From e293f98ee1ace58589cd4d708c2391a26aa907ff Mon Sep 17 00:00:00 2001
From: MadhuraWani803 <103093329+MadhuraWani803@users.noreply.github.com>
Date: Sat, 25 Nov 2023 14:10:58 -0700
Subject: [PATCH] Add files via upload

---
 Phase 3/phase3_task0a.ipynb | 124 ++++++++++++++++++++++++++++++++++++
 1 file changed, 124 insertions(+)
 create mode 100644 Phase 3/phase3_task0a.ipynb

diff --git a/Phase 3/phase3_task0a.ipynb b/Phase 3/phase3_task0a.ipynb
new file mode 100644
index 0000000..f6e4ca2
--- /dev/null
+++ b/Phase 3/phase3_task0a.ipynb	
@@ -0,0 +1,124 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from utils import *\n",
+    "warnings.filterwarnings('ignore')\n",
+    "%matplotlib inline"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "fd_collection = getCollection(\"team_5_mwdb_phase_2\", \"fd_collection\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def pca_inherent_dimensionality(data, threshold):\n",
+    "\n",
+    "    # Calculate the mean of the data\n",
+    "    mean = np.mean(data, axis=0)\n",
+    "    # Center the data by subtracting the mean\n",
+    "    centered_data = data - mean\n",
+    "    # Normalize the data\n",
+    "    normalized_data = centered_data / np.std(centered_data, axis=0)\n",
+    "\n",
+    "    # Reshape the centered data to ensure compatible dimensions\n",
+    "    if(len(normalized_data.shape)==3):\n",
+    "        reshaped_normalized_data = normalized_data.reshape(normalized_data.shape[0], normalized_data.shape[2])\n",
+    "    else:\n",
+    "        reshaped_normalized_data=normalized_data\n",
+    "\n",
+    "    # Calculate the covariance matrix\n",
+    "    #covariance_matrix = np.dot(reshaped_normalized_data.T, reshaped_normalized_data)\n",
+    "    covariance_matrix = np.dot(reshaped_normalized_data.T, reshaped_normalized_data) / (reshaped_normalized_data.shape[0] - 1) #to bring the values in the range of 0 to 1\n",
+    "\n",
+    "    # Compute the eigenvalues and eigenvectors of the covariance matrix\n",
+    "    eigenvalues, eigenvectors = np.linalg.eig(covariance_matrix)\n",
+    "    # Sort the eigenvalues in descending order\n",
+    "    #sorted_indices = np.argsort(eigenvalues)[::-1]\n",
+    "    # Sort the eigenvectors accordingly\n",
+    "    #sorted_eigenvectors = eigenvectors[:, sorted_indices]\n",
+    "    #print(sorted_eigenvectors)\n",
+    "    #print(sorted_indices)\n",
+    "\n",
+    "    # Calculate the mean of each subarray- the sorted_eigenvectors are in the form of subarrays, while computing the inherent dimensionality, each value is compared with \n",
+    "    #the threshold, hence mean of each subarray is computed and then it is compared with the threshold value (I am not sure if we can do this?)\n",
+    "    #means = np.mean(sorted_eigenvectors, axis=1)\n",
+    "    \n",
+    "    # Determine the number of eigenvalues greater than the threshold\n",
+    "    #inherent_dimensionality = np.sum(means>threshold)\n",
+    "    #inherent_dimensionality = len(significant_eigenvalues)\n",
+    "    significant_eigenvalues = eigenvalues[eigenvalues > threshold]\n",
+    "    inherent_dimensionality = len(significant_eigenvalues)\n",
+    "    #significant_eigenvalues = sorted_eigenvectors[sorted_indices][eigenvalues > threshold]\n",
+    "\n",
+    "    return inherent_dimensionality"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Inherent dimensionality associated with the even numbered images:  260\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Retrieve all feature spaces from the database\n",
+    "data = []\n",
+    "for document in fd_collection.find():\n",
+    "    feature_space = document[\"fc_fd\"]\n",
+    "    data.append(feature_space)\n",
+    "\n",
+    "threshold=0.5\n",
+    "print(\"Inherent dimensionality associated with the even numbered images: \", pca_inherent_dimensionality(data, threshold))"
+   ]
+  },
+  {
+   "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": "3.10.11"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}