{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 71,
   "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": 72,
   "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": 73,
   "metadata": {},
   "outputs": [],
   "source": [
    "fd_collection = getCollection(\"team_5_mwdb_phase_2\", \"fd_collection\")\n",
    "all_images = fd_collection.find()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "image_sim-cm_fd-lda-10-model.joblib loaded\n"
     ]
    }
   ],
   "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(\"label 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 selected_dim_reduction_method == \"lda\":\n",
    "            if os.path.exists(f\"{selected_feature_model}-{selected_dim_reduction_method}-{k}-model.joblib\") and os.path.exists(f\"{selected_feature_model}-{selected_dim_reduction_method}-{k}-semantics.json\"):\n",
    "                if os.path.exists(f\"{selected_feature_model}-{selected_dim_reduction_method}-{k}-model.joblib\"):\n",
    "                    model = load(f\"{selected_feature_model}-{selected_dim_reduction_method}-{k}-model.joblib\")\n",
    "                    data = json.load(open(f\"{selected_feature_model}-{selected_dim_reduction_method}-{k}-semantics.json\"))\n",
    "                    print(f\"{selected_feature_model}-{selected_dim_reduction_method}-{k}-model.joblib and json loaded\")\n",
    "                else:\n",
    "                    print(f\"{selected_feature_model}-{selected_dim_reduction_method}-{k}-model.joblib does not exist\")\n",
    "            else:\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",
    "                    print(f\"{selected_feature_model}-{selected_dim_reduction_method}-{k}-semantics.json loaded\")\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",
    "            print(f\"{selected_feature_model}-cp-{k}-semantics.json loaded\")\n",
    "        else:\n",
    "          print(f\"{selected_feature_model}-cp-{k}-semantics.json does not exist\")\n",
    "    case _:\n",
    "        if selected_dim_reduction_method == \"lda\":\n",
    "            if os.path.exists(f\"{selected_latent_space}-{selected_feature_model}-{selected_dim_reduction_method}-{k}-model.joblib\") and os.path.exists(f\"{selected_latent_space}-{selected_feature_model}-{selected_dim_reduction_method}-{k}-semantics.json\"):\n",
    "                model = load(f\"{selected_latent_space}-{selected_feature_model}-{selected_dim_reduction_method}-{k}-model.joblib\")\n",
    "                data = json.load(open(f\"{selected_latent_space}-{selected_feature_model}-{selected_dim_reduction_method}-{k}-semantics.json\"))\n",
    "                print(f\"{selected_latent_space}-{selected_feature_model}-{selected_dim_reduction_method}-{k}-model.joblib loaded\")\n",
    "            else:\n",
    "                print(f\"{selected_latent_space}-{selected_feature_model}-{selected_dim_reduction_method}-{k}-model.joblib does not exist\")\n",
    "        else:\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",
    "                print(f\"{selected_latent_space}-{selected_feature_model}-{selected_dim_reduction_method}-{k}-semantics.json loaded\")\n",
    "            else:\n",
    "                print(f\"{selected_latent_space}-{selected_feature_model}-{selected_dim_reduction_method}-{k}-semantics.json does not exist\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "metadata": {},
   "outputs": [],
   "source": [
    "def extract_similarities_ls1_ls4(latent_space, 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",
    "      if len(S.shape) == 1:\n",
    "        S = np.diag(S)\n",
    "      V = np.transpose(np.array(data[\"semantic-feature\"]))\n",
    "\n",
    "      if latent_space == \"image_sim\":\n",
    "        label_vectors = []\n",
    "        length = len(U)\n",
    "        for i in range(length):\n",
    "          if all_images[i][\"true_label\"] == label:\n",
    "            label_vectors.append(U[i])\n",
    "        label_rep = [sum(col) / len(col) for col in zip(*label_vectors)]\n",
    "      \n",
    "      comparison_feature_space = np.matmul(U, S)\n",
    "\n",
    "      if latent_space == \"image_sim\":\n",
    "        comparison_vector = np.matmul(label_rep, S)\n",
    "      else:\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 = W = np.array(data['image-semantic'])\n",
    "      if latent_space == \"image_sim\":\n",
    "        label_vectors = []\n",
    "        length = len(W)\n",
    "        for i in range(length):\n",
    "          if all_images[i][\"true_label\"] == label:\n",
    "            label_vectors.append(W[i])\n",
    "        label_rep = [sum(col) / len(col) for col in zip(*label_vectors)]\n",
    "\n",
    "      if latent_space == \"image_sim\":\n",
    "        comparison_vector = label_rep\n",
    "      else:\n",
    "        comparison_vector = np.matmul(label_rep, np.transpose(H))\n",
    "\n",
    "    case \"kmeans\":\n",
    "      comparison_vector = []\n",
    "      comparison_feature_space = np.array(data[\"image-semantic\"])\n",
    "      S = np.array(data[\"semantic-feature\"])\n",
    "\n",
    "      if latent_space == \"image_sim\":\n",
    "        sim_matrix = np.array(data[\"sim-matrix\"])\n",
    "        label_vectors = []\n",
    "        length = len(sim_matrix)\n",
    "        for i in range(length):\n",
    "          if all_images[i][\"true_label\"] == label:\n",
    "            label_vectors.append(sim_matrix[i])\n",
    "        label_rep = [sum(col) / len(col) for col in zip(*label_vectors)]\n",
    "\n",
    "      for centroid in S:\n",
    "        comparison_vector.append(math.dist(label_rep, centroid))\n",
    "\n",
    "    case \"lda\":\n",
    "      comparison_feature_space = np.array(data[\"image-semantic\"])\n",
    "      label_vectors = []\n",
    "      length = len(comparison_feature_space)\n",
    "      for i in range(length):\n",
    "        if all_images[i][\"true_label\"] == label:\n",
    "          label_vectors.append(comparison_feature_space[i])\n",
    "      comparison_vector = [sum(col) / len(col) for col in zip(*label_vectors)]      \n",
    "\n",
    "  n = len(comparison_feature_space)\n",
    "\n",
    "  distances = []\n",
    "  for i in range(n):\n",
    "    if all_images[i][\"true_label\"] != 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": 76,
   "metadata": {},
   "outputs": [],
   "source": [
    "def extract_similarities_ls2(data, label):\n",
    "\n",
    "  LS = np.array(data[\"label-semantic\"])\n",
    "  S = np.array(data[\"semantics-core\"])\n",
    "\n",
    "  if len(S.shape) == 1:\n",
    "    S = np.diag(S)\n",
    "\n",
    "  comparison_feature_space = np.matmul(LS, S)\n",
    "  comparison_vector = comparison_feature_space[label]\n",
    "\n",
    "  distances = []\n",
    "\n",
    "  n = len(comparison_feature_space)\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": 77,
   "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",
    "    case \"kmeans\":\n",
    "      comparison_feature_space = np.array(data[\"image-semantic\"])\n",
    "      comparison_vector = comparison_feature_space[label]\n",
    "\n",
    "    case \"lda\":\n",
    "      comparison_feature_space = np.array(data[\"image-semantic\"])\n",
    "      comparison_vector = comparison_feature_space[label]      \n",
    "\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": 78,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'image_id': 2641, 'label': 46, 'distance': 0.013618215122607105}\n",
      "{'image_id': 1686, 'label': 16, 'distance': 0.015215365128880378}\n",
      "{'image_id': 2310, 'label': 35, 'distance': 0.015383486193179943}\n",
      "{'image_id': 3781, 'label': 84, 'distance': 0.01541886635507712}\n",
      "{'image_id': 1483, 'label': 11, 'distance': 0.015474891099448796}\n",
      "{'image_id': 2719, 'label': 48, 'distance': 0.01960489858697963}\n",
      "{'image_id': 3787, 'label': 85, 'distance': 0.02006387165132467}\n",
      "{'image_id': 3877, 'label': 87, 'distance': 0.02050382578938892}\n",
      "{'image_id': 3719, 'label': 82, 'distance': 0.02293235381986182}\n",
      "{'image_id': 3403, 'label': 70, 'distance': 0.024912695992711693}\n"
     ]
    }
   ],
   "source": [
    "match selected_latent_space:\n",
    "\n",
    "  case \"\" | \"image_sim\":\n",
    "    \n",
    "    extract_similarities_ls1_ls4(selected_latent_space, 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",
    "\n",
    "  case \"cp\":\n",
    "\n",
    "    extract_similarities_ls2(data, label)\n"
   ]
  },
  {
   "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
}