dragon-ml-toolbox 1.3.0__py3-none-any.whl → 1.3.2__py3-none-any.whl

{dragon_ml_toolbox-1.3.0.dist-info → dragon_ml_toolbox-1.3.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 1.3.0
+Version: 1.3.2
 Summary: A collection of tools for data science and machine learning projects
 Author-email: Karl Loza <luigiloza@gmail.com>
 License-Expression: MIT
@@ -15,17 +15,21 @@ License-File: LICENSE-THIRD-PARTY.md
 Requires-Dist: numpy<2.0
 Requires-Dist: scikit-learn
 Requires-Dist: openpyxl
-Requires-Dist: miceforest
+Requires-Dist: miceforest<7.0.0,>=6.0.0
+Requires-Dist: plotnine<0.13,>=0.12
 Requires-Dist: matplotlib
 Requires-Dist: seaborn
 Requires-Dist: pandas
 Requires-Dist: polars
-Requires-Dist: imblearn
+Requires-Dist: imbalanced-learn
 Requires-Dist: statsmodels
 Requires-Dist: ipython
+Requires-Dist: ipykernel
+Requires-Dist: notebook
+Requires-Dist: jupyterlab
 Requires-Dist: joblib
 Requires-Dist: xgboost
-Requires-Dist: lightgbm
+Requires-Dist: lightgbm<=4.5.0
 Requires-Dist: shap
 Provides-Extra: pytorch
 Requires-Dist: torch; extra == "pytorch"

{dragon_ml_toolbox-1.3.0.dist-info → dragon_ml_toolbox-1.3.2.dist-info}/RECORD

@@ -1,6 +1,6 @@
-dragon_ml_toolbox-1.3.0.dist-info/licenses/LICENSE,sha256=2uUFNy7D0TLgHim1K5s3DIJ4q_KvxEXVilnU20cWliY,1066
-dragon_ml_toolbox-1.3.0.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=e1Hg5ZtaBpDV7ZvxhLe1ac28l7nMjvi1MSE5YvB1s-o,1472
-ml_tools/MICE_imputation.py,sha256=Xvupj6w4NJ7d8gcJbpp1y3LVVnWEfvx-It7oEksuT5I,7349
+dragon_ml_toolbox-1.3.2.dist-info/licenses/LICENSE,sha256=2uUFNy7D0TLgHim1K5s3DIJ4q_KvxEXVilnU20cWliY,1066
+dragon_ml_toolbox-1.3.2.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=e1Hg5ZtaBpDV7ZvxhLe1ac28l7nMjvi1MSE5YvB1s-o,1472
+ml_tools/MICE_imputation.py,sha256=71Kdi5rhPePIT5rJKIyRCM7ORPSjeujQCzKcLIwXs90,9428
 ml_tools/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 ml_tools/data_exploration.py,sha256=laTNbN5_xlhqWiKfF-cJ9yMZ8zAM2a-AryqgiIQBBLg,26649
 ml_tools/datasetmaster.py,sha256=VUneKshnmjOGbtqVVGTFcIMRKF3s6ZDYrosIYKDjD80,28956
@@ -12,7 +12,7 @@ ml_tools/pytorch_models.py,sha256=Oykw02sOZLCjvSadQd64UGesBN7kq0x1EGXHusvYiQI,99
 ml_tools/trainer.py,sha256=Zd7AaHeoNd8dEas2JChWoHaCUpWUVRDUMybuHaKJ0XY,16740
 ml_tools/utilities.py,sha256=mG_--EFplfI9H7OhrWI8VkdNJtTbs4Wbz32xvcFWps8,5518
 ml_tools/vision_helpers.py,sha256=lBAW6dzAK-HOswAt1fU_tfP9hkNLY5D8c_I_7hhEXno,7528
-dragon_ml_toolbox-1.3.0.dist-info/METADATA,sha256=NAQJFp18GJcSVs4W1zMjzLlxuS79Xs7gZgEru-n-2o8,2169
-dragon_ml_toolbox-1.3.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-dragon_ml_toolbox-1.3.0.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
-dragon_ml_toolbox-1.3.0.dist-info/RECORD,,
+dragon_ml_toolbox-1.3.2.dist-info/METADATA,sha256=NgNKZD1v97kBBdE96OJELolvlAXviJ-DgJvZAjjy5Ik,2309
+dragon_ml_toolbox-1.3.2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+dragon_ml_toolbox-1.3.2.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
+dragon_ml_toolbox-1.3.2.dist-info/RECORD,,

ml_tools/MICE_imputation.py

@@ -3,15 +3,15 @@ import miceforest as mf
 import os
 import matplotlib.pyplot as plt
 import numpy as np
-from ml_tools.utilities import load_dataframe, list_csv_paths
-
+from ml_tools.utilities import load_dataframe, list_csv_paths, sanitize_filename
+from plotnine import ggplot, labs, theme, element_blank # type: ignore
 
 def apply_mice(df: pd.DataFrame, df_name: str, resulting_datasets: int=1, iterations: int=20, random_state: int=101):
     
     # Initialize kernel with number of imputed datasets to generate
     kernel = mf.ImputationKernel(
         data=df,
-        datasets=resulting_datasets,
+        num_datasets=resulting_datasets,
         random_state=random_state
     )
     
@@ -21,6 +21,9 @@ def apply_mice(df: pd.DataFrame, df_name: str, resulting_datasets: int=1, iterat
     # Retrieve the imputed datasets 
     imputed_datasets = [kernel.complete_data(dataset=i) for i in range(resulting_datasets)]
     
+    if imputed_datasets is None or len(imputed_datasets) == 0:
+        raise ValueError("No imputed datasets were generated. Check the MICE process.")
+    
     if resulting_datasets == 1:
         imputed_dataset_names = [f"{df_name}_imputed"]
     else:
@@ -28,8 +31,8 @@ def apply_mice(df: pd.DataFrame, df_name: str, resulting_datasets: int=1, iterat
     
     # Ensure indexes match
     for imputed_df, subname in zip(imputed_datasets, imputed_dataset_names):
-        assert imputed_df.shape[0] == df.shape[0], f"Row count mismatch in dataset {subname}"
-        assert all(imputed_df.index == df.index), f"Index mismatch in dataset {subname}"
+        assert imputed_df.shape[0] == df.shape[0], f"Row count mismatch in dataset {subname}" # type: ignore
+        assert all(imputed_df.index == df.index), f"Index mismatch in dataset {subname}" # type: ignore
     # print("✅ All imputed datasets match the original DataFrame indexes.")
     
     return kernel, imputed_datasets, imputed_dataset_names
@@ -51,46 +54,65 @@ 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):
+def get_convergence_diagnostic(kernel: mf.ImputationKernel, imputed_dataset_names: list[str], column_names: list[str], root_dir: str, fontsize: int=16):
+    """
+    Generate and save convergence diagnostic plots for imputed variables.
+
+    Parameters:
+    - kernel: Trained miceforest.ImputationKernel.
+    - imputed_dataset_names: Names assigned to each imputed dataset.
+    - column_names: List of feature names to track over iterations.
+    - root_dir: Directory to save convergence plots.
+    """
     # get number of iterations used
     iterations_cap = kernel.iteration_count()
+    dataset_count = kernel.num_datasets
+    
+    if dataset_count != len(imputed_dataset_names):
+        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)
     
+    # Styling parameters
+    label_font = {'size': fontsize, 'weight': 'bold'}
+    
     # iterate over each imputed dataset
-    for dataset_id, imputed_dataset_name in zip(range(kernel.num_datasets), imputed_dataset_names):
+    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)
-        if not os.path.isdir(local_save_dir):
-            os.makedirs(local_save_dir)
+        os.makedirs(local_save_dir, exist_ok=True)
         
         for feature_name in column_names:
             means_per_iteration = []
             for iteration in range(iterations_cap):
                 current_imputed = kernel.complete_data(dataset=dataset_id, iteration=iteration)
-                means_per_iteration.append(np.mean(current_imputed[feature_name]))
-
+                means_per_iteration.append(np.mean(current_imputed[feature_name])) # type: ignore
+                
+            plt.figure(figsize=(10, 8))
             plt.plot(means_per_iteration, marker='o')
-            plt.xlabel("Iteration")
-            plt.ylabel("Mean of Imputed Values")
-            plt.title(f"Mean Convergence for '{feature_name}'")
+            plt.xlabel("Iteration", **label_font)
+            plt.ylabel("Mean of Imputed Values", **label_font)
+            plt.title(f"Mean Convergence for '{feature_name}'", **label_font)
             
             # Adjust plot display for the X axis
             _ticks = np.arange(iterations_cap)
             _labels = np.arange(1, iterations_cap + 1)
             plt.xticks(ticks=_ticks, labels=_labels)
+            plt.grid(True)
             
-            save_path = os.path.join(local_save_dir, feature_name + ".svg")
+            feature_save_name = sanitize_filename(feature_name)
+            
+            save_path = os.path.join(local_save_dir, feature_save_name + ".svg")
             plt.savefig(save_path, bbox_inches='tight', format="svg")
             plt.close()
             
-        print(f"{dataset_file_dir} completed.")
+        print(f"\t{dataset_file_dir} completed.")
 
 
 # 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=18):
+def get_imputed_distributions(kernel: mf.ImputationKernel, df_name: str, root_dir: str, column_names: list[str], one_plot: bool=False, fontsize: int=14):
     ''' 
     It works using miceforest's authors implementation of the method `.plot_imputed_distributions()`.
     
@@ -106,12 +128,35 @@ def get_imputed_distributions(kernel: mf.ImputationKernel, df_name: str, root_di
     legend_kwargs = {'frameon': True, 'facecolor': 'white', 'framealpha': 0.8}
     label_font = {'size': fontsize, 'weight': 'bold'}
 
-    def _process_figure(fig, filename):
+    def _process_figure(fig, filename: str):
         """Helper function to add labels and legends to a figure"""
-        for ax in fig.axes:
+        
+        if not isinstance(fig, ggplot):
+            raise TypeError("Expected a plotnine.ggplot object")
+        
+        # Edit labels and title
+        fig = fig + theme(
+                plot_title=element_blank(),  # removes labs(title=...)
+                strip_text=element_blank()   # removes facet_wrap labels
+            )
+        
+        fig = fig + labs(y="", x="")
+        
+        # Render to matplotlib figure
+        fig = fig.draw()
+        
+        if not hasattr(fig, 'axes') or len(fig.axes) == 0:
+            raise RuntimeError("Rendered figure has no axes to modify")
+        
+        if filename == "Combined_Distributions":
+            custom_xlabel = "Feature Values"
+        else:
+            custom_xlabel = filename
+        
+        for ax in fig.axes:            
             # Set axis labels
-            ax.set_xlabel('Value', **label_font)
-            ax.set_ylabel('Density', **label_font)
+            ax.set_xlabel(custom_xlabel, **label_font)
+            ax.set_ylabel('Distribution', **label_font)
             
             # Add legend based on line colors
             lines = ax.get_lines()
@@ -122,26 +167,28 @@ def get_imputed_distributions(kernel: mf.ImputationKernel, df_name: str, root_di
                 ax.legend(**legend_kwargs)
                 
         # Adjust layout and save
-        fig.tight_layout()
+        # fig.tight_layout()
+        # fig.subplots_adjust(bottom=0.2, left=0.2)  # Optional, depending on overflow
         fig.savefig(
-            os.path.join(local_save_dir, filename),
+            os.path.join(local_save_dir, filename + ".svg"),
             format='svg',
             bbox_inches='tight',
-            pad_inches=0
+            pad_inches=0.1
         )
         plt.close(fig)
-
+    
     if one_plot:
         # Generate combined plot
         fig = kernel.plot_imputed_distributions(variables=column_names)
-        _process_figure(fig, "Combined_Distributions.svg")
+        _process_figure(fig, "Combined_Distributions")
         # Generate individual plots per feature
     else:
         for feature in column_names:
             fig = kernel.plot_imputed_distributions(variables=[feature])
-            _process_figure(fig, f"{feature}.svg")
+            feature_save_name = sanitize_filename(feature)
+            _process_figure(fig, feature_save_name)
 
-    print("Imputed distributions saved successfully.")
+    print("\tImputed distributions saved successfully.")
 
 
 def run_mice_pipeline(df_path_or_dir: str, save_datasets_dir: str, save_metrics_dir: str, resulting_datasets: int=1, iterations: int=20, random_state: int=101):