best-model-toolkit 0.1.0__tar.gz

best_model_toolkit-0.1.0/PKG-INFO

@@ -0,0 +1,88 @@
+Metadata-Version: 2.4
+Name: best-model-toolkit
+Version: 0.1.0
+Summary: Train, tune, and compare sklearn/XGBoost models with built-in metric plots
+Author: Your Name
+License: MIT
+Project-URL: Homepage, https://github.com/YOUR_USERNAME/best-model-toolkit
+Project-URL: Issues, https://github.com/YOUR_USERNAME/best-model-toolkit/issues
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+Requires-Dist: numpy
+Requires-Dist: pandas
+Requires-Dist: scipy
+Requires-Dist: matplotlib
+Requires-Dist: seaborn
+Requires-Dist: scikit-learn>=1.2
+Requires-Dist: xgboost
+
+# best-model-toolkit
+
+A collection of functions for quickly training, tuning (`GridSearchCV`) and
+comparing several `scikit-learn` / `XGBoost` models for **regression** and
+**classification** tasks, with automatic plots of metrics (R², MAE, RMSE,
+F1, precision, recall, PR curves, etc).
+
+## Installation
+
+### Locally (before the package is on PyPI)
+
+```bash
+git clone https://github.com/YOUR_USERNAME/best-model-toolkit.git
+cd best-model-toolkit
+pip install -e .
+```
+
+### Directly from GitHub
+
+```bash
+pip install git+https://github.com/YOUR_USERNAME/best-model-toolkit.git
+```
+
+### From PyPI (once published, see below)
+
+```bash
+pip install best-model-toolkit
+```
+
+## Usage
+
+```python
+from best_model_toolkit import best_model
+import pandas as pd
+
+df = pd.read_csv("your_data.csv")
+X = df.drop(columns=["target"])
+y = df["target"]
+
+results = best_model(
+    features=X,
+    target=y,
+    mode="regression",      # or "classification"
+    grid="Yes",              # "Yes"/"No" — whether to run GridSearchCV
+    df=df,
+    hue=None,                 # column for pairplot hue (classification)
+)
+
+# results — dict {"model_name": {"model": ..., "param": ..., "metrics": {...}}}
+```
+
+## Package structure
+
+```
+best_model_toolkit/
+├── pyproject.toml
+├── README.md
+└── src/
+    └── best_model_toolkit/
+        ├── __init__.py
+        └── core.py
+```
+
+## Publishing to PyPI
+
+```bash
+pip install build twine
+python -m build
+twine upload dist/*
+```

best_model_toolkit-0.1.0/README.md

@@ -0,0 +1,70 @@
+# best-model-toolkit
+
+A collection of functions for quickly training, tuning (`GridSearchCV`) and
+comparing several `scikit-learn` / `XGBoost` models for **regression** and
+**classification** tasks, with automatic plots of metrics (R², MAE, RMSE,
+F1, precision, recall, PR curves, etc).
+
+## Installation
+
+### Locally (before the package is on PyPI)
+
+```bash
+git clone https://github.com/YOUR_USERNAME/best-model-toolkit.git
+cd best-model-toolkit
+pip install -e .
+```
+
+### Directly from GitHub
+
+```bash
+pip install git+https://github.com/YOUR_USERNAME/best-model-toolkit.git
+```
+
+### From PyPI (once published, see below)
+
+```bash
+pip install best-model-toolkit
+```
+
+## Usage
+
+```python
+from best_model_toolkit import best_model
+import pandas as pd
+
+df = pd.read_csv("your_data.csv")
+X = df.drop(columns=["target"])
+y = df["target"]
+
+results = best_model(
+    features=X,
+    target=y,
+    mode="regression",      # or "classification"
+    grid="Yes",              # "Yes"/"No" — whether to run GridSearchCV
+    df=df,
+    hue=None,                 # column for pairplot hue (classification)
+)
+
+# results — dict {"model_name": {"model": ..., "param": ..., "metrics": {...}}}
+```
+
+## Package structure
+
+```
+best_model_toolkit/
+├── pyproject.toml
+├── README.md
+└── src/
+    └── best_model_toolkit/
+        ├── __init__.py
+        └── core.py
+```
+
+## Publishing to PyPI
+
+```bash
+pip install build twine
+python -m build
+twine upload dist/*
+```

best_model_toolkit-0.1.0/pyproject.toml

@@ -0,0 +1,30 @@
+[build-system]
+requires = ["setuptools>=68", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "best-model-toolkit"
+version = "0.1.0"
+description = "Train, tune, and compare sklearn/XGBoost models with built-in metric plots"
+readme = "README.md"
+requires-python = ">=3.9"
+license = { text = "MIT" }
+authors = [
+    { name = "Your Name" }
+]
+dependencies = [
+    "numpy",
+    "pandas",
+    "scipy",
+    "matplotlib",
+    "seaborn",
+    "scikit-learn>=1.2",
+    "xgboost",
+]
+
+[project.urls]
+Homepage = "https://github.com/YOUR_USERNAME/best-model-toolkit"
+Issues = "https://github.com/YOUR_USERNAME/best-model-toolkit/issues"
+
+[tool.setuptools.packages.find]
+where = ["src"]

best_model_toolkit-0.1.0/setup.cfg

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

best_model_toolkit-0.1.0/src/best_model_toolkit/__init__.py

@@ -0,0 +1,75 @@
+"""
+best_model_toolkit
+===================
+
+Utilities for training, tuning (GridSearchCV) and comparing scikit-learn /
+XGBoost models for regression and classification tasks, together with
+ready-made plots of performance metrics (R^2, MAE, RMSE, F1, precision,
+recall, PR curves, etc).
+
+Main function:
+
+    from best_model_toolkit import best_model
+
+    results = best_model(
+        features=X, target=y,
+        mode="regression",       # or "classification"
+        grid="Yes",               # whether to run GridSearchCV
+        df=df, hue=None,
+        pairplot_type="heatmap",  # "heatmap" | "top_corr" | "full" | "none"
+    )
+"""
+
+from .core import (
+    best_model,
+    test_model_reg,
+    test_model_class,
+    grid_reg,
+    grid_class,
+    plot_r2,
+    plot_score_reg,
+    plot_mae,
+    plot_rmse,
+    plot_score,
+    plot_f1_score,
+    plot_score_precision,
+    plot_score_recall,
+    plot_score_ap,
+    plot_score_generic,
+    plot_curve_generic,
+    plot_cv_r2,
+    plot_mae_mse,
+    plot_cv_metrics,
+    plot_pair_grid_ref,
+    plot_pair_grid_class,
+    plot_corr_heatmap,
+    plot_pair_grid_top_corr,
+)
+
+__version__ = "0.2.0"
+
+__all__ = [
+    "best_model",
+    "test_model_reg",
+    "test_model_class",
+    "grid_reg",
+    "grid_class",
+    "plot_r2",
+    "plot_score_reg",
+    "plot_mae",
+    "plot_rmse",
+    "plot_score",
+    "plot_f1_score",
+    "plot_score_precision",
+    "plot_score_recall",
+    "plot_score_ap",
+    "plot_score_generic",
+    "plot_curve_generic",
+    "plot_cv_r2",
+    "plot_mae_mse",
+    "plot_cv_metrics",
+    "plot_pair_grid_ref",
+    "plot_pair_grid_class",
+    "plot_corr_heatmap",
+    "plot_pair_grid_top_corr",
+]