dwvml 0.1.0__tar.gz

dwvml-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Dev
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

dwvml-0.1.0/PKG-INFO

@@ -0,0 +1,46 @@
+Metadata-Version: 2.4
+Name: dwvml
+Version: 0.1.0
+Summary: Reusable preprocessing utilities for machine learning
+Author: Dev
+License: MIT
+Project-URL: Homepage, https://github.com/yourusername/dwvml
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: numpy>=1.23
+Requires-Dist: pandas>=1.5
+Requires-Dist: scipy>=1.9
+Requires-Dist: scikit-learn>=1.2
+Dynamic: license-file
+Dynamic: requires-python
+
+# DWVML
+
+Reusable preprocessing utilities for tabular machine learning.
+
+## Install
+
+```bash
+pip install dwvml
+```
+
+## Usage
+
+```python
+from dwvml import preprocess_train_test
+
+x_train_final, x_test_final, preprocessors = preprocess_train_test(
+    x_train,
+    x_test
+)
+```
+
+The package automatically detects numerical and categorical columns, imputes missing values, scales numerical features, one-hot encodes categorical features, and combines the resulting features.
+
+Transform another dataset later with the fitted preprocessors:
+
+```python
+from dwvml import transform_new_data
+x_new_final = transform_new_data(x_new, preprocessors)
+```

dwvml-0.1.0/README.md

@@ -0,0 +1,29 @@
+# DWVML
+
+Reusable preprocessing utilities for tabular machine learning.
+
+## Install
+
+```bash
+pip install dwvml
+```
+
+## Usage
+
+```python
+from dwvml import preprocess_train_test
+
+x_train_final, x_test_final, preprocessors = preprocess_train_test(
+    x_train,
+    x_test
+)
+```
+
+The package automatically detects numerical and categorical columns, imputes missing values, scales numerical features, one-hot encodes categorical features, and combines the resulting features.
+
+Transform another dataset later with the fitted preprocessors:
+
+```python
+from dwvml import transform_new_data
+x_new_final = transform_new_data(x_new, preprocessors)
+```

dwvml-0.1.0/dwvml/__init__.py

@@ -0,0 +1,10 @@
+"""DWVML - reusable preprocessing utilities for machine learning."""
+
+from .preprocessing import preprocess_train_test, transform_new_data
+
+__version__ = "0.1.0"
+
+__all__ = [
+    "preprocess_train_test",
+    "transform_new_data",
+]

dwvml-0.1.0/dwvml/preprocessing.py

@@ -0,0 +1,111 @@
+"""Preprocessing helpers for tabular machine-learning data."""
+
+import numpy as np
+import pandas as pd
+from scipy.sparse import hstack
+from sklearn.impute import SimpleImputer
+from sklearn.preprocessing import OneHotEncoder, StandardScaler
+
+
+def preprocess_train_test(x_train: pd.DataFrame, x_test: pd.DataFrame):
+    """Preprocess train/test tabular data with consistent fitted transformers.
+
+    Numerical columns: median imputation -> StandardScaler
+    Categorical columns: most-frequent imputation -> OneHotEncoder
+    The transformers are fitted only on x_train.
+
+    Returns
+    -------
+    x_train_final, x_test_final, preprocessors
+    """
+    if not isinstance(x_train, pd.DataFrame):
+        raise TypeError("x_train must be a pandas DataFrame.")
+    if not isinstance(x_test, pd.DataFrame):
+        raise TypeError("x_test must be a pandas DataFrame.")
+
+    missing_in_test = [c for c in x_train.columns if c not in x_test.columns]
+    extra_in_test = [c for c in x_test.columns if c not in x_train.columns]
+    if missing_in_test:
+        raise ValueError(f"Columns missing in x_test: {missing_in_test}")
+    if extra_in_test:
+        raise ValueError(f"Extra columns in x_test: {extra_in_test}")
+
+    x_test = x_test[x_train.columns]
+
+    numeric_cols = x_train.select_dtypes(include="number").columns.tolist()
+    categorical_cols = x_train.select_dtypes(include=["object", "category", "string"]).columns.tolist()
+
+    num_imputer = SimpleImputer(strategy="median")
+    scaler = None
+    if numeric_cols:
+        x_train_num = num_imputer.fit_transform(x_train[numeric_cols])
+        x_test_num = num_imputer.transform(x_test[numeric_cols])
+        scaler = StandardScaler()
+        x_train_scl = scaler.fit_transform(x_train_num)
+        x_test_scl = scaler.transform(x_test_num)
+    else:
+        x_train_scl = np.empty((len(x_train), 0))
+        x_test_scl = np.empty((len(x_test), 0))
+
+    cat_imputer = SimpleImputer(strategy="most_frequent")
+    ohe = None
+    if categorical_cols:
+        x_train_cat = cat_imputer.fit_transform(x_train[categorical_cols])
+        x_test_cat = cat_imputer.transform(x_test[categorical_cols])
+        ohe = OneHotEncoder(handle_unknown="ignore")
+        x_train_ohe = ohe.fit_transform(x_train_cat)
+        x_test_ohe = ohe.transform(x_test_cat)
+    else:
+        x_train_ohe = None
+        x_test_ohe = None
+
+    if numeric_cols and categorical_cols:
+        x_train_final = hstack((x_train_scl, x_train_ohe)).tocsr()
+        x_test_final = hstack((x_test_scl, x_test_ohe)).tocsr()
+    elif numeric_cols:
+        x_train_final = x_train_scl
+        x_test_final = x_test_scl
+    elif categorical_cols:
+        x_train_final = x_train_ohe
+        x_test_final = x_test_ohe
+    else:
+        raise ValueError("No numerical or categorical feature columns were found.")
+
+    preprocessors = {
+        "numeric_cols": numeric_cols,
+        "categorical_cols": categorical_cols,
+        "num_imputer": num_imputer,
+        "cat_imputer": cat_imputer,
+        "scaler": scaler,
+        "ohe": ohe,
+    }
+    return x_train_final, x_test_final, preprocessors
+
+
+def transform_new_data(x_new: pd.DataFrame, preprocessors: dict):
+    """Transform new data using preprocessors already fitted by preprocess_train_test."""
+    if not isinstance(x_new, pd.DataFrame):
+        raise TypeError("x_new must be a pandas DataFrame.")
+
+    numeric_cols = preprocessors["numeric_cols"]
+    categorical_cols = preprocessors["categorical_cols"]
+
+    if numeric_cols:
+        x_new_num = preprocessors["num_imputer"].transform(x_new[numeric_cols])
+        x_new_scl = preprocessors["scaler"].transform(x_new_num)
+    else:
+        x_new_scl = np.empty((len(x_new), 0))
+
+    if categorical_cols:
+        x_new_cat = preprocessors["cat_imputer"].transform(x_new[categorical_cols])
+        x_new_ohe = preprocessors["ohe"].transform(x_new_cat)
+    else:
+        x_new_ohe = None
+
+    if numeric_cols and categorical_cols:
+        return hstack((x_new_scl, x_new_ohe)).tocsr()
+    if numeric_cols:
+        return x_new_scl
+    if categorical_cols:
+        return x_new_ohe
+    raise ValueError("No numerical or categorical feature columns were found.")

dwvml-0.1.0/dwvml.egg-info/PKG-INFO

@@ -0,0 +1,46 @@
+Metadata-Version: 2.4
+Name: dwvml
+Version: 0.1.0
+Summary: Reusable preprocessing utilities for machine learning
+Author: Dev
+License: MIT
+Project-URL: Homepage, https://github.com/yourusername/dwvml
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: numpy>=1.23
+Requires-Dist: pandas>=1.5
+Requires-Dist: scipy>=1.9
+Requires-Dist: scikit-learn>=1.2
+Dynamic: license-file
+Dynamic: requires-python
+
+# DWVML
+
+Reusable preprocessing utilities for tabular machine learning.
+
+## Install
+
+```bash
+pip install dwvml
+```
+
+## Usage
+
+```python
+from dwvml import preprocess_train_test
+
+x_train_final, x_test_final, preprocessors = preprocess_train_test(
+    x_train,
+    x_test
+)
+```
+
+The package automatically detects numerical and categorical columns, imputes missing values, scales numerical features, one-hot encodes categorical features, and combines the resulting features.
+
+Transform another dataset later with the fitted preprocessors:
+
+```python
+from dwvml import transform_new_data
+x_new_final = transform_new_data(x_new, preprocessors)
+```

dwvml-0.1.0/dwvml.egg-info/SOURCES.txt

@@ -0,0 +1,11 @@
+LICENSE
+README.md
+pyproject.toml
+setup.py
+dwvml/__init__.py
+dwvml/preprocessing.py
+dwvml.egg-info/PKG-INFO
+dwvml.egg-info/SOURCES.txt
+dwvml.egg-info/dependency_links.txt
+dwvml.egg-info/requires.txt
+dwvml.egg-info/top_level.txt

dwvml-0.1.0/dwvml.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

dwvml-0.1.0/dwvml.egg-info/requires.txt

@@ -0,0 +1,4 @@
+numpy>=1.23
+pandas>=1.5
+scipy>=1.9
+scikit-learn>=1.2

dwvml-0.1.0/dwvml.egg-info/top_level.txt

@@ -0,0 +1 @@
+dwvml

dwvml-0.1.0/pyproject.toml

@@ -0,0 +1,24 @@
+[build-system]
+requires = ["setuptools>=68", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "dwvml"
+version = "0.1.0"
+description = "Reusable preprocessing utilities for machine learning"
+readme = "README.md"
+requires-python = ">=3.9"
+license = { text = "MIT" }
+authors = [{ name = "Dev" }]
+dependencies = [
+    "numpy>=1.23",
+    "pandas>=1.5",
+    "scipy>=1.9",
+    "scikit-learn>=1.2",
+]
+
+[project.urls]
+Homepage = "https://github.com/yourusername/dwvml"
+
+[tool.setuptools.packages.find]
+include = ["dwvml*"]

dwvml-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

dwvml-0.1.0/setup.py

@@ -0,0 +1,16 @@
+from setuptools import setup, find_packages
+
+setup(
+    name="dwvml",
+    version="0.1.0",
+    description="Reusable preprocessing utilities for machine learning",
+    author="Dev",
+    packages=find_packages(),
+    python_requires=">=3.9",
+    install_requires=[
+        "numpy>=1.23",
+        "pandas>=1.5",
+        "scipy>=1.9",
+        "scikit-learn>=1.2",
+    ],
+)