iints-sdk-python35 0.1.7__tar.gz → 0.1.9__tar.gz

{iints_sdk_python35-0.1.7/src/iints_sdk_python35.egg-info → iints_sdk_python35-0.1.9}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: iints-sdk-python35
-Version: 0.1.7
+Version: 0.1.9
 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
@@ -33,10 +33,15 @@ Provides-Extra: torch
 Requires-Dist: torch>=1.9.0; extra == "torch"
 Dynamic: license-file
 
-# IINTS-AF SDK (v0.1.5)
+# IINTS-AF SDK
+[![PyPI version](https://badge.fury.io/py/iints-sdk-python35.svg)](https://badge.fury.io/py/iints-sdk-python35)
 [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/python35/IINTS-SDK/blob/main/examples/notebooks/00_Quickstart.ipynb)
 [![Python Package CI](https://github.com/python35/IINTS-SDK/actions/workflows/python-package.yml/badge.svg)](https://github.com/python35/IINTS-SDK/actions/workflows/python-package.yml)
 
+<div style="text-align:center;">
+  <img src="Ontwerp zonder titel.png" alt="" style="display:block; margin:0 auto;">
+</div>
+
 ## Intelligent Insulin Titration System for Artificial Pancreas
 
 IINTS-AF is a **safety-first simulation and validation platform** for insulin dosing algorithms. It lets you test AI or classical controllers on virtual patients, enforce deterministic safety constraints, and generate audit-ready clinical reports before anything touches a real patient.
@@ -54,6 +59,14 @@ IINTS-AF is a **safety-first simulation and validation platform** for insulin do
 * ML engineers benchmarking AI controllers with medical safety rails
 * Developers building decision-support systems for closed-loop insulin delivery
 
+## Installation
+
+Install the SDK directly via PyPI:
+
+```bash
+pip install iints-sdk-python35
+```
+
 ### Quick Start (CLI)
 ```bash
 iints quickstart --project-name iints_quickstart
@@ -99,7 +112,8 @@ outputs = iints.run_simulation(
 ```
 
 ### Notebook Guide
-Hands-on Jupyter notebooks live in `examples/notebooks/` and cover the full workflow (each is Colab-ready):
+Hands-on Jupyter notebooks live in [`examples/notebooks/`](examples/notebooks/)  
+
 
 * Quickstart end-to-end run
 * Presets + scenario validation

{iints_sdk_python35-0.1.7 → iints_sdk_python35-0.1.9}/README.md

@@ -1,7 +1,12 @@
-# IINTS-AF SDK (v0.1.5)
+# IINTS-AF SDK
+[![PyPI version](https://badge.fury.io/py/iints-sdk-python35.svg)](https://badge.fury.io/py/iints-sdk-python35)
 [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/python35/IINTS-SDK/blob/main/examples/notebooks/00_Quickstart.ipynb)
 [![Python Package CI](https://github.com/python35/IINTS-SDK/actions/workflows/python-package.yml/badge.svg)](https://github.com/python35/IINTS-SDK/actions/workflows/python-package.yml)
 
+<div style="text-align:center;">
+  <img src="Ontwerp zonder titel.png" alt="" style="display:block; margin:0 auto;">
+</div>
+
 ## Intelligent Insulin Titration System for Artificial Pancreas
 
 IINTS-AF is a **safety-first simulation and validation platform** for insulin dosing algorithms. It lets you test AI or classical controllers on virtual patients, enforce deterministic safety constraints, and generate audit-ready clinical reports before anything touches a real patient.
@@ -19,6 +24,14 @@ IINTS-AF is a **safety-first simulation and validation platform** for insulin do
 * ML engineers benchmarking AI controllers with medical safety rails
 * Developers building decision-support systems for closed-loop insulin delivery
 
+## Installation
+
+Install the SDK directly via PyPI:
+
+```bash
+pip install iints-sdk-python35
+```
+
 ### Quick Start (CLI)
 ```bash
 iints quickstart --project-name iints_quickstart
@@ -64,7 +77,8 @@ outputs = iints.run_simulation(
 ```
 
 ### Notebook Guide
-Hands-on Jupyter notebooks live in `examples/notebooks/` and cover the full workflow (each is Colab-ready):
+Hands-on Jupyter notebooks live in [`examples/notebooks/`](examples/notebooks/)  
+
 
 * Quickstart end-to-end run
 * Presets + scenario validation

{iints_sdk_python35-0.1.7 → iints_sdk_python35-0.1.9}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "iints-sdk-python35" 
-version = "0.1.7"
+version = "0.1.9"
 authors = [
   { name="Rune Bobbaers", email="rune.bobbaers@gmail.com" },
 ]
@@ -54,6 +54,7 @@ iints = "iints.cli.cli:app"
 iints = [
   "templates/*.py",
   "templates/scenarios/*.json",
+  "assets/*.png",
   "data/virtual_patients/*.yaml",
   "data/demo/*.csv",
   "presets/*.json",

{iints_sdk_python35-0.1.7 → iints_sdk_python35-0.1.9}/src/iints/__init__.py

@@ -3,7 +3,7 @@
 import pandas as pd # Required for type hints like pd.DataFrame
 from typing import Optional
 
-__version__ = "0.1.5"
+__version__ = "0.1.9"
 
 # API Components for Algorithm Development
 from .api.base_algorithm import (

{iints_sdk_python35-0.1.7 → iints_sdk_python35-0.1.9}/src/iints/analysis/reporting.py

@@ -1,11 +1,15 @@
+import os
 import tempfile
 from pathlib import Path
 from typing import Any, Dict, Optional
 
+os.environ.setdefault("MPLBACKEND", "Agg")
+
 import matplotlib.pyplot as plt
 import numpy as np
 import pandas as pd
 from fpdf import FPDF
+from fpdf.enums import XPos, YPos
 
 from iints.analysis.clinical_metrics import ClinicalMetricsCalculator
 from iints.utils.plotting import apply_plot_style
@@ -17,6 +21,30 @@ class ClinicalReportGenerator:
     def __init__(self) -> None:
         self.metrics_calculator = ClinicalMetricsCalculator()
 
+    def _resolve_logo_path(self) -> Optional[Path]:
+        candidates = []
+        # Package asset (installed)
+        candidates.append(Path(__file__).resolve().parent.parent / "assets" / "iints_logo.png")
+        # Repo root img/ (dev)
+        candidates.append(Path(__file__).resolve().parents[3] / "img" / "iints_logo.png")
+        for path in candidates:
+            if path.exists():
+                return path
+        return None
+
+    def _render_logo(self, pdf: FPDF) -> None:
+        logo_path = self._resolve_logo_path()
+        if not logo_path:
+            return
+        try:
+            logo_width = 36
+            x_pos = pdf.w - pdf.r_margin - logo_width
+            y_pos = 6
+            pdf.image(str(logo_path), x=x_pos, y=y_pos, w=logo_width)
+        except Exception:
+            # Fallback silently if image fails to load
+            return
+
     def _plot_glucose(self, df: pd.DataFrame, output_path: Path) -> None:
         apply_plot_style()
         plt.figure(figsize=(10, 4))
@@ -104,44 +132,93 @@ class ClinicalReportGenerator:
             pdf = FPDF()
             pdf.set_auto_page_break(auto=True, margin=12)
             pdf.add_page()
+            self._render_logo(pdf)
 
             pdf.set_font("Helvetica", "B", 16)
-            pdf.cell(0, 10, title, ln=1)
+            pdf.cell(0, 10, title, new_x=XPos.LMARGIN, new_y=YPos.NEXT)
 
             pdf.set_font("Helvetica", "", 11)
-            pdf.cell(0, 7, f"Duration: {simulation_data['time_minutes'].max()/60:.1f} hours", ln=1)
-            pdf.cell(0, 7, f"Data points: {len(simulation_data)}", ln=1)
+            pdf.cell(
+                0,
+                7,
+                f"Duration: {simulation_data['time_minutes'].max()/60:.1f} hours",
+                new_x=XPos.LMARGIN,
+                new_y=YPos.NEXT,
+            )
+            pdf.cell(0, 7, f"Data points: {len(simulation_data)}", new_x=XPos.LMARGIN, new_y=YPos.NEXT)
 
             pdf.ln(3)
             pdf.set_font("Helvetica", "B", 12)
-            pdf.cell(0, 8, "Clinical Metrics", ln=1)
+            pdf.cell(0, 8, "Clinical Metrics", new_x=XPos.LMARGIN, new_y=YPos.NEXT)
             pdf.set_font("Helvetica", "", 10)
-            pdf.cell(0, 6, f"TIR (70-180): {metrics.get('tir_70_180', 0):.1f}%", ln=1)
-            pdf.cell(0, 6, f"Time <70: {metrics.get('tir_below_70', 0):.1f}%", ln=1)
-            pdf.cell(0, 6, f"Time >180: {metrics.get('tir_above_180', 0):.1f}%", ln=1)
-            pdf.cell(0, 6, f"CV: {metrics.get('cv', 0):.1f}%", ln=1)
-            pdf.cell(0, 6, f"GMI: {metrics.get('gmi', 0):.1f}%", ln=1)
+            pdf.cell(
+                0,
+                6,
+                f"TIR (70-180): {metrics.get('tir_70_180', 0):.1f}%",
+                new_x=XPos.LMARGIN,
+                new_y=YPos.NEXT,
+            )
+            pdf.cell(
+                0,
+                6,
+                f"Time <70: {metrics.get('tir_below_70', 0):.1f}%",
+                new_x=XPos.LMARGIN,
+                new_y=YPos.NEXT,
+            )
+            pdf.cell(
+                0,
+                6,
+                f"Time >180: {metrics.get('tir_above_180', 0):.1f}%",
+                new_x=XPos.LMARGIN,
+                new_y=YPos.NEXT,
+            )
+            pdf.cell(
+                0,
+                6,
+                f"CV: {metrics.get('cv', 0):.1f}%",
+                new_x=XPos.LMARGIN,
+                new_y=YPos.NEXT,
+            )
+            pdf.cell(
+                0,
+                6,
+                f"GMI: {metrics.get('gmi', 0):.1f}%",
+                new_x=XPos.LMARGIN,
+                new_y=YPos.NEXT,
+            )
 
             pdf.ln(2)
             pdf.set_font("Helvetica", "B", 12)
-            pdf.cell(0, 8, "Safety Summary", ln=1)
+            pdf.cell(0, 8, "Safety Summary", new_x=XPos.LMARGIN, new_y=YPos.NEXT)
             pdf.set_font("Helvetica", "", 10)
-            pdf.cell(0, 6, f"Total violations: {safety_report.get('total_violations', 0)}", ln=1)
-            pdf.cell(0, 6, f"Bolus interventions: {safety_report.get('bolus_interventions_count', 0)}", ln=1)
+            pdf.cell(
+                0,
+                6,
+                f"Total violations: {safety_report.get('total_violations', 0)}",
+                new_x=XPos.LMARGIN,
+                new_y=YPos.NEXT,
+            )
+            pdf.cell(
+                0,
+                6,
+                f"Bolus interventions: {safety_report.get('bolus_interventions_count', 0)}",
+                new_x=XPos.LMARGIN,
+                new_y=YPos.NEXT,
+            )
             top_reasons = self._top_safety_reasons(simulation_data)
             if top_reasons:
                 pdf.ln(1)
                 pdf.set_font("Helvetica", "B", 10)
-                pdf.cell(0, 6, "Top intervention reasons:", ln=1)
+                pdf.cell(0, 6, "Top intervention reasons:", new_x=XPos.LMARGIN, new_y=YPos.NEXT)
                 pdf.set_font("Helvetica", "", 10)
                 for reason, count in top_reasons.items():
-                    pdf.cell(0, 5, f"- {reason}: {count}", ln=1)
+                    pdf.cell(0, 5, f"- {reason}: {count}", new_x=XPos.LMARGIN, new_y=YPos.NEXT)
 
             baseline = safety_report.get("baseline_comparison")
             if baseline and baseline.get("rows"):
                 pdf.ln(3)
                 pdf.set_font("Helvetica", "B", 12)
-                pdf.cell(0, 7, "Head-to-Head Comparison", ln=1)
+                pdf.cell(0, 7, "Head-to-Head Comparison", new_x=XPos.LMARGIN, new_y=YPos.NEXT)
                 pdf.set_font("Helvetica", "B", 9)
                 col_widths = [52, 26, 26, 26, 30]
                 headers = ["Algorithm", "TIR 70-180", "Time <70", "Time >180", "Safety Overrides"]
@@ -160,12 +237,12 @@ class ClinicalReportGenerator:
 
             pdf.ln(4)
             pdf.set_font("Helvetica", "B", 12)
-            pdf.cell(0, 8, "Glucose Trace", ln=1)
+            pdf.cell(0, 8, "Glucose Trace", new_x=XPos.LMARGIN, new_y=YPos.NEXT)
             pdf.image(str(glucose_plot), w=180)
 
             pdf.ln(4)
             pdf.set_font("Helvetica", "B", 12)
-            pdf.cell(0, 8, "Insulin Delivery", ln=1)
+            pdf.cell(0, 8, "Insulin Delivery", new_x=XPos.LMARGIN, new_y=YPos.NEXT)
             pdf.image(str(insulin_plot), w=180)
 
             pdf.output(str(output_file))
@@ -200,11 +277,18 @@ class ClinicalReportGenerator:
             pdf = FPDF()
             pdf.set_auto_page_break(auto=True, margin=12)
             pdf.add_page()
+            self._render_logo(pdf)
 
             pdf.set_font("Helvetica", "B", 18)
-            pdf.cell(0, 12, title, ln=1)
+            pdf.cell(0, 12, title, new_x=XPos.LMARGIN, new_y=YPos.NEXT)
             pdf.set_font("Helvetica", "", 11)
-            pdf.cell(0, 7, f"Duration: {simulation_data['time_minutes'].max()/60:.1f} hours", ln=1)
+            pdf.cell(
+                0,
+                7,
+                f"Duration: {simulation_data['time_minutes'].max()/60:.1f} hours",
+                new_x=XPos.LMARGIN,
+                new_y=YPos.NEXT,
+            )
             pdf.ln(2)
 
             # Metric tiles
@@ -231,30 +315,30 @@ class ClinicalReportGenerator:
                 pdf.set_fill_color(230, 244, 246)
                 pdf.rect(x, y, tile_w, tile_h, style="F")
                 pdf.set_xy(x + 2, y + 3)
-                pdf.cell(tile_w - 4, 5, label, ln=1)
+                pdf.cell(tile_w - 4, 5, label, new_x=XPos.LEFT, new_y=YPos.NEXT)
                 pdf.set_font("Helvetica", "B", 13)
                 pdf.set_xy(x + 2, y + 9)
-                pdf.cell(tile_w - 4, 8, value, ln=1)
+                pdf.cell(tile_w - 4, 8, value, new_x=XPos.LEFT, new_y=YPos.NEXT)
                 pdf.set_font("Helvetica", "B", 10)
 
             pdf.ln(36)
             pdf.set_font("Helvetica", "B", 12)
-            pdf.cell(0, 8, "Glucose Trace", ln=1)
+            pdf.cell(0, 8, "Glucose Trace", new_x=XPos.LMARGIN, new_y=YPos.NEXT)
             pdf.image(str(glucose_plot), w=180)
 
             pdf.ln(4)
             pdf.set_font("Helvetica", "B", 12)
-            pdf.cell(0, 8, "Insulin Delivery", ln=1)
+            pdf.cell(0, 8, "Insulin Delivery", new_x=XPos.LMARGIN, new_y=YPos.NEXT)
             pdf.image(str(insulin_plot), w=180)
 
             top_reasons = self._top_safety_reasons(simulation_data)
             if top_reasons:
                 pdf.ln(4)
                 pdf.set_font("Helvetica", "B", 11)
-                pdf.cell(0, 7, "Top Safety Interventions", ln=1)
+                pdf.cell(0, 7, "Top Safety Interventions", new_x=XPos.LMARGIN, new_y=YPos.NEXT)
                 pdf.set_font("Helvetica", "", 10)
                 for reason, count in top_reasons.items():
-                    pdf.cell(0, 5, f"- {reason}: {count}", ln=1)
+                    pdf.cell(0, 5, f"- {reason}: {count}", new_x=XPos.LMARGIN, new_y=YPos.NEXT)
 
             pdf.output(str(output_file))
 

{iints_sdk_python35-0.1.7 → iints_sdk_python35-0.1.9}/src/iints/cli/cli.py

@@ -334,7 +334,7 @@ def presets_show(
 def presets_run(
     name: Annotated[str, typer.Option(help="Preset name (e.g., baseline_t1d)")],
     algo: Annotated[Path, typer.Option(help="Path to the algorithm Python file")],
-    output_dir: Annotated[Path, typer.Option(help="Directory to save outputs")] = Path("./results/presets"),
+    output_dir: Annotated[Optional[Path], typer.Option(help="Directory to save outputs")] = None,
     compare_baselines: Annotated[bool, typer.Option(help="Run PID and standard pump baselines in the background")] = True,
     seed: Annotated[Optional[int], typer.Option(help="Random seed for deterministic runs")] = None,
 ):
@@ -392,13 +392,20 @@ def presets_run(
     for event in build_stress_events(stress_event_payloads):
         simulator.add_stress_event(event)
 
+    if output_dir is None:
+        output_dir = algo.parent / "results" / "presets"
+    output_dir = output_dir.expanduser()
+    if not output_dir.is_absolute():
+        output_dir = (Path.cwd() / output_dir).resolve()
+    else:
+        output_dir = output_dir.resolve()
     output_dir.mkdir(parents=True, exist_ok=True)
     results_df, safety_report = simulator.run_batch(duration)
 
     algo_name = algorithm_instance.get_algorithm_metadata().name.replace(" ", "_").lower()
     results_file = output_dir / f"preset_{name}_{algo_name}.csv"
     results_df.to_csv(results_file, index=False)
-    console.print(f"Results saved to: [link file://{results_file}]{results_file}[/link]")
+    console.print(f"Results saved to: [link=file://{results_file}]{results_file}[/link]")
 
     audit_dir = output_dir / "audit"
     try:
@@ -424,7 +431,7 @@ def presets_run(
 
     report_path = output_dir / f"preset_{name}_{algo_name}.pdf"
     iints.generate_report(results_df, str(report_path), safety_report)
-    console.print(f"PDF report saved to: [link file://{report_path}]{report_path}[/link]")
+    console.print(f"PDF report saved to: [link=file://{report_path}]{report_path}[/link]")
 
 
 @presets_app.command("create")
@@ -657,7 +664,7 @@ def run(
     
     simulation_results_df.to_csv(results_file, index=False)
     
-    console.print(f"\nSimulation completed. Results saved to: [link file://{results_file}]{results_file}[/link]") # Formatted link
+    console.print(f"\nSimulation completed. Results saved to: [link=file://{results_file}]{results_file}[/link]") # Formatted link
     console.print("\n--- Safety Report ---")
     for key, value in safety_report.items():
         console.print(f"{key}: {value}")
@@ -761,7 +768,7 @@ def report(
         generator.export_plots(results_df, str(plots_dir))
     output_path.parent.mkdir(parents=True, exist_ok=True)
     iints.generate_report(results_df, str(output_path), safety_report)
-    console.print(f"PDF report saved to: [link file://{output_path}]{output_path}[/link]")
+    console.print(f"PDF report saved to: [link=file://{output_path}]{output_path}[/link]")
 
     if audit_output_dir:
         audit_output_dir.mkdir(parents=True, exist_ok=True)

iints_sdk_python35-0.1.9/src/iints/templates/default_algorithm.py

@@ -0,0 +1,91 @@
+from iints import InsulinAlgorithm, AlgorithmInput, AlgorithmResult, AlgorithmMetadata
+from typing import Dict, Any
+
+class {{ALGO_NAME}}(InsulinAlgorithm):
+    def __init__(self, settings: Dict[str, Any] = None):
+        super().__init__(settings)
+        self.set_algorithm_metadata(AlgorithmMetadata(
+            name="{{ALGO_NAME}}",
+            author="{{AUTHOR_NAME}}",
+            description="A new custom insulin algorithm.",
+            algorithm_type="rule_based" # Change as appropriate
+        ))
+        # Initialize any specific state or parameters for your algorithm here
+
+    def predict_insulin(self, data: AlgorithmInput) -> Dict[str, Any]:
+        # --- SAFETY-FIRST STARTER LOGIC ---
+        # This template is intentionally conservative to avoid hypoglycemia.
+
+        self.why_log = []
+
+        current_glucose = data.current_glucose
+        iob = data.insulin_on_board
+        carbs = data.carb_intake
+
+        previous_glucose = self.state.get("previous_glucose", current_glucose)
+        glucose_trend = (current_glucose - previous_glucose) / max(data.time_step, 1)
+        self.state["previous_glucose"] = current_glucose
+
+        total_insulin = 0.0
+        bolus_insulin = 0.0
+        basal_insulin = 0.0
+        correction_bolus = 0.0
+        meal_bolus = 0.0
+
+        # Hard safety cutoff
+        if current_glucose < 90:
+            self._log_reason("Glucose below 90 mg/dL; holding insulin.", "safety_cutoff", current_glucose)
+            return {
+                "total_insulin_delivered": 0.0,
+                "bolus_insulin": 0.0,
+                "basal_insulin": 0.0,
+                "correction_bolus": 0.0,
+                "meal_bolus": 0.0,
+            }
+
+        # If glucose is falling quickly, avoid correction bolus
+        if glucose_trend < -1.0:
+            self._log_reason(
+                f"Glucose dropping at {glucose_trend:.2f} mg/dL/min; skipping correction bolus.",
+                "safety_trend",
+                glucose_trend,
+            )
+        else:
+            # Conservative correction only if quite high
+            if current_glucose > 180:
+                correction_bolus = (current_glucose - 140) / self.isf
+                correction_bolus = min(max(correction_bolus, 0.0), 0.5)
+                total_insulin += correction_bolus
+                self._log_reason(
+                    f"Conservative correction bolus {correction_bolus:.2f} U.",
+                    "correction",
+                    current_glucose,
+                )
+
+        # Meal bolus (capped)
+        if carbs > 0:
+            meal_bolus = min(carbs / self.icr, 2.0)
+            total_insulin += meal_bolus
+            self._log_reason(
+                f"Meal bolus {meal_bolus:.2f} U for {carbs:.0f} g carbs.",
+                "meal_bolus",
+                carbs,
+            )
+
+        # Optional: cap total insulin based on IOB
+        if iob > 2.0:
+            total_insulin = min(total_insulin, 0.2)
+            self._log_reason("High IOB; capping total insulin to 0.2 U.", "iob_cap", iob)
+
+        total_insulin = max(0.0, total_insulin)
+        bolus_insulin = total_insulin
+
+        self._log_reason(f"Final insulin decision: {total_insulin:.2f} units", "decision", total_insulin)
+
+        return {
+            "total_insulin_delivered": total_insulin,
+            "bolus_insulin": bolus_insulin,
+            "basal_insulin": basal_insulin,
+            "correction_bolus": correction_bolus,
+            "meal_bolus": meal_bolus,
+        }

{iints_sdk_python35-0.1.7 → iints_sdk_python35-0.1.9/src/iints_sdk_python35.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: iints-sdk-python35
-Version: 0.1.7
+Version: 0.1.9
 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
@@ -33,10 +33,15 @@ Provides-Extra: torch
 Requires-Dist: torch>=1.9.0; extra == "torch"
 Dynamic: license-file
 
-# IINTS-AF SDK (v0.1.5)
+# IINTS-AF SDK
+[![PyPI version](https://badge.fury.io/py/iints-sdk-python35.svg)](https://badge.fury.io/py/iints-sdk-python35)
 [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/python35/IINTS-SDK/blob/main/examples/notebooks/00_Quickstart.ipynb)
 [![Python Package CI](https://github.com/python35/IINTS-SDK/actions/workflows/python-package.yml/badge.svg)](https://github.com/python35/IINTS-SDK/actions/workflows/python-package.yml)
 
+<div style="text-align:center;">
+  <img src="Ontwerp zonder titel.png" alt="" style="display:block; margin:0 auto;">
+</div>
+
 ## Intelligent Insulin Titration System for Artificial Pancreas
 
 IINTS-AF is a **safety-first simulation and validation platform** for insulin dosing algorithms. It lets you test AI or classical controllers on virtual patients, enforce deterministic safety constraints, and generate audit-ready clinical reports before anything touches a real patient.
@@ -54,6 +59,14 @@ IINTS-AF is a **safety-first simulation and validation platform** for insulin do
 * ML engineers benchmarking AI controllers with medical safety rails
 * Developers building decision-support systems for closed-loop insulin delivery
 
+## Installation
+
+Install the SDK directly via PyPI:
+
+```bash
+pip install iints-sdk-python35
+```
+
 ### Quick Start (CLI)
 ```bash
 iints quickstart --project-name iints_quickstart
@@ -99,7 +112,8 @@ outputs = iints.run_simulation(
 ```
 
 ### Notebook Guide
-Hands-on Jupyter notebooks live in `examples/notebooks/` and cover the full workflow (each is Colab-ready):
+Hands-on Jupyter notebooks live in [`examples/notebooks/`](examples/notebooks/)  
+
 
 * Quickstart end-to-end run
 * Presets + scenario validation

{iints_sdk_python35-0.1.7 → iints_sdk_python35-0.1.9}/src/iints_sdk_python35.egg-info/SOURCES.txt

@@ -22,6 +22,7 @@ src/iints/analysis/validator.py
 src/iints/api/__init__.py
 src/iints/api/base_algorithm.py
 src/iints/api/template_algorithm.py
+src/iints/assets/iints_logo.png
 src/iints/cli/__init__.py
 src/iints/cli/cli.py
 src/iints/core/__init__.py

iints_sdk_python35-0.1.7/src/iints/templates/default_algorithm.py

@@ -1,56 +0,0 @@
-from iints import InsulinAlgorithm, AlgorithmInput, AlgorithmResult, AlgorithmMetadata
-from typing import Dict, Any
-
-class {{ALGO_NAME}}(InsulinAlgorithm):
-    def __init__(self, settings: Dict[str, Any] = None):
-        super().__init__(settings)
-        self.set_algorithm_metadata(AlgorithmMetadata(
-            name="{{ALGO_NAME}}",
-            author="{{AUTHOR_NAME}}",
-            description="A new custom insulin algorithm.",
-            algorithm_type="rule_based" # Change as appropriate
-        ))
-        # Initialize any specific state or parameters for your algorithm here
-
-    def predict_insulin(self, data: AlgorithmInput) -> Dict[str, Any]:
-        # --- YOUR ALGORITHM LOGIC GOES HERE ---
-        # This is a basic placeholder. Implement your actual insulin prediction logic.
-
-        # Example: Deliver 0.1 units if glucose is above 120 mg/dL
-        total_insulin = 0.0
-        bolus_insulin = 0.0
-        basal_insulin = 0.0
-        correction_bolus = 0.0
-        meal_bolus = 0.0
-
-        if data.current_glucose > 120:
-            correction_bolus = (data.current_glucose - 120) / self.isf / 5 # Example: 1 unit per 50 mg/dL above 120
-            total_insulin += correction_bolus
-            self._log_reason(f"Correcting high glucose", "glucose_level", data.current_glucose, f"Delivered {correction_bolus:.2f} units to reduce {data.current_glucose} mg/dL")
-
-        if data.carb_intake > 0:
-            meal_bolus = data.carb_intake / self.icr
-            total_insulin += meal_bolus
-            self._log_reason(f"Meal intake detected", "carb_intake", data.carb_intake, f"Delivered {meal_bolus:.2f} units for {data.carb_intake}g carbs")
-
-        # Simulate basal rate (e.g., a continuous small delivery)
-        # For simplicity, let's assume a fixed basal delivery over the time step
-        # You might integrate this with your overall basal strategy
-        # basal_insulin = 0.01 * data.time_step # Example: 0.01 units per minute basal
-        # total_insulin += basal_insulin
-        self._log_reason(f"Maintaining basal rate", "basal", data.time_step, f"Delivered {basal_insulin:.2f} units basal")
-
-
-        # Ensure no negative insulin delivery
-        total_insulin = max(0.0, total_insulin)
-
-        # Store important decisions in the why_log for transparency
-        self._log_reason(f"Final insulin decision: {total_insulin:.2f} units", "decision", total_insulin)
-
-        return { 
-            "total_insulin_delivered": total_insulin,
-            "bolus_insulin": bolus_insulin, # You might differentiate between meal and correction bolus here
-            "basal_insulin": basal_insulin,
-            "correction_bolus": correction_bolus,
-            "meal_bolus": meal_bolus,
-        }