statslibx 0.1.6__tar.gz → 0.1.7__tar.gz

{statslibx-0.1.6 → statslibx-0.1.7}/PKG-INFO

@@ -1,47 +1,28 @@
 Metadata-Version: 2.4
 Name: statslibx
-Version: 0.1.6
-Summary: Librería de estadística descriptiva e inferencial para Python
-Home-page: https://github.com/Immanuel3008/StatsLibX
-Author: Emmanuel Ascendra Perez
-Author-email: ascendraemmanuel@gmail.com
+Version: 0.1.7
+Summary: StatsLibx - Librería de estadística descriptiva e inferencial
+Author-email: Emmanuel Ascendra Perez <ascendraemmanuel@gmail.com>
+License: MIT
 Classifier: Development Status :: 3 - Alpha
 Classifier: Intended Audience :: Science/Research
 Classifier: Topic :: Scientific/Engineering :: Mathematics
 Classifier: License :: OSI Approved :: MIT License
 Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.8
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Requires-Python: >=3.8
 Description-Content-Type: text/markdown
-Requires-Dist: numpy>=1.20.0
-Requires-Dist: pandas>=1.3.0
-Requires-Dist: scipy>=1.7.0
-Requires-Dist: matplotlib>=3.4.0
+Requires-Dist: pandas>=1.5
+Requires-Dist: polars>=0.20
 Provides-Extra: viz
-Requires-Dist: seaborn>=0.11.0; extra == "viz"
-Requires-Dist: plotly>=5.0.0; extra == "viz"
+Requires-Dist: seaborn>=0.11; extra == "viz"
+Requires-Dist: plotly>=5.0; extra == "viz"
 Provides-Extra: advanced
-Requires-Dist: scikit-learn>=1.0.0; extra == "advanced"
-Requires-Dist: statsmodels>=0.13.0; extra == "advanced"
-Provides-Extra: all
-Requires-Dist: seaborn>=0.11.0; extra == "all"
-Requires-Dist: plotly>=5.0.0; extra == "all"
-Requires-Dist: scikit-learn>=1.0.0; extra == "all"
-Requires-Dist: statsmodels>=0.13.0; extra == "all"
-Dynamic: author
-Dynamic: author-email
-Dynamic: classifier
-Dynamic: description
-Dynamic: description-content-type
-Dynamic: home-page
-Dynamic: provides-extra
-Dynamic: requires-dist
-Dynamic: requires-python
-Dynamic: summary
+Requires-Dist: scikit-learn>=1.0; extra == "advanced"
+Requires-Dist: statsmodels>=0.13; extra == "advanced"
 
 # 📦 Descripción para PyPI (Plantilla Profesional)
 

statslibx-0.1.7/pyproject.toml

@@ -0,0 +1,42 @@
+[build-system]
+requires = ["setuptools>=68", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "statslibx"
+version = "0.1.7"
+description = "StatsLibx - Librería de estadística descriptiva e inferencial"
+readme = "README.md"
+requires-python = ">=3.8"
+license = { text = "MIT" }
+
+authors = [
+    { name = "Emmanuel Ascendra Perez", email = "ascendraemmanuel@gmail.com" }
+]
+
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Science/Research",
+    "Topic :: Scientific/Engineering :: Mathematics",
+    "License :: OSI Approved :: MIT License",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12"
+]
+
+dependencies = [
+    "pandas>=1.5",
+    "polars>=0.20"
+]
+
+[project.optional-dependencies]
+viz = ["seaborn>=0.11", "plotly>=5.0"]
+advanced = ["scikit-learn>=1.0", "statsmodels>=0.13"]
+
+[project.scripts]
+statslibx = "statslibx.cli:main"
+
+[tool.setuptools.packages.find]
+where = ["."]

{statslibx-0.1.6 → statslibx-0.1.7}/statslibx/__init__.py

@@ -11,6 +11,7 @@ __author__ = "Emmanuel Ascendra"
 from .descriptive import DescriptiveStats, DescriptiveSummary
 from .inferential import InferentialStats, TestResult
 from .utils import UtilsStats
+from .preprocessing import Preprocessing
 from .datasets import load_dataset
 
 # Definir qué se expone cuando se hace: from statslib import *
@@ -22,6 +23,7 @@ __all__ = [
     'DescriptiveSummary',
     'TestResult',
     'UtilsStats',
+    'Preprocessing',
     'load_dataset'
 ]
 
@@ -35,4 +37,5 @@ def welcome():
     print(f"  - DescriptiveStats: Estadística descriptiva")
     print(f"  - InferentialStats: Estadística inferencial")
     print(f"  - UtilsStats: Utilidades Extras")
+    print(f"  - Preprocessing: Preprocesamiento de datos")
     print(f"\nPara más información: help(statslibx)")

statslibx-0.1.7/statslibx/cli.py

@@ -0,0 +1,47 @@
+import argparse
+from statslibx.io import load_file
+from statslibx.preprocessing import Preprocessing
+
+
+def main():
+    parser = argparse.ArgumentParser(
+        prog="statslibx",
+        description="Statslibx - Data analysis from terminal"
+    )
+
+    subparsers = parser.add_subparsers(dest="command")
+
+    # describe
+    describe = subparsers.add_parser("describe")
+    describe.add_argument("file")
+
+    # quality
+    quality = subparsers.add_parser("quality")
+    quality.add_argument("file")
+
+    # preview
+    preview = subparsers.add_parser("preview")
+    preview.add_argument("file")
+    preview.add_argument("-n", "--rows", type=int, default=5)
+
+    args = parser.parse_args()
+
+    if not args.command:
+        parser.print_help()
+        return
+
+    df = load_file(args.file)
+    pp = Preprocessing(df)
+
+    if args.command == "describe":
+        print(pp.describe_numeric())
+
+    elif args.command == "quality":
+        print(pp.data_quality())
+
+    elif args.command == "preview":
+        print(pp.preview_data(args.rows))
+
+
+if __name__ == "__main__":
+    main()

statslibx-0.1.7/statslibx/datasets/__init__.py

@@ -0,0 +1,71 @@
+from typing import Optional, Union, Literal, List
+import polars as pl
+import pandas as pd
+import pkgutil
+import io
+
+def load_dataset(
+        name: str,
+        backend: Literal['pandas', 'polars'] = 'pandas'
+    ) -> Union[pd.DataFrame, pl.DataFrame]:
+    """Carga un dataset interno del paquete.
+    Datasets Disponibles:
+    - iris.csv
+    - penguins.csv
+    - sp500_companies.csv
+    - titanic.csv
+    - course_completion.csv
+    """
+    data_bytes = pkgutil.get_data("statslibx.datasets", name)
+    if data_bytes is None:
+        raise FileNotFoundError(f"Dataset '{name}' no encontrado.")
+    
+    if backend == "pandas":
+        return pd.read_csv(io.BytesIO(data_bytes))
+    elif backend == "polars":
+        return pl.read_csv(io.BytesIO(data_bytes))
+    else:
+        raise ValueError(
+            "Backend no soportado. Use 'pandas' o 'polars'."
+        )
+    
+def load_iris(
+        backend: Literal['pandas', 'polars'] = 'pandas'
+    ) -> Union[pd.DataFrame, pl.DataFrame]:
+    """Carga el dataset interno de la libreria: Iris
+    """
+    data_bytes = pkgutil.get_data("statslibx.datasets", "iris.csv")
+    if data_bytes is None:
+        raise FileNotFoundError(f"Dataset \"iris.csv\" no encontrado.")
+    
+    if backend == "pandas":
+        return pd.read_csv(io.BytesIO(data_bytes))
+    elif backend == "polars":
+        raise ValueError(
+            "Backend no soportado aun. Use 'pandas'."
+        )
+    else:
+        raise ValueError(
+            "Backend no soportado. Use 'pandas' o 'polars'."
+        )
+    
+def load_penguins(
+        backend: Literal['pandas', 'polars'] = 'pandas'
+    ) -> Union[pd.DataFrame, pl.DataFrame]:
+    """Carga un dataset interno de la libreria: Penguins
+    """
+    data_bytes = pkgutil.get_data("statslibx.datasets", "penguins.csv")
+    if data_bytes is None:
+        raise FileNotFoundError(f"Dataset \"penguins.csv\" no encontrado.")
+    
+    if backend == "pandas":
+        return pd.read_csv(io.BytesIO(data_bytes))
+    elif backend == "polars":
+        raise ValueError(
+            "Backend no soportado aun. Use 'pandas'."
+        )
+    else:
+        raise ValueError(
+            "Backend no soportado. Use 'pandas' o 'polars'."
+        )
+