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

statslibx/io.py

@@ -0,0 +1,21 @@
+import pandas as pd
+import polars as pl
+from pathlib import Path
+
+
+def load_file(path: str):
+    path = Path(path)
+
+    if not path.exists():
+        raise FileNotFoundError(f"{path} not found")
+
+    if path.suffix == ".csv":
+        return pd.read_csv(path)
+
+    if path.suffix == ".json":
+        return pd.read_json(path)
+
+    if path.suffix in {".txt", ".tsv"}:
+        return pd.read_csv(path, sep="\t")
+
+    raise ValueError(f"Unsupported file type: {path.suffix}")

statslibx/preprocessing/__init__.py

@@ -0,0 +1,221 @@
+from typing import Optional, Union, List, Dict, Any
+import pandas as pd
+import polars as pl
+import numpy as np
+
+
+class Preprocessing:
+
+    def __init__(self, data: Union[pd.DataFrame, pl.DataFrame]):
+        if not isinstance(data, (pd.DataFrame, pl.DataFrame)):
+            raise TypeError("data must be a pandas or polars DataFrame")
+        self.data = data
+
+    # ------------------------------------------------------------------
+    # Internal helpers
+    # ------------------------------------------------------------------
+
+    def _is_pandas(self) -> bool:
+        return isinstance(self.data, pd.DataFrame)
+
+    def _is_polars(self) -> bool:
+        return isinstance(self.data, pl.DataFrame)
+
+    def _count_nulls(self, column: str) -> int:
+        if self._is_pandas():
+            return int(self.data[column].isna().sum())
+        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
+
+    # ------------------------------------------------------------------
+    # Inspection
+    # ------------------------------------------------------------------
+
+    def detect_nulls(
+        self,
+        columns: Optional[Union[str, List[str]]] = None
+    ) -> pd.DataFrame:
+
+        columns = self._get_columns(columns)
+        total = self.data.shape[0]
+
+        rows = []
+        for col in columns:
+            nulls = self._count_nulls(col)
+            rows.append({
+                "column": col,
+                "nulls": nulls,
+                "non_nulls": total - nulls,
+                "null_pct": nulls / total
+            })
+
+        return pd.DataFrame(rows)
+
+    def check_uniqueness(self) -> pd.DataFrame:
+        if self._is_pandas():
+            unique = self.data.nunique()
+            return pd.DataFrame({
+                "column": unique.index,
+                "unique_values": unique.values
+            })
+
+        unique = self.data.select(pl.all().n_unique())
+        return unique.to_pandas().melt(
+            var_name="column",
+            value_name="unique_values"
+        )
+
+    def preview_data(self, n: int = 5):
+        return self.data.head(n)
+
+    # ------------------------------------------------------------------
+    # Description
+    # ------------------------------------------------------------------
+
+    def describe_numeric(self):
+        if self._is_pandas():
+            return self.data.select_dtypes(include=np.number).describe()
+
+        return self.data.select(pl.all().filter(pl.col(pl.NUMERIC))).describe()
+
+    def describe_categorical(self):
+        if self._is_pandas():
+            return self.data.select_dtypes(include="object").describe()
+
+        return self.data.select(pl.all().filter(pl.col(pl.Utf8))).describe()
+
+    # ------------------------------------------------------------------
+    # Transformations
+    # ------------------------------------------------------------------
+
+    def fill_nulls(
+        self,
+        fill_with: Any,
+        columns: Optional[Union[str, List[str]]] = None
+    ):
+        columns = self._get_columns(columns)
+
+        if self._is_pandas():
+            self.data[columns] = self.data[columns].fillna(fill_with)
+
+        else:
+            self.data = self.data.with_columns([
+                pl.col(col).fill_null(fill_with) for col in columns
+            ])
+
+        return self
+
+    def normalize(self, column: str):
+        if self._is_pandas():
+            col = self.data[column]
+            self.data[column] = (col - col.min()) / (col.max() - col.min())
+        else:
+            self.data = self.data.with_columns(
+                ((pl.col(column) - pl.col(column).min()) /
+                 (pl.col(column).max() - pl.col(column).min()))
+                .alias(column)
+            )
+        return self
+
+    def standardize(self, column: str):
+        if self._is_pandas():
+            col = self.data[column]
+            self.data[column] = (col - col.mean()) / col.std()
+        else:
+            self.data = self.data.with_columns(
+                ((pl.col(column) - pl.col(column).mean()) /
+                 pl.col(column).std())
+                .alias(column)
+            )
+        return self
+
+    # ------------------------------------------------------------------
+    # Filtering
+    # ------------------------------------------------------------------
+
+    def filter_rows(self, condition):
+        if self._is_pandas():
+            self.data = self.data.loc[condition]
+        else:
+            self.data = self.data.filter(condition)
+        return self
+
+    def filter_columns(self, columns: List[str]):
+        if self._is_pandas():
+            self.data = self.data[columns]
+        else:
+            self.data = self.data.select(columns)
+        return self
+
+    def rename_columns(self, mapping: Dict[str, str]):
+        if self._is_pandas():
+            self.data = self.data.rename(columns=mapping)
+        else:
+            self.data = self.data.rename(mapping)
+        return self
+
+    # ------------------------------------------------------------------
+    # Outliers
+    # ------------------------------------------------------------------
+
+    def detect_outliers(
+        self,
+        column: str,
+        method: str = "iqr"
+    ) -> pd.DataFrame:
+
+        if self._is_pandas():
+            series = self.data[column]
+        else:
+            series = self.data[column].to_pandas()
+
+        if method == "iqr":
+            q1 = series.quantile(0.25)
+            q3 = series.quantile(0.75)
+            iqr = q3 - q1
+            mask = (series < q1 - 1.5 * iqr) | (series > q3 + 1.5 * iqr)
+
+        elif method == "zscore":
+            z = (series - series.mean()) / series.std()
+            mask = z.abs() > 3
+
+        else:
+            raise ValueError("method must be 'iqr' or 'zscore'")
+
+        return self.data[mask]
+
+    # ------------------------------------------------------------------
+    # Data Quality Report
+    # ------------------------------------------------------------------
+
+    def data_quality(self) -> pd.DataFrame:
+        total_rows = self.data.shape[0]
+        rows = []
+
+        for col in self.data.columns:
+            nulls = self._count_nulls(col)
+
+            if self._is_pandas():
+                dtype = str(self.data[col].dtype)
+                unique = self.data[col].nunique()
+            else:
+                dtype = str(self.data.schema[col])
+                unique = self.data[col].n_unique()
+
+            rows.append({
+                "column": col,
+                "dtype": dtype,
+                "nulls": nulls,
+                "null_pct": nulls / total_rows,
+                "unique_values": unique,
+                "completeness_pct": 1 - (nulls / total_rows)
+            })
+
+        return pd.DataFrame(rows)
+

{statslibx-0.1.6.dist-info → statslibx-0.1.7.dist-info}/METADATA

@@ -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.dist-info/RECORD

@@ -0,0 +1,18 @@
+statslibx/__init__.py,sha256=vXAOPdog5n_b64FRybiWI4VNA_eou7eQuZBcQiQz79E,1297
+statslibx/cli.py,sha256=DqXaoP85n9xgLDlFnEkeqj-HJG0_IKX0uSqxRcHbzII,1122
+statslibx/descriptive.py,sha256=UTb104Gho0uNeSALlukgrYwXrGMDwmIEy39-yvHuy8M,60184
+statslibx/inferential.py,sha256=0lpVAp2SiKDgWkH3z3JoVFAjMaXW2VboxtA2vwPwq04,49947
+statslibx/io.py,sha256=v7pxpmlEMeKyfXftl3WbkUtC9FOh1pymz7MmKPPNw98,493
+statslibx/utils.py,sha256=qDqF_XgvEJbdQURA2v0gF0sw0nNQR4-MFXDvVTl_00s,68480
+statslibx/datasets/__init__.py,sha256=HlOjJFalKVAycJEi7_J_OB7ss8jgSWpPQnsHTynt0uo,2273
+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=B6qI_KuqWf0FFnLLFafIaPOIM9ABo73InKCscSypdqI,7107
+statslibx-0.1.7.dist-info/METADATA,sha256=GN3chKZ7qSdoAKeD54rCxiwRoWk0wiFpLxHmxtc6Skc,2321
+statslibx-0.1.7.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+statslibx-0.1.7.dist-info/entry_points.txt,sha256=bkCY7JDWNCZFE3I4sjgJ2oGrUgoBBbCbYmWkBAymT70,49
+statslibx-0.1.7.dist-info/top_level.txt,sha256=eeYZXyFm0hIjuI0ba3wF6XW938Mv9tv7Nk9qgjYfCtU,10
+statslibx-0.1.7.dist-info/RECORD,,

statslibx-0.1.7.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+statslibx = statslibx.cli:main

statslibx-0.1.6.dist-info/RECORD

@@ -1,14 +0,0 @@
-statslibx/__init__.py,sha256=gA9uNJ7Th8mJunugVps8UWgBNJtMeo_mHqU-QSkEXQE,1173
-statslibx/descriptive.py,sha256=Hjti-Cs-7-SzrTb0k4s92c4nasLthVwhYU75GS56LAc,40124
-statslibx/inferential.py,sha256=0lpVAp2SiKDgWkH3z3JoVFAjMaXW2VboxtA2vwPwq04,49947
-statslibx/utils.py,sha256=qDqF_XgvEJbdQURA2v0gF0sw0nNQR4-MFXDvVTl_00s,68480
-statslibx/datasets/__init__.py,sha256=wQ4p8hXIhJqV-msWzTvvnbv-l7jyWz5Rn3JZyMSYJ44,452
-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-0.1.6.dist-info/METADATA,sha256=7djbcDCGKwPIIjMnF3hjrsjpgeJFUYxEO9zrVTayUj0,2943
-statslibx-0.1.6.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-statslibx-0.1.6.dist-info/top_level.txt,sha256=eeYZXyFm0hIjuI0ba3wF6XW938Mv9tv7Nk9qgjYfCtU,10
-statslibx-0.1.6.dist-info/RECORD,,