{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Data Exploration\n",
    "\n",
    "This notebook explores the CrisisLandMark dataset structure and verifies preprocessing."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import sys\n",
    "sys.path.insert(0, '..')\n",
    "\n",
    "import torch\n",
    "import numpy as np\n",
    "from PIL import Image\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "from src.data.preprocessing import preprocess_image, handle_channels\n",
    "from src.data.dataset import CrisisLandMarkDataset, create_splits"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 1. Create Dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create dataset for each modality\n",
    "optical_dataset = CrisisLandMarkDataset(modality='optical')\n",
    "sar_dataset = CrisisLandMarkDataset(modality='sar')\n",
    "\n",
    "print(f\"Optical dataset: {len(optical_dataset)} samples\")\n",
    "print(f\"SAR dataset: {len(sar_dataset)} samples\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 2. Sample Images"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Get sample images\n",
    "optical_img, optical_mod, optical_class = optical_dataset[0]\n",
    "sar_img, sar_mod, sar_class = sar_dataset[0]\n",
    "\n",
    "print(f\"Optical shape: {optical_img.shape}\")\n",
    "print(f\"SAR shape: {sar_img.shape}\")\n",
    "print(f\"Optical modality label: {optical_mod}\")\n",
    "print(f\"SAR modality label: {sar_mod}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 3. Data Splitting"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Test splitting\n",
    "query_idx, gallery_idx = create_splits(optical_dataset, query_ratio=0.2)\n",
    "\n",
    "print(f\"Query set: {len(query_idx)} samples\")\n",
    "print(f\"Gallery set: {len(gallery_idx)} samples\")\n",
    "print(f\"Overlap: {len(set(query_idx) & set(gallery_idx))} (should be 0)\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 4. Class Distribution"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Check class distribution\n",
    "class_counts = {}\n",
    "for i in range(len(optical_dataset)):\n",
    "    _, _, class_label = optical_dataset[i]\n",
    "    class_counts[class_label] = class_counts.get(class_label, 0) + 1\n",
    "\n",
    "print(\"Class distribution:\")\n",
    "for cls, count in sorted(class_counts.items()):\n",
    "    print(f\"  Class {cls}: {count} samples\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 5. Summary"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(\"\\n=== Data Exploration Summary ===\")\n",
    "print(f\"Total optical samples: {len(optical_dataset)}\")\n",
    "print(f\"Total SAR samples: {len(sar_dataset)}\")\n",
    "print(f\"Number of classes: {len(class_counts)}\")\n",
    "print(f\"Query/Gallery split: 80/20 with no overlap\")\n",
    "print(\"\\nPreprocessing verified for optical and SAR modalities.\")"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "name": "python",
   "version": "3.10.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}