SuperModelingFactory 0.7.2__tar.gz → 0.8.1__tar.gz

{supermodelingfactory-0.7.2 → supermodelingfactory-0.8.1}/Modeling_Tool/Core/Parallel_Engine.py

@@ -189,9 +189,15 @@ class ParallelApplyEngine:
         func_args: tuple[Any, ...],
         func_kwargs: dict[str, Any],
     ) -> None:
+        # joblib < 1.6 vendors cloudpickle; joblib >= 1.6 dropped the copy and depends on
+        # the cloudpickle package. Resolve the serializer outside the check below so an
+        # import problem is never reported as a non-serializable callable.
         try:
             from joblib.externals import cloudpickle
+        except ImportError:
+            import cloudpickle
 
+        try:
             cloudpickle.dumps((func, func_args, func_kwargs))
         except Exception as exc:
             raise TypeError(

{supermodelingfactory-0.7.2 → supermodelingfactory-0.8.1}/Modeling_Tool/Feature/Feature_Screen.py

@@ -51,6 +51,10 @@ _MONOTONE_INIT_KEYS = frozenset({
     "direction_conflict_policy",
     "missing_bin_strategy",
     "refine_min_n_bins_policy",
+    "sv_min_bin_size",
+    "sv_small_policy",
+    "sv_woe_smoothing",
+    "sv_smoothing_alpha",
 })
 _MONOTONE_FIT_KEYS = frozenset({"chi2_binning", "chi2_p", "chi2_init_size", "n_jobs"})
 

{supermodelingfactory-0.7.2 → supermodelingfactory-0.8.1}/Modeling_Tool/Pipeline/credit_model.py

@@ -62,11 +62,30 @@ class CreditModelPipelineConfig:
     woe_engine: str = "equal_freq"
     woe_fit_query: str | None = None
     extra_eval_datasets: dict[str, pd.DataFrame] | None = None
+    # sv_* govern special-value (SV) WOE bins only; the defaults below reproduce
+    # pre-0.8.0 behavior bit-for-bit. They reach WOE_Master via fit(**woe_params)
+    # and MonotoneWOEBinner via __init__(**monotone_woe_params).
     woe_params: dict[str, Any] = field(
-        default_factory=lambda: {"nbins": 10, "equal_freq": True, "min_bin_prop": 0.05}
+        default_factory=lambda: {
+            "nbins": 10,
+            "equal_freq": True,
+            "min_bin_prop": 0.05,
+            "sv_min_bin_size": 0.0,
+            "sv_small_policy": "keep",
+            "sv_woe_smoothing": "none",
+            "sv_smoothing_alpha": 0.0,
+        }
     )
     monotone_woe_params: dict[str, Any] = field(
-        default_factory=lambda: {"n_init_bins": 20, "min_bin_size": 0.03, "min_n_bins": 2}
+        default_factory=lambda: {
+            "n_init_bins": 20,
+            "min_bin_size": 0.03,
+            "min_n_bins": 2,
+            "sv_min_bin_size": 0.0,
+            "sv_small_policy": "keep",
+            "sv_woe_smoothing": "none",
+            "sv_smoothing_alpha": 0.0,
+        }
     )
 
     train_models: list[str] = field(default_factory=lambda: ["lr", "lgb", "xgb", "cat"])

{supermodelingfactory-0.7.2 → supermodelingfactory-0.8.1}/Modeling_Tool/Pipeline/feature_validation.py

@@ -66,11 +66,31 @@ class FeatureValidationPipelineConfig:
     woe_enabled: bool = True
     woe_fit_query: str | None = None
     woe_engine: str = "monotone"
+    # sv_* govern special-value (SV) WOE bins only; the defaults below reproduce
+    # pre-0.8.0 behavior bit-for-bit. Monotone-side sv_* keys only survive because
+    # they are listed in _MONOTONE_INIT_KEYS below — unlisted keys are dropped
+    # silently, so the two lists must be kept in sync.
     woe_params: dict[str, Any] = field(
-        default_factory=lambda: {"nbins": 10, "equal_freq": True, "min_bin_prop": 0.05}
+        default_factory=lambda: {
+            "nbins": 10,
+            "equal_freq": True,
+            "min_bin_prop": 0.05,
+            "sv_min_bin_size": 0.0,
+            "sv_small_policy": "keep",
+            "sv_woe_smoothing": "none",
+            "sv_smoothing_alpha": 0.0,
+        }
     )
     monotone_woe_params: dict[str, Any] = field(
-        default_factory=lambda: {"n_init_bins": 20, "min_bin_size": 0.03, "min_n_bins": 2}
+        default_factory=lambda: {
+            "n_init_bins": 20,
+            "min_bin_size": 0.03,
+            "min_n_bins": 2,
+            "sv_min_bin_size": 0.0,
+            "sv_small_policy": "keep",
+            "sv_woe_smoothing": "none",
+            "sv_smoothing_alpha": 0.0,
+        }
     )
     categorical_features: list[str] | None = None
     monotone_refine_cate_enabled: bool = False
@@ -170,6 +190,10 @@ class FeatureValidationPipeline:
         "direction_conflict_policy",
         "missing_bin_strategy",
         "refine_min_n_bins_policy",
+        "sv_min_bin_size",
+        "sv_small_policy",
+        "sv_woe_smoothing",
+        "sv_smoothing_alpha",
     }
     _MONOTONE_FIT_KEYS = {"chi2_binning", "chi2_p", "chi2_init_size", "n_jobs"}
 

{supermodelingfactory-0.7.2 → supermodelingfactory-0.8.1}/Modeling_Tool/WOE/WOE_Master.py

@@ -289,7 +289,9 @@ class WOE_Master(object):
         self.varlist = varlist
 
     def fit(self, nbins=10, equal_freq=True, tree_binning_seed=None, chi2_config=None,
-            precision=5, min_bin_prop=0.05, include_missing=True, fillna=None, spec_values=[]):
+            precision=5, min_bin_prop=0.05, include_missing=True, fillna=None, spec_values=[],
+            sv_min_bin_size=0.0, sv_small_policy="keep",
+            sv_woe_smoothing="none", sv_smoothing_alpha=0.0):
         """Fit WOE binning for variables in varlist.
 
         Args:
@@ -302,6 +304,11 @@ class WOE_Master(object):
             include_missing: bool, include missing value bin (default True)
             fillna: int/float, value to fill missing data
             spec_values: list, special values to handle
+            sv_min_bin_size: float, low-frequency special-value bin threshold as a
+                share of all samples; 0.0 disables the fallback (legacy behaviour)
+            sv_small_policy: str, 'keep' (default) / 'neutral' / 'merge_missing'
+            sv_woe_smoothing: str, 'none' (default) / 'laplace'
+            sv_smoothing_alpha: float, Laplace smoothing strength alpha (pseudo-counts)
         Returns:
             None, updates self.woe_dict attribute
         """
@@ -323,6 +330,10 @@ class WOE_Master(object):
                                     ascending=True,
                                     fillna=fillna,
                                     spec_values=spec_values,
+                                    sv_min_bin_size=sv_min_bin_size,
+                                    sv_small_policy=sv_small_policy,
+                                    sv_woe_smoothing=sv_woe_smoothing,
+                                    sv_smoothing_alpha=sv_smoothing_alpha,
                                     drop_bin_info=True,
                                     ret_woe_table=True)
             woe_table = woe_res[-1]
@@ -381,7 +392,9 @@ class WOE_Master(object):
         return data_woe
 
     def update_woe(self, varlist, nbins=10, equal_freq=True, tree_binning_seed=None, chi2_config=None,
-                   precision=5, min_bin_prop=0.05, include_missing=True, fillna=None, spec_values=[]):
+                   precision=5, min_bin_prop=0.05, include_missing=True, fillna=None, spec_values=[],
+                   sv_min_bin_size=0.0, sv_small_policy="keep",
+                   sv_woe_smoothing="none", sv_smoothing_alpha=0.0):
         """Update WOE binning for specified variables.
 
         Args:
@@ -395,6 +408,11 @@ class WOE_Master(object):
             include_missing: bool, include missing value bin (default True)
             fillna: int/float, value to fill missing data
             spec_values: list, special values to handle
+            sv_min_bin_size: float, low-frequency special-value bin threshold as a
+                share of all samples; 0.0 disables the fallback (legacy behaviour)
+            sv_small_policy: str, 'keep' (default) / 'neutral' / 'merge_missing'
+            sv_woe_smoothing: str, 'none' (default) / 'laplace'
+            sv_smoothing_alpha: float, Laplace smoothing strength alpha (pseudo-counts)
         Returns:
             None, updates self.woe_dict attribute
         """
@@ -417,6 +435,10 @@ class WOE_Master(object):
                                     ascending=True,
                                     fillna=fillna,
                                     spec_values=spec_values,
+                                    sv_min_bin_size=sv_min_bin_size,
+                                    sv_small_policy=sv_small_policy,
+                                    sv_woe_smoothing=sv_woe_smoothing,
+                                    sv_smoothing_alpha=sv_smoothing_alpha,
                                     drop_bin_info=True,
                                     ret_woe_table=True)
             woe_table = woe_res[-1]

{supermodelingfactory-0.7.2 → supermodelingfactory-0.8.1}/Modeling_Tool/WOE/WOE_Master.pyi

@@ -27,11 +27,11 @@ class WOE_Master(object):
     def __init__(self, train_data, varlist, dep = None, graph_save_dir = '', woe_suffix = '_woe', missing_ref_value = ..., remove_exist_dir = False): ...
     def remove_folder(file_path): ...
     def load_mapping_table(self, mapping_table_csv): ...
-    def fit(self, nbins = 10, equal_freq = True, tree_binning_seed = None, chi2_config = None, precision = 5, min_bin_prop = 0.05, include_missing = True, fillna = None, spec_values = []): ...
+    def fit(self, nbins = 10, equal_freq = True, tree_binning_seed = None, chi2_config = None, precision = 5, min_bin_prop = 0.05, include_missing = True, fillna = None, spec_values = [], sv_min_bin_size = 0.0, sv_small_policy = 'keep', sv_woe_smoothing = 'none', sv_smoothing_alpha = 0.0): ...
     def get_mapping_table(self): ...
     def save_mapping_table(self, save_dir): ...
     def transform(self, data = None, varlist = None): ...
-    def update_woe(self, varlist, nbins = 10, equal_freq = True, tree_binning_seed = None, chi2_config = None, precision = 5, min_bin_prop = 0.05, include_missing = True, fillna = None, spec_values = []): ...
+    def update_woe(self, varlist, nbins = 10, equal_freq = True, tree_binning_seed = None, chi2_config = None, precision = 5, min_bin_prop = 0.05, include_missing = True, fillna = None, spec_values = [], sv_min_bin_size = 0.0, sv_small_policy = 'keep', sv_woe_smoothing = 'none', sv_smoothing_alpha = 0.0): ...
     def plot_bivar_graph(self, data, group = None, dirname = None, varlist = None): ...
 def load_mapping_table(mapping_table_csv): ...
 def get_mapping_table(woe_dict): ...