SuperModelingFactory 0.2.0__py3-none-any.whl

Modeling_Tool/WOE/WOE_Monotone_Binner.pyi

@@ -0,0 +1,71 @@
+# =============================================================================
+# Modeling_Tool.WOE.WOE_Monotone_Binner
+# -----------------------------------------------------------------------------
+# Copyright (c) 2026 Kyle Sun <github.com/Kyle-J-Sun>. All rights reserved.
+# SuperModelingFactory — Licensed under the Business Source License 1.1.
+#
+# This stub describes the public API of a closed-source module compiled to a
+# native extension (.so / .pyd). The original source is not distributed.
+# Production / commercial use requires a separate commercial license.
+#
+# FINGERPRINT: SMF-WOEMONOTONEB-b02e5879
+#   (Unique trace marker. Do not remove or alter — used for plagiarism
+#    detection across the public internet.)
+# =============================================================================
+
+from __future__ import annotations
+import logging
+import io
+import os
+import math
+import warnings
+import textwrap
+import tempfile
+from typing import List, Optional, Dict, Any, Union
+import copy
+from concurrent.futures import ProcessPoolExecutor, as_completed
+import numpy as np
+import pandas as pd
+import matplotlib
+import matplotlib.pyplot as plt
+import matplotlib.ticker as mticker
+_SPECIAL_BIN_PREFIX: object
+_CATE_GROUP_SEP: object
+
+class MonotoneWOEBinner:
+    def __init__(self, feature_cols: List[str], target_col: str, n_init_bins: int = 20, min_bin_size: float = 0.03, min_n_bins: int = 2, eps: float = 1e-06, missing_woe: float = 0.0, special_values: Optional[List] = None, cate_feats: Optional[List[str]] = None, bin_label_decimals: Optional[int] = None): ...
+    def _split_special(self, df: pd.DataFrame, feat: str): ...
+    def _cat_to_bin_map(vr: Dict) -> Dict: ...
+    def _split_special_for_plot(self, df: pd.DataFrame, feat: str, vr: Dict): ...
+    def _assign_normal_bins(self, sub: pd.DataFrame, feat: str, vr: Dict, fitted_edges: list) -> pd.Series: ...
+    def _compute_woe_single_bin(self, sub: pd.DataFrame, total_bad: float, total_good: float) -> Dict[str, float]: ...
+    def _compute_woe_table(self, df: pd.DataFrame, feat: str, edges: list) -> tuple: ...
+    def _compute_sv_table(self, sv_groups: Dict, total_bad: float, total_good: float) -> pd.DataFrame: ...
+    def _is_monotone(woe_values: np.ndarray) -> bool: ...
+    def _chi2_merge_one(self, df_normal: pd.DataFrame, feat: str, edges: list, chi2_p: float, chi2_init_size: int) -> list: ...
+    def _greedy_fit_one(self, df: pd.DataFrame, feat: str, chi2_binning: bool = False, chi2_p: float = 0.99, chi2_init_size: int = 1000) -> Dict[str, Any]: ...
+    def _sort_categories(cats: list) -> list: ...
+    def _categorical_fit_one(self, df: pd.DataFrame, feat: str) -> Dict[str, Any]: ...
+    def fit(self, df: pd.DataFrame, chi2_binning: bool = False, chi2_p: float = 0.99, chi2_init_size: int = 1000, n_jobs: int = 1) -> 'MonotoneWOEBinner': ...
+    def _check_fitted(self): ...
+    def refine_chi2(self, df: pd.DataFrame, features: Optional[List[str]] = None, chi2_p: float = 0.99, chi2_init_size: int = 1000, n_jobs: int = 1) -> 'MonotoneWOEBinner': ...
+    def _dtree_edges(df_normal: pd.DataFrame, feat: str, target_col: str, max_bins: int, min_samples_leaf) -> list: ...
+    def _monotone_merge_edges(df_normal: pd.DataFrame, feat: str, target_col: str, edges: list, eps: float) -> list: ...
+    def refine_dtree(self, df: pd.DataFrame, features: Optional[List[str]] = None, max_bins: int = 6, min_samples_leaf: float = 0.05, monotone: bool = True, n_jobs: int = 1) -> 'MonotoneWOEBinner': ...
+    def _cluster_cate_one(self, vr: Dict, max_bins: int, min_bin_size: float, badrate_tol: Optional[float]) -> Optional[Dict[str, Any]]: ...
+    def refine_cate(self, features: Optional[List[str]] = None, max_bins: int = 5, min_bin_size: float = 0.0, badrate_tol: Optional[float] = None) -> 'MonotoneWOEBinner': ...
+    def _bin_label(edges: list, bin_idx: int, n_bins: int, decimals: Optional[int] = None) -> str: ...
+    def get_final_bins(self) -> Dict[str, pd.DataFrame]: ...
+    def get_bin_edges(self) -> Dict[str, List[float]]: ...
+    def load_woe_bins(self, bins_dict: dict) -> 'MonotoneWOEBinner': ...
+    def _make_bin_labels(edges: List[float], n_bins: int, decimals: Optional[int] = None) -> List[str]: ...
+    def _reconstruct_edges(bin_labels: List[str]) -> List[float]: ...
+    def _looks_like_interval(label: str) -> bool: ...
+    def _infer_cat_value(label): ...
+    def apply_woe(self, data: pd.DataFrame, suffix: str = '_woe', inplace: bool = False) -> pd.DataFrame: ...
+    def export_woe_report(self, report_path: str) -> None: ...
+    def _render_woe_chart(self, feat: str, normal_df: pd.DataFrame, sv_df: pd.DataFrame, vr: Dict, dpi: int = 120, figsize: tuple = (9, 4.5)) -> io.BytesIO: ...
+    def plot_woe_graph(self, graph_path: str, group_name: Optional[str] = None, _df_for_group: Optional[pd.DataFrame] = None, dpi: int = 150, figsize: tuple = (9, 6), bar_mode: str = 'clustered') -> None: ...
+    def _plot_feat_small_multiples(self, feat, normal_df, sv_df, n_normal, n_sv, n_total, x_normal, x_sv, x_all, group_name, _df_for_group, graph_path, dpi, figsize, GOOD_COLOR, BAD_COLOR, SV_GOOD, SV_BAD, SV_WOE): ...
+    def iv_summary(self) -> pd.DataFrame: ...
+    def __repr__(self) -> str: ...