SuperModelingFactory 0.3.2__tar.gz → 0.3.3__tar.gz

{supermodelingfactory-0.3.2 → supermodelingfactory-0.3.3}/Modeling_Tool/WOE/WOE_Monotone_Binner.py

@@ -2129,45 +2129,85 @@ class MonotoneWOEBinner:
                     # 整箱标签也登记一次（兜底；通常不会命中真实类别）
                     if "bin_label" in wt.columns:
                         cat_woe_map_str.setdefault(str(r["bin_label"]), woe_v)
-                nan_woe = sv_woe_map.get("__nan__", feat_missing_woe)
-
-                def _get_cat_woe(val):
-                    if val is None or (isinstance(val, float) and math.isnan(val)):
-                        return nan_woe
-                    if val in cat_woe_map:
-                        return cat_woe_map[val]
-                    sval = str(val)
-                    if sval in cat_woe_map_str:
-                        return cat_woe_map_str[sval]
-                    # 训练时未见过的新类别 → 中性 missing_woe
-                    return feat_missing_woe
-
-                df[woe_col] = series.apply(_get_cat_woe).astype(float)
+                nan_woe = float(sv_woe_map.get("__nan__", feat_missing_woe))
+                missing_mask = series.isna()
+                if cat_woe_map:
+                    mapped = series.map(cat_woe_map)
+                else:
+                    mapped = pd.Series(np.nan, index=series.index, dtype=float)
+
+                fallback_mask = mapped.isna() & ~missing_mask
+                if cat_woe_map_str and fallback_mask.any():
+                    mapped.loc[fallback_mask] = (
+                        series.loc[fallback_mask].astype(str).map(cat_woe_map_str)
+                    )
+
+                out = np.full(len(series), feat_missing_woe, dtype=float)
+                missing_arr = missing_mask.to_numpy()
+                if missing_arr.any():
+                    out[missing_arr] = nan_woe
+                hit_arr = mapped.notna().to_numpy() & ~missing_arr
+                if hit_arr.any():
+                    out[hit_arr] = mapped.to_numpy(dtype=float)[hit_arr]
+
+                df[woe_col] = out
                 continue
 
+
             # ── 数值特征：按 edges 做 bin 查找 ──
             edges  = [float(e) for e in vr["edges"]]
             wt_map = vr["woe_table"].set_index("bin")["woe"].to_dict()
 
-            # 逐元素赋 WOE
-            def _get_woe(val):
-                # NaN
-                if val is None or (isinstance(val, float) and math.isnan(val)):
-                    if "__nan__" in sv_woe_map:
-                        return sv_woe_map["__nan__"]
-                    return feat_missing_woe
-                # 数值特殊值
-                if val in sv_woe_map:
-                    return sv_woe_map[val]
-                # 普通值：做 bin 查找
+            out = np.full(len(series), feat_missing_woe, dtype=float)
+
+            is_missing = series.isna().to_numpy()
+            if is_missing.any():
+                out[is_missing] = float(sv_woe_map.get("__nan__", feat_missing_woe))
+
+            special_mask = np.zeros(len(series), dtype=bool)
+            for sv_val, sv_woe in sv_woe_map.items():
+                if sv_val == "__nan__":
+                    continue
+                try:
+                    mask = series.eq(sv_val).to_numpy(dtype=bool, na_value=False)
+                except TypeError:
+                    mask = series.astype(object).eq(sv_val).to_numpy(dtype=bool, na_value=False)
+                if mask.any():
+                    out[mask] = float(sv_woe)
+                    special_mask |= mask
+
+            normal_mask = ~(is_missing | special_mask)
+            if normal_mask.any():
                 if not edges:
-                    return wt_map.get(0, feat_missing_woe)
-                import bisect
-                # pd.cut right=True → bin_idx = bisect_right(edges, val)
-                bin_idx = bisect.bisect_right(edges, val)
-                return wt_map.get(bin_idx, feat_missing_woe)
+                    out[normal_mask] = float(wt_map.get(0, feat_missing_woe))
+                else:
+                    try:
+                        values_arr = series.to_numpy(dtype=float, copy=False, na_value=np.nan)
+                    except (TypeError, ValueError):
+                        values_arr = pd.to_numeric(series, errors="coerce").to_numpy(dtype=float)
+                    normal_values = values_arr[normal_mask]
+                    valid_values = ~np.isnan(normal_values)
+                    if valid_values.any():
+                        normal_pos = np.flatnonzero(normal_mask)
+                        valid_pos = normal_pos[valid_values]
+                        bin_idx = np.searchsorted(
+                            np.asarray(edges, dtype=float),
+                            normal_values[valid_values],
+                            side="right",
+                        )
+                        woe_values = np.full(len(edges) + 1, feat_missing_woe, dtype=float)
+                        for bin_key, woe_val in wt_map.items():
+                            try:
+                                bin_i = int(bin_key)
+                            except (TypeError, ValueError):
+                                continue
+                            if 0 <= bin_i < len(woe_values):
+                                woe_values[bin_i] = float(woe_val)
+                        out[valid_pos] = woe_values[bin_idx]
+
+            df[woe_col] = out.astype(float)
+            continue
 
-            df[woe_col] = series.apply(_get_woe).astype(float)
 
         return df
 

{supermodelingfactory-0.3.2 → supermodelingfactory-0.3.3}/Modeling_Tool/__init__.py

@@ -1,7 +1,7 @@
 # encoding: utf-8
 
 __author__ = "Jingkai Sun"
-__version__ = "0.3.2"
+__version__ = "0.3.3"
 
 # Core module - base data structures
 from .Core import (

{supermodelingfactory-0.3.2 → supermodelingfactory-0.3.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: SuperModelingFactory
-Version: 0.3.2
+Version: 0.3.3
 Summary: Credit risk modeling factory: WOE binning, scorecards, LightGBM, Excel reporting.
 Home-page: https://github.com/Kyle-J-Sun/SuperModelingFactory
 Author: Kyle Sun
@@ -262,7 +262,7 @@ em.close_workbook()
 
 ## 版本
 
-- **Version**: 0.3.2
+- **Version**: 0.3.3
 - **Author**: Jingkai Sun
 
 ## 许可证

{supermodelingfactory-0.3.2 → supermodelingfactory-0.3.3}/README.md

@@ -205,7 +205,7 @@ em.close_workbook()
 
 ## 版本
 
-- **Version**: 0.3.2
+- **Version**: 0.3.3
 - **Author**: Jingkai Sun
 
 ## 许可证

{supermodelingfactory-0.3.2 → supermodelingfactory-0.3.3}/SuperModelingFactory.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: SuperModelingFactory
-Version: 0.3.2
+Version: 0.3.3
 Summary: Credit risk modeling factory: WOE binning, scorecards, LightGBM, Excel reporting.
 Home-page: https://github.com/Kyle-J-Sun/SuperModelingFactory
 Author: Kyle Sun
@@ -262,7 +262,7 @@ em.close_workbook()
 
 ## 版本
 
-- **Version**: 0.3.2
+- **Version**: 0.3.3
 - **Author**: Jingkai Sun
 
 ## 许可证

{supermodelingfactory-0.3.2 → supermodelingfactory-0.3.3}/pyproject.toml

@@ -12,7 +12,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "SuperModelingFactory"
-version = "0.3.2"
+version = "0.3.3"
 description = "Credit risk modeling factory: WOE binning, scorecards, LightGBM, Excel reporting."
 readme = "README.md"
 requires-python = ">=3.10"

{supermodelingfactory-0.3.2 → supermodelingfactory-0.3.3}/setup.py

@@ -15,7 +15,7 @@ def _read(path: str) -> str:
 
 setup(
     name="SuperModelingFactory",
-    version=os.environ.get("SMF_VERSION", "0.3.2"),
+    version=os.environ.get("SMF_VERSION", "0.3.3"),
     description="Credit risk modeling factory: WOE binning, scorecards, LightGBM, Excel reporting.",
     long_description=_read("README.md"),
     long_description_content_type="text/markdown",