statslibx 0.1.4__py3-none-any.whl → 0.1.6__py3-none-any.whl

statslibx/inferential.py

@@ -4,6 +4,7 @@ import pandas as pd
 from typing import Optional, Union, Literal, List, Dict, Any
 from datetime import datetime
 from scipy import stats
+import os
 
 class InferentialStats:
     """
@@ -11,10 +12,21 @@ class InferentialStats:
     """
     
     def __init__(self, data: Union[pd.DataFrame, np.ndarray],
-                 backend: Literal['pandas', 'polars'] = 'pandas'):
+                backend: Literal['pandas', 'polars'] = 'pandas'):
         """
         Inicializar con DataFrame o array numpy
+
+        Parameters:
+        -----------
+        data : DataFrame o ndarray
+            Datos a analizar
+        backend : str
+            'pandas' o 'polars' para procesamiento
         """
+
+        if isinstance(data, str) and os.path.exists(data):
+                data = InferentialStats.from_file(data).data
+
         if isinstance(data, np.ndarray):
             if data.ndim == 1:
                 data = pd.DataFrame({'var': data})
@@ -24,11 +36,45 @@ class InferentialStats:
         self.data = data
         self.backend = backend
         self._numeric_cols = data.select_dtypes(include=[np.number]).columns.tolist()
+
+    @staticmethod
+    def from_file(path: str):
+        """
+        Carga automática de archivos y devuelve instancia de Intelligence.
+        Soporta CSV, Excel, TXT, JSON, Parquet, Feather, TSV.
+        """
+        if not os.path.exists(path):
+            raise FileNotFoundError(f"Archivo no encontrado: {path}")
+
+        ext = os.path.splitext(path)[1].lower()
+
+        if ext == ".csv":
+            df = pd.read_csv(path)
+
+        elif ext in [".xlsx", ".xls"]:
+            df = pd.read_excel(path)
+
+        elif ext in [".txt", ".tsv"]:
+            df = pd.read_table(path)
+
+        elif ext == ".json":
+            df = pd.read_json(path)
+
+        elif ext == ".parquet":
+            df = pd.read_parquet(path)
+
+        elif ext == ".feather":
+            df = pd.read_feather(path)
+
+        else:
+            raise ValueError(f"Formato no soportado: {ext}")
+
+        return InferentialStats(df)
     
     # ============= INTERVALOS DE CONFIANZA =============
     
     def confidence_interval(self, column: str, confidence: float = 0.95,
-                           statistic: Literal['mean', 'median', 'proportion'] = 'mean') -> tuple:
+                            statistic: Literal['mean', 'median', 'proportion'] = 'mean') -> tuple:
         """
         Intervalo de confianza para diferentes estadísticos
         
@@ -81,8 +127,8 @@ class InferentialStats:
     # ============= PRUEBAS DE HIPÓTESIS =============
     
     def t_test_1sample(self, column: str, popmean: float = None, 
-                       popmedian: float = None,
-                       alternative: Literal['two-sided', 'less', 'greater'] = 'two-sided') -> 'TestResult':
+                        popmedian: float = None,
+                        alternative: Literal['two-sided', 'less', 'greater'] = 'two-sided') -> 'TestResult':
         """
         Prueba t de una muestra (para media o mediana)
         
@@ -137,8 +183,8 @@ class InferentialStats:
             raise ValueError("Debe especificar popmean o popmedian")
     
     def t_test_2sample(self, column1: str, column2: str,
-                       equal_var: bool = True,
-                       alternative: Literal['two-sided', 'less', 'greater'] = 'two-sided') -> 'TestResult':
+                        equal_var: bool = True,
+                        alternative: Literal['two-sided', 'less', 'greater'] = 'two-sided') -> 'TestResult':
         """
         Prueba t de dos muestras independientes
         
@@ -172,9 +218,16 @@ class InferentialStats:
         )
     
     def t_test_paired(self, column1: str, column2: str,
-                     alternative: Literal['two-sided', 'less', 'greater'] = 'two-sided') -> 'TestResult':
+                        alternative: Literal['two-sided', 'less', 'greater'] = 'two-sided') -> 'TestResult':
         """
         Prueba t pareada
+
+        Parameters:
+        -----------
+        column1, column2: 
+            Datos a analizar
+        alternative:
+            "two-sided", "less" o "greater"
         """
         from scipy import stats
         
@@ -192,7 +245,7 @@ class InferentialStats:
         )
     
     def mann_whitney_test(self, column1: str, column2: str,
-                         alternative: Literal['two-sided', 'less', 'greater'] = 'two-sided') -> 'TestResult':
+                            alternative: Literal['two-sided', 'less', 'greater'] = 'two-sided') -> 'TestResult':
         """
         Prueba de Mann-Whitney U (alternativa no paramétrica al t-test)
         
@@ -300,8 +353,8 @@ class InferentialStats:
         )
     
     def normality_test(self, column: str, 
-                      method: Literal['shapiro', 'ks', 'anderson', 'jarque_bera', 'all'] = 'shapiro',
-                      test_statistic: Literal['mean', 'median', 'mode'] = 'mean') -> Union['TestResult', dict]:
+                        method: Literal['shapiro', 'ks', 'anderson', 'jarque_bera', 'all'] = 'shapiro',
+                        test_statistic: Literal['mean', 'median', 'mode'] = 'mean') -> Union['TestResult', dict]:
         """
         Prueba de normalidad con múltiples métodos y estadísticos
         
@@ -456,74 +509,88 @@ class InferentialStats:
             column1: str = None,
             column2: str = None,
             alpha: float = 0.05,
-            homoscedasticity: Literal["levene", "bartlett", "var_test"] = "levene"
-        ) -> Dict[str, Any]:
-
-            data = self.data
-
-            if column1 is None:
-                raise ValueError("Debes especificar 'column1'.")
-
-            x = data[column1].dropna()
-
-            if method in ["difference_mean", "variance"] and column2 is None:
-                raise ValueError("Para este método debes pasar 'column2'.")
-
-            y = data[column2].dropna() if column2 else None
-
-            # --- homoscedasticity test ---
-            homo_result = None
-            if method in ["difference_mean", "variance"]:
-                homo_result = self._homoscedasticity_test(x, y, homoscedasticity)
-
-            # --- MAIN HYPOTHESIS TESTS ---
-            if method == "mean":
-                # One-sample t-test
-                t_stat, p_value = stats.ttest_1samp(x, popmean=np.mean(x))
-                test_name = "One-sample t-test"
-
-            elif method == "difference_mean":
-                # Two-sample t-test
-                equal_var = homo_result["equal_var"]
-                t_stat, p_value = stats.ttest_ind(x, y, equal_var=equal_var)
-                test_name = "Two-sample t-test"
-
-            elif method == "proportion":
-                # Proportion test (z-test)
-                p_hat = np.mean(x)
-                n = len(x)
-                z_stat = (p_hat - 0.5) / np.sqrt(0.5 * 0.5 / n)
-                p_value = 2 * (1 - stats.norm.cdf(abs(z_stat)))
-                t_stat = z_stat
-                test_name = "Proportion Z-test"
-
-            elif method == "variance":
-                # Classic F-test
-                var_x = np.var(x, ddof=1)
-                var_y = np.var(y, ddof=1)
-                F = var_x / var_y
-                dfn = len(x) - 1
-                dfd = len(y) - 1
-
-                p_value = 2 * min(stats.f.cdf(F, dfn, dfd), 1 - stats.f.cdf(F, dfn, dfd))
-                t_stat = F
-                test_name = "Variance F-test"
+            homoscedasticity: Literal["levene", "bartlett", "var_test"] = "levene") -> Dict[str, Any]:
+            
+        """
+        Test de Hipotesis   
 
-            return {
-                "test": test_name,
-                "statistic": t_stat,
-                "p_value": p_value,
-                "alpha": alpha,
-                "reject_H0": p_value < alpha,
-                "homoscedasticity_test": homo_result
-            }
+        Parameters:
+        -----------
+        method : str
+            'mean', 'difference_mean', 'proportion' o 'variance'
+        column1, column2 : str
+            Columnas numéricas a comparar
+        alpha : float
+            Nivel de significancia (default 0.05)
+        homoscedasticity : str
+            Método de homocedasticidad
+            'levene', 'bartlett' o 'var_test' 
+        """
+
+        data = self.data
+
+        if column1 is None:
+            raise ValueError("Debes especificar 'column1'.")
+
+        x = data[column1].dropna()
+
+        if method in ["difference_mean", "variance"] and column2 is None:
+            raise ValueError("Para este método debes pasar 'column2'.")
+
+        y = data[column2].dropna() if column2 else None
+
+        # --- homoscedasticity test ---
+        homo_result = None
+        if method in ["difference_mean", "variance"]:
+            homo_result = self._homoscedasticity_test(x, y, homoscedasticity)
+
+        # --- MAIN HYPOTHESIS TESTS ---
+        if method == "mean":
+            # One-sample t-test
+            t_stat, p_value = stats.ttest_1samp(x, popmean=np.mean(x))
+            test_name = "One-sample t-test"
+
+        elif method == "difference_mean":
+            # Two-sample t-test
+            equal_var = homo_result["equal_var"]
+            t_stat, p_value = stats.ttest_ind(x, y, equal_var=equal_var)
+            test_name = "Two-sample t-test"
+
+        elif method == "proportion":
+            # Proportion test (z-test)
+            p_hat = np.mean(x)
+            n = len(x)
+            z_stat = (p_hat - 0.5) / np.sqrt(0.5 * 0.5 / n)
+            p_value = 2 * (1 - stats.norm.cdf(abs(z_stat)))
+            t_stat = z_stat
+            test_name = "Proportion Z-test"
+
+        elif method == "variance":
+            # Classic F-test
+            var_x = np.var(x, ddof=1)
+            var_y = np.var(y, ddof=1)
+            F = var_x / var_y
+            dfn = len(x) - 1
+            dfd = len(y) - 1
+
+            p_value = 2 * min(stats.f.cdf(F, dfn, dfd), 1 - stats.f.cdf(F, dfn, dfd))
+            t_stat = F
+            test_name = "Variance F-test"
+
+        return {
+            "test": test_name,
+            "statistic": t_stat,
+            "p_value": p_value,
+            "alpha": alpha,
+            "reject_H0": p_value < alpha,
+            "homoscedasticity_test": homo_result
+        }
 
     def _homoscedasticity_test(
         self,
         x,
         y,
-        method: Literal["levene", "bartlett", "var_test"] = "levene"
-    ) -> Dict[str, Any]:
+        method: Literal["levene", "bartlett", "var_test"] = "levene") -> Dict[str, Any]:
 
         if method == "levene":
             stat, p = stats.levene(x, y)