From 3ca1614746080cb2b038383daeac3eb4302fec21 Mon Sep 17 00:00:00 2001 From: pranavbrkr Date: Fri, 13 Oct 2023 17:59:45 -0700 Subject: [PATCH] ls4 cases for svd and nmf --- Phase 2/task_9.ipynb | 152 ++++++++++++++++++++++--------------------- 1 file changed, 79 insertions(+), 73 deletions(-) diff --git a/Phase 2/task_9.ipynb b/Phase 2/task_9.ipynb index a034da5..3985b51 100644 --- a/Phase 2/task_9.ipynb +++ b/Phase 2/task_9.ipynb @@ -2,7 +2,7 @@ "cells": [ { "cell_type": "code", - "execution_count": 62, + "execution_count": 64, "metadata": {}, "outputs": [ { @@ -21,7 +21,7 @@ }, { "cell_type": "code", - "execution_count": 63, + "execution_count": 65, "metadata": {}, "outputs": [], "source": [ @@ -35,7 +35,7 @@ }, { "cell_type": "code", - "execution_count": 64, + "execution_count": 66, "metadata": {}, "outputs": [], "source": [ @@ -45,9 +45,17 @@ }, { "cell_type": "code", - "execution_count": 65, + "execution_count": 67, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "image_sim-cm_fd-nmf-10-semantics.json loaded\n" + ] + } + ], "source": [ "selected_latent_space = valid_latent_spaces[\n", " str(input(\"Enter latent space - one of \" + str(list(valid_latent_spaces.keys()))))\n", @@ -82,53 +90,87 @@ " 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", + " 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", + " 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", + " 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 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\" )\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, + "execution_count": 83, "metadata": {}, "outputs": [], "source": [ - "def extract_similarities_ls1(dim_reduction, data, label, label_rep):\n", + "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", - " comparison_vector = np.matmul(np.matmul(label_rep, V), S)\n", + "\n", + " if latent_space == \"image_sim\":\n", + " print(np.array(label_rep).shape)\n", + " print(np.array(S).shape)\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 = np.array(data['image-semantic'])\n", - " comparison_vector = np.matmul(label_rep, np.transpose(H))\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", - " case \"\"\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", + " for centroid in S:\n", + " comparison_vector.append(math.dist(label_rep, centroid))\n", "\n", - " print(comparison_feature_space.shape)\n", " n = len(comparison_feature_space)\n", - " \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", + " 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", @@ -150,7 +192,7 @@ }, { "cell_type": "code", - "execution_count": 67, + "execution_count": 84, "metadata": {}, "outputs": [], "source": [ @@ -170,6 +212,10 @@ " 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", " n = len(comparison_feature_space)\n", " distances = []\n", " for i in range(n):\n", @@ -184,72 +230,32 @@ }, { "cell_type": "code", - "execution_count": 68, + "execution_count": 85, "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" + "{'image_id': 1102, 'label': 5, 'distance': 0.4995439271653643}\n", + "{'image_id': 637, 'label': 3, 'distance': 0.6162759255696203}\n", + "{'image_id': 1450, 'label': 9, 'distance': 0.6537940561051517}\n", + "{'image_id': 2148, 'label': 30, 'distance': 0.6885146297494956}\n", + "{'image_id': 3574, 'label': 77, 'distance': 0.6970323320729979}\n", + "{'image_id': 2202, 'label': 31, 'distance': 0.6975621319006345}\n", + "{'image_id': 2917, 'label': 54, 'distance': 0.7112049573397025}\n", + "{'image_id': 4325, 'label': 100, 'distance': 0.7394787087142192}\n", + "{'image_id': 1543, 'label': 12, 'distance': 0.7404143327603417}\n", + "{'image_id': 2333, 'label': 35, 'distance': 0.7432769566450207}\n" ] } ], "source": [ "match selected_latent_space:\n", "\n", - " case \"\":\n", + " case \"\" | \"image_sim\":\n", " \n", - " extract_similarities_ls1(selected_dim_reduction_method, data, label, label_rep)\n", + " extract_similarities_ls1_ls4(selected_latent_space, selected_dim_reduction_method, data, label, label_rep)\n", "\n", " case \"label_sim\":\n", "\n",