{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import json\n",
    "from pymongo import MongoClient\n",
    "from task0a import *\n",
    "import scipy\n",
    "import numpy as np\n",
    "from sklearn.decomposition import NMF\n",
    "from sklearn.discriminant_analysis import LinearDiscriminantAnalysis\n",
    "from sklearn.cluster import KMeans\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "client = MongoClient()\n",
    "client = MongoClient(host=\"localhost\", port=27017)\n",
    "\n",
    "# Select the database\n",
    "db = client.Multimedia_Web_DBs\n",
    "\n",
    "# Fetch all documents from the collection and then sort them by \"_id\"\n",
    "feature_descriptors = list(db.Caltech101_Feature_Descriptors.find({}))\n",
    "feature_descriptors = sorted(list(db.Caltech101_Feature_Descriptors.find({})), key=lambda x: x[\"_id\"], reverse=False)\n",
    "\n",
    "num_labels = 101"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def extractKLatentSemantics(k, feature_model, dim_reduction):\n",
    "\n",
    "  feature_vectors = [x[feature_model] for x in feature_descriptors if x[\"_id\"] % 2 == 0]\n",
    "  feature_labels = [x[\"label\"] for x in feature_descriptors if x[\"_id\"] % 2 == 0]\n",
    "  feature_ids = [x[\"_id\"] for x in feature_descriptors if x[\"_id\"] % 2 == 0]\n",
    "\n",
    "  filename = ''\n",
    "\n",
    "\n",
    "  match dim_reduction:\n",
    "\n",
    "    case 1:\n",
    "      filename = f'{feature_model}-svd-semantics.json'\n",
    "      U, S, Vh = scipy.sparse.linalg.svds(np.array(feature_vectors), k=k)\n",
    "      k_latent_semantics = sorted(list(zip(feature_ids, U.tolist())), key = lambda x: x[1][0], reverse = True)\n",
    "\n",
    "    case 2:\n",
    "      filename = f'{feature_model}-nnmf-semantics.json'\n",
    "      model = NMF(n_components = k, init = 'random', solver = 'cd', alpha_H = 0.01, alpha_W = 0.01, max_iter = 10000)\n",
    "      min_value = np.min(feature_vectors)\n",
    "      feature_vectors_shifted = feature_vectors - min_value\n",
    "      U = model.fit_transform(np.array(feature_vectors_shifted))\n",
    "      k_latent_semantics = sorted(list(zip(feature_ids, U.tolist())), key = lambda x: x[1][0], reverse = True)\n",
    "\n",
    "    case 3:\n",
    "      filename = f'{feature_model}-lda-semantics.json'\n",
    "      U = LinearDiscriminantAnalysis(n_components = k).fit_transform(feature_vectors, feature_labels)\n",
    "      k_latent_semantics = sorted(list(zip(feature_ids, U.tolist())), key = lambda x: x[1][0], reverse = True)\n",
    "\n",
    "    case 4:\n",
    "      filename = f'{feature_model}-kmeans-semantics.json'\n",
    "      kmeans = KMeans(n_clusters = k)\n",
    "      kmeans.fit(feature_vectors)\n",
    "      U = kmeans.transform(feature_vectors)\n",
    "      k_latent_semantics = sorted(list(zip(feature_ids, U.tolist())), key = lambda x: x[1][0], reverse = True)\n",
    "  \n",
    "  k_latent_semantics = [{\"_id\": item[0], \"semantics\": item[1]} for item in k_latent_semantics]\n",
    "  with open(filename, 'w', encoding='utf-8') as f:\n",
    "    json.dump(k_latent_semantics, f, ensure_ascii = False)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def main():\n",
    "\n",
    "  # Load dataset\n",
    "\n",
    "  # User input for Image ID\n",
    "  k = int(input(\"Enter k: \"))\n",
    "\n",
    "  features = ['color_moments', 'hog', 'layer3', 'avgpool', 'fc']\n",
    "\n",
    "  # User input for feature model to extract\n",
    "  print(\"\\n1: Color moments\")\n",
    "  print(\"2: HOG\")\n",
    "  print(\"3: Resnet50 Avgpool layer\")\n",
    "  print(\"4: Resnet50 Layer 3\")\n",
    "  print(\"5: Resnet50 FC layer\")\n",
    "  feature_model = features[int(input(\"Select the feature model: \")) - 1]\n",
    "\n",
    "  print(\"\\n1. SVD\")\n",
    "  print(\"2. NNMF\")\n",
    "  print(\"3. LDA\")\n",
    "  print(\"4. k-means\")\n",
    "  dim_reduction = int(input(\"Select the dimensionality reduction technique: \"))\n",
    "\n",
    "  extractKLatentSemantics(k, feature_model, dim_reduction)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "if __name__ == \"__main__\":\n",
    "   main()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "language_info": {
   "name": "python"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}