my-asu-archive/CSE515_MWDB_Project
1
0
Fork 0
mirror of https://github.com/20kaushik02/CSE515_MWDB_Project.git synced 2025-12-06 09:34:07 +00:00
Code Issues Packages Projects Releases Wiki Activity

task 11 code, to be tested

Browse Source
This commit is contained in:
Kaushik Narayan R 2023-10-15 13:49:39 -07:00
parent 91f782a485
commit 992ea2db24
3 changed files with 329 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

322
Phase 2/task_11.ipynb Normal file
View File

@ -0,0 +1,322 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"from utils import *\n",
"warnings.filterwarnings('ignore')\n",
"%matplotlib inline\n"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"fd_collection = getCollection(\"team_5_mwdb_phase_2\", \"fd_collection\")\n"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [],
"source": [
"class ImageGraph:\n",
" \"\"\"\n",
" Construct image-similarity graph and apply personalized pagerank algorithm to get PPR scores and find relevant images\n",
" \"\"\"\n",
"\n",
" def __init__(self, fd_collection, verbose=False):\n",
" self.fd_collection = fd_collection\n",
" self.similarity_graph = None\n",
" self.verbose = verbose\n",
"\n",
" def create_similarity_graph(\n",
" self, n, feature_model, semantic_data=None, dim_reduction_method=None\n",
" ):\n",
" if semantic_data is None:\n",
" # Similarity graph from feature models\n",
" image_sim_matrix = find_image_image_similarity(fd_collection, feature_model)\n",
" if self.verbose:\n",
" print(\"Image-image similarity matrix constructed from\", feature_model)\n",
" else:\n",
" # Similarity graph from image-semantic latent space\n",
" # LS3, LS4\n",
" if \"sim-matrix\" in semantic_data:\n",
" # for now, don't work with LS3\n",
" # TODO: do similar to task 7 and 10\n",
" image_sim_matrix = np.array(semantic_data[\"sim-matrix\"])\n",
" if image_sim_matrix.shape[0] != NUM_IMAGES:\n",
" raise TypeError(\n",
" \"Functionality to construct similarity graph from LS3 not yet done\"\n",
" )\n",
" if self.verbose:\n",
" print(\"Using image-image similarity matrix from semantic data\")\n",
" # LS1, LS2\n",
" else:\n",
" image_semantic = semantic_data[\"image-semantic\"]\n",
" # SVD, CP\n",
" if \"semantics-core\" in semantic_data:\n",
" semantics_core = np.array(semantic_data[\"semantics-core\"])\n",
" if len(semantics_core.shape) == 1:\n",
" semantics_core = np.diag(semantics_core)\n",
" image_semantic = np.matmul(image_semantic, semantics_core)\n",
"\n",
" image_sim_matrix = np.zeros((NUM_IMAGES, NUM_IMAGES))\n",
" # Calculate half and fill the other\n",
" for i in range(NUM_IMAGES):\n",
" for j in range(i + 1, NUM_IMAGES):\n",
" # Note: lower the value, lower the distance => higher the similarity\n",
" distance_measure = (\n",
" kl_divergence_measure\n",
" if dim_reduction_method == \"lda\"\n",
" else euclidean_distance_measure\n",
" )\n",
" image_sim_matrix[j][i] = distance_measure(\n",
" np.array(image_semantic[i]),\n",
" np.array(image_semantic[j]),\n",
" )\n",
" image_sim_matrix[i][j] = image_sim_matrix[j][i]\n",
" if self.verbose:\n",
" print(\n",
" \"Image-image similarity matrix constructed from given image-semantic\"\n",
" )\n",
"\n",
" # Create an unweighted directed similarity graph, with no self-loops\n",
" self.similarity_graph = []\n",
" for i in range(len(image_sim_matrix)):\n",
" # distances should be small, so sort in ascending order\n",
" similar_image_ids = np.argsort(image_sim_matrix[i])[\n",
" 1 : n + 1\n",
" ] # exclude self\n",
" self.similarity_graph.extend(\n",
" [(i * 2, j * 2) for j in similar_image_ids]\n",
" ) # i*2 cuz even IDs\n",
" if self.verbose:\n",
" print(\"Similarity graph created\")\n",
"\n",
" def personalized_pagerank(\n",
" self, label, m, damping_factor=0.85, max_iter=1000, tol=1e-6\n",
" ):\n",
" import time\n",
" if self.similarity_graph is None:\n",
" raise ValueError(\n",
" \"Similarity graph not created. Call create_similarity_graph() first.\"\n",
" )\n",
"\n",
" label_indices = [\n",
" img[\"image_id\"] for img in self.fd_collection.find({\"true_label\": label})\n",
" ] # IDs of images with the given label\n",
"\n",
" pr_scores = np.ones(NUM_IMAGES) / NUM_IMAGES # Initialize PageRank scores\n",
" if self.verbose:\n",
" print(\"Initialized pagerank scores\")\n",
"\n",
" for _iter in range(max_iter):\n",
" prev_scores = np.copy(pr_scores)\n",
" # for every node,\n",
" for i in range(NUM_IMAGES):\n",
" tic = time.time()\n",
" # add sum of connected nodes' PR scores\n",
" pr_scores[i] = damping_factor * sum(\n",
" pr_scores[j]\n",
" for j in range(NUM_IMAGES)\n",
" if (i * 2, j * 2) in self.similarity_graph\n",
" # and add the prob for random teleport *if node in given label*\n",
" ) + (1 - damping_factor) * (1 if i * 2 in label_indices else 0) / len(\n",
" label_indices\n",
" )\n",
" toc = time.time()\n",
" print(toc-tic)\n",
"\n",
" pr_scores /= sum(pr_scores) # Normalize\n",
"\n",
" # check for convergence\n",
" conv_tol = np.sum(np.abs(prev_scores - pr_scores))\n",
" if self.verbose:\n",
" print(f\"Iter {_iter}, conv_tol={conv_tol}\")\n",
" if conv_tol < tol:\n",
" if self.verbose:\n",
" print(f\"Converged\")\n",
" break\n",
"\n",
" # Select top m images based on PageRank scores\n",
" top_m_indices = np.argsort(pr_scores)[::-1][\n",
" :m\n",
" ] # sort indices, reverse and take top m\n",
" return top_m_indices * 2 # again, even IDs\n"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"image_sim-cm_fd-svd-10-semantics.json loaded\n"
]
}
],
"source": [
"n = int(input(\"Enter value of n (no. of edges for each image in similarity graph): \"))\n",
"if n < 1:\n",
" raise ValueError(\"n should be a positive integer\")\n",
"\n",
"l = int(input(\"Enter target label l:\"))\n",
"if l < 0 or l > 100:\n",
" raise ValueError(\"l should be in range[0,100]\")\n",
"\n",
"m = int(input(\"Enter value of m (no. of significant images relative to given label): \"))\n",
"if m < 1:\n",
" raise ValueError(\"m should be a positive integer\")\n",
"\n",
"given_ls = int(\n",
" (input(\"Enter 0 to select a feature model, 1 to select a latent space: \"))\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",
"if given_ls:\n",
" selected_latent_space = valid_latent_spaces[\n",
" str(\n",
" input(\n",
" \"Enter latent space - one of \" + str(list(valid_latent_spaces.keys()))\n",
" )\n",
" )\n",
" ]\n",
"\n",
" k = int(input(\"Enter value of k (no. of latent semantics): \"))\n",
" if k < 1:\n",
" raise ValueError(\"k should be a positive integer\")\n",
"\n",
" if selected_latent_space != \"cp\":\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",
" # Loading latent semantics\n",
" match selected_latent_space:\n",
" # LS1\n",
" case \"\":\n",
" file_prefix = (\n",
" f\"{selected_feature_model}-{selected_dim_reduction_method}-{k}\"\n",
" )\n",
" file_name = file_prefix + \"-semantics.json\"\n",
" model_name = file_prefix + \"-model.joblib\"\n",
" if os.path.exists(file_name):\n",
" data = json.load(open(file_name))\n",
" print(file_name + \" loaded\")\n",
" else:\n",
" raise Exception(file_name + \" does not exist\")\n",
" # LDA model\n",
" if selected_dim_reduction_method == \"lda\":\n",
" if os.path.exists(model_name):\n",
" data_model = load(model_name)\n",
" print(model_name + \" loaded\")\n",
" else:\n",
" raise Exception(model_name + \" does not exist\")\n",
" # LS2\n",
" case \"cp\":\n",
" file_name = f\"{selected_feature_model}-cp-{k}-semantics.json\"\n",
" if os.path.exists(file_name):\n",
" data = json.load(open(file_name))\n",
" print(file_name + \" loaded\")\n",
" else:\n",
" raise Exception(file_name + \" does not exist\")\n",
" # LS3, LS4\n",
" case _:\n",
" file_name = f\"{selected_latent_space}-{selected_feature_model}-{selected_dim_reduction_method}-{k}-semantics.json\"\n",
" if os.path.exists(file_name):\n",
" data = json.load(open(file_name))\n",
" print(file_name + \" loaded\")\n",
" else:\n",
" raise Exception(file_name + \" does not exist\")\n"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Using image-image similarity matrix from semantic data\n",
"Similarity graph created\n",
"Initialized pagerank scores\n"
]
},
{
"ename": "KeyboardInterrupt",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[1;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)",
"\u001b[1;32mc:\\Kaushik\\ASU\\CSE 515 - Multimedia and Web Databases\\Project\\Phase 2\\task_11.ipynb Cell 5\u001b[0m line \u001b[0;36m1\n\u001b[0;32m <a href='vscode-notebook-cell:/c%3A/Kaushik/ASU/CSE%20515%20-%20Multimedia%20and%20Web%20Databases/Project/Phase%202/task_11.ipynb#W5sZmlsZQ%3D%3D?line=5'>6</a>\u001b[0m img_graph \u001b[39m=\u001b[39m ImageGraph(fd_collection, \u001b[39mTrue\u001b[39;00m)\n\u001b[0;32m <a href='vscode-notebook-cell:/c%3A/Kaushik/ASU/CSE%20515%20-%20Multimedia%20and%20Web%20Databases/Project/Phase%202/task_11.ipynb#W5sZmlsZQ%3D%3D?line=6'>7</a>\u001b[0m img_graph\u001b[39m.\u001b[39mcreate_similarity_graph(\n\u001b[0;32m <a href='vscode-notebook-cell:/c%3A/Kaushik/ASU/CSE%20515%20-%20Multimedia%20and%20Web%20Databases/Project/Phase%202/task_11.ipynb#W5sZmlsZQ%3D%3D?line=7'>8</a>\u001b[0m n,\n\u001b[0;32m <a href='vscode-notebook-cell:/c%3A/Kaushik/ASU/CSE%20515%20-%20Multimedia%20and%20Web%20Databases/Project/Phase%202/task_11.ipynb#W5sZmlsZQ%3D%3D?line=8'>9</a>\u001b[0m selected_feature_model,\n\u001b[0;32m <a href='vscode-notebook-cell:/c%3A/Kaushik/ASU/CSE%20515%20-%20Multimedia%20and%20Web%20Databases/Project/Phase%202/task_11.ipynb#W5sZmlsZQ%3D%3D?line=9'>10</a>\u001b[0m data,\n\u001b[0;32m <a href='vscode-notebook-cell:/c%3A/Kaushik/ASU/CSE%20515%20-%20Multimedia%20and%20Web%20Databases/Project/Phase%202/task_11.ipynb#W5sZmlsZQ%3D%3D?line=10'>11</a>\u001b[0m selected_dim_reduction_method\n\u001b[0;32m <a href='vscode-notebook-cell:/c%3A/Kaushik/ASU/CSE%20515%20-%20Multimedia%20and%20Web%20Databases/Project/Phase%202/task_11.ipynb#W5sZmlsZQ%3D%3D?line=11'>12</a>\u001b[0m )\n\u001b[1;32m---> <a href='vscode-notebook-cell:/c%3A/Kaushik/ASU/CSE%20515%20-%20Multimedia%20and%20Web%20Databases/Project/Phase%202/task_11.ipynb#W5sZmlsZQ%3D%3D?line=12'>13</a>\u001b[0m imgs \u001b[39m=\u001b[39m img_graph\u001b[39m.\u001b[39;49mpersonalized_pagerank(l, m)\n",
"\u001b[1;32mc:\\Kaushik\\ASU\\CSE 515 - Multimedia and Web Databases\\Project\\Phase 2\\task_11.ipynb Cell 5\u001b[0m line \u001b[0;36m9\n\u001b[0;32m <a href='vscode-notebook-cell:/c%3A/Kaushik/ASU/CSE%20515%20-%20Multimedia%20and%20Web%20Databases/Project/Phase%202/task_11.ipynb#W5sZmlsZQ%3D%3D?line=92'>93</a>\u001b[0m \u001b[39m# for every node,\u001b[39;00m\n\u001b[0;32m <a href='vscode-notebook-cell:/c%3A/Kaushik/ASU/CSE%20515%20-%20Multimedia%20and%20Web%20Databases/Project/Phase%202/task_11.ipynb#W5sZmlsZQ%3D%3D?line=93'>94</a>\u001b[0m \u001b[39mfor\u001b[39;00m i \u001b[39min\u001b[39;00m \u001b[39mrange\u001b[39m(NUM_IMAGES):\n\u001b[0;32m <a href='vscode-notebook-cell:/c%3A/Kaushik/ASU/CSE%20515%20-%20Multimedia%20and%20Web%20Databases/Project/Phase%202/task_11.ipynb#W5sZmlsZQ%3D%3D?line=94'>95</a>\u001b[0m \u001b[39m# add sum of connected nodes' PR scores\u001b[39;00m\n\u001b[1;32m---> <a href='vscode-notebook-cell:/c%3A/Kaushik/ASU/CSE%20515%20-%20Multimedia%20and%20Web%20Databases/Project/Phase%202/task_11.ipynb#W5sZmlsZQ%3D%3D?line=95'>96</a>\u001b[0m pr_scores[i] \u001b[39m=\u001b[39m damping_factor \u001b[39m*\u001b[39m \u001b[39msum\u001b[39;49m(\n\u001b[0;32m <a href='vscode-notebook-cell:/c%3A/Kaushik/ASU/CSE%20515%20-%20Multimedia%20and%20Web%20Databases/Project/Phase%202/task_11.ipynb#W5sZmlsZQ%3D%3D?line=96'>97</a>\u001b[0m pr_scores[j]\n\u001b[0;32m <a href='vscode-notebook-cell:/c%3A/Kaushik/ASU/CSE%20515%20-%20Multimedia%20and%20Web%20Databases/Project/Phase%202/task_11.ipynb#W5sZmlsZQ%3D%3D?line=97'>98</a>\u001b[0m \u001b[39mfor\u001b[39;49;00m j \u001b[39min\u001b[39;49;00m \u001b[39mrange\u001b[39;49m(NUM_IMAGES)\n\u001b[0;32m <a href='vscode-notebook-cell:/c%3A/Kaushik/ASU/CSE%20515%20-%20Multimedia%20and%20Web%20Databases/Project/Phase%202/task_11.ipynb#W5sZmlsZQ%3D%3D?line=98'>99</a>\u001b[0m \u001b[39mif\u001b[39;49;00m (i \u001b[39m*\u001b[39;49m \u001b[39m2\u001b[39;49m, j \u001b[39m*\u001b[39;49m \u001b[39m2\u001b[39;49m) \u001b[39min\u001b[39;49;00m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49msimilarity_graph\n\u001b[0;32m <a href='vscode-notebook-cell:/c%3A/Kaushik/ASU/CSE%20515%20-%20Multimedia%20and%20Web%20Databases/Project/Phase%202/task_11.ipynb#W5sZmlsZQ%3D%3D?line=99'>100</a>\u001b[0m \u001b[39m# and add the prob for random teleport *if node in given label*\u001b[39;49;00m\n\u001b[0;32m <a href='vscode-notebook-cell:/c%3A/Kaushik/ASU/CSE%20515%20-%20Multimedia%20and%20Web%20Databases/Project/Phase%202/task_11.ipynb#W5sZmlsZQ%3D%3D?line=100'>101</a>\u001b[0m ) \u001b[39m+\u001b[39m (\u001b[39m1\u001b[39m \u001b[39m-\u001b[39m damping_factor) \u001b[39m*\u001b[39m (\u001b[39m1\u001b[39m \u001b[39mif\u001b[39;00m i \u001b[39m*\u001b[39m \u001b[39m2\u001b[39m \u001b[39min\u001b[39;00m label_indices \u001b[39melse\u001b[39;00m \u001b[39m0\u001b[39m) \u001b[39m/\u001b[39m \u001b[39mlen\u001b[39m(\n\u001b[0;32m <a href='vscode-notebook-cell:/c%3A/Kaushik/ASU/CSE%20515%20-%20Multimedia%20and%20Web%20Databases/Project/Phase%202/task_11.ipynb#W5sZmlsZQ%3D%3D?line=101'>102</a>\u001b[0m label_indices\n\u001b[0;32m <a href='vscode-notebook-cell:/c%3A/Kaushik/ASU/CSE%20515%20-%20Multimedia%20and%20Web%20Databases/Project/Phase%202/task_11.ipynb#W5sZmlsZQ%3D%3D?line=102'>103</a>\u001b[0m )\n\u001b[0;32m <a href='vscode-notebook-cell:/c%3A/Kaushik/ASU/CSE%20515%20-%20Multimedia%20and%20Web%20Databases/Project/Phase%202/task_11.ipynb#W5sZmlsZQ%3D%3D?line=103'>104</a>\u001b[0m pr_scores \u001b[39m/\u001b[39m\u001b[39m=\u001b[39m \u001b[39msum\u001b[39m(pr_scores) \u001b[39m# Normalize\u001b[39;00m\n\u001b[0;32m <a href='vscode-notebook-cell:/c%3A/Kaushik/ASU/CSE%20515%20-%20Multimedia%20and%20Web%20Databases/Project/Phase%202/task_11.ipynb#W5sZmlsZQ%3D%3D?line=105'>106</a>\u001b[0m \u001b[39m# check for convergence\u001b[39;00m\n",
"\u001b[1;32mc:\\Kaushik\\ASU\\CSE 515 - Multimedia and Web Databases\\Project\\Phase 2\\task_11.ipynb Cell 5\u001b[0m line \u001b[0;36m9\n\u001b[0;32m <a href='vscode-notebook-cell:/c%3A/Kaushik/ASU/CSE%20515%20-%20Multimedia%20and%20Web%20Databases/Project/Phase%202/task_11.ipynb#W5sZmlsZQ%3D%3D?line=92'>93</a>\u001b[0m \u001b[39m# for every node,\u001b[39;00m\n\u001b[0;32m <a href='vscode-notebook-cell:/c%3A/Kaushik/ASU/CSE%20515%20-%20Multimedia%20and%20Web%20Databases/Project/Phase%202/task_11.ipynb#W5sZmlsZQ%3D%3D?line=93'>94</a>\u001b[0m \u001b[39mfor\u001b[39;00m i \u001b[39min\u001b[39;00m \u001b[39mrange\u001b[39m(NUM_IMAGES):\n\u001b[0;32m <a href='vscode-notebook-cell:/c%3A/Kaushik/ASU/CSE%20515%20-%20Multimedia%20and%20Web%20Databases/Project/Phase%202/task_11.ipynb#W5sZmlsZQ%3D%3D?line=94'>95</a>\u001b[0m \u001b[39m# add sum of connected nodes' PR scores\u001b[39;00m\n\u001b[0;32m <a href='vscode-notebook-cell:/c%3A/Kaushik/ASU/CSE%20515%20-%20Multimedia%20and%20Web%20Databases/Project/Phase%202/task_11.ipynb#W5sZmlsZQ%3D%3D?line=95'>96</a>\u001b[0m pr_scores[i] \u001b[39m=\u001b[39m damping_factor \u001b[39m*\u001b[39m \u001b[39msum\u001b[39m(\n\u001b[0;32m <a href='vscode-notebook-cell:/c%3A/Kaushik/ASU/CSE%20515%20-%20Multimedia%20and%20Web%20Databases/Project/Phase%202/task_11.ipynb#W5sZmlsZQ%3D%3D?line=96'>97</a>\u001b[0m pr_scores[j]\n\u001b[0;32m <a href='vscode-notebook-cell:/c%3A/Kaushik/ASU/CSE%20515%20-%20Multimedia%20and%20Web%20Databases/Project/Phase%202/task_11.ipynb#W5sZmlsZQ%3D%3D?line=97'>98</a>\u001b[0m \u001b[39mfor\u001b[39;00m j \u001b[39min\u001b[39;00m \u001b[39mrange\u001b[39m(NUM_IMAGES)\n\u001b[1;32m---> <a href='vscode-notebook-cell:/c%3A/Kaushik/ASU/CSE%20515%20-%20Multimedia%20and%20Web%20Databases/Project/Phase%202/task_11.ipynb#W5sZmlsZQ%3D%3D?line=98'>99</a>\u001b[0m \u001b[39mif\u001b[39;00m (i \u001b[39m*\u001b[39;49m \u001b[39m2\u001b[39;49m, j \u001b[39m*\u001b[39;49m \u001b[39m2\u001b[39;49m) \u001b[39min\u001b[39;49;00m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49msimilarity_graph\n\u001b[0;32m <a href='vscode-notebook-cell:/c%3A/Kaushik/ASU/CSE%20515%20-%20Multimedia%20and%20Web%20Databases/Project/Phase%202/task_11.ipynb#W5sZmlsZQ%3D%3D?line=99'>100</a>\u001b[0m \u001b[39m# and add the prob for random teleport *if node in given label*\u001b[39;00m\n\u001b[0;32m <a href='vscode-notebook-cell:/c%3A/Kaushik/ASU/CSE%20515%20-%20Multimedia%20and%20Web%20Databases/Project/Phase%202/task_11.ipynb#W5sZmlsZQ%3D%3D?line=100'>101</a>\u001b[0m ) \u001b[39m+\u001b[39m (\u001b[39m1\u001b[39m \u001b[39m-\u001b[39m damping_factor) \u001b[39m*\u001b[39m (\u001b[39m1\u001b[39m \u001b[39mif\u001b[39;00m i \u001b[39m*\u001b[39m \u001b[39m2\u001b[39m \u001b[39min\u001b[39;00m label_indices \u001b[39melse\u001b[39;00m \u001b[39m0\u001b[39m) \u001b[39m/\u001b[39m \u001b[39mlen\u001b[39m(\n\u001b[0;32m <a href='vscode-notebook-cell:/c%3A/Kaushik/ASU/CSE%20515%20-%20Multimedia%20and%20Web%20Databases/Project/Phase%202/task_11.ipynb#W5sZmlsZQ%3D%3D?line=101'>102</a>\u001b[0m label_indices\n\u001b[0;32m <a href='vscode-notebook-cell:/c%3A/Kaushik/ASU/CSE%20515%20-%20Multimedia%20and%20Web%20Databases/Project/Phase%202/task_11.ipynb#W5sZmlsZQ%3D%3D?line=102'>103</a>\u001b[0m )\n\u001b[0;32m <a href='vscode-notebook-cell:/c%3A/Kaushik/ASU/CSE%20515%20-%20Multimedia%20and%20Web%20Databases/Project/Phase%202/task_11.ipynb#W5sZmlsZQ%3D%3D?line=103'>104</a>\u001b[0m pr_scores \u001b[39m/\u001b[39m\u001b[39m=\u001b[39m \u001b[39msum\u001b[39m(pr_scores) \u001b[39m# Normalize\u001b[39;00m\n\u001b[0;32m <a href='vscode-notebook-cell:/c%3A/Kaushik/ASU/CSE%20515%20-%20Multimedia%20and%20Web%20Databases/Project/Phase%202/task_11.ipynb#W5sZmlsZQ%3D%3D?line=105'>106</a>\u001b[0m \u001b[39m# check for convergence\u001b[39;00m\n",
"\u001b[1;31mKeyboardInterrupt\u001b[0m: "
]
}
],
"source": [
"if not given_ls:\n",
" img_graph = ImageGraph(fd_collection, True)\n",
" img_graph.create_similarity_graph(n, selected_feature_model)\n",
" imgs = img_graph.personalized_pagerank(l, m)\n",
"else:\n",
" img_graph = ImageGraph(fd_collection, True)\n",
" img_graph.create_similarity_graph(\n",
" n,\n",
" selected_feature_model,\n",
" data,\n",
" selected_dim_reduction_method\n",
" )\n",
" imgs = img_graph.personalized_pagerank(l, m)\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": "3.10.5"
}
},
"nbformat": 4,
"nbformat_minor": 2
}

4
Phase 2/task_7.ipynb
View File

@ -310,7 +310,7 @@
"\n", "\n",
" distances = []\n", " distances = []\n",
" for i in range(NUM_LABELS):\n", " for i in range(NUM_LABELS):\n",
" if i != label:\n", " if i != img_label:\n",
" distances.append(\n", " distances.append(\n",
" {\n", " {\n",
" \"label\": i,\n", " \"label\": i,\n",
@ -326,7 +326,7 @@
" similar_images = []\n", " similar_images = []\n",
" for i in range(len(dataset)):\n", " for i in range(len(dataset)):\n",
" _, l = dataset[i]\n", " _, l = dataset[i]\n",
" if l == label:\n", " if l == img_label:\n",
" similar_images.append(i)\n", " similar_images.append(i)\n",
"\n", "\n",
" similar_images = random.sample(similar_images, k_2)\n", " similar_images = random.sample(similar_images, k_2)\n",

6
Phase 2/utils.py
View File

@ -5,6 +5,7 @@ import random
import cv2 import cv2
import numpy as np import numpy as np
from scipy.stats import pearsonr from scipy.stats import pearsonr
# from scipy.sparse.linalg import svds # from scipy.sparse.linalg import svds
# from sklearn.decomposition import NMF # from sklearn.decomposition import NMF
from sklearn.decomposition import LatentDirichletAllocation from sklearn.decomposition import LatentDirichletAllocation
@ -355,11 +356,14 @@ def pearson_distance_measure(img_1_fd, img_2_fd):
# such that lower distance implies more similarity # such that lower distance implies more similarity
return 0.5 * (1 - pearsonr(img_1_fd_reshaped, img_2_fd_reshaped).statistic) return 0.5 * (1 - pearsonr(img_1_fd_reshaped, img_2_fd_reshaped).statistic)
def kl_divergence_measure(p, q): def kl_divergence_measure(p, q):
p_f = p.flatten()
q_f = q.flatten()
# Avoid division by zero # Avoid division by zero
epsilon = 1e-10 epsilon = 1e-10
return np.sum(p * np.log((p + epsilon) / (q + epsilon))) return np.sum(p_f * np.log((p_f + epsilon) / (q_f + epsilon)))
valid_feature_models = { valid_feature_models = {