diff --git a/Phase 2/task5.ipynb b/Phase 2/task5.ipynb
new file mode 100644
index 0000000..63f1ba0
--- /dev/null
+++ b/Phase 2/task5.ipynb
@@ -0,0 +1,198 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import json\n",
+ "import math\n",
+ "from pymongo import MongoClient\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"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "metadata": {},
+ "outputs": [
+ {
+ "ename": "ValueError",
+ "evalue": "invalid literal for int() with base 10: ''",
+ "output_type": "error",
+ "traceback": [
+ "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+ "\u001b[1;31mValueError\u001b[0m Traceback (most recent call last)",
+ "\u001b[1;32me:\\Fall 23\\CSE 515 - Multimedia and web databases\\CSE515_MWDB_Project\\Phase 2\\task5.ipynb Cell 2\u001b[0m line \u001b[0;36m9\n\u001b[0;32m 89\u001b[0m extractKLatentSemantics(k, label_sim_matrix, feature_model, dim_reduction)\n\u001b[0;32m 93\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39m__name__\u001b[39m \u001b[39m==\u001b[39m \u001b[39m\"\u001b[39m\u001b[39m__main__\u001b[39m\u001b[39m\"\u001b[39m:\n\u001b[1;32m---> 94\u001b[0m main()\n",
+ "\u001b[1;32me:\\Fall 23\\CSE 515 - Multimedia and web databases\\CSE515_MWDB_Project\\Phase 2\\task5.ipynb Cell 2\u001b[0m line \u001b[0;36m6\n\u001b[0;32m 67\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39mmain\u001b[39m():\n\u001b[1;32m---> 69\u001b[0m k \u001b[39m=\u001b[39m \u001b[39mint\u001b[39;49m(\u001b[39minput\u001b[39;49m(\u001b[39m\"\u001b[39;49m\u001b[39mEnter k: \u001b[39;49m\u001b[39m\"\u001b[39;49m))\n\u001b[0;32m 71\u001b[0m features \u001b[39m=\u001b[39m [\u001b[39m'\u001b[39m\u001b[39mcolor_moments\u001b[39m\u001b[39m'\u001b[39m, \u001b[39m'\u001b[39m\u001b[39mhog\u001b[39m\u001b[39m'\u001b[39m, \u001b[39m'\u001b[39m\u001b[39mlayer3\u001b[39m\u001b[39m'\u001b[39m, \u001b[39m'\u001b[39m\u001b[39mavgpool\u001b[39m\u001b[39m'\u001b[39m, \u001b[39m'\u001b[39m\u001b[39mfc\u001b[39m\u001b[39m'\u001b[39m]\n\u001b[0;32m 73\u001b[0m \u001b[39m# User input for feature model to extract\u001b[39;00m\n",
+ "\u001b[1;31mValueError\u001b[0m: invalid literal for int() with base 10: ''"
+ ]
+ }
+ ],
+ "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)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def extractKLatentSemantics(k, image_sim_matrix, feature_model, dim_reduction):\n",
+ "\n",
+ " feature_ids = [x[\"_id\"] 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",
+ "\n",
+ " filename = 'ls3.json'\n",
+ "\n",
+ " match dim_reduction:\n",
+ "\n",
+ " case 1:\n",
+ " U, S, Vh = scipy.sparse.linalg.svds(np.array(image_sim_matrix), 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",
+ " 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(image_sim_matrix)\n",
+ " feature_vectors_shifted = image_sim_matrix - 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",
+ " U = LinearDiscriminantAnalysis(n_components = k).fit_transform(image_sim_matrix, 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",
+ " kmeans = KMeans(n_clusters = k)\n",
+ " kmeans.fit(image_sim_matrix)\n",
+ " U = kmeans.transform(image_sim_matrix)\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)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def findLabelLabelSimMatrix(feature_model):\n",
+ "\n",
+ " label_sim_matrix = []\n",
+ " label_mean_vectors = []\n",
+ "\n",
+ " for label in range(101):\n",
+ " label_vectors = [x[feature_model] for x in feature_descriptors if x[\"label\"] == label and x[\"_id\"] % 2 == 0]\n",
+ " mean_vector = [sum(col)/len(col) for col in zip(*label_vectors)]\n",
+ " label_mean_vectors.append(mean_vector)\n",
+ " \n",
+ "\n",
+ " n = len(label_mean_vectors)\n",
+ "\n",
+ " label_sim_matrix = np.zeros((n, n))\n",
+ "\n",
+ " for i in range(n):\n",
+ " for j in range(i + 1, n):\n",
+ "\n",
+ " match feature_model:\n",
+ "\n",
+ " case \"color_moments\":\n",
+ " label_sim_matrix[i][j] = label_sim_matrix[j][i] = math.dist(label_mean_vectors[i], label_mean_vectors[j])\n",
+ " \n",
+ " case \"hog\":\n",
+ " label_sim_matrix[i][j] = label_sim_matrix[j][i] = (np.dot(label_mean_vectors[i], label_mean_vectors[j]) / (np.linalg.norm(label_mean_vectors[i]) * np.linalg.norm(label_mean_vectors[j])))\n",
+ "\n",
+ " case \"avgpool\" | \"layer3\" | \"fc\":\n",
+ " label_sim_matrix[i][j] = label_sim_matrix[j][i] = scipy.stats.pearsonr(label_mean_vectors[i], label_mean_vectors[j]).statistic\n",
+ " \n",
+ " return label_sim_matrix"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def main():\n",
+ "\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",
+ " label_sim_matrix = findLabelLabelSimMatrix(feature_model)\n",
+ "\n",
+ " extractKLatentSemantics(k, label_sim_matrix, 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": {
+ "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
+}