dragon-ml-toolbox 20.0.0__py3-none-any.whl → 20.0.1__py3-none-any.whl

{dragon_ml_toolbox-20.0.0.dist-info → dragon_ml_toolbox-20.0.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 20.0.0
+Version: 20.0.1
 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

{dragon_ml_toolbox-20.0.0.dist-info → dragon_ml_toolbox-20.0.1.dist-info}/RECORD

@@ -1,5 +1,5 @@
-dragon_ml_toolbox-20.0.0.dist-info/licenses/LICENSE,sha256=L35WDmmLZNTlJvxF6Vy7Uy4SYNi6rCfWUqlTHpoRMoU,1081
-dragon_ml_toolbox-20.0.0.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=0-HBRMMgKuwtGy6nMJZvIn1fLxhx_ksyyVB2U_iyYZU,2818
+dragon_ml_toolbox-20.0.1.dist-info/licenses/LICENSE,sha256=L35WDmmLZNTlJvxF6Vy7Uy4SYNi6rCfWUqlTHpoRMoU,1081
+dragon_ml_toolbox-20.0.1.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=0-HBRMMgKuwtGy6nMJZvIn1fLxhx_ksyyVB2U_iyYZU,2818
 ml_tools/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 ml_tools/constants.py,sha256=3br5Rk9cL2IUo638eJuMOGdbGQaWssaUecYEvSeRBLM,3322
 ml_tools/ETL_cleaning/__init__.py,sha256=TytE8RKmtW4KQlkaTxpYKlJAbCu-VAc82eDdHwVD3Jo,427
@@ -21,7 +21,7 @@ ml_tools/IO_tools/__init__.py,sha256=ZeEM5bbZ5udgRXFAL51uRXzoCzPLO8TWZ4AiME7NNy0
 ml_tools/IO_tools/_imprimir.py,sha256=eN-V60xtDNFINThuRTjXknMxtbK8Ah0MWgc8l2GTXMA,250
 ml_tools/MICE/_MICE_imputation.py,sha256=N1cDwVYfoHvIZz7FLLcW-guZUo8iFKedtkfS7CU6TVE,5318
 ml_tools/MICE/__init__.py,sha256=i5N_fd3rxpEgLsKKDoLbokW0rHm-ADEg8r3gBB5426E,313
-ml_tools/MICE/_dragon_mice.py,sha256=E6LyCe7JjEvDeKJfDfDd1iKJS86pDQLYGYoajahtuyg,17736
+ml_tools/MICE/_dragon_mice.py,sha256=qEOy9Gx1QzVBvkvGR8790TkvKw8-fp06vCDGWM6j9os,17806
 ml_tools/MICE/_imprimir.py,sha256=YVhgZlUQ-NrDUVhHTK3u8s1QEbZ_jvDVF7-0FptVsxs,215
 ml_tools/ML_callbacks/__init__.py,sha256=dF37KXezy6P3VArhZbm5CI6si65GA-qVY70jvZFZYkA,427
 ml_tools/ML_callbacks/_base.py,sha256=xLVAFOhBHjqnf8a_wKgW1F-tn2u6EqV3IHXsXKTn2NE,3269
@@ -125,11 +125,11 @@ ml_tools/_core/__init__.py,sha256=m-VP0RW0tOTm9N5NI3kFNcpM7WtVgs0RK9pK3ZJRZQQ,14
 ml_tools/_core/_logger.py,sha256=xzhn_FouMDRVNwXGBGlPC9Ruq6i5uCrmNaS5jesguMU,4972
 ml_tools/_core/_schema_load_ops.py,sha256=KLs9vBzANz5ESe2wlP-C41N4VlgGil-ywcfvWKSOGss,1551
 ml_tools/_core/_script_info.py,sha256=LtFGt10gEvCnhIRMKJPi2yXkiGLcdr7lE-oIP2XGHzQ,234
-ml_tools/data_exploration/__init__.py,sha256=a4hlq6Pyc_cQjiys_2CUFd5nIvzqPc4g8asWEHJz9Es,1674
+ml_tools/data_exploration/__init__.py,sha256=w9dM6wjmxfbEXQCWGFVL_cIuLHtYVP364aQvzRwfZXY,1674
 ml_tools/data_exploration/_analysis.py,sha256=H6LryV56FFCHWjvQdkhZbtprZy6aP8EqU_hC2Cf9CLE,7832
 ml_tools/data_exploration/_cleaning.py,sha256=LpoOHOB6HVtdObZExg-B8SxZW-JUc51tblnkCFDZxKg,20846
 ml_tools/data_exploration/_features.py,sha256=wW-M8n2aLIy05DR2z4fI8wjpPjn3mOAnm9aSGYbMKwI,23363
-ml_tools/data_exploration/_imprimir.py,sha256=PkvDvQkYTQC_KnfI1gxxUxtC-XeSRePniM1TyJj8Caw,876
+ml_tools/data_exploration/_imprimir.py,sha256=0nXu60HpeJZ8s83mpVoRtdKILK3t8EHRFVk7d9vRVUo,876
 ml_tools/data_exploration/_plotting.py,sha256=zH1dPcIoAlOuww23xIoBCsQOAshPPv9OyGposOA2RvI,19883
 ml_tools/data_exploration/_schema_ops.py,sha256=PoFeHaS9dXI9gfL0SRD-8uSP4owqmbQFbtfA-HxkLnY,7108
 ml_tools/ensemble_evaluation/__init__.py,sha256=Xxx-F-_TvSVzMaocKXOo_tEXLibMJtf_YY85Ac3U0EI,483
@@ -162,7 +162,7 @@ ml_tools/plot_fonts/__init__.py,sha256=l-vSSpjZb6IeWjjgPTcNmEs7M-vbw0lqgEKD5jhtX
 ml_tools/plot_fonts/_imprimir.py,sha256=zNi6naa5eWBFfa_yV569MhUtSAL44H0xDjMcgrJSlXk,131
 ml_tools/plot_fonts/_plot_fonts.py,sha256=mfjXNT9P59ymHoTI85Q8CcvfxfK5BIFBWtTZH-hNIC4,2209
 ml_tools/schema/__init__.py,sha256=9LQtKz3OO9wm-1piUgAhCJZVZT-F-YSg5QLus9pxfgA,263
-ml_tools/schema/_feature_schema.py,sha256=QLsxBS3_CIJp4c4dknvMs7RHZl_GZDEBJQ0MxLrQo6Y,8536
+ml_tools/schema/_feature_schema.py,sha256=ICymTIL05n1qs61TvyY7rapDOJ9PlaOHi0F86N4tNlU,8547
 ml_tools/schema/_gui_schema.py,sha256=IVwN4THAdFrvh2TpV4SFd_zlzMX3eioF-w-qcSVTndE,7245
 ml_tools/schema/_imprimir.py,sha256=waNHozZmkCKKNFWSw0HFf9489FkSXogl6KuT5cn5V74,190
 ml_tools/serde/__init__.py,sha256=Gj6B8Sgf0-ad72jFXq2W_k5pXOT2iNx5Dvzwrd7Tj1U,229
@@ -172,7 +172,7 @@ ml_tools/utilities/__init__.py,sha256=pkR2HxUIlKZMDderP2awYXVIFxkU2Xt3FkJmcmuRIp
 ml_tools/utilities/_imprimir.py,sha256=sV3ASBOsTdVYvGojOTIpZYFyrnd4panS5h_4HcMzob4,432
 ml_tools/utilities/_utility_save_load.py,sha256=7skiiuYGVLVMK_nU9uLfUZw16ePvF3i9ub7G7LMyUgs,16085
 ml_tools/utilities/_utility_tools.py,sha256=bN0J9d1S0W5wNzNntBWqDsJcEAK7-1OgQg3X2fwXns0,6918
-dragon_ml_toolbox-20.0.0.dist-info/METADATA,sha256=ILeGioHn8qeLS5vaaqOs-zId8QvQxoWZcjKgHYmeuPo,7866
-dragon_ml_toolbox-20.0.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-dragon_ml_toolbox-20.0.0.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
-dragon_ml_toolbox-20.0.0.dist-info/RECORD,,
+dragon_ml_toolbox-20.0.1.dist-info/METADATA,sha256=ApSFj2vI7jdgUYtlYgjBpAXFQw9OKcd6em0ssSVZvGg,7866
+dragon_ml_toolbox-20.0.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+dragon_ml_toolbox-20.0.1.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
+dragon_ml_toolbox-20.0.1.dist-info/RECORD,,

ml_tools/MICE/_dragon_mice.py

@@ -197,7 +197,7 @@ class DragonMICE:
                  _LOGGER.error(f"Index mismatch in dataset {subname}")
                  raise ValueError()
         
-        _LOGGER.info("Schema-based MICE imputation complete.")
+        _LOGGER.info("⬅️ Schema-based MICE imputation complete.")
         
         return kernel, imputed_datasets, imputed_dataset_names
         
@@ -237,9 +237,6 @@ class DragonMICE:
                 # We pass an empty DF as 'targets' to save_imputed_datasets to prevent duplication.
                 df_input = df
                 df_targets_to_save = pd.DataFrame(index=df.index) 
-                
-                # Monitor all columns that had NaNs
-                imputed_column_names = [col for col in df.columns if df[col].isna().any()]
             else:
                 # Explicitly cast tuple to list for Pandas indexing
                 feature_cols = list(self._schema.feature_names)
@@ -253,8 +250,9 @@ class DragonMICE:
                 df_input = df[feature_cols]
                 # Drop features to get targets (more robust than explicit selection if targets vary)
                 df_targets_to_save = df.drop(columns=feature_cols)
-                
-                imputed_column_names = _get_na_column_names(df=df_input) # type: ignore
+            
+            # Monitor all columns that had NaNs
+            imputed_column_names = [col for col in df_input.columns if df_input[col].isna().any()]
 
             # Run core logic
             kernel, imputed_datasets, imputed_dataset_names = self._run_mice(df=df_input, df_name=df_name) # type: ignore
@@ -316,35 +314,41 @@ def get_convergence_diagnostic(kernel: mf.ImputationKernel, imputed_dataset_name
     
     # iterate over each imputed dataset
     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 = make_fullpath(input_path=root_path / dataset_file_dir, make=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])) # type: ignore
-                
+        # 1. Pre-calculate means for all features across all iterations
+        # Structure: {feature_name: [mean_iter_0, mean_iter_1, ...]}
+        history = {col: [] for col in column_names}
+        
+        for iteration in range(iterations_cap):
+            # Resolve dataset ONLY ONCE per iteration
+            current_imputed = kernel.complete_data(dataset=dataset_id, iteration=iteration)
+            
+            for col in column_names:
+                # Fast lookup
+                val = np.mean(current_imputed[col])
+                history[col].append(val)
+
+        # 2. Plotting loop
+        for feature_name, means_per_iteration in history.items():
             plt.figure(figsize=(10, 8))
             plt.plot(means_per_iteration, marker='o')
             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) # type: ignore
+            plt.xticks(ticks=_ticks, labels=_labels)
             plt.grid(True)
             
-            feature_save_name = sanitize_filename(feature_name)
-            feature_save_name = feature_save_name + ".svg"
+            feature_save_name = sanitize_filename(feature_name) + ".svg"
             save_path = local_save_dir / feature_save_name
             plt.savefig(save_path, bbox_inches='tight', format="svg")
             plt.close()
             
-        _LOGGER.info(f"{dataset_file_dir} process completed.")
+    _LOGGER.info(f"📉 Convergence diagnostics complete.")
 
 
 # Imputed distributions
@@ -431,5 +435,5 @@ def get_imputed_distributions(kernel: mf.ImputationKernel, df_name: str, root_di
             fig = kernel.plot_imputed_distributions(variables=[feature])
             _process_figure(fig, feature)
 
-    _LOGGER.info(f"{local_dir_name} completed.")
+    _LOGGER.info(f"📊 Imputed distributions complete.")
     

ml_tools/data_exploration/__init__.py

@@ -53,13 +53,13 @@ __all__ = [
     "split_features_targets", 
     "split_continuous_binary", 
     "split_continuous_categorical_targets",
-    "encode_categorical_features",
     "clip_outliers_single", 
     "clip_outliers_multi",
     "drop_outlier_samples",
     "plot_continuous_vs_target",
     "plot_categorical_vs_target",
     "plot_correlation_heatmap", 
+    "encode_categorical_features",
     "finalize_feature_schema",
     "apply_feature_schema",
     "match_and_filter_columns_by_regex",

ml_tools/data_exploration/_imprimir.py

@@ -12,13 +12,13 @@ _GRUPOS = [
     "split_features_targets", 
     "split_continuous_binary", 
     "split_continuous_categorical_targets",
-    "encode_categorical_features",
     "clip_outliers_single", 
     "clip_outliers_multi",
     "drop_outlier_samples",
     "plot_continuous_vs_target",
     "plot_categorical_vs_target",
     "plot_correlation_heatmap", 
+    "encode_categorical_features",
     "finalize_feature_schema",
     "apply_feature_schema",
     "match_and_filter_columns_by_regex",

ml_tools/schema/_feature_schema.py

@@ -44,7 +44,7 @@ class FeatureSchema(NamedTuple):
         Handles conversion of Tuple->List and IntKeys->StrKeys automatically.
         """
         # validate path
-        dir_path = make_fullpath(directory, enforce="directory")
+        dir_path = make_fullpath(directory, make=True, enforce="directory")
         file_path = dir_path / SchemaKeys.SCHEMA_FILENAME
         
         try: