{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 62,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "The autoreload extension is already loaded. To reload it, use:\n",
      "  %reload_ext autoreload\n"
     ]
    }
   ],
   "source": [
    "%load_ext autoreload\n",
    "%autoreload 2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "metadata": {},
   "outputs": [],
   "source": [
    "import json\n",
    "import os\n",
    "import numpy as np\n",
    "from utils import *\n",
    "import math\n",
    "import heapq"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "metadata": {},
   "outputs": [],
   "source": [
    "fd_collection = getCollection(\"team_5_mwdb_phase_2\", \"fd_collection\")\n",
    "all_images = fd_collection.find()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "metadata": {},
   "outputs": [],
   "source": [
    "selected_latent_space = valid_latent_spaces[\n",
    "    str(input(\"Enter latent space - one of \" + str(list(valid_latent_spaces.keys()))))\n",
    "]\n",
    "\n",
    "selected_feature_model = valid_feature_models[\n",
    "    str(input(\"Enter feature model - one of \" + str(list(valid_feature_models.keys()))))\n",
    "]\n",
    "\n",
    "k = int(input(\"Enter value of k: \"))\n",
    "if k < 1:\n",
    "    raise ValueError(\"k should be a positive integer\")\n",
    "\n",
    "selected_dim_reduction_method = str(\n",
    "    input(\n",
    "        \"Enter dimensionality reduction method - one of \"\n",
    "        + str(list(valid_dim_reduction_methods.keys()))\n",
    "    )\n",
    ")\n",
    "\n",
    "label = int(input(\"Enter label: \"))\n",
    "if label < 0 and label > 100:\n",
    "    raise ValueError(\"k should be between 0 and 100\")\n",
    "\n",
    "knum = int(input(\"Enter value of knum: \"))\n",
    "if knum < 1:\n",
    "    raise ValueError(\"knum should be a positive integer\")\n",
    "\n",
    "label_rep = calculate_label_representatives(fd_collection, label, selected_feature_model)\n",
    "\n",
    "match selected_latent_space:\n",
    "    case \"\":\n",
    "        if os.path.exists(f\"{selected_feature_model}-{selected_dim_reduction_method}-{k}-semantics.json\"):\n",
    "            data = json.load(open(f\"{selected_feature_model}-{selected_dim_reduction_method}-{k}-semantics.json\"))\n",
    "        else:\n",
    "          print(f\"{selected_feature_model}-{selected_dim_reduction_method}-{k}-semantics.json does not exist\" )\n",
    "    case \"cp\":\n",
    "        if os.path.exists(f\"{selected_feature_model}-cp-{k}-semantics.json\"):\n",
    "            data = json.load(open(f\"{selected_feature_model}-cp-{k}-semantics.json\"))\n",
    "        else:\n",
    "          \n",
    "          print(f\"{selected_feature_model}-cp-{k}-semantics.json does not exist\" )\n",
    "    case _:\n",
    "        if os.path.exists(f\"{selected_latent_space}-{selected_feature_model}-{selected_dim_reduction_method}-{k}-semantics.json\"):\n",
    "            data = json.load(open(f\"{selected_latent_space}-{selected_feature_model}-{selected_dim_reduction_method}-{k}-semantics.json\"))\n",
    "        else:\n",
    "          print(f\"{selected_latent_space}-{selected_feature_model}-{selected_dim_reduction_method}-{k}-semantics.json does not exist\" )\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "metadata": {},
   "outputs": [],
   "source": [
    "def extract_similarities_ls1(dim_reduction, data, label, label_rep):\n",
    "\n",
    "  match dim_reduction:\n",
    "\n",
    "    case 'svd':\n",
    "      U = np.array(data[\"image-semantic\"])\n",
    "      S = np.array(data[\"semantics-core\"])\n",
    "      V = np.transpose(np.array(data[\"semantic-feature\"]))\n",
    "\n",
    "      comparison_feature_space = np.matmul(U, S)\n",
    "      comparison_vector = np.matmul(np.matmul(label_rep, V), S)\n",
    "    \n",
    "    case \"nmf\":\n",
    "      H = np.array(data['semantic-feature'])\n",
    "      comparison_feature_space = np.array(data['image-semantic'])\n",
    "      comparison_vector = np.matmul(label_rep, np.transpose(H))\n",
    "\n",
    "    case \"\"\n",
    "\n",
    "  print(comparison_feature_space.shape)\n",
    "  n = len(comparison_feature_space)\n",
    " \n",
    "  distances = []\n",
    "  for i in range(n):\n",
    "    if i != label:\n",
    "      distances.append({\"image_id\": i, \"label\": all_images[i][\"true_label\"],\"distance\": math.dist(comparison_vector, comparison_feature_space[i])})\n",
    "\n",
    "  distances = sorted(distances, key=lambda x: x[\"distance\"], reverse=False)\n",
    "\n",
    "  similar_labels = []\n",
    "  unique_labels = set()\n",
    "\n",
    "  for img in distances:\n",
    "    if img['label'] not in unique_labels:\n",
    "      similar_labels.append(img)\n",
    "      unique_labels.add(img[\"label\"])\n",
    "\n",
    "      if len(similar_labels) == knum:\n",
    "        break\n",
    "\n",
    "\n",
    "  for x in similar_labels:\n",
    "    print(x)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "metadata": {},
   "outputs": [],
   "source": [
    "def extract_similarities_ls3(dim_reduction, data, label):\n",
    "\n",
    "  match dim_reduction:\n",
    "\n",
    "    case 'svd':\n",
    "      U = np.array(data[\"image-semantic\"])\n",
    "      S = np.array(data[\"semantics-core\"])\n",
    "      V = np.transpose(np.array(data[\"semantic-feature\"]))\n",
    "\n",
    "      comparison_feature_space = np.matmul(U, S)\n",
    "      comparison_vector = comparison_feature_space[label]\n",
    "    \n",
    "    case \"nmf\":\n",
    "      comparison_feature_space = np.array(data['image-semantic'])\n",
    "      comparison_vector = comparison_feature_space[label]\n",
    "\n",
    "  n = len(comparison_feature_space)\n",
    "  distances = []\n",
    "  for i in range(n):\n",
    "    if i != label:\n",
    "      distances.append({\"label\": i, \"distance\": math.dist(comparison_vector, comparison_feature_space[i])})\n",
    "\n",
    "  distances = sorted(distances, key=lambda x: x[\"distance\"], reverse=False)[:knum]\n",
    "\n",
    "  for x in distances:\n",
    "    print(x)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'label': 4, 'distance': 0.9931105104385977}\n",
      "{'label': 92, 'distance': 1.1209182190288185}\n",
      "{'label': 65, 'distance': 1.2107732156271573}\n",
      "{'label': 21, 'distance': 1.5053484881391492}\n",
      "{'label': 2, 'distance': 1.698430977110922}\n",
      "{'label': 100, 'distance': 1.8636096001573115}\n",
      "{'label': 95, 'distance': 2.003755992104511}\n",
      "{'label': 11, 'distance': 2.069066281581252}\n",
      "{'label': 60, 'distance': 2.070894540798742}\n",
      "{'label': 88, 'distance': 2.0925931256031}\n",
      "{'label': 43, 'distance': 2.1056747598887218}\n",
      "{'label': 33, 'distance': 2.165431005806523}\n",
      "{'label': 90, 'distance': 2.174626607979455}\n",
      "{'label': 83, 'distance': 2.188609736988739}\n",
      "{'label': 68, 'distance': 2.209562202827548}\n",
      "{'label': 59, 'distance': 2.27130902508622}\n",
      "{'label': 35, 'distance': 2.276916489521396}\n",
      "{'label': 70, 'distance': 2.283111150497479}\n",
      "{'label': 53, 'distance': 2.2871296343421075}\n",
      "{'label': 42, 'distance': 2.2943393449254192}\n",
      "{'label': 1, 'distance': 2.299515307388396}\n",
      "{'label': 89, 'distance': 2.300444335700286}\n",
      "{'label': 64, 'distance': 2.3105619552648906}\n",
      "{'label': 47, 'distance': 2.3258018764464126}\n",
      "{'label': 28, 'distance': 2.33793138436563}\n",
      "{'label': 91, 'distance': 2.348432279582375}\n",
      "{'label': 66, 'distance': 2.378823252101462}\n",
      "{'label': 52, 'distance': 2.3845656934663344}\n",
      "{'label': 17, 'distance': 2.3851103284430946}\n",
      "{'label': 29, 'distance': 2.392106657184808}\n",
      "{'label': 46, 'distance': 2.4059349825734024}\n",
      "{'label': 98, 'distance': 2.425981349727766}\n",
      "{'label': 12, 'distance': 2.4320238781945878}\n",
      "{'label': 5, 'distance': 2.433658250868235}\n",
      "{'label': 72, 'distance': 2.4438014606638965}\n",
      "{'label': 96, 'distance': 2.446857205149324}\n",
      "{'label': 18, 'distance': 2.4473786634019508}\n",
      "{'label': 0, 'distance': 2.4482053195868017}\n",
      "{'label': 49, 'distance': 2.451590137889849}\n",
      "{'label': 14, 'distance': 2.4717097207497414}\n",
      "{'label': 85, 'distance': 2.473715190942228}\n",
      "{'label': 19, 'distance': 2.4754273396104534}\n",
      "{'label': 51, 'distance': 2.4810475345400316}\n",
      "{'label': 75, 'distance': 2.4850838216864224}\n",
      "{'label': 93, 'distance': 2.4867224184341175}\n",
      "{'label': 44, 'distance': 2.498509815319209}\n",
      "{'label': 82, 'distance': 2.501339416798757}\n",
      "{'label': 54, 'distance': 2.506342353975533}\n",
      "{'label': 9, 'distance': 2.5065630929096394}\n",
      "{'label': 41, 'distance': 2.51345667730748}\n"
     ]
    }
   ],
   "source": [
    "match selected_latent_space:\n",
    "\n",
    "  case \"\":\n",
    "    \n",
    "    extract_similarities_ls1(selected_dim_reduction_method, data, label, label_rep)\n",
    "\n",
    "  case \"label_sim\":\n",
    "\n",
    "    extract_similarities_ls3(selected_dim_reduction_method, data, label)\n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.11.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}