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

statslibx/inferential.py

@@ -8,12 +8,67 @@ from scipy import stats
 import os
 
 class InferentialStats:
-    """
-    Class for inferential statistics (hypothesis tests, confidence intervals, etc.)
+    """    
+    InferentialStats
+    A class for performing inferential statistical analysis, including hypothesis tests, confidence intervals, 
+    normality tests, and more. This class supports operations on pandas DataFrame or numpy arrays.
+    Attributes:
+    -----------
+    data : pd.DataFrame
+        The dataset to analyze.
+        The backend used for processing ('pandas' or 'polars').
+    sep : str
+        Separator for reading files.
+    decimal : str
+        Decimal separator for reading files.
+    thousand : str
+        Thousand separator for reading files.
+    lang : str
+        Language for help and error messages ('es-ES' or 'en-US').
+    
+    Methods:
+    --------
+    from_file(path: str):
+        Load data from a file and return an instance of InferentialStats.
+    
+    confidence_interval(column: str, confidence: float = 0.95, statistic: Literal['mean', 'median', 'proportion'] = 'mean') -> tuple:
+        Calculate confidence intervals for mean, median, or proportion.
+    
+    t_test_1sample(column: str, popmean: float = None, popmedian: float = None, alternative: Literal['two-sided', 'less', 'greater'] = 'two-sided', alpha: float = 0.05) -> 'TestResult':
+        Perform a one-sample t-test or Wilcoxon signed-rank test for median.
+    
+    t_test_2sample(column1: str, column2: str, equal_var: bool = True, alternative: Literal['two-sided', 'less', 'greater'] = 'two-sided', alpha: float = 0.05) -> 'TestResult':
+        Perform a two-sample independent t-test.
+    
+    t_test_paired(column1: str, column2: str, alternative: Literal['two-sided', 'less', 'greater'] = 'two-sided', alpha: float = 0.05) -> 'TestResult':
+        Perform a paired t-test for dependent samples.
+    
+    mann_whitney_test(column1: str, column2: str, alternative: Literal['two-sided', 'less', 'greater'] = 'two-sided', alpha: float = 0.05) -> 'TestResult':
+        Perform the Mann-Whitney U test, a non-parametric alternative to the two-sample t-test.
+    
+    chi_square_test(column1: str, column2: str, alpha: float = 0.05) -> 'TestResult':
+        Perform a Chi-square test of independence between two categorical variables.
+    
+    anova_oneway(column: str, groups: str, alpha: float = 0.05) -> 'TestResult':
+        Perform a one-way ANOVA test to compare means across multiple groups.
+    
+    kruskal_wallis_test(column: str, groups: str, alpha: float = 0.05) -> 'TestResult':
+        Perform the Kruskal-Wallis test, a non-parametric alternative to one-way ANOVA.
+    
+    normality_test(column: str, method: Literal['shapiro', 'ks', 'anderson', 'jarque_bera', 'all'] = 'shapiro', test_statistic: Literal['mean', 'median', 'mode'] = 'mean', alpha: float = 0.05) -> Union['TestResult', dict]:
+        Perform normality tests using various methods.
+    
+    hypothesis_test(method: Literal["mean", "difference_mean", "proportion", "variance"] = "mean", column1: str = None, column2: str = None, pop_mean: float = None, pop_proportion: Union[float, Tuple[float, float]] = 0.5, alpha: float = 0.05, homoscedasticity: Literal["levene", "bartlett", "var_test"] = "levene") -> Dict[str, Any]:
+        Perform hypothesis testing for mean, difference of means, proportion, or variance.
+    
+    variance_test(column1: str, column2: str, method: Literal['levene', 'bartlett', 'var_test'] = 'levene', center: Literal['mean', 'median', 'trimmed'] = 'median', alpha: float = 0.05) -> 'TestResult':
+        Perform a test for equality of variances between two columns.
+    
+    help():
+        Display a detailed help guide for the InferentialStats class and its methods.
     """
     
     def __init__(self, data: Union[pd.DataFrame, np.ndarray],
-                backend: Literal['pandas', 'polars'] = 'pandas',
                 lang: Literal['es-ES', 'en-US'] = 'es-ES'):
         """
         Initialize DataFrame
@@ -22,17 +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:
@@ -41,44 +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.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: {path}")
-
-        ext = os.path.splitext(path)[1].lower()
-
-        if ext == ".csv":
-            df = pd.read_csv(path)
-
-        elif ext in [".xlsx", ".xls"]:
-            df = pd.read_excel(path)
-
-        elif ext in [".txt", ".tsv"]:
-            df = pd.read_table(path)
-
-        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/utils.py

@@ -11,23 +11,81 @@ from pathlib import Path
 
 class UtilsStats:
     """
-    Clase utilitaria para operaciones estadísticas comunes y visualización
+    UtilsStats
+    A utility class for common statistical operations and visualization.
+    This class provides methods for data validation, basic statistical analysis,
+    and visualization of results. It also supports loading data directly from files.
+    >>> # Load data from a file
+    >>> data = utils.load_data("data.csv")
+    >>> utils.check_normality(data, column='age')
+    >>> # Analyze data from an array
+    Methods:
+    --------
+    _setup_plotting_style():
+        Configures default plotting styles for matplotlib.
     
-    Esta clase proporciona métodos para validación de datos, análisis estadísticos
-    básicos y visualización de resultados. Ahora con soporte para leer archivos directamente.
+    set_plot_backend(backend: Literal['matplotlib', 'seaborn', 'plotly']):
+        Sets the default visualization backend.
     
-    Examples:
-    ---------
-    >>> utils = UtilsStats()
-    >>> # Desde archivo
-    >>> data = utils.load_data("datos.csv")
-    >>> utils.check_normality(data, column='edad')
-    >>> # Desde array
-    >>> data = np.random.normal(0, 1, 100)
-    >>> utils.check_normality(data)
-    >>> utils.plot_distribution(data)
+    set_default_figsize(figsize: Tuple[int, int]):
+        Sets the default figure size for plots.
+    
+    set_save_fig_options(save_fig: Optional[bool] = False, fig_format: str = 'png', 
+                         fig_dpi: int = 300, figures_dir: str = 'figures'):
+        Configures options for saving figures.
+    
+    load_data(path: Union[str, Path], **kwargs) -> pd.DataFrame:
+        Loads data from a file in various formats (CSV, Excel, JSON, etc.).
+    
+    validate_dataframe(data: Union[pd.DataFrame, np.ndarray, list, str, Path]) -> pd.DataFrame:
+        Validates and converts data to a DataFrame. Also accepts file paths.
+    
+    format_number(num: float, decimals: int = 6, scientific: bool = False) -> str:
+        Formats a number with specified decimal places.
+    
+    check_normality(data: Union[pd.Series, np.ndarray, pd.DataFrame, str, Path], 
+                    column: Optional[str] = None, alpha: float = 0.05) -> dict:
+        Checks if the data follows a normal distribution using the Shapiro-Wilk test.
+    
+    calculate_confidence_intervals(data: Union[pd.Series, np.ndarray, pd.DataFrame, str, Path],
+                                    column: Optional[str] = None, confidence_level: float = 0.95,
+        Calculates confidence intervals for the mean using parametric or bootstrap methods.
+    
+    detect_outliers(data: Union[pd.Series, np.ndarray, pd.DataFrame, str, Path],
+                    column: Optional[str] = None, method: Literal['iqr', 'zscore', 'isolation_forest'] = 'iqr',
+        Detects outliers using different methods: 'iqr', 'zscore', or 'isolation_forest'.
+    
+    calculate_effect_size(data: Union[pd.Series, np.ndarray, pd.DataFrame, str, Path] = None, 
+        Calculates the effect size between two groups using Cohen's d or Hedges' g.
+    
+    plot_distribution(data: Union[pd.DataFrame, pd.Series, np.ndarray, str, Path],
+                      column: Optional[str] = None, plot_type: Literal['hist', 'kde', 'box', 'violin', 'all'] = 'hist',
+                      bins: int = 30, figsize: Optional[Tuple[int, int]] = None,
+                      save_fig: Optional[bool] = False, filename: Optional[str] = None, **kwargs):
+        Plots the distribution of a variable using various plot types and backends.
+    
+    plot_correlation_matrix(data: Union[pd.DataFrame, str, Path],
+                            filename: Optional[str] = None, **kwargs):
+        Visualizes the correlation matrix using a heatmap.
+    
+    plot_scatter_matrix(data: Union[pd.DataFrame, str, Path],
+                        filename: Optional[str] = None, **kwargs):
+        Creates a scatter matrix (pairplot) for visualizing relationships between variables.
+    
+    plot_distribution_with_ci(data: Union[pd.DataFrame, pd.Series, np.ndarray, str, Path],
+                              column: Optional[str] = None, confidence_level: float = 0.95,
+                              ci_method: str = 'parametric', bins: int = 30,
+                              filename: Optional[str] = None, **kwargs) -> plt.Figure:
+        Plots the distribution of a variable with confidence intervals.
+    
+    get_descriptive_stats(data, column=None) -> dict:
+        Returns a dictionary of descriptive statistics for the given data.
+    
+    help():
+        Displays a complete help guide for the UtilsStats class.
     """
     
+    
     def __init__(self):
         """Inicializar la clase utilitaria"""
         self._plot_backend = 'seaborn'

{statslibx-0.1.8.dist-info → statslibx-0.2.1.dist-info}/METADATA

@@ -1,7 +1,7 @@
 Metadata-Version: 2.4
 Name: statslibx
-Version: 0.1.8
-Summary: StatsLibx - Librería de estadística descriptiva e inferencial
+Version: 0.2.1
+Summary: StatsLibx - Librería de estadística descriptiva, inferencial y computacional
 Author-email: Emmanuel Ascendra Perez <ascendraemmanuel@gmail.com>
 License: MIT
 Classifier: Development Status :: 3 - Alpha
@@ -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"
@@ -28,9 +27,9 @@ Requires-Dist: statsmodels>=0.13; extra == "advanced"
 
 StatsLibX es un paquete de Python diseñado para proporcionar una solución sencilla, eficiente y flexible para manejar volumenes de datos.
 
-Este proyecto surge con la idea de ofrecer una alternativa moderna, intuitiva y ligera que permita a desarrolladores y entusiastas integrar la **estadistica descriptiva e inferencial** sin complicaciones, con multiples funcionalidades y utilidades pensadas para el futuro.
+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.
 
-GitHub del Proyecto: [text](https://github.com/GhostAnalyst30/StatsLibX)
+GitHub del Proyecto: [https://github.com/GhostAnalyst30/StatsLibX](https://github.com/GhostAnalyst30/StatsLibX)
 
 ## ✨ Características principales
 
@@ -55,7 +54,7 @@ stats = DescriptiveStats(data) # InferentialStats(data), UtilsStats()
 
 stats.summary()
 ```
-Para ver mas funciones: [text](https://github.com/GhostAnalyst30/StatsLibX/blob/main/how_use_statslibx.ipynb)
+Para ver mas funciones: [https://github.com/GhostAnalyst30/StatsLibX/blob/main/how_use_statslibx.ipynb](https://github.com/GhostAnalyst30/StatsLibX/blob/main/how_use_statslibx.ipynb)
 
 ##  📦 Instalación
 ```bash

statslibx-0.2.1.dist-info/RECORD

@@ -0,0 +1,20 @@
+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=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=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
+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-0.1.8.dist-info → statslibx-0.2.1.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (80.9.0)
+Generator: setuptools (80.10.2)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

{statslibx-0.1.8.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)
+
+
+
+

statslibx/probability.py

@@ -1,2 +0,0 @@
-class ProbabilityStats:
-    pass

statslibx-0.1.8.dist-info/RECORD

@@ -1,15 +0,0 @@
-statslibx/__init__.py,sha256=KeEoEZVPUR_PZACWoCpS_2l6luPbEee7VRlcrLgbKQQ,1490
-statslibx/cli.py,sha256=DqXaoP85n9xgLDlFnEkeqj-HJG0_IKX0uSqxRcHbzII,1122
-statslibx/computacional.py,sha256=Nv8wk67RUuuv15oBRu2XPp0_k7O4ZgmT51vThH2OuFk,35
-statslibx/descriptive.py,sha256=r5D4reP1Cdzsu1tSLmf2OEaFAkGvHSd3FIYfUclEaRU,60178
-statslibx/inferential.py,sha256=H0R6g3dJFk-53m1bKldrXObgk0SSmpcdqQg_tIgRKBI,79169
-statslibx/io.py,sha256=v7pxpmlEMeKyfXftl3WbkUtC9FOh1pymz7MmKPPNw98,493
-statslibx/probability.py,sha256=MUME4eXWzbdU93F-QdKwmmyd9IgZK1flFUYQHitp10o,33
-statslibx/utils.py,sha256=iJzt0jDacaoUfjtp4dU2PFuIBEheMP9Qrq-HnLTW_Qw,66515
-statslibx/datasets/__init__.py,sha256=GuUl_7-d6YanuDFht1dwB1bFrqjShvKh1m-iRYAbYZE,6875
-statslibx/preprocessing/__init__.py,sha256=ZwdwjBodxeOry-umJ__6yUSeubpRlZg41yve366ArkY,7395
-statslibx-0.1.8.dist-info/METADATA,sha256=uyhAd0xghADIfVee7WzDp76nLA2snjqQcNayio_UrIc,2835
-statslibx-0.1.8.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-statslibx-0.1.8.dist-info/entry_points.txt,sha256=bkCY7JDWNCZFE3I4sjgJ2oGrUgoBBbCbYmWkBAymT70,49
-statslibx-0.1.8.dist-info/top_level.txt,sha256=eeYZXyFm0hIjuI0ba3wF6XW938Mv9tv7Nk9qgjYfCtU,10
-statslibx-0.1.8.dist-info/RECORD,,