hossam 0.4.4__py3-none-any.whl → 0.4.5__py3-none-any.whl

hossam/hs_prep.py

@@ -5,6 +5,7 @@
 import joblib
 import numpy as np
 from itertools import combinations
+from typing import Any
 
 import pandas as pd
 import jenkspy
@@ -19,7 +20,7 @@ from .hs_util import pretty_table
 # 연속형 변수를 표준정규화(Z-score)로 변환한다
 # ===================================================================
 def standard_scaler(
-    data: any, yname: str | None = None, save_path: str | None = None, load_path: str | None = None
+    data: Any, yname: str | None = None, save_path: str | None = None, load_path: str | None = None
 ) -> DataFrame:
     """연속형 변수에 대해 Standard Scaling을 수행한다.
 
@@ -54,7 +55,7 @@ def standard_scaler(
         sdata = scaler.transform(arr) if load_path else scaler.fit_transform(arr)
         if save_path:
             joblib.dump(value=scaler, filename=save_path)
-        return sdata
+        return sdata # type: ignore
 
     df = data.copy()
 
@@ -90,7 +91,7 @@ def standard_scaler(
 # 연속형 변수를 0부터 1 사이의 값으로 정규화한다
 # ===================================================================
 def minmax_scaler(
-    data: any, yname: str | None = None, save_path: str | None = None, load_path: str | None = None
+    data: Any, yname: str | None = None, save_path: str | None = None, load_path: str | None = None
 ) -> DataFrame:
     """연속형 변수에 대해 MinMax Scaling을 수행한다.
 
@@ -123,7 +124,7 @@ def minmax_scaler(
         sdata = scaler.transform(arr) if load_path else scaler.fit_transform(arr)
         if save_path:
             joblib.dump(scaler, save_path)
-        return sdata
+        return sdata # type: ignore
 
     df = data.copy()
 
@@ -158,7 +159,7 @@ def minmax_scaler(
 # ===================================================================
 # 지정된 컬럼들을 범주형 데이터로 설정한다
 # ===================================================================
-def set_category(data: DataFrame, *args: str, columns: list = None) -> DataFrame:
+def set_category(data: DataFrame, *args: str, columns: list | None = None) -> DataFrame:
     """카테고리 데이터를 설정한다.
 
     Args:
@@ -173,7 +174,7 @@ def set_category(data: DataFrame, *args: str, columns: list = None) -> DataFrame
     if columns is not None:
         if args:
             raise ValueError("args와 columns 인자는 중복 사용할 수 없습니다.")
-        args = columns
+        args = columns # type: ignore
 
     df = data.copy()
 
@@ -226,7 +227,7 @@ def unmelt(
 # ===================================================================
 # 지정된 변수의 이상치 테이블로 반환한다
 # ===================================================================
-def outlier_table(data: DataFrame, *fields: str, columns: list = None) -> DataFrame:
+def outlier_table(data: DataFrame, *fields: str, columns: list | None = None) -> DataFrame:
     """수치형 컬럼에 대한 사분위수 및 IQR 기반 이상치 경계를 계산한다.
 
     전달된 `fields`가 없으면 데이터프레임의 모든 수치형 컬럼을 대상으로 한다.
@@ -246,7 +247,7 @@ def outlier_table(data: DataFrame, *fields: str, columns: list = None) -> DataFr
     """
     # columns 인자가 있으면 args보다 우선한다.
     if columns is not None:
-        if args:
+        if args: # type: ignore
             raise ValueError("args와 columns 인자는 중복 사용할 수 없습니다.")
         args = columns
 
@@ -286,7 +287,7 @@ def outlier_table(data: DataFrame, *fields: str, columns: list = None) -> DataFr
 # ===================================================================
 # 이상치를 대체값(NaN, 0) 또는 중앙값으로 교체한다
 # ===================================================================
-def replace_outliner(data: DataFrame, method: str = "nan", *fields: str, columns: list = None) -> DataFrame:
+def replace_outliner(data: DataFrame, method: str = "nan", *fields: str, columns: list | None = None) -> DataFrame:
     """이상치 경계값을 넘어가는 데이터를 경계값으로 대체한다.
 
     Args:
@@ -305,7 +306,7 @@ def replace_outliner(data: DataFrame, method: str = "nan", *fields: str, columns
     """
     # columns 인자가 있으면 args보다 우선한다.
     if columns is not None:
-        if args:
+        if args: # type: ignore
             raise ValueError("args와 columns 인자는 중복 사용할 수 없습니다.")
         args = columns
 
@@ -354,7 +355,7 @@ def replace_outliner(data: DataFrame, method: str = "nan", *fields: str, columns
 # ===================================================================
 # 중빈 이상치를 제거한 연처리된 데이터프레임을 반환한다
 # ===================================================================
-def drop_outliner(data: DataFrame, *fields: str, columns: list = None) -> DataFrame:
+def drop_outliner(data: DataFrame, *fields: str, columns: list | None = None) -> DataFrame:
     """이상치를 결측치로 변환한 후 모두 삭제한다.
 
     Args:
@@ -367,7 +368,7 @@ def drop_outliner(data: DataFrame, *fields: str, columns: list = None) -> DataFr
     """
     # columns 인자가 있으면 args보다 우선한다.
     if columns is not None:
-        if args:
+        if args: # type: ignore
             raise ValueError("args와 columns 인자는 중복 사용할 수 없습니다.")
         args = columns
 
@@ -378,7 +379,7 @@ def drop_outliner(data: DataFrame, *fields: str, columns: list = None) -> DataFr
 # ===================================================================
 # 범주 변수를 더미 변수(One-Hot 인코딩)로 변환한다
 # ===================================================================
-def get_dummies(data: DataFrame, *args: str, columns: list = None, drop_first: bool = True, dtype: str = "int") -> DataFrame:
+def get_dummies(data: DataFrame, *args: str, columns: list | None = None, drop_first: bool = True, dtype: str = "int") -> DataFrame:
     """명목형 변수를 더미 변수로 변환한다.
 
     컬럼명을 지정하면 그 컬럼들만 더미 변수로 변환하고,
@@ -409,7 +410,7 @@ def get_dummies(data: DataFrame, *args: str, columns: list = None, drop_first: b
     if columns is not None:
         if args:
             raise ValueError("args와 columns 인자는 중복 사용할 수 없습니다.")
-        args = columns
+        args = columns # type: ignore
 
     if not args:
         # args가 없으면 숫자 타입이 아닌 모든 컬럼 자동 선택
@@ -417,13 +418,13 @@ def get_dummies(data: DataFrame, *args: str, columns: list = None, drop_first: b
         for f in data.columns:
             if not pd.api.types.is_numeric_dtype(data[f]):
                 cols_to_convert.append(f)
-        args = cols_to_convert
+        args = cols_to_convert # type: ignore
     else:
         # args가 있으면 그 컬럼들만 사용 (존재 여부 확인)
-        args = [c for c in args if c in data.columns]
+        args = [c for c in args if c in data.columns] # type: ignore
 
     # pandas.get_dummies 사용 (재귀 문제 없음)
-    return pd.get_dummies(data, columns=args, drop_first=drop_first, dtype=dtype) if args else data.copy()
+    return pd.get_dummies(data, columns=args, drop_first=drop_first, dtype=dtype) if args else data.copy() # type: ignore
 
 
 # ===================================================================
@@ -630,7 +631,7 @@ def bin_continuous(
         if apply_labels:
             # 숫자 인덱스 사용 (0, 1, 2, ...)
             numeric_labels = list(range(len(edges) - 1))
-            df[new_col] = pd.cut(series, bins=edges, labels=numeric_labels, include_lowest=True, ordered=False)
+            df[new_col] = pd.cut(series, bins=edges, labels=numeric_labels, include_lowest=True, ordered=False) # type: ignore
         else:
             # 문자 레이블 적용
             if labels is None:
@@ -645,9 +646,9 @@ def bin_continuous(
                     except:
                         pass
                     auto_labels.append(f"{left}~{right}")
-                df[new_col] = pd.cut(series, bins=edges, labels=auto_labels, include_lowest=True, ordered=False)
+                df[new_col] = pd.cut(series, bins=edges, labels=auto_labels, include_lowest=True, ordered=False) # type: ignore
             else:
-                df[new_col] = pd.cut(series, bins=edges, labels=labels, include_lowest=True, ordered=False)
+                df[new_col] = pd.cut(series, bins=edges, labels=labels, include_lowest=True, ordered=False) # type: ignore
 
         df[new_col] = df[new_col].astype("category")
         return df
@@ -671,26 +672,24 @@ def bin_continuous(
             n_bins = len(edges) - 1
             if apply_labels:
                 numeric_labels = list(range(n_bins))
-                df[new_col] = pd.cut(series, bins=edges, labels=numeric_labels, include_lowest=True, ordered=False)
+                df[new_col] = pd.cut(series, bins=edges, labels=numeric_labels, include_lowest=True, ordered=False) # type: ignore
             else:
                 if labels is None:
                     position_labels = [f"Q{i+1}" for i in range(n_bins)]
-                    df[new_col] = pd.cut(
-                        series, bins=edges, labels=position_labels, include_lowest=True, ordered=False
-                    )
+                    df[new_col] = pd.cut(series, bins=edges, labels=position_labels, include_lowest=True, ordered=False) # type: ignore
                 else:
-                    df[new_col] = pd.cut(series, bins=edges, labels=labels, include_lowest=True, ordered=False)
+                    df[new_col] = pd.cut(series, bins=edges, labels=labels, include_lowest=True, ordered=False) # type: ignore
         df[new_col] = df[new_col].astype("category")
         return df
 
     # 자연 구간화 (Jenks) - 의존성 없으면 분위수로 폴백
     if method_key in {"natural_breaks", "natural", "jenks"}:
         k = bins if isinstance(bins, int) and bins > 1 else 5
-        series_nonnull = series.dropna()
+        series_nonnull = series.dropna() # type: ignore
         k = min(k, max(2, series_nonnull.nunique()))
         edges = None
         try:
-            edges = jenkspy.jenks_breaks(series_nonnull.to_list(), nb_class=k)
+            edges = jenkspy.jenks_breaks(series_nonnull.to_list(), nb_class=k) # type: ignore
             edges[0] = -np.inf
             edges[-1] = np.inf
         except Exception:
@@ -730,7 +729,7 @@ def bin_continuous(
             if apply_labels:
                 # 숫자 인덱스 사용
                 numeric_labels = list(range(len(cut_edges) - 1))
-                df[new_col] = pd.cut(series, bins=cut_edges, labels=numeric_labels, include_lowest=True, ordered=False)
+                df[new_col] = pd.cut(series, bins=cut_edges, labels=numeric_labels, include_lowest=True, ordered=False) # type: ignore
             else:
                 if labels is None:
                     auto_labels = []
@@ -744,9 +743,9 @@ def bin_continuous(
                         except:
                             pass
                         auto_labels.append(f"{left}~{right}")
-                    df[new_col] = pd.cut(series, bins=cut_edges, labels=auto_labels, include_lowest=True, ordered=False)
+                    df[new_col] = pd.cut(series, bins=cut_edges, labels=auto_labels, include_lowest=True, ordered=False) # type: ignore
                 else:
-                    df[new_col] = pd.cut(series, bins=cut_edges, labels=labels, include_lowest=True, ordered=False)
+                    df[new_col] = pd.cut(series, bins=cut_edges, labels=labels, include_lowest=True, ordered=False) # type: ignore
             df[new_col] = df[new_col].astype("category")
         return df
 

hossam/hs_stats.py

@@ -1,7 +1,7 @@
 # -*- coding: utf-8 -*-
 
 from __future__ import annotations
-from typing import overload, Tuple, Literal, Union
+from typing import overload, Tuple, Literal, Union, Any
 
 # -------------------------------------------------------------
 import numpy as np
@@ -24,9 +24,9 @@ from scipy.stats import (
     normaltest,
     bartlett,
     levene,
-    ttest_1samp,
+    ttest_1samp,    # type: ignore
     ttest_ind as scipy_ttest_ind,
-    ttest_rel,
+    ttest_rel,      # type: ignore
     wilcoxon,
     pearsonr,
     spearmanr,
@@ -375,29 +375,29 @@ def describe(data: DataFrame, *fields: str, columns: list | None = None):
         outlier_rate = (outlier_count / len(data)) * 100
 
         # 분포 특성 판정 (왜도 기준)
-        abs_skew = abs(skew)
-        if abs_skew < 0.5:
+        abs_skew = abs(skew)    # type: ignore
+        if abs_skew < 0.5:      # type: ignore
             dist = "거의 대칭"
-        elif abs_skew < 1.0:
-            if skew > 0:
+        elif abs_skew < 1.0:    # type: ignore
+            if skew > 0:        # type: ignore
                 dist = "약한 우측 꼬리"
             else:
                 dist = "약한 좌측 꼬리"
-        elif abs_skew < 2.0:
-            if skew > 0:
+        elif abs_skew < 2.0:    # type: ignore
+            if skew > 0:        # type: ignore
                 dist = "중간 우측 꼬리"
             else:
                 dist = "중간 좌측 꼬리"
         else:
-            if skew > 0:
+            if skew > 0:        # type: ignore
                 dist = "극단 우측 꼬리"
             else:
                 dist = "극단 좌측 꼬리"
 
         # 로그변환 필요성 판정
-        if abs_skew < 0.5:
+        if abs_skew < 0.5:      # type: ignore
             log_need = "낮음"
-        elif abs_skew < 1.0:
+        elif abs_skew < 1.0:    # type: ignore
             log_need = "중간"
         else:
             log_need = "높음"
@@ -473,7 +473,7 @@ def category_describe(data: DataFrame, *fields: str):
     """
     if not fields:
         # 명목형(범주형) 컬럼 선택: object, category, bool 타입
-        fields = data.select_dtypes(include=['object', 'category', 'bool']).columns
+        fields = data.select_dtypes(include=['object', 'category', 'bool']).columns # type: ignore
 
     result = []
     summary = []
@@ -730,7 +730,7 @@ def equal_var_test(data: DataFrame, columns: list | str | None = None, normal_di
         normality_result = normal_test(data[numeric_cols], method="n")
         # 모든 컬럼이 정규분포를 따르는지 확인
         all_normal = normality_result["is_normal"].all()
-        normal_dist = all_normal
+        normal_dist = all_normal    # type: ignore
 
     try:
         if normal_dist:
@@ -829,7 +829,7 @@ def ttest_1samp(data, mean_value: float = 0.0) -> DataFrame:
     else:
         for a in alternative:
             try:
-                s, p = ttest_1samp(col_data, mean_value, alternative=a)
+                s, p = ttest_1samp(col_data, mean_value, alternative=a) # type: ignore
 
                 itp = None
 
@@ -939,26 +939,26 @@ def ttest_ind(x, y, equal_var: bool | None = None) -> DataFrame:
 
     for a in alternative:
         try:
-            s, p = scipy_ttest_ind(x_data, y_data, equal_var=equal_var, alternative=a)
+            s, p = scipy_ttest_ind(x_data, y_data, equal_var=equal_var, alternative=a)  # type: ignore
             n = "t-test_ind" if equal_var else "Welch's t-test"
 
             # 검정 결과 해석
             itp = None
 
             if a == "two-sided":
-                itp = fmt.format("==" if p > 0.05 else "!=")
+                itp = fmt.format("==" if p > 0.05 else "!=")    # type: ignore
             elif a == "less":
-                itp = fmt.format(">=" if p > 0.05 else "<")
+                itp = fmt.format(">=" if p > 0.05 else "<")     # type: ignore
             else:
-                itp = fmt.format("<=" if p > 0.05 else ">")
+                itp = fmt.format("<=" if p > 0.05 else ">")     # type: ignore
 
             result.append({
                 "test": n,
                 "alternative": a,
-                "statistic": round(s, 3),
-                "p-value": round(p, 4),
-                "H0": p > 0.05,
-                "H1": p <= 0.05,
+                "statistic": round(s, 3),   # type: ignore
+                "p-value": round(p, 4),     # type: ignore
+                "H0": p > 0.05,             # type: ignore
+                "H1": p <= 0.05,            # type: ignore
                 "interpretation": itp,
                 "equal_var_checked": var_checked
             })
@@ -1068,7 +1068,7 @@ def ttest_rel(x, y, parametric: bool | None = None) -> DataFrame:
     for a in alternative:
         try:
             if parametric:
-                s, p = ttest_rel(x_data, y_data, alternative=a)
+                s, p = ttest_rel(x_data, y_data, alternative=a) # type: ignore
                 n = "t-test_paired"
             else:
                 # Wilcoxon signed-rank test (대응표본용 비모수 검정)
@@ -1078,19 +1078,19 @@ def ttest_rel(x, y, parametric: bool | None = None) -> DataFrame:
             itp = None
 
             if a == "two-sided":
-                itp = fmt.format("==" if p > 0.05 else "!=")
+                itp = fmt.format("==" if p > 0.05 else "!=")    # type: ignore
             elif a == "less":
-                itp = fmt.format(">=" if p > 0.05 else "<")
+                itp = fmt.format(">=" if p > 0.05 else "<")     # type: ignore
             else:
-                itp = fmt.format("<=" if p > 0.05 else ">")
+                itp = fmt.format("<=" if p > 0.05 else ">")     # type: ignore
 
             result.append({
                 "test": n,
                 "alternative": a,
-                "statistic": round(s, 3) if not np.isnan(s) else s,
-                "p-value": round(p, 4) if not np.isnan(p) else p,
-                "H0": p > 0.05,
-                "H1": p <= 0.05,
+                "statistic": round(s, 3) if not np.isnan(s) else s, # type: ignore
+                "p-value": round(p, 4) if not np.isnan(p) else p,   # type: ignore
+                "H0": p > 0.05,     # type: ignore
+                "H1": p <= 0.05,    # type: ignore
                 "interpretation": itp,
                 "normality_checked": var_checked
             })
@@ -1117,7 +1117,7 @@ def ttest_rel(x, y, parametric: bool | None = None) -> DataFrame:
 # ===================================================================
 def vif_filter(
     data: DataFrame,
-    yname: str = None,
+    yname: str | None = None,
     ignore: list | None = None,
     threshold: float = 10.0,
     verbose: bool = False,
@@ -1182,7 +1182,7 @@ def vif_filter(
         for i, col in enumerate(X_clean.columns, start=0):
             # exog의 첫 열은 상수항이므로 변수 인덱스는 +1
             try:
-                vifs[col] = float(variance_inflation_factor(exog.values, i + 1))
+                vifs[col] = float(variance_inflation_factor(exog.values, i + 1))# type: ignore
             except Exception:
                 # 계산 실패 시 무한대로 처리하여 우선 제거 대상으로
                 vifs[col] = float("inf")
@@ -1220,7 +1220,7 @@ def vif_filter(
 # ===================================================================
 # x, y 데이터에 대한 추세선을 구한다.
 # ===================================================================
-def trend(x: any, y: any, degree: int = 1, value_count: int = 100) -> Tuple[np.ndarray, np.ndarray]:
+def trend(x: Any, y: Any, degree: int = 1, value_count: int = 100) -> Tuple[np.ndarray, np.ndarray]:
     """x, y 데이터에 대한 추세선을 구한다.
 
     Args:
@@ -1324,7 +1324,7 @@ def ols_report(fit, data, full=False, alpha=0.05) -> Union[
     for i, col in enumerate(indi_df.columns, start=1):  # 상수항이 0이므로 1부터 시작
         try:
             with np.errstate(divide='ignore', invalid='ignore'):
-                vif_value = variance_inflation_factor(indi_df_const.values, i)
+                vif_value = variance_inflation_factor(indi_df_const.values, i)  # type: ignore
                 # inf나 매우 큰 값 처리
                 if np.isinf(vif_value) or vif_value > 1e10:
                     vif_dict[col] = np.inf
@@ -1531,11 +1531,11 @@ def ols(df: DataFrame, yname: str, report: bool | str | int = False) -> Union[
         return linear_fit
     elif report == 1 or report == 'summary':
         # 요약 리포트 (full=False)
-        pdf, rdf = ols_report(linear_fit, df, full=False, alpha=0.05)
+        pdf, rdf = ols_report(linear_fit, df, full=False, alpha=0.05)   # type: ignore
         return linear_fit, pdf, rdf
     elif report == 2 or report == 'full' or report is True:
         # 풀 리포트 (full=True)
-        pdf, rdf, result_report, model_report, variable_reports, equation_text = ols_report(linear_fit, df, full=True, alpha=0.05)
+        pdf, rdf, result_report, model_report, variable_reports, equation_text = ols_report(linear_fit, df, full=True, alpha=0.05)  # type: ignore
         return linear_fit, pdf, rdf, result_report, model_report, variable_reports, equation_text
     else:
         # 기본값: 리포트 미사용
@@ -1657,7 +1657,7 @@ def logit_report(
     vif_dict = {}
     x_const = sm.add_constant(x, has_constant="add")
     for i, col in enumerate(x.columns, start=1):  # 상수항이 0이므로 1부터 시작
-        vif_dict[col] = variance_inflation_factor(x_const.values, i)
+        vif_dict[col] = variance_inflation_factor(x_const.values, i)    # type: ignore
 
     for idx, row in tbl.iterrows():
         name = idx
@@ -1770,7 +1770,7 @@ def logit(
         DataFrame,
         str,
         str,
-        List[str]
+        list[str]
     ]
 ]:
     """로지스틱 회귀분석을 수행하고 적합 결과를 반환한다.
@@ -1838,13 +1838,13 @@ def logit(
         return logit_fit
     elif report == 1 or report == 'summary':
         # 요약 리포트 (full=False)
-        cdf, rdf = logit_report(logit_fit, df, threshold=0.5, full=False, alpha=0.05)
+        cdf, rdf = logit_report(logit_fit, df, threshold=0.5, full=False, alpha=0.05)   # type: ignore
         # 요약에서는 result_report와 variable_reports만 포함
         # 간단한 버전으로 result와 variable_reports만 생성
         return logit_fit, rdf
     elif report == 2 or report == 'full' or report is True:
         # 풀 리포트 (full=True)
-        cdf, rdf, result_report, model_report, variable_reports, cm = logit_report(logit_fit, df, threshold=0.5, full=True, alpha=0.05)
+        cdf, rdf, result_report, model_report, variable_reports, cm = logit_report(logit_fit, df, threshold=0.5, full=True, alpha=0.05) # type: ignore
         return logit_fit, cdf, rdf, result_report, model_report, variable_reports
     else:
         # 기본값: 리포트 미사용
@@ -1854,7 +1854,7 @@ def logit(
 # ===================================================================
 # 선형성 검정 (Linearity Test)
 # ===================================================================
-def ols_linearity_test(fit, power: int = 2, alpha: float = 0.05, plot: bool = False, title: str = None, save_path: str = None) -> DataFrame:
+def ols_linearity_test(fit, power: int = 2, alpha: float = 0.05, plot: bool = False, title: str | None = None, save_path: str | None = None) -> DataFrame:
     """회귀모형의 선형성을 Ramsey RESET 검정으로 평가한다.
 
     적합된 회귀모형에 대해 Ramsey RESET(Regression Specification Error Test) 검정을 수행하여
@@ -1961,7 +1961,7 @@ def ols_linearity_test(fit, power: int = 2, alpha: float = 0.05, plot: bool = Fa
 # ===================================================================
 # 정규성 검정 (Normality Test)
 # ===================================================================
-def ols_normality_test(fit, alpha: float = 0.05, plot: bool = False, title: str = None, save_path: str = None) -> DataFrame:
+def ols_normality_test(fit, alpha: float = 0.05, plot: bool = False, title: str | None = None, save_path: str | None = None) -> DataFrame:
     """회귀모형 잔차의 정규성을 검정한다.
 
     회귀모형의 잔차가 정규분포를 따르는지 Shapiro-Wilk 검정과 Jarque-Bera 검정으로 평가한다.
@@ -2029,7 +2029,7 @@ def ols_normality_test(fit, alpha: float = 0.05, plot: bool = False, title: str
     # 2. Jarque-Bera 검정 (항상 수행)
     try:
         stat_jb, p_jb = jarque_bera(residuals)
-        significant_jb = p_jb <= alpha
+        significant_jb = p_jb <= alpha  # type: ignore
 
         if significant_jb:
             interpretation_jb = f"정규성 위반 (p={p_jb:.4f} <= {alpha})"
@@ -2362,8 +2362,8 @@ def corr_pairwise(
             corr_val, pval = np.nan, np.nan
 
         # 4) 유의성, 강도
-        significant = False if np.isnan(pval) else pval <= alpha
-        abs_r = abs(corr_val) if not np.isnan(corr_val) else 0
+        significant = False if np.isnan(pval) else pval <= alpha    # type: ignore
+        abs_r = abs(corr_val) if not np.isnan(corr_val) else 0      # type: ignore
         if abs_r > 0.7:
             strength = "strong"
         elif abs_r > 0.3:
@@ -2530,13 +2530,13 @@ def oneway_anova(data: DataFrame, dv: str, between: str, alpha: float = 0.05) ->
         anova_df['significant'] = anova_df['p-unc'] <= alpha
 
     # ANOVA 결과가 유의한지 확인
-    p_unc = float(anova_df.loc[0, 'p-unc'])
+    p_unc = float(anova_df.loc[0, 'p-unc']) # type: ignore
     anova_significant = p_unc <= alpha
 
     # ANOVA 보고 문장 생성
     def _safe_get(col: str, default: float = np.nan) -> float:
         try:
-            return float(anova_df.loc[0, col]) if col in anova_df.columns else default
+            return float(anova_df.loc[0, col]) if col in anova_df.columns else default  # type: ignore
         except Exception:
             return default
 
@@ -2851,7 +2851,7 @@ def predict(fit, data: DataFrame | Series) -> DataFrame | Series | float:
 
         # Series 입력인 경우 단일 값 반환
         if is_series:
-            return float(predictions.iloc[0])
+            return float(predictions.iloc[0])   # type: ignore
 
         # DataFrame 입력인 경우
         if isinstance(data, DataFrame):
@@ -2924,8 +2924,7 @@ def corr_effect_size(data: DataFrame, dv: str, *fields: str, alpha: float = 0.05
 
     # fields가 지정되지 않으면 수치형 컬럼 중 dv 제외 모두 사용
     if not fields:
-        fields = [col for col in data.columns
-                 if is_numeric_dtype(data[col]) and col != dv]
+        fields = [col for col in data.columns if is_numeric_dtype(data[col]) and col != dv] # type: ignore
 
     # dv가 수치형인지 확인
     if not is_numeric_dtype(data[dv]):
@@ -2953,8 +2952,8 @@ def corr_effect_size(data: DataFrame, dv: str, *fields: str, alpha: float = 0.05
         normal_y_result = normal_test(data[[dv]], columns=[dv], method=method_y)
 
         # 정규성 판정 (p > alpha면 정규분포 가정)
-        normal_x = normal_x_result.loc[var, 'p-val'] > alpha if var in normal_x_result.index else False
-        normal_y = normal_y_result.loc[dv, 'p-val'] > alpha if dv in normal_y_result.index else False
+        normal_x = normal_x_result.loc[var, 'p-val'] > alpha if var in normal_x_result.index else False     # type: ignore
+        normal_y = normal_y_result.loc[dv, 'p-val'] > alpha if dv in normal_y_result.index else False   # type: ignore
 
         # Pearson (모두 정규) vs Spearman (하나라도 비정규)
         if normal_x and normal_y:
@@ -2966,8 +2965,8 @@ def corr_effect_size(data: DataFrame, dv: str, *fields: str, alpha: float = 0.05
 
         # Cohen's d 계산 (상관계수에서 효과크기로 변환)
         # d = 2*r / sqrt(1-r^2)
-        if r**2 < 1:
-            d = (2 * r) / np.sqrt(1 - r**2)
+        if r ** 2 < 1:    # type: ignore
+            d = (2 * r) / np.sqrt(1 - r ** 2) # type: ignore
         else:
             d = 0
 

hossam/hs_util.py

@@ -122,11 +122,9 @@ def pretty_table(data: DataFrame, tablefmt="simple", headers: str = "keys") -> N
         ```
     """
 
-    tabulate.WIDE_CHARS_MODE = False
+    tabulate.WIDE_CHARS_MODE = False # type: ignore
     print(
-        tabulate(
-            data, headers=headers, tablefmt=tablefmt, showindex=True, numalign="right"
-        )
+        tabulate(data, headers=headers, tablefmt=tablefmt, showindex=True, numalign="right") # type: ignore
     )
 
 
@@ -167,7 +165,7 @@ def __data_info(
 
     if info:
         print("\n✅ 테이블 정보")
-        pretty_table(data.info(), tablefmt="pretty")
+        pretty_table(data.info(), tablefmt="pretty") # type: ignore
 
         print("\n✅ 상위 5개 행")
         pretty_table(data.head(), tablefmt="pretty")
@@ -229,7 +227,7 @@ def load_data(key: str,
     elif k.endswith(".csv"):
         origin = read_csv(key)
     else:
-        origin = _load_data_remote(key, local)
+        origin = _load_data_remote(key, local) # type: ignore
 
     if origin is None:
         raise RuntimeError("Data loading failed: origin is None")

{hossam-0.4.4.dist-info → hossam-0.4.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: hossam
-Version: 0.4.4
+Version: 0.4.5
 Summary: Hossam Data Helper
 Author-email: Lee Kwang-Ho <leekh4232@gmail.com>
 License-Expression: MIT

hossam-0.4.5.dist-info/RECORD

@@ -0,0 +1,16 @@
+hossam/NotoSansKR-Regular.ttf,sha256=0SCufUQwcVWrWTu75j4Lt_V2bgBJIBXl1p8iAJJYkVY,6185516
+hossam/__init__.py,sha256=OkMeP15jt6aCy7QNXMtkO0YRVvgOQYumkb7GuVKrbcs,2712
+hossam/data_loader.py,sha256=K0-MJaVeedF5x8mSp22X2rD_CZ-T185EhoUFEqzP8Ss,6352
+hossam/hs_classroom.py,sha256=rgayol3U5PSo4rLfdbClfiAtG21bFrASaSW56PUsjus,27144
+hossam/hs_gis.py,sha256=DVmndBK-_7GMK3J1_on3ieEQk1S0MfUZ8_wlX-cDdZQ,11581
+hossam/hs_plot.py,sha256=3j9B69pl-zQM_09lTXxLKAMaDM0vwOTsUWbzcU8hCK8,86228
+hossam/hs_prep.py,sha256=kCmFxnMyFZ5tLUfoE8msbwTracajHAmruJbFj6A6eIU,38020
+hossam/hs_stats.py,sha256=uGYkEk8Rb8qMoZ5FiZ7Yg6jssLIGl_EBbmwvvSYljhQ,115780
+hossam/hs_timeserise.py,sha256=gSj3cPgOGLOZEXhfW1anXbwpoJja847ZY9F8l9piJPE,42601
+hossam/hs_util.py,sha256=xuNXC6FJSAmyAbcRAUMsigCKHXM25t3H90nFMgq7IBs,8482
+hossam/leekh.png,sha256=1PB5NQ24SDoHA5KMiBBsWpSa3iniFcwFTuGwuOsTHfI,6395
+hossam-0.4.5.dist-info/licenses/LICENSE,sha256=nIqzhlcFY_2D6QtFsYjwU7BWkafo-rUJOQpDZ-DsauI,941
+hossam-0.4.5.dist-info/METADATA,sha256=HM5qrrvaFZWAyUlhgV_BLPHAcxEZdZ4gp2p3V4X4pzo,3676
+hossam-0.4.5.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+hossam-0.4.5.dist-info/top_level.txt,sha256=_-7bwjhthHplWhywEaHIJX2yL11CQCaLjCNSBlk6wiQ,7
+hossam-0.4.5.dist-info/RECORD,,

hossam-0.4.4.dist-info/RECORD

@@ -1,16 +0,0 @@
-hossam/NotoSansKR-Regular.ttf,sha256=0SCufUQwcVWrWTu75j4Lt_V2bgBJIBXl1p8iAJJYkVY,6185516
-hossam/__init__.py,sha256=OkMeP15jt6aCy7QNXMtkO0YRVvgOQYumkb7GuVKrbcs,2712
-hossam/data_loader.py,sha256=oUIsqbHQoRiHA_1tdElDaYo1ipmUB5fYSXYMB5gLOl0,6395
-hossam/hs_classroom.py,sha256=rgayol3U5PSo4rLfdbClfiAtG21bFrASaSW56PUsjus,27144
-hossam/hs_gis.py,sha256=DLogaf5nxJBbG-d8QoH2g8UfZ1omMtmEXDYgNg8jtT0,11410
-hossam/hs_plot.py,sha256=tsJMi2q9SzHRSs25dXsHkkImW-Jk7su1M6TbKwX9koU,83887
-hossam/hs_prep.py,sha256=ocZNGzHzqgasVNLcb_LClTZaAeTYiIg4mzrixeEzBQU,37693
-hossam/hs_stats.py,sha256=LpUG8U9ybnh6qSMW2SKCSDJZTeMhLH2xH2Pj4i7U6TU,114889
-hossam/hs_timeserise.py,sha256=gSj3cPgOGLOZEXhfW1anXbwpoJja847ZY9F8l9piJPE,42601
-hossam/hs_util.py,sha256=8byLj_VR93vS__lyf0xgQKArgMy9qFm2VvZVSCxfQX0,8444
-hossam/leekh.png,sha256=1PB5NQ24SDoHA5KMiBBsWpSa3iniFcwFTuGwuOsTHfI,6395
-hossam-0.4.4.dist-info/licenses/LICENSE,sha256=nIqzhlcFY_2D6QtFsYjwU7BWkafo-rUJOQpDZ-DsauI,941
-hossam-0.4.4.dist-info/METADATA,sha256=R6qOrcnZhbTzUrRK2x9vNksDjw8rVK1DVZrbRIPSPQQ,3676
-hossam-0.4.4.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-hossam-0.4.4.dist-info/top_level.txt,sha256=_-7bwjhthHplWhywEaHIJX2yL11CQCaLjCNSBlk6wiQ,7
-hossam-0.4.4.dist-info/RECORD,,