iints-sdk-python35 0.1.9__tar.gz → 0.1.11__tar.gz

{iints_sdk_python35-0.1.9/src/iints_sdk_python35.egg-info → iints_sdk_python35-0.1.11}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: iints-sdk-python35
-Version: 0.1.9
+Version: 0.1.11
 Summary: A pre-clinical Edge-AI SDK for diabetes management validation.
 Author-email: Rune Bobbaers <rune.bobbaers@gmail.com>
 Project-URL: Homepage, https://github.com/python35/IINTS-SDK
@@ -91,6 +91,20 @@ Try the bundled demo data pack:
 iints import-demo --output-dir results/demo_import
 ```
 
+Official real-world datasets (download on demand):
+```bash
+iints data list
+iints data info aide_t1d
+iints data fetch aide_t1d
+```
+Some datasets require approval and are marked as `request` in the registry.
+`iints data info` prints BibTeX + citation text for easy referencing.
+
+Offline sample dataset (no download required):
+```bash
+iints data fetch sample --output-dir data_packs/sample
+```
+
 Or run the full demo workflow (import + run + report) in one script:
 ```bash
 python3 examples/demo_quickstart_flow.py

{iints_sdk_python35-0.1.9 → iints_sdk_python35-0.1.11}/README.md

@@ -56,6 +56,20 @@ Try the bundled demo data pack:
 iints import-demo --output-dir results/demo_import
 ```
 
+Official real-world datasets (download on demand):
+```bash
+iints data list
+iints data info aide_t1d
+iints data fetch aide_t1d
+```
+Some datasets require approval and are marked as `request` in the registry.
+`iints data info` prints BibTeX + citation text for easy referencing.
+
+Offline sample dataset (no download required):
+```bash
+iints data fetch sample --output-dir data_packs/sample
+```
+
 Or run the full demo workflow (import + run + report) in one script:
 ```bash
 python3 examples/demo_quickstart_flow.py

{iints_sdk_python35-0.1.9 → iints_sdk_python35-0.1.11}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "iints-sdk-python35" 
-version = "0.1.9"
+version = "0.1.11"
 authors = [
   { name="Rune Bobbaers", email="rune.bobbaers@gmail.com" },
 ]
@@ -55,6 +55,7 @@ iints = [
   "templates/*.py",
   "templates/scenarios/*.json",
   "assets/*.png",
+  "data/*.json",
   "data/virtual_patients/*.yaml",
   "data/demo/*.csv",
   "presets/*.json",

{iints_sdk_python35-0.1.9 → iints_sdk_python35-0.1.11}/src/iints/__init__.py

@@ -3,7 +3,7 @@
 import pandas as pd # Required for type hints like pd.DataFrame
 from typing import Optional
 
-__version__ = "0.1.9"
+__version__ = "0.1.11"
 
 # API Components for Algorithm Development
 from .api.base_algorithm import (

{iints_sdk_python35-0.1.9 → iints_sdk_python35-0.1.11}/src/iints/cli/cli.py

@@ -26,6 +26,13 @@ from iints.data.importer import (
     scenario_from_csv,
     scenario_from_dataframe,
 )
+from iints.data.registry import (
+    load_dataset_registry,
+    get_dataset,
+    fetch_dataset,
+    DatasetFetchError,
+    DatasetRegistryError,
+)
 from iints.validation import (
     build_stress_events,
     format_validation_error,
@@ -43,9 +50,11 @@ app = typer.Typer(help="IINTS-AF SDK CLI - Intelligent Insulin Titration System
 docs_app = typer.Typer(help="Generate documentation and technical summaries for IINTS-AF components.")
 presets_app = typer.Typer(help="Clinic-safe presets and quickstart runs.")
 profiles_app = typer.Typer(help="Patient profiles and physiological presets.")
+data_app = typer.Typer(help="Official datasets and data packs.")
 app.add_typer(docs_app, name="docs")
 app.add_typer(presets_app, name="presets")
 app.add_typer(profiles_app, name="profiles")
+app.add_typer(data_app, name="data")
 
 def _load_algorithm_instance(algo: Path, console: Console) -> iints.InsulinAlgorithm:
     if not algo.is_file():
@@ -847,6 +856,91 @@ def validate(
     console.print("[green]Scenario validation passed.[/green]")
 
 
+@data_app.command("list")
+def data_list():
+    """List official datasets and access requirements."""
+    console = Console()
+    datasets = load_dataset_registry()
+    table = Table(title="IINTS-AF Official Datasets", show_header=True, header_style="bold cyan")
+    table.add_column("ID", style="green")
+    table.add_column("Name", style="white")
+    table.add_column("Access", style="magenta")
+    table.add_column("Source", style="yellow")
+    for entry in datasets:
+        table.add_row(
+            entry.get("id", ""),
+            entry.get("name", ""),
+            entry.get("access", ""),
+            entry.get("source", ""),
+        )
+    console.print(table)
+
+
+@data_app.command("info")
+def data_info(
+    dataset_id: Annotated[str, typer.Argument(help="Dataset id (see `iints data list`)")],
+):
+    """Show metadata and access info for a dataset."""
+    console = Console()
+    try:
+        dataset = get_dataset(dataset_id)
+    except DatasetRegistryError as e:
+        console.print(f"[bold red]{e}[/bold red]")
+        raise typer.Exit(code=1)
+    console.print_json(json.dumps(dataset, indent=2))
+    citation = dataset.get("citation", {})
+    if citation:
+        text = citation.get("text")
+        bibtex = citation.get("bibtex")
+        if text:
+            console.print("\n[bold]Citation (text)[/bold]")
+            console.print(text)
+        if bibtex:
+            console.print("\n[bold]Citation (BibTeX)[/bold]")
+            console.print(bibtex)
+
+
+@data_app.command("fetch")
+def data_fetch(
+    dataset_id: Annotated[str, typer.Argument(help="Dataset id (see `iints data list`)")],
+    output_dir: Annotated[Optional[Path], typer.Option(help="Output directory (default: data_packs/official/<id>)")] = None,
+    extract: Annotated[bool, typer.Option(help="Extract zip files if present")] = True,
+    verify: Annotated[bool, typer.Option(help="Verify SHA-256 if available and emit SHA256SUMS.txt")] = True,
+):
+    """Download a dataset (public-download only)."""
+    console = Console()
+    try:
+        dataset = get_dataset(dataset_id)
+    except DatasetRegistryError as e:
+        console.print(f"[bold red]{e}[/bold red]")
+        raise typer.Exit(code=1)
+
+    if output_dir is None:
+        output_dir = Path("data_packs") / "official" / dataset_id
+    output_dir = output_dir.expanduser()
+    if not output_dir.is_absolute():
+        output_dir = (Path.cwd() / output_dir).resolve()
+    else:
+        output_dir = output_dir.resolve()
+
+    access = dataset.get("access", "manual")
+    landing = dataset.get("landing_page", "")
+    if access in {"request", "manual"}:
+        console.print("[yellow]Manual download required for this dataset.[/yellow]")
+        if landing:
+            console.print(f"Source: {landing}")
+        console.print("After downloading, place files in:")
+        console.print(f"  {output_dir}")
+        return
+
+    try:
+        downloaded = fetch_dataset(dataset_id, output_dir=output_dir, extract=extract, verify=verify)
+        console.print(f"[green]Downloaded {len(downloaded)} file(s) to {output_dir}[/green]")
+    except DatasetFetchError as e:
+        console.print(f"[bold red]{e}[/bold red]")
+        raise typer.Exit(code=1)
+
+
 @app.command("import-data")
 def import_data(
     input_csv: Annotated[Path, typer.Option(help="Path to CGM CSV file")],

{iints_sdk_python35-0.1.9 → iints_sdk_python35-0.1.11}/src/iints/data/__init__.py

@@ -18,6 +18,7 @@ from .importer import (
 )
 from .quality_checker import DataQualityChecker, QualityReport, DataGap, DataAnomaly
 from .universal_parser import UniversalParser, StandardDataPack, ParseResult
+from .registry import load_dataset_registry, get_dataset, list_dataset_ids, fetch_dataset
 
 __all__ = [
     'DataAdapter',
@@ -38,5 +39,9 @@ __all__ = [
     'DataAnomaly',
     'UniversalParser',
     'StandardDataPack',
-    'ParseResult'
+    'ParseResult',
+    'load_dataset_registry',
+    'get_dataset',
+    'list_dataset_ids',
+    'fetch_dataset',
 ]

iints_sdk_python35-0.1.11/src/iints/data/datasets.json

@@ -0,0 +1,132 @@
+[
+  {
+    "id": "sample",
+    "name": "IINTS Sample CGM (Bundled)",
+    "source": "IINTS-AF",
+    "access": "bundled",
+    "license": "Demo-only (bundled with SDK)",
+    "description": "Tiny CGM sample for quickstart and offline demos.",
+    "bundled_path": "data/demo/demo_cgm.csv",
+    "sha256": "e869e033887e595ab4c41cb14cde6f2328cc9d55e0fb2c741e7fbe3e0ae3af96",
+    "citation": {
+      "text": "IINTS-AF Team. IINTS Sample CGM (bundled). Accessed 2026-02-16.",
+      "bibtex": "@misc{iints_sample_cgm, title={IINTS Sample CGM (bundled)}, author={IINTS-AF Team}, year={2026}, note={Bundled with IINTS-AF SDK, accessed 2026-02-16}}"
+    }
+  },
+  {
+    "id": "aide_t1d",
+    "name": "AIDE T1D Public Dataset",
+    "source": "Jaeb Center for Health Research",
+    "access": "public-download",
+    "license": "Public dataset (see Jaeb public datasets page)",
+    "description": "Automated Insulin Delivery in Elderly with Type 1 Diabetes (AIDE T1D) public dataset.",
+    "landing_page": "https://public.jaeb.org/datasets/",
+    "download_urls": [
+      "https://live-jchrpublicdatasets.s3.amazonaws.com/Diabetes/Public%20Datasets/AIDET1D_Public_Dataset.zip"
+    ],
+    "sha256": null,
+    "sha256_note": "Checksum not published by source; SHA256SUMS.txt will be generated after download.",
+    "citation": {
+      "text": "Jaeb Center for Health Research. Automated Insulin Delivery in Elderly with Type 1 Diabetes (AIDE T1D) Public Dataset. Public Study Websites. Accessed 2026-02-16. https://public.jaeb.org/datasets/",
+      "bibtex": "@misc{jaeb_aide_t1d, title={Automated Insulin Delivery in Elderly with Type 1 Diabetes (AIDE T1D) Public Dataset}, author={Jaeb Center for Health Research}, howpublished={Public Study Websites}, note={Accessed 2026-02-16}, url={https://public.jaeb.org/datasets/}}"
+    }
+  },
+  {
+    "id": "pedap",
+    "name": "PEDAP Public Dataset",
+    "source": "Jaeb Center for Health Research",
+    "access": "public-download",
+    "license": "Public dataset (see Jaeb public datasets page)",
+    "description": "Pediatric Artificial Pancreas (PEDAP) public dataset (Release 5).",
+    "landing_page": "https://public.jaeb.org/datasets/",
+    "download_urls": [
+      "https://live-jchrpublicdatasets.s3.amazonaws.com/Diabetes/Public%20Datasets/PEDAP%20Public%20Dataset%20-%20Release%205%20-%202025-05-12.zip"
+    ],
+    "sha256": null,
+    "sha256_note": "Checksum not published by source; SHA256SUMS.txt will be generated after download.",
+    "citation": {
+      "text": "Jaeb Center for Health Research. Pediatric Artificial Pancreas (PEDAP) Public Dataset, Release 5. Public Study Websites. Accessed 2026-02-16. https://public.jaeb.org/datasets/",
+      "bibtex": "@misc{jaeb_pedap_2025, title={Pediatric Artificial Pancreas (PEDAP) Public Dataset, Release 5}, author={Jaeb Center for Health Research}, howpublished={Public Study Websites}, note={Accessed 2026-02-16}, url={https://public.jaeb.org/datasets/}}"
+    }
+  },
+  {
+    "id": "azt1d",
+    "name": "AZT1D: A Real-World Dataset for Type 1 Diabetes",
+    "source": "Mendeley Data",
+    "access": "manual",
+    "license": "CC BY 4.0",
+    "description": "Real-world T1D dataset (CGM + insulin + meals) from 25 individuals on AID systems.",
+    "landing_page": "https://data.mendeley.com/datasets/gk9m674wcx/1",
+    "doi": "10.17632/gk9m674wcx.1",
+    "citation": {
+      "text": "Khamesian S, Arefeen A, Thompson BM, Grando A, Ghasemzadeh H. AZT1D: A Real-World Dataset for Type 1 Diabetes. Mendeley Data, v1, 2025. doi:10.17632/gk9m674wcx.1",
+      "bibtex": "@misc{azt1d_2025, title={AZT1D: A Real-World Dataset for Type 1 Diabetes}, author={Khamesian, Saman and Arefeen, Asiful and Thompson, Bithika M. and Grando, Adela and Ghasemzadeh, Hassan}, year={2025}, doi={10.17632/gk9m674wcx.1}, publisher={Mendeley Data}}"
+    }
+  },
+  {
+    "id": "hupa_ucm",
+    "name": "HUPA-UCM Diabetes Dataset",
+    "source": "Mendeley Data",
+    "access": "manual",
+    "license": "CC BY 4.0",
+    "description": "Free-living T1D dataset with CGM, insulin, meals, and activity data.",
+    "landing_page": "https://data.mendeley.com/datasets/3hbcscwz44/1",
+    "doi": "10.17632/3hbcscwz44.1",
+    "citation": {
+      "text": "Hidalgo JI, Alvarado J, Botella M, Aramendi A, Velasco JM, Garnica O. HUPA-UCM Diabetes Dataset. Mendeley Data, v1, 2024. doi:10.17632/3hbcscwz44.1",
+      "bibtex": "@misc{hupa_ucm_2024, title={HUPA-UCM Diabetes Dataset}, author={Hidalgo, J. Ignacio and Alvarado, Jorge and Botella, Marta and Aramendi, Aranzazu and Velasco, J. Manuel and Garnica, Oscar}, year={2024}, doi={10.17632/3hbcscwz44.1}, publisher={Mendeley Data}}"
+    }
+  },
+  {
+    "id": "openaps_data_commons",
+    "name": "OpenAPS Data Commons",
+    "source": "OpenAPS",
+    "access": "request",
+    "license": "Data use agreement (see OpenAPS)",
+    "description": "Community-contributed open APS data commons.",
+    "landing_page": "https://openaps.org/outcomes/data-commons/",
+    "citation": {
+      "text": "OpenAPS. OpenAPS Data Commons. Accessed 2026-02-16. https://openaps.org/outcomes/data-commons/",
+      "bibtex": "@misc{openaps_datacommons, title={OpenAPS Data Commons}, author={OpenAPS}, note={Accessed 2026-02-16}, url={https://openaps.org/outcomes/data-commons/}}"
+    }
+  },
+  {
+    "id": "tidepool_bigdata",
+    "name": "Tidepool Big Data Donation",
+    "source": "Tidepool",
+    "access": "request",
+    "license": "Research collaboration / approval required",
+    "description": "Large-scale real-world diabetes data donation program.",
+    "landing_page": "https://www.tidepool.org/bigdata",
+    "citation": {
+      "text": "Tidepool. Big Data Donation Project. Accessed 2026-02-16. https://www.tidepool.org/bigdata",
+      "bibtex": "@misc{tidepool_bddp, title={Big Data Donation Project}, author={Tidepool}, note={Accessed 2026-02-16}, url={https://www.tidepool.org/bigdata}}"
+    }
+  },
+  {
+    "id": "niddk_central",
+    "name": "NIDDK Central Repository",
+    "source": "NIDDK",
+    "access": "request",
+    "license": "Repository access agreement",
+    "description": "NIH/NIDDK centralized repository of clinical diabetes studies.",
+    "landing_page": "https://repository.niddk.nih.gov/",
+    "citation": {
+      "text": "NIDDK Central Repository. Accessed 2026-02-16. https://repository.niddk.nih.gov/",
+      "bibtex": "@misc{niddk_central_repo, title={NIDDK Central Repository}, author={NIDDK}, note={Accessed 2026-02-16}, url={https://repository.niddk.nih.gov/}}"
+    }
+  },
+  {
+    "id": "t1d_exchange",
+    "name": "T1D Exchange Clinic Registry",
+    "source": "Jaeb Center / T1D Exchange",
+    "access": "request",
+    "license": "Data request / approval required",
+    "description": "Large clinical registry for type 1 diabetes research.",
+    "landing_page": "https://datacatalog.med.nyu.edu/dataset/10129",
+    "citation": {
+      "text": "NYU Data Catalog. T1D Exchange Clinic Registry. Accessed 2026-02-16. https://datacatalog.med.nyu.edu/dataset/10129",
+      "bibtex": "@misc{t1d_exchange_registry, title={T1D Exchange Clinic Registry}, author={NYU Data Catalog}, note={Accessed 2026-02-16}, url={https://datacatalog.med.nyu.edu/dataset/10129}}"
+    }
+  }
+]

iints_sdk_python35-0.1.11/src/iints/data/registry.py

@@ -0,0 +1,146 @@
+from __future__ import annotations
+
+import json
+import urllib.request
+import zipfile
+import hashlib
+import shutil
+from dataclasses import dataclass
+from pathlib import Path
+from typing import Any, Dict, List, Optional
+from importlib.abc import Traversable
+
+try:  # Python 3.9+
+    from importlib.resources import files
+except Exception:  # pragma: no cover
+    from importlib import resources as files  # type: ignore
+
+
+class DatasetRegistryError(RuntimeError):
+    pass
+
+
+class DatasetFetchError(RuntimeError):
+    pass
+
+
+def _registry_path() -> Traversable:
+    try:
+        return files("iints.data").joinpath("datasets.json")  # type: ignore[attr-defined]
+    except Exception as exc:
+        raise DatasetRegistryError(f"Unable to locate datasets.json: {exc}") from exc
+
+
+def load_dataset_registry() -> List[Dict[str, Any]]:
+    registry_path = _registry_path()
+    return json.loads(registry_path.read_text())
+
+
+def get_dataset(dataset_id: str) -> Dict[str, Any]:
+    for entry in load_dataset_registry():
+        if entry.get("id") == dataset_id:
+            return entry
+    raise DatasetRegistryError(f"Unknown dataset '{dataset_id}'. Run 'iints data list' to see options.")
+
+
+def list_dataset_ids() -> List[str]:
+    ids: List[str] = []
+    for entry in load_dataset_registry():
+        dataset_id = entry.get("id")
+        if isinstance(dataset_id, str) and dataset_id:
+            ids.append(dataset_id)
+    return ids
+
+
+def _download_file(url: str, output_path: Path) -> Path:
+    output_path.parent.mkdir(parents=True, exist_ok=True)
+    try:
+        urllib.request.urlretrieve(url, output_path)
+    except Exception as exc:
+        raise DatasetFetchError(f"Failed to download {url}: {exc}") from exc
+    return output_path
+
+
+def _sha256(path: Path) -> str:
+    digest = hashlib.sha256()
+    with path.open("rb") as handle:
+        for chunk in iter(lambda: handle.read(8192), b""):
+            digest.update(chunk)
+    return digest.hexdigest()
+
+
+def _get_expected_hash(dataset: Dict[str, Any], index: int = 0) -> Optional[str]:
+    expected = dataset.get("sha256")
+    if isinstance(expected, list):
+        if index < len(expected):
+            return expected[index] or None
+        return None
+    if isinstance(expected, str):
+        return expected or None
+    return None
+
+
+def _maybe_extract_zip(path: Path, output_dir: Path) -> None:
+    if path.suffix.lower() != ".zip":
+        return
+    try:
+        with zipfile.ZipFile(path, "r") as zip_ref:
+            zip_ref.extractall(output_dir)
+    except Exception as exc:
+        raise DatasetFetchError(f"Failed to extract {path.name}: {exc}") from exc
+
+
+def fetch_dataset(
+    dataset_id: str,
+    output_dir: Path,
+    extract: bool = True,
+    verify: bool = True,
+) -> List[Path]:
+    dataset = get_dataset(dataset_id)
+    urls = dataset.get("download_urls") or []
+    access = dataset.get("access", "manual")
+
+    if access == "bundled":
+        bundled_path = dataset.get("bundled_path")
+        if not bundled_path:
+            raise DatasetFetchError("Bundled dataset missing bundled_path entry.")
+        try:
+            source_path = files("iints.data").joinpath(bundled_path)  # type: ignore[attr-defined]
+        except Exception as exc:
+            raise DatasetFetchError(f"Unable to locate bundled dataset: {exc}") from exc
+        output_dir.mkdir(parents=True, exist_ok=True)
+        target = output_dir / Path(bundled_path).name
+        # Traversable may not be a real filesystem path; stream bytes instead.
+        with source_path.open("rb") as src, target.open("wb") as dst:
+            shutil.copyfileobj(src, dst)
+        expected = _get_expected_hash(dataset, 0)
+        if verify and expected:
+            actual = _sha256(target)
+            if actual != expected:
+                raise DatasetFetchError(f"SHA-256 mismatch for {target.name}. Expected {expected}, got {actual}.")
+        return [target]
+
+    if not urls:
+        raise DatasetFetchError(
+            "This dataset requires manual download or approval. Use 'iints data info' for instructions."
+        )
+    output_dir.mkdir(parents=True, exist_ok=True)
+    downloaded: List[Path] = []
+    for idx, url in enumerate(urls):
+        filename = url.split("/")[-1]
+        target = output_dir / filename
+        downloaded.append(_download_file(url, target))
+        expected = _get_expected_hash(dataset, idx)
+        if verify and expected:
+            actual = _sha256(target)
+            if actual != expected:
+                raise DatasetFetchError(f"SHA-256 mismatch for {target.name}. Expected {expected}, got {actual}.")
+        elif verify and expected is None:
+            # If no hash is provided, at least emit the computed hash for user reference.
+            actual = _sha256(target)
+            checksum_path = output_dir / "SHA256SUMS.txt"
+            with checksum_path.open("a") as handle:
+                handle.write(f"{actual}  {target.name}\n")
+        if extract:
+            _maybe_extract_zip(target, output_dir)
+    return downloaded

{iints_sdk_python35-0.1.9 → iints_sdk_python35-0.1.11/src/iints_sdk_python35.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: iints-sdk-python35
-Version: 0.1.9
+Version: 0.1.11
 Summary: A pre-clinical Edge-AI SDK for diabetes management validation.
 Author-email: Rune Bobbaers <rune.bobbaers@gmail.com>
 Project-URL: Homepage, https://github.com/python35/IINTS-SDK
@@ -91,6 +91,20 @@ Try the bundled demo data pack:
 iints import-demo --output-dir results/demo_import
 ```
 
+Official real-world datasets (download on demand):
+```bash
+iints data list
+iints data info aide_t1d
+iints data fetch aide_t1d
+```
+Some datasets require approval and are marked as `request` in the registry.
+`iints data info` prints BibTeX + citation text for easy referencing.
+
+Offline sample dataset (no download required):
+```bash
+iints data fetch sample --output-dir data_packs/sample
+```
+
 Or run the full demo workflow (import + run + report) in one script:
 ```bash
 python3 examples/demo_quickstart_flow.py

{iints_sdk_python35-0.1.9 → iints_sdk_python35-0.1.11}/src/iints_sdk_python35.egg-info/SOURCES.txt

@@ -54,9 +54,11 @@ src/iints/core/simulation/scenario_parser.py
 src/iints/data/__init__.py
 src/iints/data/adapter.py
 src/iints/data/column_mapper.py
+src/iints/data/datasets.json
 src/iints/data/importer.py
 src/iints/data/ingestor.py
 src/iints/data/quality_checker.py
+src/iints/data/registry.py
 src/iints/data/universal_parser.py
 src/iints/data/demo/__init__.py
 src/iints/data/demo/demo_cgm.csv