UI Improvement & Design Fixes

.editorconfig

@@ -2,4 +2,5 @@
 # This configuration is used by ktlint when spotless invokes it
 
 [*.{kt,kts}]
-ktlint_function_naming_ignore_when_annotated_with=Composable, Test
+ktlint_function_naming_ignore_when_annotated_with=Composable, Test
+ktlint_disabled_rules=no-wildcard-imports

AI Guardian/Docs/AI Guardian/Docs/Guardian_alert_syastem/Synthetic_data_gen.ipynb

@@ -0,0 +1,103 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d078fc22",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "from datetime import datetime, timedelta\n",
+    "import os\n",
+    "\n",
+    "# Function to simulate one day of vitals, wearable, and emotion data for one patient\n",
+    "def simulate_patient_day(patient_id, start_time, minutes=1440):\n",
+    "    timestamps = [start_time + timedelta(minutes=i) for i in range(minutes)]\n",
+    "\n",
+    "    # Vitals (simulate with realistic normal ranges)\n",
+    "    heart_rate = np.random.normal(loc=75, scale=10, size=minutes)\n",
+    "    spo2 = np.random.normal(loc=97, scale=1.5, size=minutes)\n",
+    "    bp_sys = np.random.normal(loc=115, scale=10, size=minutes)\n",
+    "    bp_dia = np.random.normal(loc=75, scale=8, size=minutes)\n",
+    "    resp_rate = np.random.normal(loc=16, scale=3, size=minutes)\n",
+    "    temp = np.random.normal(loc=36.8, scale=0.3, size=minutes)\n",
+    "\n",
+    "    # Wearables\n",
+    "    steps = np.random.poisson(lam=12, size=minutes)\n",
+    "    acc_x = np.random.normal(0, 1, size=minutes)\n",
+    "    acc_y = np.random.normal(0, 1, size=minutes)\n",
+    "    acc_z = np.random.normal(0, 1, size=minutes)\n",
+    "    activity_levels = np.random.choice(['sedentary', 'light', 'moderate', 'vigorous'],\n",
+    "                                       size=minutes, p=[0.4, 0.3, 0.2, 0.1])\n",
+    "\n",
+    "    # Emotion\n",
+    "    emotions = np.random.choice(['neutral', 'happy', 'sad', 'angry'],\n",
+    "                                size=minutes, p=[0.5, 0.2, 0.2, 0.1])\n",
+    "    voice_pitch = np.random.normal(loc=150, scale=30, size=minutes)\n",
+    "    facial_intensity = np.random.uniform(0.2, 0.9, size=minutes)\n",
+    "\n",
+    "    # Risk logic (simple rule-based)\n",
+    "    risk_alert = (\n",
+    "        (heart_rate > 100) |\n",
+    "        (spo2 < 92) |\n",
+    "        (bp_sys > 140) |\n",
+    "        (bp_dia < 60) |\n",
+    "        (resp_rate > 25) |\n",
+    "        (temp > 38) |\n",
+    "        (emotions == 'angry') |\n",
+    "        (emotions == 'sad')\n",
+    "    ).astype(int)\n",
+    "\n",
+    "    df = pd.DataFrame({\n",
+    "        'patient_id': patient_id,\n",
+    "        'timestamp': timestamps,\n",
+    "        'heart_rate': heart_rate,\n",
+    "        'spo2': spo2,\n",
+    "        'bp_sys': bp_sys,\n",
+    "        'bp_dia': bp_dia,\n",
+    "        'resp_rate': resp_rate,\n",
+    "        'temperature': temp,\n",
+    "        'steps': steps,\n",
+    "        'acc_x': acc_x,\n",
+    "        'acc_y': acc_y,\n",
+    "        'acc_z': acc_z,\n",
+    "        'activity_level': activity_levels,\n",
+    "        'emotion': emotions,\n",
+    "        'voice_pitch': voice_pitch,\n",
+    "        'facial_intensity': facial_intensity,\n",
+    "        'risk_alert': risk_alert\n",
+    "    })\n",
+    "\n",
+    "    return df\n",
+    "\n",
+    "# Simulate and save data in batches\n",
+    "def simulate_patients_batch(total_patients=10000, batch_size=500, save_path=\"/content/guardian_data\"):\n",
+    "    os.makedirs(save_path, exist_ok=True)\n",
+    "    start_time = datetime(2025, 1, 1, 0, 0)\n",
+    "\n",
+    "    for i in range(0, total_patients, batch_size):\n",
+    "        batch_data = []\n",
+    "        for j in range(batch_size):\n",
+    "            pid = i + j\n",
+    "            df = simulate_patient_day(pid, start_time)\n",
+    "            batch_data.append(df)\n",
+    "        combined_df = pd.concat(batch_data)\n",
+    "        file_path = f\"{save_path}/guardian_data_patients_{i}_{i+batch_size-1}.csv\"\n",
+    "        combined_df.to_csv(file_path, index=False)\n",
+    "        print(f\"Saved batch: {file_path}\")\n",
+    "\n",
+    "# Example: Run for first 10000 patients in 2 batches of 5000\n",
+    "simulate_patients_batch(total_patients=10000, batch_size=5000, save_path=\"/content/guardian_data\")\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}