scale-forecasting 1.0.0__tar.gz

scale_forecasting-1.0.0/.gitignore

@@ -0,0 +1,68 @@
+# Python
+__pycache__/
+*.py[cod]
+*.egg-info/
+.eggs/
+build/
+dist/
+
+# Virtual envs (.venv-ci is the second env `make ci-offline` syncs exactly like the CI offline job)
+.venv/
+.venv-ci/
+venv/
+
+# uv
+# (uv.lock IS committed — it pins the reproducible env)
+
+# Artifacts / caches
+*.pkl
+*.parquet
+.pytest_cache/
+.ruff_cache/
+.mypy_cache/
+htmlcov/
+.coverage
+.coverage.*
+
+# Documentation site build output (published by CI, never committed)
+site/
+.cache/
+
+# Credentials / local config — never commit
+.env
+*.json.key
+service-account*.json
+application_default_credentials.json
+
+# Terraform local state (remote GCS backend is authoritative)
+*.tfstate
+*.tfstate.*
+.terraform/
+.terraform-tmp/
+.terraform.lock.hcl
+# Never commit real ids (billing/org) or generated plans
+terraform.tfvars
+*.auto.tfvars
+*.tfplan
+
+# Throwaway spikes — live-infra experiments, never product surface
+spikes/
+
+# Notebooks
+.ipynb_checkpoints/
+
+# NeuralProphet / PyTorch-Lightning training artifacts (written to CWD on fit)
+lightning_logs/
+# Lightning's learning-rate finder drops a uuid-named checkpoint beside the process, not under
+# lightning_logs/, so the directory rule above never catches it.
+.lr_find_*.ckpt
+
+# Local-only working files — never tracked (AGENTS.md at repo root is tracked).
+.claude/
+CLAUDE.md
+NOTES.md
+
+# OS / editor
+.DS_Store
+.idea/
+.vscode/

scale_forecasting-1.0.0/CHANGELOG.md

@@ -0,0 +1,52 @@
+# Changelog
+
+All notable changes to `scale-forecasting` are documented in this file.
+
+The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
+and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+
+---
+
+## [Unreleased]
+
+---
+
+## [1.0.0] - 2026-10-12
+
+### Added
+
+- **Declarative Execution Contract (`RunConfig`):** One JSON/dict contract ([`src/scale_forecasting/config.py`](./src/scale_forecasting/config.py)) drives execution across Local CLI, Python SDK (`Forecaster`), Interactive Notebooks, Cloud Composer 3 DAGs (`--emit-airflow`), and Headless Cloud Batch containers, with deterministic content-addressed `run_id` and per-model `model_spec_hash` hashing ([`src/scale_forecasting/registry/ids.py`](./src/scale_forecasting/registry/ids.py)).
+- **34 Forecasting Models Across 5 Families + Multi-Instance `<base_model>@<tag>` Variants:**
+  - `statistical` (`18`): `theta`, `auto_theta`, `holtwinters`, `autoets`, `auto_arima`, `sarimax`, `tbats`, `auto_ces`, `stl_bagging`, `ucm`, `kalman`, `prophet`, `croston` (`classic`, `sba`, `tsb`), `fft`, `naive_mean`, `naive_seasonal`, `naive_drift`, `naive_moving_average`.
+  - `ml` (`5`): `lightgbm`, `xgboost`, `catboost`, `random_forest`, `regression_lags` with both `"recursive"` and `"direct"` multi-step horizon strategies and customizable target `lags`.
+  - `deep_learning` (`5`): `tide`, `tft`, `tsmixer`, `patchtst`, `neuralprophet` across `local`, `global`, and `hybrid` panel regimes.
+  - `automl` (`4`): `vertex_l2l`, `vertex_tide`, `vertex_tft`, `vertex_seq2seq` via Vertex AI Tabular Workflows and managed AutoML training jobs.
+  - `native` (`2`): `arima_plus` and `timesfm` (`AI.FORECAST`) executed natively in BigQuery SQL with SQL-enforced `output` bounds and integer rounding.
+- **21 Evaluation Metrics & Conformal Calibration:** 16 point metrics (`wape`, `smape`, `mape`, `maape`, `ope`, `mae`, `rmse`, `mse`, `rmsle`, `bias`, `mase`, `mase_seasonal`, `rmsse`, `msse`, `r2`, `cv`) and 5 interval metrics (`coverage`, `pinball`, `interval_score`, `interval_width`, `msis`), plus empirical conformal residual calibration ([`src/scale_forecasting/calibration.py`](./src/scale_forecasting/calibration.py)).
+- **7 Google Cloud Compute Runtimes & Per-Family DAG Router:** Parallel per-family job dispatch ([`src/scale_forecasting/dag.py`](./src/scale_forecasting/dag.py)) across Dataproc Serverless / Cluster / Connect (`spark`), Ray on Vertex AI or GKE (`ray`), Vertex AI CustomJob (`vertex`), self-deleting Compute Engine Single-VM (`gce`), GKE Indexed Job (`gke`), Vertex AI AutoML (`vertex_automl`), and BigQuery ML (`bigquery`), supporting CPU and NVIDIA `T4`, `L4`, `A100`, and `A100_80GB` GPUs with BigQuery Storage Read API `[start_id, end_id]` worker sharding and LPT chunk scheduling.
+- **Hierarchical Reconciliation, Smart Ensembles & Two-Tier Explainability:** All 8 Hyndman FPP3 reconciliation methods (`mint_shrink`, `mint_nonneg` active-set non-negative QP, `wls_var`, `wls_struct`, `ols`, `bottom_up`, `top_down`, `middle_out`), 9 ensemble strategies (`mean`, `median`, `trimmed_mean`, `inverse_error`, `champion`, `horizon_specialist`, `nnls`, `ridge`, `xgb`) with `top_k`, `parsimony_margin`, and `variant_policy` (`"all"`, `"best_per_base_model"`, `"primary_only"`), calibrated ensemble prediction intervals, cross-run ensembling (`ensemble_cross_runs`), and two-tier feature attributions (`feature_attributions()` and `explain()`).
+- **Forecaster Decision Workbench (`Phases G.1–G.5`):**
+  - **Physical Bounds & Quantile/Newsvendor Targets (`output`):** Scalar and per-series bounds (`floor`, `cap`, `floor_col`, `cap_col`), integer rounding (`"none"`, `"round"`, `"ceil"`, `"floor"`, `"cumulative_round"`), monotone multi-percentile fans (`output.quantiles`), and Newsvendor asymmetric cost optimization (`underage_cost`, `overage_cost`, `target_quantile`).
+  - **Pre-Fit Data Hygiene & SBC Regime Routing (`data`, `features`):** Grid regularization (`grid_policy`), `trim_leading_zeros`, X-13 `trading_days`, fold-safe outlier despiking (`outlier_policy` / `outlier_handling`), censored stockout recovery (`censored_col`), and Syntetos–Boylan–Croston demand classification (`compute_demand_profile`) with optional `regime_routing`.
+  - **Econometric Diagnostics, Scenarios, Lifecycle Governance & HTML Reports (`diagnostics.py`, `scenarios.py`, `report.py`):** Multi-baseline Forecast Value Added (`compute_fva` with Total, Covariate, Drop-One, and Pooling FVA + Harvey–Leybourne–Newbold modified Diebold–Mariano & Wilcoxon $p$-values), horizon decay (`compute_horizon_decay`), directional bias & Trigg Tracking Signal audits (`compute_bias_report`), AR(1) autocorrelation-aware temporal rollups (`rollup_time`), date-scoped promo/price scenario simulation with revenue impact (`simulate_scenarios`), realized accuracy vs. new actuals (`compute_realized_accuracy`), cross-run revision stability (`compute_revision_stability`), Top-$N$ exception triage queues (`compute_exceptions_queue`), and single-file interactive HTML/JSON executive reports (`export_report`).
+  - **Ablation Ladders & Snapshot-Verified Cross-Run Cell Borrowing (`reuse_prior_runs`):** Declarative `ablation_modes` (`cov_ladder`, `cov_by_tier`, `cov_by_column`, `cov_drop_one`, `scope_ladder`, `transform_ladder`) and server-side BigQuery cell borrowing (`ops.find_reusable_models`, `ops.borrow_model_results`) that skips cloud compute for invariant models.
+- **BigQuery Registry & Analytical SQL Views:** 4 source tables, 5 registry tables (`run_registry`, `run_jobs`, `forecast_metadata`, `forecast_predictions`, `backtest_oof`), and 5 analytical SQL views (`v_model_leaderboard`, `v_model_leaderboard_comparable`, `v_backtest_coverage`, `v_run_summary` with per-job time ledger, and `v_run_jobs`), plus surgical per-cell repair ([`src/scale_forecasting/retry_run.py`](./src/scale_forecasting/retry_run.py)) and `Registry.doctor()`.
+- **Two-Stage Terraform Infrastructure, 11 Notebooks & 42 Live Smoke Configs:** Complete bootstrap + main Terraform modules ([`terraform/`](./terraform/README.md)), 11 interactive notebooks across 4 learning tracks ([`notebooks/`](./notebooks/README.md)), and 42 live-validated smoke configurations + 4 full-breadth multi-runtime verification runs recorded in [`docs/validation.md`](./docs/validation.md).
+- **Agent-First Surfaces (`SKILL.md`, Built-in `stdio` MCP Server, JSON Schema, `llms.txt` & Cloud Shell Tutorial):** Portable Agent Skill ([`skills/scale-forecasting/SKILL.md`](./skills/scale-forecasting/SKILL.md)) with workspace auto-discovery ([`.agents/skills.json`](./.agents/skills.json) and `.agents/skills/scale-forecasting`), zero-extra JSON-RPC 2.0 MCP server ([`src/scale_forecasting/mcp.py`](./src/scale_forecasting/mcp.py)) exposing 7 `forecast://*` resources and 9 tools with `--allow-launch` safety gating, published `RunConfig` JSON Schema ([`docs/schemas/run_config.schema.json`](./docs/schemas/run_config.schema.json)), `llms.txt` / `llms-full.txt`, Google Antigravity [`plugin.json`](./plugin.json) + [`mcp_config.json`](./mcp_config.json), portable [`.mcp.json`](./.mcp.json), [`cloudshell_tutorial.md`](./cloudshell_tutorial.md), and pre-commit zero-drift synthesis ([`src/scale_forecasting/agent_surfaces.py`](./src/scale_forecasting/agent_surfaces.py)).
+
+### Changed
+
+- **Modular Dependency Extras (`pyproject.toml`):** Core `pip install scale-forecasting` installs only the pure offline forecasting layer with zero Google Cloud clients. All Google Cloud SDKs live in `[gcp]`, with composable `[notebook]`, `[spark]`, `[ray]`, `[submit]`, `[models-stats]`, `[models-trees]`, `[models-prophet]`, `[models-dl]`, `[models-automl]`, `[models]`, and `[all]` extras and actionable `MissingExtraError` guidance at every cloud and plotting entry point.
+- **Static Typing, Logging & Test Ratchet:** Added PEP 561 `py.typed` marker with zero `mypy` errors across all 181 source modules, library-safe `NullHandler` logging (`configure_cli_logging` on CLI entry points), widened Ruff lint families (`SIM`, `C4`, `PIE`, `PERF`, `RUF`, `BLE`), and enforced an 85 % offline line-coverage ratchet in CI (`4,960` offline unit tests).
+- **Python 3.11–3.12 Package Support:** `requires-python` widened from `>=3.11,<3.12` to `>=3.11,<3.13` with `3.12` classifiers and a per-interpreter CI `core-install` matrix; the cloud stack stays pinned to `3.11.15` (`.python-version`) for Spark Connect and Ray on Vertex pickle parity ([`docs/version_matrix.md`](./docs/version_matrix.md)). 3.13 waits on the `numpy<2` pin `neuralprophet` still needs.
+- **Per-Job Provisioning vs. Execution Telemetry:** `run_jobs.job_telemetry.$.platform` (`provision_s`, `execute_s`, `total_wall_s`) is stamped from one probe read of each finished Dataproc Serverless batch or Vertex `CustomJob` (`batch_telemetry.platform_phases`), and `v_run_jobs` projects it as `provision_seconds` / `execute_seconds` beside `runtime_seconds`; the Serverless header telemetry carries the same split.
+- **One BigQuery Client Factory:** Every `bigquery.Client(...)` in the package (73 sites) now goes through `registry.tables.bigquery_client`, which guards on `google.cloud.bigquery` alone via the new `errors.require_modules` so an on-cluster worker that never holds the launch clients still reaches the registry, and a core-only install gets the `[gcp]` install line instead of a `ModuleNotFoundError`.
+- **`DataConfig` Identifier Validation:** `source_table` must be `table`, `dataset.table`, or `project.dataset.table` with no backticks, whitespace, or control characters, and `ts_id_col` / `date_col` / `target_col` must be BigQuery column names — checked once at config load, where the values are interpolated into backticked SQL. No field is added, so no `run_id` moves.
+
+### Security
+
+- **HTML Report Hardening (`report.py`):** The inline `EXPLORER_DATA` JSON escapes `<`, `>`, and `&` as `\u003c` / `\u003e` / `\u0026` so a series id containing `</script>` cannot close the script block, and the fan-chart label is HTML-escaped (`escHtml`) before `innerHTML` assignment.
+- **FIPS-Safe Content Addressing:** `code_delivery` tags staged code archives with `hashlib.md5(..., usedforsecurity=False)` (a content-address, not a digest), so staging works on FIPS-enforced hosts.
+
+[Unreleased]: https://github.com/statmike/scale-forecasting/compare/v1.0.0...HEAD
+[1.0.0]: https://github.com/statmike/scale-forecasting/releases/tag/v1.0.0

scale_forecasting-1.0.0/LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.