statslibx 0.1.8__py3-none-any.whl → 0.2.1__py3-none-any.whl

statslibx/__init__.py

@@ -1,17 +1,16 @@
 """
 StatsLibx - Librería de Estadística para Python
 Autor: Emmanuel Ascendra
-Versión: 0.1.8
+Versión: 0.2.1
 """
 
-__version__ = "0.1.8"
+__version__ = "0.2.1"
 __author__ = "Emmanuel Ascendra"
 
 # Importar las clases principales
 from .descriptive import DescriptiveStats, DescriptiveSummary
 from .inferential import InferentialStats, TestResult
-from .probability import ProbabilityStats
-from .computacional import ComputacionalStats
+from .computacional import ComputationalStats
 from .utils import UtilsStats
 from .preprocessing import Preprocessing
 from .datasets import load_dataset, generate_dataset
@@ -22,7 +21,7 @@ __all__ = [
     'DescriptiveStats',
     'InferentialStats',
     'ProbabilityStats',
-    'ComputacionalStats',
+    'ComputationalStats',
     'UtilsStats',
     'Preprocessing',
     'load_dataset',
@@ -38,6 +37,7 @@ def welcome():
     print(f"\nClases disponibles:")
     print(f"  - DescriptiveStats: Estadística descriptiva")
     print(f"  - InferentialStats: Estadística inferencial")
+    print(f"  - ComputacionalStats: En desarrollo")
     print(f"  - UtilsStats: Utilidades Extras")
     print(f"\nMódulos disponibles:")
     print(f"  - Datasets: Carga de Datasets")

statslibx/computacional.py

@@ -1,2 +1,126 @@
-class ComputacionalStats:
-    pass
+from typing import Union, Optional, Literal
+import numpy as np
+import pandas as pd
+import polars as pl
+import os
+
+class ComputationalStats:
+    """
+    Class for computational statistics
+    """
+    
+    def __init__(self, data: Union[pd.DataFrame, np.ndarray],
+                sep: str = None,
+                decimal: str = None,
+                thousand: str = None,
+                backend: Literal['pandas', 'polars'] = 'pandas'):
+        """
+        # Initialize DataFrame
+        
+        ## **Parameters:**
+
+        - **data** : Data to analyze
+        - **sep** : Column separator
+        - **decimal** : Decimal separator
+        - **thousand** : Thousand separator
+        - **backend** : 'pandas' or 'polars' for processing
+        (Proximamente estara habilitado polars para big data)
+
+        **Examples:**
+
+        ``Example 1:
+        stats = DescriptiveStats(data)
+        ``
+        """
+
+        if isinstance(data, str) and os.path.exists(data):
+                data = ComputationalStats.from_file(data).data
+
+        if isinstance(data, pl.DataFrame):
+            raise TypeError(
+                "Polars aún no soportado. Use pandas.DataFrame."
+            )
+
+
+        if isinstance(data, np.ndarray):
+            if data.ndim == 1:
+                data = pd.DataFrame({'var': data})
+            else:
+                data = pd.DataFrame(data, columns=[f'var_{i}' for i in range(data.shape[1])]) \
+                    if isinstance(data, pd.DataFrame) else pl.DataFrame(data, )
+        
+        self.data = data
+        self.backend = backend
+        self._numeric_cols = data.select_dtypes(include=[np.number]).columns.tolist()
+        self.sep = sep
+        self.decimal = decimal
+        self.thousand = thousand
+    
+    @classmethod
+    def from_file(self, path: str):
+        """
+        Carga automática de archivos y devuelve instancia de Intelligence.
+        Soporta CSV, Excel, TXT, JSON, Parquet, Feather, TSV.
+        Automatic file upload and returns Intelligence instance. 
+        Supports CSV, Excel, TXT, JSON, Parquet, Feather, TSV.
+
+        Parametros / Parameters:
+        ------------------------
+        path : str
+            Ruta del archivo
+            File path
+        """
+        if not os.path.exists(path):
+            raise FileNotFoundError(f"Archivo no encontrado / File not found: {path}")
+
+        ext = os.path.splitext(path)[1].lower()
+
+        if ext == ".csv":
+            df = pd.read_csv(path, sep=self.sep, decimal=self.decimal, thousand=self.thousand)
+
+        elif ext in [".xlsx", ".xls"]:
+            df = pd.read_excel(path, decimal=self.decimal, thousand=self.thousand)
+
+        elif ext in [".txt", ".tsv"]:
+            df = pd.read_table(path, sep=self.sep, decimal=self.decimal, thousand=self.thousand)
+
+        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 / Unsupported format: {ext}")
+
+        return ComputationalStats(df)
+    
+    def monte_carlo(self, function, n: int = 100, return_simulations: bool = False, **kwargs) -> pd.DataFrame:
+        """
+        Realiza simulaciones de Monte Carlo para una función y devuelve un DataFrame con las simulaciones y sus resultados.
+        """
+        samples = []
+
+        for _ in range(n):
+            sample = function(**kwargs)
+            samples.append(float(sample))
+
+        mean = sum(samples) / n
+        variance = sum((x - mean)**2 for x in samples) / n
+        std = variance**0.5
+
+        if return_simulations:
+            return {
+                "mean": float(mean),
+                "std": float(std),
+                "samples": samples
+            }
+
+        else:
+            return {
+                "mean": float(mean),
+                "std": float(std)
+            }

statslibx/datasets/__init__.py

@@ -48,10 +48,22 @@ def _X_y(
         )
 
 
+import io
+import pkgutil
+import pandas as pd
+import polars as pl
+from typing import Literal, Optional, Tuple, List, Union
+from numpy.typing import NDArray
+
+_SUPPORTED_BACKENDS = {"pandas", "polars"}
+
 def load_dataset(
     name: str,
     backend: Literal["pandas", "polars"] = "pandas",
-    return_X_y: Optional[Tuple[List[str], str]] = None
+    return_X_y: Optional[Tuple[List[str], str]] = None,
+    sep: str = ",",
+    save: Optional[bool] = False,
+    filename: Optional[str] = None,
 ) -> Union[pd.DataFrame, pl.DataFrame, Tuple[NDArray, NDArray]]:
     """
     Carga un dataset interno del paquete.
@@ -76,27 +88,32 @@ def load_dataset(
     -------
     DataFrame o (X, y)
     """
+
     if backend not in _SUPPORTED_BACKENDS:
         raise ValueError(
             f"Backend '{backend}' no soportado. "
             f"Use uno de {_SUPPORTED_BACKENDS}."
         )
 
-    # ---------- 1️⃣ Intentar cargar desde el paquete ----------
-    data_bytes = pkgutil.get_data("statslibx.datasets", name)
+    df = None
 
-    if data_bytes is not None:
-        df = (
-            pd.read_csv(io.BytesIO(data_bytes))
-            if backend == "pandas"
-            else pl.read_csv(io.BytesIO(data_bytes))
-        )
+    # ---------- 1️⃣ Intentar cargar desde el paquete ----------
+    try:
+        data_bytes = pkgutil.get_data("statslibx.datasets", name)
+        if data_bytes is not None:
+            df = (
+                pd.read_csv(io.BytesIO(data_bytes), sep=sep)
+                if backend == "pandas"
+                else pl.read_csv(io.BytesIO(data_bytes))
+            )
+    except FileNotFoundError:
+        pass  # seguimos al siguiente intento
 
-    # ---------- 2️⃣ Si no está en el paquete, buscar en ruta actual ----------
-    else:
+    # ---------- 2️⃣ Intentar cargar desde ruta local ----------
+    if df is None:
         try:
             df = (
-                pd.read_csv(name)
+                pd.read_csv(name, sep=sep)
                 if backend == "pandas"
                 else pl.read_csv(name)
             )