onet-match 0.3.0__tar.gz

onet_match-0.3.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2024 Benjamin Chan
+
+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.

onet_match-0.3.0/PKG-INFO

@@ -0,0 +1,238 @@
+Metadata-Version: 2.4
+Name: onet-match
+Version: 0.3.0
+Summary: Map free text (job titles, resume lines, projects, interests, skills) to O*NET occupations with skills, tasks and calibrated confidence.
+Author: Benjamin Chan
+License-Expression: MIT
+Project-URL: Homepage, https://github.com/Benjamin-V-Chan/onet-match
+Project-URL: Repository, https://github.com/Benjamin-V-Chan/onet-match
+Project-URL: Documentation, https://github.com/Benjamin-V-Chan/onet-match/tree/main/docs
+Keywords: onet,o*net,occupations,soc-codes,job-title-normalization,occupation-classification,semantic-search,job-matching,resume-parsing,career-exploration,skills-taxonomy,sentence-transformers,embeddings,reranker,riasec
+Classifier: Programming Language :: Python :: 3
+Classifier: Operating System :: OS Independent
+Classifier: Topic :: Scientific/Engineering :: Information Analysis
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Text Processing :: Linguistic
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: Intended Audience :: Education
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pandas>=1.3
+Requires-Dist: numpy>=1.21
+Requires-Dist: scikit-learn>=1.1
+Requires-Dist: matplotlib>=3.5
+Requires-Dist: pyarrow>=12
+Provides-Extra: plots
+Requires-Dist: seaborn>=0.12; extra == "plots"
+Provides-Extra: matching
+Requires-Dist: torch>=2.2; extra == "matching"
+Requires-Dist: sentence-transformers[train]>=5.0; extra == "matching"
+Requires-Dist: transformers>=4.41; extra == "matching"
+Requires-Dist: huggingface_hub>=0.23; extra == "matching"
+Provides-Extra: serve
+Requires-Dist: fastapi>=0.110; extra == "serve"
+Requires-Dist: uvicorn>=0.29; extra == "serve"
+Requires-Dist: pydantic>=2; extra == "serve"
+Provides-Extra: synth
+Requires-Dist: anthropic>=0.70; extra == "synth"
+Requires-Dist: openai>=1.40; extra == "synth"
+Provides-Extra: dev
+Requires-Dist: pytest>=7; extra == "dev"
+Requires-Dist: seaborn>=0.12; extra == "dev"
+Requires-Dist: httpx>=0.27; extra == "dev"
+Requires-Dist: onet-match[matching,serve,synth]; extra == "dev"
+Dynamic: license-file
+
+# onet-match
+
+**Map free text about work to O\*NET occupations.** Job titles, resume
+bullets, job postings, project descriptions, interest statements and skill
+lists go in. Ranked O\*NET-SOC occupations come out, each with key tasks,
+skills, knowledge, RIASEC interests and a calibrated confidence score.
+
+- Open source (MIT) and runs locally. No API key or account needed to match.
+- Fine-tuned bi-encoder + cross-encoder reranker over all 923 O\*NET 31.0
+  occupations. Top-1 accuracy is **51%** on held-out O\*NET text and **65%** on
+  messy human-style text, vs 21% and 17% for a TF-IDF baseline.
+- Python API, CLI, REST API (FastAPI) and Docker. About 47 ms per query on a laptop.
+- Also includes the O\*NET data pipeline it's built on: bulk database download,
+  a Web Services client and analysis tools.
+
+| input | top match (confidence) |
+|---|---|
+| `ran the robotics club's CAD team` | Robotics Engineers, 17-2199.08 (0.52) |
+| `Excel, QuickBooks, payroll, AP/AR` | Payroll and Timekeeping Clerks, 43-3051.00 (0.49) |
+| `I love drawing and figuring out how machines work` | Mechanical Drafters, 17-3013.00 (0.41) |
+| `Looking for someone to keep our trucks on the road, diesel exp a plus` | Heavy and Tractor-Trailer Truck Drivers, 53-3032.00 (0.30); #2 Bus and Truck Mechanics (0.21) |
+| `Sr. Backend Eng II` | Web Developers, 15-1254.00 (0.43); #2 Software Developers (0.10). A miss: seniority-coded titles are a known weak spot |
+
+Real outputs of the served model, saved in `outputs/examples/readme_examples.json`.
+
+## Quickstart
+
+```bash
+pip install "onet-match[matching] @ git+https://github.com/Benjamin-V-Chan/onet-match"
+```
+
+```python
+from onet_match import match
+
+result = match("ran the robotics club's CAD team", top_k=5)
+for m in result.matches:
+    print(m.soc, m.title, m.confidence)
+print(result.profile["riasec_code"])      # aggregate interest code, e.g. "RIC"
+```
+
+The package imports as `onet_match` and provides the `onet-match` command.
+The first call downloads the pretrained model bundle (about 0.5 GB) from the
+Hugging Face Hub ([BenjaminChan12/onet-match](https://huggingface.co/BenjaminChan12/onet-match)) and caches it.
+
+```bash
+onet-match match "Excel, QuickBooks, payroll, AP/AR"          # CLI (add --json for JSON)
+pip install "onet-match[matching,serve] @ git+https://github.com/Benjamin-V-Chan/onet-match"
+onet-match serve --port 8000                                   # REST API
+curl -s localhost:8000/match -H 'content-type: application/json' \
+     -d '{"text": "ran the robotics club'\''s CAD team", "top_k": 3}'
+```
+
+REST routes: `POST /match`, `POST /match/batch`, `GET /occupation/{soc}` and
+`GET /health`. The full request and response contract and the Docker setup are
+in [docs/API.md](https://github.com/Benjamin-V-Chan/onet-match/blob/main/docs/API.md).
+
+### What each match contains
+
+`soc`, `title`, `confidence` (calibrated, 0–1), `score`, `major_group` and its
+title, `job_zone`, `riasec_code`, `description`, `top_tasks`, `top_skills`
+and `top_knowledge` (with O\*NET importance and level). Each result also
+carries a `profile` that aggregates skills, knowledge and all six RIASEC
+interests across the matches, weighted by confidence.
+
+## Use cases
+
+- **Career exploration (EdTech).** Map what students say they did or enjoy to
+  occupations and skills.
+- **Resume and profile parsing.** Code experience bullets and skill lists to
+  SOC codes.
+- **Job-posting normalization.** Turn informal titles and descriptions into
+  standard occupations.
+- **Workforce and labor-market analytics.** Batch-code large text collections.
+- **Career counseling tools.** Show the tasks and skills behind a suggestion.
+- **LLM agents.** Ground occupation questions in O\*NET instead of free
+  generation (see [`llms.txt`](https://github.com/Benjamin-V-Chan/onet-match/blob/main/llms.txt)).
+
+Details and integration patterns: [docs/APPLICATIONS.md](https://github.com/Benjamin-V-Chan/onet-match/blob/main/docs/APPLICATIONS.md).
+
+## Accuracy
+
+All models are evaluated on the same held-out splits. Every number traces to a
+saved run in `outputs/runs/`.
+
+| model | O\*NET test top-1 | O\*NET test top-5 | messy-text test top-1 | messy-text test top-5 | p50 latency |
+|---|---|---|---|---|---|
+| TF-IDF baseline | 20.5% | 40.5% | 17.4% | 39.2% | 0.5 ms |
+| BM25 | 20.7% | 40.1% | 24.1% | 45.2% | 0.2 ms |
+| bge-base-en-v1.5, off the shelf | 36.1% | 64.3% | 45.4% | 77.6% | 6.9 ms |
+| fine-tuned bge-base | 50.2% | 78.2% | 65.2% | 92.6% | 6.8 ms |
+| **fine-tuned bge-base + reranker (served)** | **51.1%** | **79.1%** | **65.4%** | **92.9%** | 46.7 ms |
+
+- **O\*NET test:** 6,792 held-out titles, task statements, work activities and
+  descriptions.
+- **Messy-text test:** 4,703 informal snippets written by a different LLM than
+  the one that wrote the training text.
+- **Confidence:** temperature-calibrated, ECE 0.037.
+- **Full results:** per-input-type tables, calibration, ablations, learning
+  curves and error analysis are in [docs/RESULTS.md](https://github.com/Benjamin-V-Chan/onet-match/blob/main/docs/RESULTS.md).
+
+## How it works
+
+```mermaid
+flowchart LR
+    B["O*NET 31.0 database<br/>(bulk download)"] --> C["Occupation catalog<br/>923 occupations"]
+    C --> P["Labeled pairs<br/>titles · tasks · activities"]
+    C --> S["LLM-written messy text<br/>train: model A · test: model B"]
+    P --> T["Fine-tune bi-encoder<br/>+ cross-encoder reranker"]
+    S --> T
+    T --> BU["Model bundle<br/>(Hugging Face Hub)"]
+    BU --> API["match() · onet-match CLI · REST API"]
+```
+
+1. A fine-tuned bi-encoder (bge-base) embeds the input and retrieves the 20
+   nearest occupations.
+2. A fine-tuned cross-encoder rescores those 20.
+3. The two scores are blended with a weight chosen on validation data.
+4. A temperature-scaled softmax turns the blended scores into calibrated
+   confidence.
+
+The validation and test tasks are removed from the occupation documents the
+models search, so no test text leaks into retrieval. Synthetic training and
+test text come from different LLMs. Details are in
+[docs/SYNTHETIC_DATA.md](https://github.com/Benjamin-V-Chan/onet-match/blob/main/docs/SYNTHETIC_DATA.md).
+
+## O\*NET data pipeline
+
+The `onet_data_collector` package (`onet-collect`) downloads and verifies O\*NET
+database releases, which needs no credentials. It also wraps O\*NET Web
+Services: keyword search, occupation details and flattened profiles. See
+[docs/COLLECTOR.md](https://github.com/Benjamin-V-Chan/onet-match/blob/main/docs/COLLECTOR.md).
+
+```bash
+onet-collect bulk download                         # download + verify the latest O*NET database
+onet-match collect "healthcare" "technology"       # Web Services search (free O*NET account, see .env.example)
+onet-match eda | keywords | cluster                # classic analysis: coverage, keyword attribution, TF-IDF clusters
+```
+
+## Train your own
+
+```bash
+git clone https://github.com/Benjamin-V-Chan/onet-match && cd onet-match
+pip install -e ".[dev]"
+onet-match matching build-data          # O*NET catalog, labeled pairs, splits
+scripts/matching/reproduce.sh           # every model, ablation and the results report
+onet-match matching bundle "<spec>" --run <run>   # package a model for serving
+```
+
+- **Synthetic text:** `WITH_SYNTH=1 TRAIN_LLM=<model> EVAL_PROVIDER=<provider> EVAL_LLM=<model> scripts/matching/reproduce.sh`
+  also generates the messy training and test text, using a different LLM for
+  each. It needs LLM API keys; see [docs/SYNTHETIC_DATA.md](https://github.com/Benjamin-V-Chan/onet-match/blob/main/docs/SYNTHETIC_DATA.md).
+- **Training time:** bge-base took 58 minutes for one epoch on a laptop GPU
+  (Apple Silicon, MPS). The exact scripts behind every saved run are in
+  `scripts/matching/`.
+- **Tests:** `pytest` runs fully offline, using tiny local models and a
+  mocked LLM.
+
+Set `ONET_MATCH_BUNDLE=/path/to/bundle` to serve your own model, or
+`ONET_MATCH_HF_REPO=owner/repo` to load one from the Hub.
+
+## Background
+
+This project was originally built in 2024 as an open-source edtech tool for
+analyzing O*NET occupational data at scale, and as part of my capstone project
+for an engineering course. Its analytics pipeline (EDA, occupation clustering,
+and keyword attribution) was later integrated into production products at
+**Project Leo**, and has inspired related work at other companies and projects.
+
+In 2026 it was rebuilt around semantic occupation matching, and the former
+`ONET-Data-Collector` repository was merged in.
+
+## Citation
+
+```bibtex
+@software{chan_onet_match,
+  author = {Chan, Benjamin},
+  title  = {onet-match: mapping free text to O*NET occupations},
+  url    = {https://github.com/Benjamin-V-Chan/onet-match},
+  year   = {2026}
+}
+```
+
+## License and data attribution
+
+The code is MIT-licensed; see [LICENSE](https://github.com/Benjamin-V-Chan/onet-match/blob/main/LICENSE).
+
+This product includes information from the O\*NET 31.0 Database by the U.S.
+Department of Labor, Employment and Training Administration (USDOL/ETA), used
+under the [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/) license.
+O\*NET® is a trademark of USDOL/ETA. USDOL/ETA has not approved, endorsed or
+tested this product.

onet_match-0.3.0/README.md

@@ -0,0 +1,191 @@
+# onet-match
+
+**Map free text about work to O\*NET occupations.** Job titles, resume
+bullets, job postings, project descriptions, interest statements and skill
+lists go in. Ranked O\*NET-SOC occupations come out, each with key tasks,
+skills, knowledge, RIASEC interests and a calibrated confidence score.
+
+- Open source (MIT) and runs locally. No API key or account needed to match.
+- Fine-tuned bi-encoder + cross-encoder reranker over all 923 O\*NET 31.0
+  occupations. Top-1 accuracy is **51%** on held-out O\*NET text and **65%** on
+  messy human-style text, vs 21% and 17% for a TF-IDF baseline.
+- Python API, CLI, REST API (FastAPI) and Docker. About 47 ms per query on a laptop.
+- Also includes the O\*NET data pipeline it's built on: bulk database download,
+  a Web Services client and analysis tools.
+
+| input | top match (confidence) |
+|---|---|
+| `ran the robotics club's CAD team` | Robotics Engineers, 17-2199.08 (0.52) |
+| `Excel, QuickBooks, payroll, AP/AR` | Payroll and Timekeeping Clerks, 43-3051.00 (0.49) |
+| `I love drawing and figuring out how machines work` | Mechanical Drafters, 17-3013.00 (0.41) |
+| `Looking for someone to keep our trucks on the road, diesel exp a plus` | Heavy and Tractor-Trailer Truck Drivers, 53-3032.00 (0.30); #2 Bus and Truck Mechanics (0.21) |
+| `Sr. Backend Eng II` | Web Developers, 15-1254.00 (0.43); #2 Software Developers (0.10). A miss: seniority-coded titles are a known weak spot |
+
+Real outputs of the served model, saved in `outputs/examples/readme_examples.json`.
+
+## Quickstart
+
+```bash
+pip install "onet-match[matching] @ git+https://github.com/Benjamin-V-Chan/onet-match"
+```
+
+```python
+from onet_match import match
+
+result = match("ran the robotics club's CAD team", top_k=5)
+for m in result.matches:
+    print(m.soc, m.title, m.confidence)
+print(result.profile["riasec_code"])      # aggregate interest code, e.g. "RIC"
+```
+
+The package imports as `onet_match` and provides the `onet-match` command.
+The first call downloads the pretrained model bundle (about 0.5 GB) from the
+Hugging Face Hub ([BenjaminChan12/onet-match](https://huggingface.co/BenjaminChan12/onet-match)) and caches it.
+
+```bash
+onet-match match "Excel, QuickBooks, payroll, AP/AR"          # CLI (add --json for JSON)
+pip install "onet-match[matching,serve] @ git+https://github.com/Benjamin-V-Chan/onet-match"
+onet-match serve --port 8000                                   # REST API
+curl -s localhost:8000/match -H 'content-type: application/json' \
+     -d '{"text": "ran the robotics club'\''s CAD team", "top_k": 3}'
+```
+
+REST routes: `POST /match`, `POST /match/batch`, `GET /occupation/{soc}` and
+`GET /health`. The full request and response contract and the Docker setup are
+in [docs/API.md](https://github.com/Benjamin-V-Chan/onet-match/blob/main/docs/API.md).
+
+### What each match contains
+
+`soc`, `title`, `confidence` (calibrated, 0–1), `score`, `major_group` and its
+title, `job_zone`, `riasec_code`, `description`, `top_tasks`, `top_skills`
+and `top_knowledge` (with O\*NET importance and level). Each result also
+carries a `profile` that aggregates skills, knowledge and all six RIASEC
+interests across the matches, weighted by confidence.
+
+## Use cases
+
+- **Career exploration (EdTech).** Map what students say they did or enjoy to
+  occupations and skills.
+- **Resume and profile parsing.** Code experience bullets and skill lists to
+  SOC codes.
+- **Job-posting normalization.** Turn informal titles and descriptions into
+  standard occupations.
+- **Workforce and labor-market analytics.** Batch-code large text collections.
+- **Career counseling tools.** Show the tasks and skills behind a suggestion.
+- **LLM agents.** Ground occupation questions in O\*NET instead of free
+  generation (see [`llms.txt`](https://github.com/Benjamin-V-Chan/onet-match/blob/main/llms.txt)).
+
+Details and integration patterns: [docs/APPLICATIONS.md](https://github.com/Benjamin-V-Chan/onet-match/blob/main/docs/APPLICATIONS.md).
+
+## Accuracy
+
+All models are evaluated on the same held-out splits. Every number traces to a
+saved run in `outputs/runs/`.
+
+| model | O\*NET test top-1 | O\*NET test top-5 | messy-text test top-1 | messy-text test top-5 | p50 latency |
+|---|---|---|---|---|---|
+| TF-IDF baseline | 20.5% | 40.5% | 17.4% | 39.2% | 0.5 ms |
+| BM25 | 20.7% | 40.1% | 24.1% | 45.2% | 0.2 ms |
+| bge-base-en-v1.5, off the shelf | 36.1% | 64.3% | 45.4% | 77.6% | 6.9 ms |
+| fine-tuned bge-base | 50.2% | 78.2% | 65.2% | 92.6% | 6.8 ms |
+| **fine-tuned bge-base + reranker (served)** | **51.1%** | **79.1%** | **65.4%** | **92.9%** | 46.7 ms |
+
+- **O\*NET test:** 6,792 held-out titles, task statements, work activities and
+  descriptions.
+- **Messy-text test:** 4,703 informal snippets written by a different LLM than
+  the one that wrote the training text.
+- **Confidence:** temperature-calibrated, ECE 0.037.
+- **Full results:** per-input-type tables, calibration, ablations, learning
+  curves and error analysis are in [docs/RESULTS.md](https://github.com/Benjamin-V-Chan/onet-match/blob/main/docs/RESULTS.md).
+
+## How it works
+
+```mermaid
+flowchart LR
+    B["O*NET 31.0 database<br/>(bulk download)"] --> C["Occupation catalog<br/>923 occupations"]
+    C --> P["Labeled pairs<br/>titles · tasks · activities"]
+    C --> S["LLM-written messy text<br/>train: model A · test: model B"]
+    P --> T["Fine-tune bi-encoder<br/>+ cross-encoder reranker"]
+    S --> T
+    T --> BU["Model bundle<br/>(Hugging Face Hub)"]
+    BU --> API["match() · onet-match CLI · REST API"]
+```
+
+1. A fine-tuned bi-encoder (bge-base) embeds the input and retrieves the 20
+   nearest occupations.
+2. A fine-tuned cross-encoder rescores those 20.
+3. The two scores are blended with a weight chosen on validation data.
+4. A temperature-scaled softmax turns the blended scores into calibrated
+   confidence.
+
+The validation and test tasks are removed from the occupation documents the
+models search, so no test text leaks into retrieval. Synthetic training and
+test text come from different LLMs. Details are in
+[docs/SYNTHETIC_DATA.md](https://github.com/Benjamin-V-Chan/onet-match/blob/main/docs/SYNTHETIC_DATA.md).
+
+## O\*NET data pipeline
+
+The `onet_data_collector` package (`onet-collect`) downloads and verifies O\*NET
+database releases, which needs no credentials. It also wraps O\*NET Web
+Services: keyword search, occupation details and flattened profiles. See
+[docs/COLLECTOR.md](https://github.com/Benjamin-V-Chan/onet-match/blob/main/docs/COLLECTOR.md).
+
+```bash
+onet-collect bulk download                         # download + verify the latest O*NET database
+onet-match collect "healthcare" "technology"       # Web Services search (free O*NET account, see .env.example)
+onet-match eda | keywords | cluster                # classic analysis: coverage, keyword attribution, TF-IDF clusters
+```
+
+## Train your own
+
+```bash
+git clone https://github.com/Benjamin-V-Chan/onet-match && cd onet-match
+pip install -e ".[dev]"
+onet-match matching build-data          # O*NET catalog, labeled pairs, splits
+scripts/matching/reproduce.sh           # every model, ablation and the results report
+onet-match matching bundle "<spec>" --run <run>   # package a model for serving
+```
+
+- **Synthetic text:** `WITH_SYNTH=1 TRAIN_LLM=<model> EVAL_PROVIDER=<provider> EVAL_LLM=<model> scripts/matching/reproduce.sh`
+  also generates the messy training and test text, using a different LLM for
+  each. It needs LLM API keys; see [docs/SYNTHETIC_DATA.md](https://github.com/Benjamin-V-Chan/onet-match/blob/main/docs/SYNTHETIC_DATA.md).
+- **Training time:** bge-base took 58 minutes for one epoch on a laptop GPU
+  (Apple Silicon, MPS). The exact scripts behind every saved run are in
+  `scripts/matching/`.
+- **Tests:** `pytest` runs fully offline, using tiny local models and a
+  mocked LLM.
+
+Set `ONET_MATCH_BUNDLE=/path/to/bundle` to serve your own model, or
+`ONET_MATCH_HF_REPO=owner/repo` to load one from the Hub.
+
+## Background
+
+This project was originally built in 2024 as an open-source edtech tool for
+analyzing O*NET occupational data at scale, and as part of my capstone project
+for an engineering course. Its analytics pipeline (EDA, occupation clustering,
+and keyword attribution) was later integrated into production products at
+**Project Leo**, and has inspired related work at other companies and projects.
+
+In 2026 it was rebuilt around semantic occupation matching, and the former
+`ONET-Data-Collector` repository was merged in.
+
+## Citation
+
+```bibtex
+@software{chan_onet_match,
+  author = {Chan, Benjamin},
+  title  = {onet-match: mapping free text to O*NET occupations},
+  url    = {https://github.com/Benjamin-V-Chan/onet-match},
+  year   = {2026}
+}
+```
+
+## License and data attribution
+
+The code is MIT-licensed; see [LICENSE](https://github.com/Benjamin-V-Chan/onet-match/blob/main/LICENSE).
+
+This product includes information from the O\*NET 31.0 Database by the U.S.
+Department of Labor, Employment and Training Administration (USDOL/ETA), used
+under the [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/) license.
+O\*NET® is a trademark of USDOL/ETA. USDOL/ETA has not approved, endorsed or
+tested this product.

onet_match-0.3.0/onet_analysis/__init__.py

@@ -0,0 +1,20 @@
+"""onet_analysis — the analytics layer of the O*NET career-intelligence pipeline.
+
+Consumes the tidy tables produced by the ``onet_data_collector`` package and
+turns them into diagnostics and interpretable structure:
+
+* :mod:`onet_analysis.schema` — resilient column resolution across export variants.
+* :mod:`onet_analysis.eda` — coverage stats and distribution plots.
+* :mod:`onet_analysis.clustering` — TF-IDF -> TruncatedSVD -> KMeans role clusters.
+* :mod:`onet_analysis.keyword_attribution` — where each keyword lands in feature space.
+* :mod:`onet_analysis.collect` — thin re-exports of the collector's ETL stages.
+
+The full pipeline (collect -> EDA -> keywords -> cluster) is driven by the
+``onet-analyze`` CLI in :mod:`onet_analysis.cli`.
+"""
+
+from __future__ import annotations
+
+__version__ = "0.3.0"
+
+__all__ = ["__version__"]