statslibx 0.2.0__py3-none-any.whl → 0.2.1__py3-none-any.whl

statslibx/__init__.py

@@ -1,10 +1,10 @@
 """
 StatsLibx - Librería de Estadística para Python
 Autor: Emmanuel Ascendra
-Versión: 0.2.0
+Versión: 0.2.1
 """
 
-__version__ = "0.2.0"
+__version__ = "0.2.1"
 __author__ = "Emmanuel Ascendra"
 
 # Importar las clases principales

statslibx/datasets/__init__.py

@@ -61,8 +61,9 @@ def load_dataset(
     name: str,
     backend: Literal["pandas", "polars"] = "pandas",
     return_X_y: Optional[Tuple[List[str], str]] = None,
+    sep: str = ",",
     save: Optional[bool] = False,
-    filename: Optional[str] = None
+    filename: Optional[str] = None,
 ) -> Union[pd.DataFrame, pl.DataFrame, Tuple[NDArray, NDArray]]:
     """
     Carga un dataset interno del paquete.
@@ -101,7 +102,7 @@ def load_dataset(
         data_bytes = pkgutil.get_data("statslibx.datasets", name)
         if data_bytes is not None:
             df = (
-                pd.read_csv(io.BytesIO(data_bytes))
+                pd.read_csv(io.BytesIO(data_bytes), sep=sep)
                 if backend == "pandas"
                 else pl.read_csv(io.BytesIO(data_bytes))
             )
@@ -112,7 +113,7 @@ def load_dataset(
     if df is None:
         try:
             df = (
-                pd.read_csv(name)
+                pd.read_csv(name, sep=sep)
                 if backend == "pandas"
                 else pl.read_csv(name)
             )

statslibx/descriptive.py

@@ -3,7 +3,6 @@ import pandas as pd
 import polars as pl
 from typing import Optional, Union, Literal, List
 from datetime import datetime
-import flet as ft
 import os
 import matplotlib.pyplot as plt
 import seaborn as sns
@@ -81,10 +80,6 @@ class DescriptiveStats:
     """
     
     def __init__(self, data: Union[pd.DataFrame, np.ndarray],
-                sep: str = None,
-                decimal: str = None,
-                thousand: str = None,
-                backend: Literal['pandas', 'polars'] = 'pandas',
                 lang: Literal['es-ES', 'en-US'] = 'es-ES'):
         """
         # Initialize DataFrame
@@ -92,9 +87,6 @@ class DescriptiveStats:
         ## **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)
 
@@ -104,72 +96,26 @@ class DescriptiveStats:
         stats = DescriptiveStats(data)
         ``
         """
-
-        if isinstance(data, str) and os.path.exists(data):
-                data = DescriptiveStats.from_file(data).data
-
-        if isinstance(data, pl.DataFrame):
+        if isinstance(data, pd.DataFrame):
+            self.data = data
+        elif isinstance(data, np.ndarray):
+            self.data = pd.DataFrame(data)
+        else:
             raise TypeError(
-                "Polars aún no soportado. Use pandas.DataFrame."
+                "Data must be a pandas.DataFrame or numpy.ndarray."
             )
 
-
         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])]) \
+                data = pd.DataFrame(data, columns=[f'var_{i}' for i in range(data.shape[1])],
+                                    sep=self.sep) \
                     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
         self.lang = lang
-    
-    @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 DescriptiveStats(df)
         
     # ============= MÉTODOS UNIVARIADOS =============
     
@@ -1262,3 +1208,4 @@ class LinearRegressionResult:
             plt.ylabel("Residuos")
             plt.title("Residuos vs Predicciones")
             plt.show()
+

statslibx/inferential.py

@@ -69,8 +69,6 @@ class InferentialStats:
     """
     
     def __init__(self, data: Union[pd.DataFrame, np.ndarray],
-                backend: Literal['pandas', 'polars'] = 'pandas',
-                sep: str = None, decimal: str = None, thousand: str = None, 
                 lang: Literal['es-ES', 'en-US'] = 'es-ES'):
         """
         Initialize DataFrame
@@ -79,17 +77,16 @@ class InferentialStats:
         -----------
         data : DataFrame o ndarray
             Data to analyze
-        backend : str
-            'pandas' or 'polars' for processing
         """
 
-        if isinstance(data, str) and os.path.exists(data):
-                data = InferentialStats.from_file(data).data
-
-        if isinstance(data, pl.DataFrame):
+        if isinstance(data, pd.DataFrame):
+            self.data = data
+        elif isinstance(data, np.ndarray):
+            self.data = pd.DataFrame(data)
+        else:
             raise TypeError(
-                "Polars aún no soportado. Use pandas.DataFrame."
-            )
+                "Data must be a pandas.DataFrame or numpy.ndarray."
+            )   
 
         if isinstance(data, np.ndarray):
             if data.ndim == 1:
@@ -98,48 +95,9 @@ class InferentialStats:
                 data = pd.DataFrame(data, columns=[f'var_{i}' for i in range(data.shape[1])])
         
         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
         self.lang = lang
 
-    @classmethod
-    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 / 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: {ext}")
-
-        return InferentialStats(df)
-    
     # ============= INTERVALOS DE CONFIANZA =============
     
     def confidence_interval(self, column: str, confidence: float = 0.95,

{statslibx-0.2.0.dist-info → statslibx-0.2.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: statslibx
-Version: 0.2.0
+Version: 0.2.1
 Summary: StatsLibx - Librería de estadística descriptiva, inferencial y computacional
 Author-email: Emmanuel Ascendra Perez <ascendraemmanuel@gmail.com>
 License: MIT
@@ -16,7 +16,6 @@ Classifier: Programming Language :: Python :: 3.12
 Requires-Python: >=3.8
 Description-Content-Type: text/markdown
 Requires-Dist: pandas>=1.5
-Requires-Dist: polars>=0.20
 Provides-Extra: viz
 Requires-Dist: seaborn>=0.11; extra == "viz"
 Requires-Dist: plotly>=5.0; extra == "viz"

{statslibx-0.2.0.dist-info → statslibx-0.2.1.dist-info}/RECORD

@@ -1,19 +1,20 @@
-statslibx/__init__.py,sha256=YUKUQhO1vUYvcUQmlz1ZtvU6MWNZERdAG55-trf25ZY,1500
+statslibx/__init__.py,sha256=82KG6z_wJZf_ZF8jpViRvtzn4qV9uEZd8a3sRUucKLE,1500
 statslibx/cli.py,sha256=DqXaoP85n9xgLDlFnEkeqj-HJG0_IKX0uSqxRcHbzII,1122
 statslibx/computacional.py,sha256=z46bRUiH9a3ajxVTYE2sGO-pg20L87MdOKM3Y_Tcq44,4062
-statslibx/descriptive.py,sha256=GrUR4QfstUeLTXdxKSZsmKaOJkDso-QH51hlwTUaubA,63513
-statslibx/inferential.py,sha256=xiJCppezhWK4TrAARdOufuxjZcoGKsfHtRujKfuXbgg,83068
+statslibx/descriptive.py,sha256=QLIzPB-pEC2BXCIUsjpDyU7peHAs6fRduPukj1gA160,61671
+statslibx/inferential.py,sha256=_mUzX-Uo2Y55zVTZbQnIRloqKcHjh40djLW1J12HQPU,81617
 statslibx/io.py,sha256=v7pxpmlEMeKyfXftl3WbkUtC9FOh1pymz7MmKPPNw98,493
 statslibx/utils.py,sha256=gWXduW8LMN1q4ZwNggmodRsT9Rcsot-S82NsQiqrjUo,69992
-statslibx/datasets/__init__.py,sha256=wiSp4qGwpILCiaN5vVuwWgKnbdELpbi5pxnNB9Wg2nI,7282
+statslibx/datasets/__init__.py,sha256=KI1N2ByjWpmr9F9_1CDDHEnZ-kDJEKmZON7_4E6Jf_4,7322
 statslibx/datasets/course_completion.csv,sha256=jaqyxAh4YCsYuH5OFsjvGV7KUyM_7vQt6LgnqnNAFsI,22422135
 statslibx/datasets/iris.csv,sha256=xSdC5QMVqZ-Vajg_rt91dVUmdfZAnvD5pHB23QhHmTA,3858
 statslibx/datasets/penguins.csv,sha256=4HY2vYr3QmAJnqL4Z44uq7813vV5lAzHb2cGHuFsBsE,13478
 statslibx/datasets/sp500_companies.csv,sha256=WKS72YOGnAbyLR6kD95fOpIYZt5oXGjPryyFVqLRF_k,803820
 statslibx/datasets/titanic.csv,sha256=5seOS8ybyBMBCCWhgKZrsbu06m_OWyKtD9l0YXOImXU,29474
 statslibx/preprocessing/__init__.py,sha256=ZwdwjBodxeOry-umJ__6yUSeubpRlZg41yve366ArkY,7395
-statslibx-0.2.0.dist-info/METADATA,sha256=w7f-3RgizY3PHUSxoBl6YuHImHz2qFyillhZk82WUfE,2993
-statslibx-0.2.0.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
-statslibx-0.2.0.dist-info/entry_points.txt,sha256=bkCY7JDWNCZFE3I4sjgJ2oGrUgoBBbCbYmWkBAymT70,49
-statslibx-0.2.0.dist-info/top_level.txt,sha256=eeYZXyFm0hIjuI0ba3wF6XW938Mv9tv7Nk9qgjYfCtU,10
-statslibx-0.2.0.dist-info/RECORD,,
+tests/test1.py,sha256=zGaLe9cKLCLrgNbjo-WeDGIjdH4bODtm1_juOn96Mtk,306
+statslibx-0.2.1.dist-info/METADATA,sha256=mNVj_Qo9pROrznPaOkCvWBH7ypw_0j0p9WdCWHgFt5o,2964
+statslibx-0.2.1.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
+statslibx-0.2.1.dist-info/entry_points.txt,sha256=bkCY7JDWNCZFE3I4sjgJ2oGrUgoBBbCbYmWkBAymT70,49
+statslibx-0.2.1.dist-info/top_level.txt,sha256=Mz7hCT3d_WEbs8d6hWac4m3fkI4RlxUkXnHYt967KG8,16
+statslibx-0.2.1.dist-info/RECORD,,

{statslibx-0.2.0.dist-info → statslibx-0.2.1.dist-info}/top_level.txt

@@ -1 +1,2 @@
 statslibx
+tests

tests/test1.py

@@ -0,0 +1,14 @@
+from statslibx import load_dataset, DescriptiveStats, InferentialStats
+import pandas as pd
+# df = pd.read_csv(r"tests\bank (1).csv", sep=";")
+
+df = load_dataset(r"tests\bank (1).csv", sep=";")
+stats = DescriptiveStats(df)
+print(stats.data)
+
+infer = InferentialStats(df)
+print(infer.data)
+
+
+
+