purgedcv 0.0.1__tar.gz

purgedcv-0.0.1/.github/workflows/ci.yml

@@ -0,0 +1,127 @@
+name: CI
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+permissions:
+  contents: write
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.10", "3.11", "3.12"]
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Install
+        run: |
+          python -m pip install --upgrade pip
+          pip install -e ".[dev]"
+
+      - name: Ruff lint
+        run: ruff check .
+
+      - name: Ruff format check
+        run: ruff format --check .
+
+      - name: Mypy (strict)
+        run: mypy src tests
+
+      - name: Pytest
+        run: pytest -q
+
+  # Publish the current version, then bump the patch for next time.
+  # Order is deliberate: file starts at 0.0.1, so the first automated
+  # release is exactly 0.0.1; --skip-existing makes re-runs safe.
+  release:
+    needs: test
+    if: >-
+      github.event_name == 'push' &&
+      github.ref == 'refs/heads/main' &&
+      github.actor != 'github-actions[bot]'
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          token: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+
+      - name: Install tooling
+        run: |
+          python -m pip install --upgrade pip
+          pip install build twine anybadge
+          pip install -e ".[dev]"
+
+      - name: Read current version
+        id: ver
+        run: |
+          v=$(python -c "import tomllib,pathlib;print(tomllib.loads(pathlib.Path('pyproject.toml').read_text())['project']['version'])")
+          echo "version=$v" >> "$GITHUB_OUTPUT"
+
+      - name: Build
+        run: python -m build
+
+      - name: Publish to PyPI
+        env:
+          TWINE_USERNAME: ${{ secrets.PYPI_USERNAME }}
+          TWINE_PASSWORD: ${{ secrets.PYPI_PASSWORD }}
+        run: twine upload --non-interactive --skip-existing dist/*
+
+      - name: Coverage badge
+        run: |
+          pytest -q --cov=purgedcv --cov-report=json:coverage.json >/dev/null
+          cov=$(jq '.totals.percent_covered | round' coverage.json)
+          echo "coverage: ${cov}%"
+          mkdir -p .github/badges
+          anybadge -o --value="${cov}%" --file=.github/badges/coverage.svg --label=coverage --color="#007ec6"
+
+      - name: Bump patch version for next release
+        id: bump
+        run: |
+          new=$(python - <<'PY'
+          import re, pathlib
+          p = pathlib.Path("pyproject.toml")
+          t = p.read_text()
+          m = re.search(r'(?m)^version = "(\d+)\.(\d+)\.(\d+)"$', t)
+          if not m:
+              raise SystemExit('expected version = "X.Y.Z" in pyproject.toml')
+          maj, mnr, pat = map(int, m.groups())
+          nv = f"{maj}.{mnr}.{pat + 1}"
+          p.write_text(t[: m.start()] + f'version = "{nv}"' + t[m.end() :])
+          print(nv)
+          PY
+          )
+          echo "next=$new" >> "$GITHUB_OUTPUT"
+
+      - name: Commit badge + version bump
+        run: |
+          git config user.name 'github-actions[bot]'
+          git config user.email 'github-actions[bot]@users.noreply.github.com'
+          git add pyproject.toml .github/badges/coverage.svg
+          git commit -m "chore: release v${{ steps.ver.outputs.version }}, bump to v${{ steps.bump.outputs.next }}"
+          git push
+
+      - name: GitHub Release
+        uses: softprops/action-gh-release@v2
+        with:
+          tag_name: "v${{ steps.ver.outputs.version }}"
+          name: "v${{ steps.ver.outputs.version }}"
+          body: "Automated release of v${{ steps.ver.outputs.version }}."
+          generate_release_notes: true
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

purgedcv-0.0.1/.gitignore

@@ -0,0 +1,227 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#   Usually these files are written by a python script from a template
+#   before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py.cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+# Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+# uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+# poetry.lock
+# poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+# pdm.lock
+# pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+# pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# Redis
+*.rdb
+*.aof
+*.pid
+
+# RabbitMQ
+mnesia/
+rabbitmq/
+rabbitmq-data/
+
+# ActiveMQ
+activemq-data/
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#   JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#   be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#   and can be added to the global gitignore or merged into this file.  For a more nuclear
+#   option (not recommended) you can uncomment the following to ignore the entire idea folder.
+.idea/
+
+# Abstra
+#   Abstra is an AI-powered process automation framework.
+#   Ignore directories containing user credentials, local state, and settings.
+#   Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#   Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore
+#   that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#   and can be added to the global gitignore or merged into this file. However, if you prefer,
+#   you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+# Temporary file for partial code execution
+tempCodeRunnerFile.py
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+# Streamlit
+.streamlit/secrets.toml
+
+# Example notebook downloaded datasets (lazily fetched on first run)
+examples/data/
+
+# docs/ kept locally for reference, not published (internal plans, drafts)
+docs/
+
+# Local dev tooling, not published
+tools/

purgedcv-0.0.1/.pre-commit-config.yaml

@@ -0,0 +1,16 @@
+repos:
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.15.12
+    hooks:
+      - id: ruff
+        args: [--fix]
+      - id: ruff-format
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v6.0.0
+    hooks:
+      - id: trailing-whitespace
+      - id: end-of-file-fixer
+      - id: check-yaml
+      - id: check-toml
+      - id: check-added-large-files
+        args: [--maxkb=500]

purgedcv-0.0.1/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Evgenii Lazarev
+
+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.

purgedcv-0.0.1/PKG-INFO

@@ -0,0 +1,232 @@
+Metadata-Version: 2.4
+Name: purgedcv
+Version: 0.0.1
+Summary: scikit-learn-compatible cross-validation for time-series machine learning: purging, embargoes, combinatorial backtest paths.
+Project-URL: Homepage, https://github.com/eslazarev/purged-cross-validation
+Project-URL: Repository, https://github.com/eslazarev/purged-cross-validation
+Author: Evgenii Lazarev
+License: MIT
+License-File: LICENSE
+Keywords: combinatorial-cv,cross-validation,machine-learning,purged-kfold,scikit-learn,time-series
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.10
+Requires-Dist: numpy>=1.24
+Requires-Dist: pandas>=2.0
+Requires-Dist: scikit-learn>=1.3
+Requires-Dist: scipy>=1.10
+Provides-Extra: dev
+Requires-Dist: hypothesis>=6.80; extra == 'dev'
+Requires-Dist: mypy>=1.10; extra == 'dev'
+Requires-Dist: pandas-stubs>=2.0; extra == 'dev'
+Requires-Dist: pre-commit>=3.5; extra == 'dev'
+Requires-Dist: pytest-cov>=4.1; extra == 'dev'
+Requires-Dist: pytest>=7.4; extra == 'dev'
+Requires-Dist: ruff>=0.5; extra == 'dev'
+Provides-Extra: examples
+Requires-Dist: jupyter>=1.0; extra == 'examples'
+Requires-Dist: matplotlib>=3.7; extra == 'examples'
+Description-Content-Type: text/markdown
+
+# Purged cross validation
+
+**scikit-learn-compatible cross-validation for time-series machine learning: purging, embargoes, and combinatorial backtest paths.**
+
+[![CI](https://github.com/eslazarev/purged-cross-validation/actions/workflows/ci.yml/badge.svg)](https://github.com/eslazarev/purged-cross-validation/actions/workflows/ci.yml)
+![Coverage](https://raw.githubusercontent.com/eslazarev/purged-cross-validation/refs/heads/main/.github/badges/coverage.svg)
+[![PyPI version](https://img.shields.io/pypi/v/purgedcv)](https://pypi.org/project/purgedcv/)
+[![PyPI downloads](https://static.pepy.tech/badge/purgedcv)](https://pepy.tech/project/purgedcv)
+[![PyPI wheel](https://img.shields.io/pypi/wheel/purgedcv)](https://pypi.org/project/purgedcv/#files)
+
+[![Python versions](https://img.shields.io/badge/python-3.10%20%7C%203.11%20%7C%203.12-blue)](https://www.python.org/downloads/)
+[![License: MIT](https://img.shields.io/badge/license-MIT-green)](LICENSE)
+[![Ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json)](https://github.com/astral-sh/ruff)
+[![Checked with mypy](https://www.mypy-lang.org/static/mypy_badge.svg)](https://mypy-lang.org/)
+[![pre-commit](https://img.shields.io/badge/pre--commit-enabled-brightgreen?logo=pre-commit&logoColor=white)](https://pre-commit.com/)
+[![Development status: alpha](https://img.shields.io/badge/status-alpha-orange)](https://pypi.org/project/purgedcv/)
+
+**[Example notebooks →](examples/)** — purge/embargo, walk-forward, and CPCV with PSR/DSR worked end to end on real ICU-mortality, turbofan-RUL, rainfall, and electricity-demand data.
+
+---
+
+## The problem
+
+Standard k-fold cross-validation assumes the rows are independent. Time-series data is not. When a label resolves over the next few days, it overlaps the labels sitting right next to it, so an ordinary shuffle-split leaks tomorrow's answer back into training. The rows immediately after a test window leak too, because they are serially correlated with it. Both effects quietly inflate backtested Sharpe ratios and hand you strategies that look great on a chart and bleed money once they go live. This library removes both.
+
+Why write another one? People have asked scikit-learn, auto-sklearn, and mlpack for purging and embargo support and been turned down or left waiting for years. The one mature implementation, mlfinlab, went closed-source and paid. The free alternative has been unmaintained since 2018. That gap is the reason this exists.
+
+---
+
+## Installation
+
+```bash
+
+pip install purgedcv
+
+# Directly from the repository
+pip install git+https://github.com/eslazarev/purged-cross-validation.git
+```
+
+---
+
+## Quickstart
+
+### 1. Foundation primitives: `purge`, `apply_embargo`, and diagnostics
+
+Build a manual split, clean it with the purge and embargo primitives, then audit it with the diagnostics submodule.
+
+```python
+import numpy as np
+import pandas as pd
+from purgedcv import purge, apply_embargo
+from purgedcv.diagnostics import assert_no_temporal_leakage, assert_embargo_respected
+
+# 30 daily bars; each bar's label resolves 2 days later
+pred  = pd.Series(pd.date_range("2024-01-01", periods=30, freq="D"))
+evalu = pred + pd.Timedelta(days=2)
+
+train_idx = np.arange(0, 20)
+test_idx  = np.arange(20, 30)
+
+# Remove training rows whose label horizon overlaps the test window
+clean_train = purge(train_idx, test_idx, pred, evalu)
+
+# Drop the 3-day post-test buffer from training
+clean_train = apply_embargo(
+    clean_train, test_idx, pred, evalu, embargo=pd.Timedelta(days=3)
+)
+
+# Assert the split is now leak-free (raises TemporalLeakageError if not)
+assert_no_temporal_leakage(clean_train, test_idx, pred, evalu)
+assert_embargo_respected(clean_train, test_idx, pred, evalu, embargo="3D")
+print(f"Clean training rows: {len(clean_train)}")  # 19
+```
+
+---
+
+### 2. Splitters with scikit-learn: `PurgedKFold` inside `cross_val_score`
+
+Drop-in replacement for `KFold` that applies purge and embargo automatically on every fold.
+
+```python
+import numpy as np
+import pandas as pd
+from sklearn.linear_model import Ridge
+from sklearn.model_selection import cross_val_score
+from purgedcv import PurgedKFold
+
+rng   = np.random.default_rng(0)
+n     = 200
+pred  = pd.Series(pd.date_range("2022-01-01", periods=n, freq="D"))
+evalu = pred + pd.Timedelta(days=3)
+X     = rng.standard_normal((n, 5))
+y     = X @ rng.standard_normal(5) + rng.standard_normal(n) * 0.5
+
+cv = PurgedKFold(
+    n_splits=5,
+    prediction_times=pred,
+    evaluation_times=evalu,
+    purge_horizon="3D",   # matches label horizon
+    embargo="1D",         # 1-day post-test buffer
+)
+
+scores = cross_val_score(Ridge(), X, y, cv=cv, scoring="r2")
+print(f"R² per fold: {scores.round(3)}")
+```
+
+All four splitters (`WalkForwardSplit`, `PurgedKFold`, `PurgedGroupKFold`, `CombinatorialPurgedCV`) satisfy the sklearn splitter protocol and work inside `GridSearchCV` and `Pipeline`.
+
+---
+
+### 3. CPCV + path reconstruction + metrics: the full workflow
+
+Combinatorial Purged CV produces C(N, K) folds that tile into multiple out-of-sample backtest paths. Use PSR and DSR to evaluate them with corrections for non-normality and selection bias.
+
+```python
+import numpy as np
+import pandas as pd
+from sklearn.dummy import DummyRegressor
+from purgedcv import (
+    CombinatorialPurgedCV,
+    probabilistic_sharpe_ratio,
+    deflated_sharpe_ratio,
+    min_track_record_length,
+)
+
+rng   = np.random.default_rng(42)
+n     = 120
+pred  = pd.Series(pd.date_range("2023-01-01", periods=n, freq="D"))
+evalu = pred + pd.Timedelta(days=2)
+X     = rng.standard_normal((n, 3))
+y     = X @ np.array([0.5, -0.3, 0.2]) + rng.standard_normal(n) * 0.1
+
+# N=6, K=2  →  C(6,2) = 15 folds  →  6-2 = 4 backtest paths
+cv = CombinatorialPurgedCV(
+    n_splits=6,
+    n_test_groups=2,
+    prediction_times=pred,
+    evaluation_times=evalu,
+)
+
+# paths.shape == (n_paths, n_samples); NaN where a sample was not OOS
+paths = cv.backtest_paths(DummyRegressor(strategy="mean"), X, y)
+print(f"Backtest paths: {paths.shape}")  # (5, 120)
+
+# Derive a toy "return" series and compute per-path PSR
+per_path_returns = paths - y[np.newaxis, :]
+per_path_psr = [
+    probabilistic_sharpe_ratio(row[np.isfinite(row)], benchmark_skill=0.0)
+    for row in per_path_returns
+]
+print(f"PSR per path: {[round(p, 3) for p in per_path_psr]}")
+
+# DSR corrects for testing 5 paths simultaneously
+first = per_path_returns[0]
+dsr = deflated_sharpe_ratio(first[np.isfinite(first)], n_trials=5, var_sharpe=0.01**2)
+print(f"Deflated SR (first path): {dsr:.3f}")
+
+# Minimum observations needed to prove SR=0.7 beats benchmark SR=0.5 at 95% confidence
+n_min = min_track_record_length(
+    observed_sharpe=0.7, target_sharpe=0.5, alpha=0.05, skew=0.0, kurtosis=3.0
+)
+print(f"MinTRL: {int(n_min)} observations")
+```
+
+---
+
+## API summary
+
+| Symbol | Domain | Description |
+|---|---|---|
+| `purge` | D2 | Remove overlapping-horizon training rows |
+| `apply_embargo` | D3 | Remove post-test buffer rows |
+| `WalkForwardSplit` | D5.1 | Sliding / expanding walk-forward CV |
+| `PurgedKFold` | D5.2 | Contiguous test folds with purge + embargo |
+| `PurgedGroupKFold` | D5.3 | Group-aware purged k-fold |
+| `CombinatorialPurgedCV` | D5.4 | C(N,K) combinatorial folds |
+| `reconstruct_paths` | D6 | Assemble CPCV folds into backtest paths |
+| `probabilistic_sharpe_ratio` | D7 | PSR: P(true SR > benchmark) |
+| `deflated_sharpe_ratio` | D7 | DSR: PSR corrected for multiple testing |
+| `min_track_record_length` | D7 | Minimum observations to establish SR |
+| `diagnostics.*` | D8 | Leakage and embargo audit functions |
+
+---
+
+
+## Methodology references
+
+- Lopez de Prado, M. (2018). *Advances in Financial Machine Learning*. Wiley. Chapters 7 (purge/embargo) and 12 (CPCV).
+- Bailey, D. H., & Lopez de Prado, M. (2012). The Sharpe Ratio Efficient Frontier. *Journal of Risk*, 15(2).
+- Bailey, D. H., & Lopez de Prado, M. (2014). The Deflated Sharpe Ratio: Correcting for Selection Bias, Backtest Overfitting and Non-Normality. *Journal of Portfolio Management*, 40(5).
+
+---
+
+## License
+
+MIT. See [LICENSE](LICENSE).