statslibx 0.2.2__tar.gz → 0.2.4__tar.gz

{statslibx-0.2.2/statslibx.egg-info → statslibx-0.2.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: statslibx
-Version: 0.2.2
+Version: 0.2.4
 Summary: StatsLibx - Librería de estadística descriptiva, inferencial y computacional
 Author-email: Emmanuel Ascendra Perez <ascendraemmanuel@gmail.com>
 License: MIT
@@ -16,6 +16,14 @@ Classifier: Programming Language :: Python :: 3.12
 Requires-Python: >=3.8
 Description-Content-Type: text/markdown
 Requires-Dist: pandas>=1.5
+Requires-Dist: matplotlib>=3.5
+Requires-Dist: numpy>=1.23
+Requires-Dist: scipy>=1.9
+Requires-Dist: polars>=0.16
+Requires-Dist: scikit-learn>=1.0
+Requires-Dist: statsmodels>=0.13
+Requires-Dist: seaborn>=0.11
+Requires-Dist: plotly>=5.0
 Provides-Extra: viz
 Requires-Dist: seaborn>=0.11; extra == "viz"
 Requires-Dist: plotly>=5.0; extra == "viz"
@@ -29,6 +37,8 @@ StatsLibX es un paquete de Python diseñado para proporcionar una solución senc
 
 Este proyecto surge con la idea de ofrecer una alternativa moderna, intuitiva y ligera que permita a desarrolladores y entusiastas integrar la **estadistica descriptiva, inferencial y computacional (En desarrollo)** sin complicaciones, con multiples funcionalidades y utilidades pensadas para el futuro.
 
+Pagina Web: [StatsLibX](https://ghostanalyst30.github.io/StatsLibX/Documentation_Page/index.html)
+
 GitHub del Proyecto: [https://github.com/GhostAnalyst30/StatsLibX](https://github.com/GhostAnalyst30/StatsLibX)
 
 ## ✨ Características principales
@@ -63,6 +73,7 @@ pip install statslibx
 
 ## 👩‍💻 ¡Usalo en la terminal! (De forma preliminar)
 ```bash
+statslibx                        # Informacion general de la libreria
 statslibx describe .\archive.csv # Devuelve una descripcion de la data
 statslibx quality .\archive.csv # Devuelve la calidad de los datos
 statslibx preview .\archive.csv # Devuelve una visualizacion de los datos

{statslibx-0.2.2 → statslibx-0.2.4}/README.md

@@ -4,6 +4,8 @@ StatsLibX es un paquete de Python diseñado para proporcionar una solución senc
 
 Este proyecto surge con la idea de ofrecer una alternativa moderna, intuitiva y ligera que permita a desarrolladores y entusiastas integrar la **estadistica descriptiva, inferencial y computacional (En desarrollo)** sin complicaciones, con multiples funcionalidades y utilidades pensadas para el futuro.
 
+Pagina Web: [StatsLibX](https://ghostanalyst30.github.io/StatsLibX/Documentation_Page/index.html)
+
 GitHub del Proyecto: [https://github.com/GhostAnalyst30/StatsLibX](https://github.com/GhostAnalyst30/StatsLibX)
 
 ## ✨ Características principales
@@ -38,6 +40,7 @@ pip install statslibx
 
 ## 👩‍💻 ¡Usalo en la terminal! (De forma preliminar)
 ```bash
+statslibx                        # Informacion general de la libreria
 statslibx describe .\archive.csv # Devuelve una descripcion de la data
 statslibx quality .\archive.csv # Devuelve la calidad de los datos
 statslibx preview .\archive.csv # Devuelve una visualizacion de los datos

{statslibx-0.2.2 → statslibx-0.2.4}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "statslibx"
-version = "0.2.2"
+version = "0.2.4"
 description = "StatsLibx - Librería de estadística descriptiva, inferencial y computacional"
 readme = "README.md"
 requires-python = ">=3.8"
@@ -27,7 +27,15 @@ classifiers = [
 ]
 
 dependencies = [
-    "pandas>=1.5"
+    "pandas>=1.5",
+    "matplotlib>=3.5",
+    "numpy>=1.23",
+    "scipy>=1.9",
+    "polars>=0.16",
+    "scikit-learn>=1.0",
+    "statsmodels>=0.13",
+    "seaborn>=0.11",
+    "plotly>=5.0"
 ]
 
 [project.optional-dependencies]

{statslibx-0.2.2 → statslibx-0.2.4}/statslibx/__init__.py

@@ -1,10 +1,10 @@
 """
 StatsLibx - Librería de Estadística para Python
 Autor: Emmanuel Ascendra
-Versión: 0.2.2
+Versión: 0.2.4
 """
 
-__version__ = "0.2.2"
+__version__ = "0.2.4"
 __author__ = "Emmanuel Ascendra"
 
 # Importar las clases principales

{statslibx-0.2.2 → statslibx-0.2.4}/statslibx/cli.py

@@ -1,5 +1,6 @@
 import argparse
-from statslibx.io import load_file
+import statslibx as slx
+from statslibx.datasets import load_dataset
 from statslibx.preprocessing import Preprocessing
 
 
@@ -27,10 +28,10 @@ def main():
     args = parser.parse_args()
 
     if not args.command:
-        parser.print_help()
+        print(slx.welcome())
         return
 
-    df = load_file(args.file)
+    df = load_dataset(args.file)
     pp = Preprocessing(df)
 
     if args.command == "describe":

{statslibx-0.2.2 → statslibx-0.2.4}/statslibx/datasets/__init__.py

@@ -3,7 +3,6 @@ import io
 import pkgutil
 from pathlib import Path
 import pandas as pd
-import polars as pl
 import numpy as np
 from numpy.typing import NDArray
 
@@ -12,10 +11,10 @@ _SUPPORTED_BACKENDS = ("pandas", "polars")
 
 
 def _validate_columns(
-    df: Union[pd.DataFrame, pl.DataFrame],
-    X_columns: List[str],
-    y_column: str
-) -> None:
+    df: pd.DataFrame,  # 输入的数据框，可以是pandas或polars DataFrame
+    X_columns: List[str],  # 特征列名列表
+    y_column: str  # 目标列名
+) -> None:  # 无返回值，函数仅用于验证
     columns = set(df.columns)
     missing = set(X_columns + [y_column]) - columns
     if missing:
@@ -23,7 +22,7 @@ def _validate_columns(
 
 
 def _X_y(
-    df: Union[pd.DataFrame, pl.DataFrame],
+    df: pd.DataFrame,
     X_columns: List[str],
     y_column: str
 ) -> Tuple[NDArray, NDArray]:
@@ -37,25 +36,19 @@ def _X_y(
         y = df[y_column].to_numpy().ravel()
         return X, y
 
-    elif isinstance(df, pl.DataFrame):
-        X = df.select(X_columns).to_numpy()
-        y = df.select(y_column).to_numpy().ravel()
-        return X, y
-
     else:
         raise TypeError(
-            "Backend no soportado. Use pandas.DataFrame o polars.DataFrame."
+            "Backend no soportado. Use pandas.DataFrame"
         )
 
 
 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"}
+_SUPPORTED_BACKENDS = {"pandas"}
 _SUPPORTED_EXTENSIONS = {".csv", ".parquet", ".xlsx", ".xls", ".json"}
 
 def _read_file(
@@ -73,23 +66,15 @@ def _read_file(
             return pd.read_excel(buffer_or_path)
         if ext == ".json":
             return pd.read_json(buffer_or_path)
-    else:  # polars
-        if ext == ".csv":
-            return pl.read_csv(buffer_or_path)
-        if ext == ".parquet":
-            return pl.read_parquet(buffer_or_path)
-        if ext == ".json":
-            return pl.read_json(buffer_or_path)
 
     raise ValueError(f"Extensión '{ext}' no soportada para backend '{backend}'.")
 
-
 def load_dataset(
-    name: str,
-    backend: Literal["pandas", "polars"] = "pandas",
-    return_X_y: Optional[Tuple[List[str], str]] = None,
-    sep: str = ","
-) -> Union[pd.DataFrame, pl.DataFrame, Tuple[NDArray, NDArray]]:
+        name: str,
+        backend: str = "pandas",
+        return_X_y: Optional[Tuple[List[str], str]] = None,
+        sep: str = ","
+    ) -> Union[pd.DataFrame, Tuple[NDArray, NDArray]]:
     """
     Carga un dataset interno del paquete.
 
@@ -99,6 +84,7 @@ def load_dataset(
     - sp500_companies.csv
     - titanic.csv
     - course_completion.csv
+    - Cocoa_Bubbles_Investment_Nigeria_Ghana_1980_2023.xlsx
 
     Parámetros
     ----------
@@ -120,7 +106,10 @@ def load_dataset(
             f"Use uno de {_SUPPORTED_BACKENDS}."
         )
 
-    ext = Path(name).suffix.lower()
+    path = Path(name)
+    resource_name = path.name
+    ext = path.suffix.lower()
+
 
     if ext not in _SUPPORTED_EXTENSIONS:
         raise ValueError(
@@ -130,26 +119,26 @@ def load_dataset(
 
     df = None
 
-    # ---------- 1️⃣ Intentar cargar desde el paquete ----------
+    # 1️⃣ Intentar cargar desde el paquete
     try:
-        data_bytes = pkgutil.get_data("statslibx.datasets", name)
+        data_bytes = pkgutil.get_data("statslibx.datasets", resource_name)
+
         if data_bytes is not None:
             buffer = io.BytesIO(data_bytes)
             df = _read_file(buffer, ext, backend, sep)
     except FileNotFoundError:
         pass
 
-    # ---------- 2️⃣ Intentar cargar desde ruta local ----------
+    # 2️⃣ Intentar cargar desde ruta local
     if df is None:
-        try:
-            df = _read_file(name, ext, backend, sep)
-        except FileNotFoundError:
+        if not path.exists():
             raise FileNotFoundError(
                 f"Dataset '{name}' no encontrado "
-                f"ni en statslibx.datasets ni en la ruta actual."
+                f"ni en statslibx.datasets ni en la ruta local."
             )
+        df = _read_file(path, ext, backend, sep)
 
-    # ---------- 3️⃣ Devolver X, y si se solicita ----------
+    # 3️⃣ Devolver X, y si se solicita
     if return_X_y is not None:
         X_columns, y_column = return_X_y
         return _X_y(df, X_columns, y_column)
@@ -157,12 +146,13 @@ def load_dataset(
     return df
 
 
+
 # =========================
 # Datasets específicos
 # =========================
 
 def load_iris(
-    backend: Literal["pandas", "polars"] = "pandas",
+    backend: str = "pandas",
     return_X_y: Optional[Tuple[List[str], str]] = None
 ):
     return load_dataset(
@@ -173,7 +163,7 @@ def load_iris(
 
 
 def load_penguins(
-    backend: Literal["pandas", "polars"] = "pandas",
+    backend: str = "pandas",
     return_X_y: Optional[Tuple[List[str], str]] = None
 ):
     return load_dataset(

{statslibx-0.2.2 → statslibx-0.2.4}/statslibx/descriptive.py

@@ -1,13 +1,9 @@
 import numpy as np
 import pandas as pd
-import polars as pl
 from typing import Optional, Union, Literal, List
 from datetime import datetime
-import os
 import matplotlib.pyplot as plt
 import seaborn as sns
-import io
-import base64
 import plotly.express as px
 
 class DescriptiveStats:
@@ -104,16 +100,9 @@ class DescriptiveStats:
             raise TypeError(
                 "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])],
-                                    sep=self.sep) \
-                    if isinstance(data, pd.DataFrame) else pl.DataFrame(data, )
-
-        self._numeric_cols = data.select_dtypes(include=[np.number]).columns.tolist()
+        
+        self._numeric_cols = self.data.select_dtypes(include=["number"]).columns.tolist()
+        self._categorical_cols = self.data.select_dtypes(include=["object", "category"]).columns.tolist()
         self.lang = lang
 
         

{statslibx-0.2.2 → statslibx-0.2.4}/statslibx/inferential.py

@@ -1,11 +1,9 @@
 from dataclasses import dataclass
 import numpy as np
 import pandas as pd
-import polars as pl
-from typing import Optional, Union, Literal, List, Dict, Any, Tuple
+from typing import Union, Literal, Dict, Any, Tuple
 from datetime import datetime
 from scipy import stats
-import os
 
 class InferentialStats:
     """    
@@ -94,8 +92,8 @@ class InferentialStats:
             else:
                 data = pd.DataFrame(data, columns=[f'var_{i}' for i in range(data.shape[1])])
         
-        self.data = data
-        self._numeric_cols = data.select_dtypes(include=[np.number]).columns.tolist()
+        self._numeric_cols = data.select_dtypes(include=["number"]).columns.tolist()
+        self._categorical_cols = self.data.select_dtypes(include=["object", "category"]).columns.tolist()
         self.lang = lang
 
     # ============= INTERVALOS DE CONFIANZA =============

{statslibx-0.2.2 → statslibx-0.2.4}/statslibx/preprocessing/__init__.py

@@ -10,6 +10,7 @@ class Preprocessing:
         if not isinstance(data, (pd.DataFrame, pl.DataFrame)):
             raise TypeError("data must be a pandas or polars DataFrame")
         self.data = data
+        self.columns = list(self.data.columns)
 
     # ------------------------------------------------------------------
     # Internal helpers
@@ -27,11 +28,11 @@ class Preprocessing:
         return int(self.data[column].null_count())
 
     def _get_columns(self, columns):
-        if columns is None:
-            return list(self.data.columns)
-        if isinstance(columns, str):
-            return [columns]
-        return columns
+            if columns is None:
+                return list(self.data.columns)
+            if isinstance(columns, str):
+                return [columns]
+            return columns 
 
     # ------------------------------------------------------------------
     # Inspection
@@ -226,3 +227,103 @@ class Preprocessing:
 
         return pd.DataFrame(rows)
 
+    def change_dtypes(
+        self,
+        columns: Union[List[str], str, None] = None,
+        from_type: Optional[str] = None,
+        to_type: Optional[str] = None
+    ) -> pd.DataFrame:
+
+        data = self.data
+
+        TYPE_MAP = {
+            "string": "string",
+            "object": "object",
+            "int": "int64",
+            "float": "float64",
+            "int64": "int64",
+            "float64": "float64",
+            "number": "float64"
+        }
+
+        if columns is None:
+            columns = list(data.columns)
+        elif isinstance(columns, str):
+            columns = [columns]
+
+        if to_type and to_type not in TYPE_MAP:
+            raise ValueError(f"Unsupported to_type: {to_type}")
+
+        if self._is_pandas():
+
+            for col in columns:
+
+                if col not in data.columns:
+                    print(f"Column '{col}' does not exist in the DataFrame")
+                    return
+
+                if from_type is not None:
+                    current_type = str(data[col].dtype)
+
+                    if from_type not in current_type:
+                        continue
+
+                if to_type is not None:
+                    try:
+
+                        if to_type in ["int", "float", "number"]:
+                            data[col] = pd.to_numeric(data[col], errors="raise")
+
+                            if to_type == "int":
+                                data[col] = data[col].astype("int64")
+
+                        elif to_type == "string":
+                            data[col] = data[col].astype("string")
+
+                        elif to_type == "object":
+                            data[col] = data[col].astype("object")
+
+                        else:
+                            data[col] = data[col].astype(TYPE_MAP[to_type])
+
+                    except Exception:
+                        print(f"Cannot convert column '{col}' to {to_type}")
+
+        return data
+
+    def clean_data(
+        self,
+        # 🔍 Missing values
+        handle_missing: bool = False,
+        missing_strategy: str = "mean",  # mean, median, mode, drop, constant
+        fill_value=None,
+        
+        # 🧹 Duplicados
+        remove_duplicates: bool = False,
+        
+        # 📊 Tipos de datos
+        convert_dtypes: bool = False,
+        
+        # 🚨 Outliers
+        detect_outliers: bool = False,
+        remove_outliers: bool = False,
+        outlier_method: str = "iqr",  # iqr, zscore
+        z_thresh: float = 3.0,
+        
+        # 📏 Escalado / Normalización
+        scale: bool = False,
+        scaling_method: str = "standard",  # standard, minmax, robust
+        
+        # 🔢 Transformaciones
+        log_transform: bool = False,
+        sqrt_transform: bool = False,
+        
+        # 🧱 Columnas
+        drop_columns: list = None,
+        keep_columns: list = None,
+
+        
+        # 🧪 Analisis
+        analizer: bool = True,
+        text_analizer: bool = False) -> pd.DataFrame | str:
+        pass

{statslibx-0.2.2 → statslibx-0.2.4/statslibx.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: statslibx
-Version: 0.2.2
+Version: 0.2.4
 Summary: StatsLibx - Librería de estadística descriptiva, inferencial y computacional
 Author-email: Emmanuel Ascendra Perez <ascendraemmanuel@gmail.com>
 License: MIT
@@ -16,6 +16,14 @@ Classifier: Programming Language :: Python :: 3.12
 Requires-Python: >=3.8
 Description-Content-Type: text/markdown
 Requires-Dist: pandas>=1.5
+Requires-Dist: matplotlib>=3.5
+Requires-Dist: numpy>=1.23
+Requires-Dist: scipy>=1.9
+Requires-Dist: polars>=0.16
+Requires-Dist: scikit-learn>=1.0
+Requires-Dist: statsmodels>=0.13
+Requires-Dist: seaborn>=0.11
+Requires-Dist: plotly>=5.0
 Provides-Extra: viz
 Requires-Dist: seaborn>=0.11; extra == "viz"
 Requires-Dist: plotly>=5.0; extra == "viz"
@@ -29,6 +37,8 @@ StatsLibX es un paquete de Python diseñado para proporcionar una solución senc
 
 Este proyecto surge con la idea de ofrecer una alternativa moderna, intuitiva y ligera que permita a desarrolladores y entusiastas integrar la **estadistica descriptiva, inferencial y computacional (En desarrollo)** sin complicaciones, con multiples funcionalidades y utilidades pensadas para el futuro.
 
+Pagina Web: [StatsLibX](https://ghostanalyst30.github.io/StatsLibX/Documentation_Page/index.html)
+
 GitHub del Proyecto: [https://github.com/GhostAnalyst30/StatsLibX](https://github.com/GhostAnalyst30/StatsLibX)
 
 ## ✨ Características principales
@@ -63,6 +73,7 @@ pip install statslibx
 
 ## 👩‍💻 ¡Usalo en la terminal! (De forma preliminar)
 ```bash
+statslibx                        # Informacion general de la libreria
 statslibx describe .\archive.csv # Devuelve una descripcion de la data
 statslibx quality .\archive.csv # Devuelve la calidad de los datos
 statslibx preview .\archive.csv # Devuelve una visualizacion de los datos

statslibx-0.2.4/statslibx.egg-info/requires.txt

@@ -0,0 +1,17 @@
+pandas>=1.5
+matplotlib>=3.5
+numpy>=1.23
+scipy>=1.9
+polars>=0.16
+scikit-learn>=1.0
+statsmodels>=0.13
+seaborn>=0.11
+plotly>=5.0
+
+[advanced]
+scikit-learn>=1.0
+statsmodels>=0.13
+
+[viz]
+seaborn>=0.11
+plotly>=5.0

{statslibx-0.2.2 → statslibx-0.2.4}/statslibx.egg-info/top_level.txt

@@ -1,3 +1,4 @@
+Documentation_Page
 dist
 figures
 statslibx

statslibx-0.2.4/tests/test1.py

@@ -0,0 +1,30 @@
+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)
+
+# df = load_dataset(r"statslibx\datasets\Cocoa_Bubbles_Investment_Nigeria_Ghana_1980_2023.xlsx")
+
+# ds = DescriptiveStats(df)
+
+# print(ds.data)
+
+import statslibx as slx
+
+df = slx.datasets.load_penguins()
+infer = slx.InferentialStats(df)
+
+# Confidence Interval + Point Estimate
+print(infer.confidence_interval(
+    column="bill_length_mm",
+    statistic="mean"
+))
+
+
+

statslibx-0.2.2/statslibx.egg-info/requires.txt

@@ -1,9 +0,0 @@
-pandas>=1.5
-
-[advanced]
-scikit-learn>=1.0
-statsmodels>=0.13
-
-[viz]
-seaborn>=0.11
-plotly>=5.0

statslibx-0.2.2/tests/test1.py

@@ -1,20 +0,0 @@
-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)
-
-df = load_dataset(r"statslibx\datasets\WHR25_Data_Figure_2.1.xlsx")
-
-ds = DescriptiveStats(df)
-
-print(ds.data)
-
-
-
-