dragon-ml-toolbox 1.4.8__py3-none-any.whl → 2.1.0__py3-none-any.whl

{dragon_ml_toolbox-1.4.8.dist-info → dragon_ml_toolbox-2.1.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 1.4.8
+Version: 2.1.0
 Summary: A collection of tools for data science and machine learning projects
 Author-email: Karl Loza <luigiloza@gmail.com>
 License-Expression: MIT
@@ -8,7 +8,7 @@ Project-URL: Homepage, https://github.com/DrAg0n-BoRn/ML_tools
 Project-URL: Changelog, https://github.com/DrAg0n-BoRn/ML_tools/blob/master/CHANGELOG.md
 Classifier: Programming Language :: Python :: 3
 Classifier: Operating System :: OS Independent
-Requires-Python: >=3.9
+Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
 License-File: LICENSE-THIRD-PARTY.md
@@ -32,9 +32,10 @@ Requires-Dist: joblib
 Requires-Dist: xgboost
 Requires-Dist: lightgbm<=4.5.0
 Requires-Dist: shap
+Requires-Dist: tqdm>=4.0
+Requires-Dist: Pillow
 Provides-Extra: pytorch
 Requires-Dist: torch; extra == "pytorch"
-Requires-Dist: Pillow; extra == "pytorch"
 Requires-Dist: torchvision; extra == "pytorch"
 Dynamic: license-file
 
@@ -49,7 +50,7 @@ A collection of Python utilities for data science and machine learning, structur
 
 ## Installation
 
-**Python 3.9+ recommended.**
+**Python 3.10+ recommended.**
 
 ### Via PyPI
 
@@ -59,6 +60,16 @@ Install the latest stable release from PyPI:
 pip install dragon-ml-tools
 ```
 
+### Via GitHub (Editable)
+
+Clone the repository and install in editable mode with optional dependencies:
+
+```bash
+git clone https://github.com/DrAg0n-BoRn/ML_tools.git
+cd ML_tools
+pip install -e .
+```
+
 ### Via conda-forge
 
 Install from the conda-forge channel:
@@ -66,22 +77,21 @@ Install from the conda-forge channel:
 ```bash
 conda install -c conda-forge dragon-ml-toolbox
 ```
+**Note:** This version is outdated or broken due to dependency incompatibilities.
 
-#### Optional dependencies
+## Optional dependencies
+
+**PyTorch**, which provides different builds depending on the **platform** and **hardware acceleration** (e.g., CUDA for NVIDIA GPUs on Linux/Windows, or MPS for Apple Silicon on macOS).
+
+Install the default CPU-only version with
 
 ```bash
 pip install dragon-ml-tools[pytorch]
 ```
 
-### Via GitHub (Editable)
-
-Clone the repository and install in editable mode with optional dependencies:
+To make use of GPU acceleration use the official PyTorch installation instructions:
 
-```bash
-git clone https://github.com/DrAg0n-BoRn/ML_tools.git
-cd ML_tools
-pip install -e .
-```
+[PyTorch Instructions](https://pytorch.org/get-started/locally/)
 
 ## Usage
 
@@ -101,7 +111,7 @@ ensemble_learning
 handle_excel
 logger
 MICE_imputation
-particle_swarm_optimization
+PSO_optimization
 trainer
 utilities
 VIF_factor

dragon_ml_toolbox-2.1.0.dist-info/RECORD

@@ -0,0 +1,20 @@
+dragon_ml_toolbox-2.1.0.dist-info/licenses/LICENSE,sha256=2uUFNy7D0TLgHim1K5s3DIJ4q_KvxEXVilnU20cWliY,1066
+dragon_ml_toolbox-2.1.0.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=6cfpIeQ6D4Mcs10nkogQrkVyq1T7i2qXjjNHFoUMOyE,1892
+ml_tools/MICE_imputation.py,sha256=1fovHycZMdZ6OgVh_bk8-r3wGi4rqf6rS10LOEWYaQo,11177
+ml_tools/PSO_optimization.py,sha256=vty1dZDY7P2iGUuE_oojyGdgM1EkDj5kXCfCxRMdk28,20957
+ml_tools/VIF_factor.py,sha256=lpM3Z2X_iZfXUWbCbURoeI0Tb196lU0bAsRo7q6AzBM,10235
+ml_tools/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+ml_tools/_particle_swarm_optimization.py,sha256=b_eNNkA89Y40hj76KauivT8KLScH1B9wF2IXptOqkOw,22220
+ml_tools/data_exploration.py,sha256=CDUVRTHfww105IXDRpBQ81KZWx5HXSsA-FVsVYBzNw8,21298
+ml_tools/datasetmaster.py,sha256=EFUEX-tqq94Ak1rXXYR-XaX85olrxvF2EuytdzUK7y0,29131
+ml_tools/ensemble_learning.py,sha256=q9jbu7SupvXz61sURFQ9V2-7gUsLbA3cSgyb2MQFyyc,37351
+ml_tools/handle_excel.py,sha256=Uasx-DX7RNVQSzGHVJhX7UQ9RgBbX5H1ud1Hw_y8Kp4,12944
+ml_tools/logger.py,sha256=_k7WJdpFJj3IsjOgvjLJgUFZyF8RK3Jlgp5tAu_dLQU,4767
+ml_tools/pytorch_models.py,sha256=bpWZsrSwCvHJQkR6UfoPpElsMv9AvmiNErNHC8NYB_I,10132
+ml_tools/trainer.py,sha256=WAZ4EdrZuTOAnGXRWV3XcLNce4s7EKGf2-qchLC08Ik,15702
+ml_tools/utilities.py,sha256=5vVXqIH-jiY4PHUAoDI1o26mZYPsmrWO6I97Fs3oC90,18661
+ml_tools/vision_helpers.py,sha256=idQ-Ugp1IdsvwXiYyhYa9G3rTRTm37YRpkQDLEpANHM,7701
+dragon_ml_toolbox-2.1.0.dist-info/METADATA,sha256=LDXrXkR1nm6WiEVHudCy7wI0dwkMejT0NzPuYptGSmw,2974
+dragon_ml_toolbox-2.1.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+dragon_ml_toolbox-2.1.0.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
+dragon_ml_toolbox-2.1.0.dist-info/RECORD,,

{dragon_ml_toolbox-1.4.8.dist-info → dragon_ml_toolbox-2.1.0.dist-info}/licenses/LICENSE-THIRD-PARTY.md

@@ -5,10 +5,10 @@ This project depends on the following third-party packages. Each is governed by
 - [pandas](https://github.com/pandas-dev/pandas/blob/main/LICENSE)
 - [numpy](https://github.com/numpy/numpy/blob/main/LICENSE.txt)
 - [matplotlib](https://github.com/matplotlib/matplotlib/blob/main/LICENSE/LICENSE)
-- [seaborn](https://github.com/mwaskom/seaborn/blob/main/LICENSE)
+- [seaborn](https://github.com/mwaskom/seaborn/blob/master/LICENSE.md)
 - [statsmodels](https://github.com/statsmodels/statsmodels/blob/main/LICENSE.txt)
-- [ipython](https://github.com/ipython/ipython/blob/main/COPYING.rst)
-- [ipykernel](https://github.com/ipython/ipykernel/blob/main/COPYING.rst)
+- [ipython](https://github.com/ipython/ipython/blob/main/LICENSE)
+- [ipykernel](https://github.com/ipython/ipykernel/blob/main/LICENSE)
 - [notebook](https://github.com/jupyter/notebook/blob/main/LICENSE)
 - [jupyterlab](https://github.com/jupyterlab/jupyterlab/blob/main/LICENSE)
 - [ipywidgets](https://github.com/jupyter-widgets/ipywidgets/blob/main/LICENSE)
@@ -24,5 +24,6 @@ This project depends on the following third-party packages. Each is governed by
 - [openpyxl](https://github.com/chronossc/openpyxl/blob/main/LICENSE)
 - [miceforest](https://github.com/AnotherSamWilson/miceforest/blob/main/LICENSE)
 - [polars](https://github.com/pola-rs/polars/blob/main/LICENSE)
-- [plotnine](https://github.com/has2k1/plotnine/blob/main/LICENSE.txt)
+- [plotnine](https://github.com/has2k1/plotnine/blob/main/LICENSE)
 - [pyswarm](https://pythonhosted.org/pyswarm/#license)
+- [tqdm](https://github.com/tqdm/tqdm/blob/master/LICENSE)

ml_tools/MICE_imputation.py

@@ -1,11 +1,11 @@
 import pandas as pd
 import miceforest as mf
-import os
+from pathlib import Path
 import matplotlib.pyplot as plt
 import numpy as np
-from .utilities import load_dataframe, list_csv_paths, sanitize_filename, _script_info, merge_dataframes, save_dataframe, threshold_binary_values
+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
+from typing import Optional, Union
 
 
 __all__ = [
@@ -60,7 +60,7 @@ def apply_mice(df: pd.DataFrame, df_name: str, binary_columns: Optional[list[str
     return kernel, imputed_datasets, imputed_dataset_names
 
 
-def save_imputed_datasets(save_dir: str, imputed_datasets: list, df_targets: pd.DataFrame, imputed_dataset_names: 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)
@@ -72,7 +72,7 @@ def get_na_column_names(df: pd.DataFrame):
 
 
 #Convergence diagnostic
-def get_convergence_diagnostic(kernel: mf.ImputationKernel, imputed_dataset_names: list[str], column_names: list[str], root_dir: str, fontsize: int=16):
+def get_convergence_diagnostic(kernel: mf.ImputationKernel, imputed_dataset_names: list[str], column_names: list[str], root_dir: Union[str,Path], fontsize: int=16):
     """
     Generate and save convergence diagnostic plots for imputed variables.
 
@@ -90,7 +90,7 @@ def get_convergence_diagnostic(kernel: mf.ImputationKernel, imputed_dataset_name
         raise ValueError(f"Expected {dataset_count} names in imputed_dataset_names, got {len(imputed_dataset_names)}")
     
     # Check path
-    os.makedirs(root_dir, exist_ok=True)
+    root_path = make_fullpath(root_dir, make=True)
     
     # Styling parameters
     label_font = {'size': fontsize, 'weight': 'bold'}
@@ -99,8 +99,7 @@ def get_convergence_diagnostic(kernel: mf.ImputationKernel, imputed_dataset_name
     for dataset_id, imputed_dataset_name in zip(range(dataset_count), imputed_dataset_names):
         #Check directory for current dataset
         dataset_file_dir = f"Convergence_Metrics_{imputed_dataset_name}"
-        local_save_dir = os.path.join(root_dir, dataset_file_dir)
-        os.makedirs(local_save_dir, exist_ok=True)
+        local_save_dir = make_fullpath(input_path=root_path / dataset_file_dir, make=True)
         
         for feature_name in column_names:
             means_per_iteration = []
@@ -121,8 +120,8 @@ def get_convergence_diagnostic(kernel: mf.ImputationKernel, imputed_dataset_name
             plt.grid(True)
             
             feature_save_name = sanitize_filename(feature_name)
-            
-            save_path = os.path.join(local_save_dir, feature_save_name + ".svg")
+            feature_save_name = feature_save_name + ".svg"
+            save_path = local_save_dir / feature_save_name
             plt.savefig(save_path, bbox_inches='tight', format="svg")
             plt.close()
             
@@ -130,18 +129,17 @@ def get_convergence_diagnostic(kernel: mf.ImputationKernel, imputed_dataset_name
 
 
 # Imputed distributions
-def get_imputed_distributions(kernel: mf.ImputationKernel, df_name: str, root_dir: str, column_names: list[str], one_plot: bool=False, fontsize: int=14):
+def get_imputed_distributions(kernel: mf.ImputationKernel, df_name: str, root_dir: Union[str, Path], column_names: list[str], one_plot: bool=False, fontsize: int=14):
     ''' 
     It works using miceforest's authors implementation of the method `.plot_imputed_distributions()`.
     
     Set `one_plot=True` to save a single image including all feature distribution plots instead.
     '''
     # Check path
-    os.makedirs(root_dir, exist_ok=True)
+    root_path = make_fullpath(root_dir, make=True)
+
     local_dir_name = f"Distribution_Metrics_{df_name}_imputed"
-    local_save_dir = os.path.join(root_dir, local_dir_name)
-    if not os.path.isdir(local_save_dir):
-        os.makedirs(local_save_dir)
+    local_save_dir = make_fullpath(root_path / local_dir_name, make=True)
     
     # Styling parameters
     legend_kwargs = {'frameon': True, 'facecolor': 'white', 'framealpha': 0.8}
@@ -191,9 +189,11 @@ def get_imputed_distributions(kernel: mf.ImputationKernel, df_name: str, root_di
         
         # sanitize savename
         feature_save_name = sanitize_filename(filename)
+        feature_save_name = feature_save_name + ".svg"
+        new_save_path = local_save_dir / feature_save_name
         
         fig.savefig(
-            os.path.join(local_save_dir, feature_save_name + ".svg"),
+            new_save_path,
             format='svg',
             bbox_inches='tight',
             pad_inches=0.1
@@ -213,8 +213,8 @@ def get_imputed_distributions(kernel: mf.ImputationKernel, df_name: str, root_di
     print(f"{local_dir_name} completed.")
 
 
-def run_mice_pipeline(df_path_or_dir: str, target_columns: list[str], 
-                      save_datasets_dir: str, save_metrics_dir: str, 
+def run_mice_pipeline(df_path_or_dir: Union[str,Path], target_columns: list[str], 
+                      save_datasets_dir: Union[str,Path], save_metrics_dir: Union[str,Path], 
                       binary_columns: Optional[list[str]]=None,
                       resulting_datasets: int=1, 
                       iterations: int=20, 
@@ -230,15 +230,14 @@ def run_mice_pipeline(df_path_or_dir: str, target_columns: list[str],
     Target columns must be skipped from the imputation. Binary columns will be thresholded after imputation.
     """
     # Check paths
-    os.makedirs(save_datasets_dir, exist_ok=True)
-    os.makedirs(save_metrics_dir, exist_ok=True)
+    save_datasets_path = make_fullpath(save_datasets_dir, make=True)
+    save_metrics_path = make_fullpath(save_metrics_dir, make=True)
     
-    if os.path.isfile(df_path_or_dir):
-        all_file_paths = [df_path_or_dir]
-    elif os.path.isdir(df_path_or_dir):
-        all_file_paths = list(list_csv_paths(df_path_or_dir).values())
+    input_path = make_fullpath(df_path_or_dir)
+    if input_path.is_file():
+        all_file_paths = [input_path]
     else:
-        raise ValueError(f"Invalid path or directory: {df_path_or_dir}")
+        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)
@@ -247,13 +246,13 @@ def run_mice_pipeline(df_path_or_dir: str, target_columns: list[str],
         
         kernel, imputed_datasets, imputed_dataset_names = apply_mice(df=df, df_name=df_name, binary_columns=binary_columns, resulting_datasets=resulting_datasets, iterations=iterations, random_state=random_state)
         
-        save_imputed_datasets(save_dir=save_datasets_dir, imputed_datasets=imputed_datasets, df_targets=df_targets, imputed_dataset_names=imputed_dataset_names)
+        save_imputed_datasets(save_dir=save_datasets_path, imputed_datasets=imputed_datasets, df_targets=df_targets, imputed_dataset_names=imputed_dataset_names)
         
         imputed_column_names = get_na_column_names(df=df)
         
-        get_convergence_diagnostic(kernel=kernel, imputed_dataset_names=imputed_dataset_names, column_names=imputed_column_names, root_dir=save_metrics_dir)
+        get_convergence_diagnostic(kernel=kernel, imputed_dataset_names=imputed_dataset_names, column_names=imputed_column_names, root_dir=save_metrics_path)
         
-        get_imputed_distributions(kernel=kernel, df_name=df_name, root_dir=save_metrics_dir, column_names=imputed_column_names)
+        get_imputed_distributions(kernel=kernel, df_name=df_name, root_dir=save_metrics_path, column_names=imputed_column_names)
 
 
 def _skip_targets(df: pd.DataFrame, target_cols: list[str]):