statslibx 0.1.6__py3-none-any.whl → 0.1.7__py3-none-any.whl

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/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/datasets/__init__.py

@@ -1,16 +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):
+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.")
-    return pd.read_csv(io.BytesIO(data_bytes))
+    
+    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'."
+        )
+