Package forecasting tools with CLI entry points

.github/workflows/ci.yml

@@ -30,13 +30,12 @@ jobs:
           python-version: ${{ matrix.python-version }}
           cache: pip
           cache-dependency-path: |
-            requirements.txt
-            requirements-dev.txt
+            pyproject.toml
 
-      - name: Install dependencies
+      - name: Install project and development tools
         run: |
           python -m pip install --upgrade pip
-          python -m pip install -r requirements-dev.txt
+          python -m pip install --editable ".[dev]"
 
       - name: Lint Python sources
         run: python -m ruff check src tests streamlit_app.py
@@ -46,3 +45,15 @@ jobs:
 
       - name: Compile Python sources
         run: python -m compileall -q src tests streamlit_app.py
+
+      - name: Build wheel and source distribution
+        run: python -m build
+
+      - name: Smoke-test installed console commands
+        run: |
+          aep-demo --help
+          aep-sample-data --help
+          aep-make-features --help
+          aep-baseline-eval --help
+          aep-xgb-eval --help
+          aep-forecast --help

.gitignore

@@ -5,3 +5,6 @@ data/
 .pytest_cache/
 __pycache__/
 *.py[cod]
+build/
+dist/
+*.egg-info/

README.md

@@ -95,30 +95,32 @@ The data is **not** included in this repo. Download `AEP_hourly.csv` (columns `D
 Run the complete pipeline against a deterministic 90-day sample:
 
 ```powershell
-python -m src.demo_pipeline
+aep-demo
 ```
 
 This single command creates the sample data, features, baseline and XGBoost
 metrics, evaluation plots, trained model, and next-24h forecast under the
 existing ignored `data/`, `reports/`, and `models/` directories. Use
-`--output-dir` to keep every artifact below a different directory.
+`--output-dir` to keep every artifact below a different directory. The module
+form, `python -m src.demo_pipeline`, remains available when working directly
+from a source checkout.
 
-The equivalent individual commands are:
+The equivalent installed console commands are:
 
 ```powershell
-python -m src.sample_data
-python -m src.make_features `
+aep-sample-data
+aep-make-features `
   --input data\sample_aep_hourly.csv `
   --output data\sample_features_aep.csv
-python -m src.baseline_eval `
+aep-baseline-eval `
   --features data\sample_features_aep.csv `
   --metrics reports\sample_baseline_metrics.csv `
   --plot reports\figures\sample_baseline.png
-python -m src.xgb_eval `
+aep-xgb-eval `
   --features data\sample_features_aep.csv `
   --metrics reports\sample_xgb_metrics.csv `
   --plot reports\figures\sample_xgb_evaluation.png
-python -m src.forecast_24h `
+aep-forecast `
   --input data\sample_aep_hourly.csv `
   --features data\sample_features_aep.csv `
   --output reports\sample_forecast.csv `
@@ -136,11 +138,12 @@ must not be used to reproduce the reported benchmark metrics.
 python -m venv .venv
 .\.venv\Scripts\Activate.ps1
 python -m pip install --upgrade pip
-pip install -r requirements.txt
+python -m pip install --editable .
 ```
 
-The requirements include the Streamlit demo as well as the training and
-evaluation dependencies.
+This installs the training and evaluation dependencies, the Streamlit demo,
+and the six `aep-*` console commands. Use `python -m pip install .` instead
+when an editable source checkout is not needed.
 
 ## Usage (Windows / PowerShell)
 
@@ -215,12 +218,14 @@ python -m src.make_features `
 Run the synthetic validation tests with:
 
 ```powershell
-pip install -r requirements-dev.txt
+python -m pip install --editable ".[dev]"
 python -m ruff check src tests streamlit_app.py
 python -m pytest
+python -m build
 ```
 
-GitHub Actions runs the same lint, test, and source-compilation checks on
+GitHub Actions installs the project, runs the same lint, test, source-compilation
+and distribution-build checks, and smoke-tests all six console commands on
 Python 3.10 and 3.12 for every pull request.
 
 ## Limitations

pyproject.toml

@@ -1,3 +1,59 @@
+[build-system]
+requires = ["setuptools>=77"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "aep-load-forecasting"
+version = "0.1.0"
+description = "Reproducible AEP electricity-load forecasting with XGBoost"
+readme = "README.md"
+requires-python = ">=3.10"
+license = "MIT"
+license-files = ["LICENSE"]
+authors = [
+    { name = "Amar Akram" },
+]
+keywords = ["energy", "forecasting", "time-series", "xgboost"]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+]
+dependencies = [
+    "joblib>=1.3",
+    "matplotlib>=3.7",
+    "numpy>=1.24",
+    "pandas>=2.0",
+    "scikit-learn>=1.3",
+    "streamlit>=1.30",
+    "xgboost>=2.0",
+]
+
+[project.optional-dependencies]
+dev = [
+    "build>=1.2",
+    "pytest>=8.0",
+    "ruff==0.16.0",
+]
+
+[project.scripts]
+aep-demo = "src.demo_pipeline:main"
+aep-sample-data = "src.sample_data:main"
+aep-make-features = "src.make_features:main"
+aep-baseline-eval = "src.baseline_eval:main"
+aep-xgb-eval = "src.xgb_eval:main"
+aep-forecast = "src.forecast_24h:main"
+
+[project.urls]
+Homepage = "https://github.com/amarakramali/load-forecasting-xgboost"
+Issues = "https://github.com/amarakramali/load-forecasting-xgboost/issues"
+
+[tool.setuptools]
+packages = ["src"]
+
 [tool.ruff]
 target-version = "py310"
 line-length = 88