataset_by_target(
@@ -351,7 +400,7 @@ def train_dataset_orchestrator(list_of_dirs: list[Union[str,Path]],
                         filename = df_dir.name + '_' + target_name + '_' + df_name
                     else:
                         filename = target_name + '_' + df_name
-                    save_dataframe(df=df, save_dir=save_dir, filename=filename)
+                    save_dataframe_filename(df=df, save_dir=save_dir, filename=filename)
                     total_saved += 1
             except Exception as e:
                 _LOGGER.error(f"Failed to process file '{df_path}'. Reason: {e}")

{dragon_ml_toolbox-12.5.0 → dragon_ml_toolbox-12.7.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "dragon-ml-toolbox"
-version = "12.5.0"
+version = "12.7.0"
 description = "A collection of tools for data science and machine learning projects."
 authors = [
     { name = "Karl L. Loza Vidaurre", email = "luigiloza@gmail.com" }