{
"cells": [
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"The autoreload extension is already loaded. To reload it, use:\n",
" %reload_ext autoreload\n"
]
}
],
"source": [
"%load_ext autoreload\n",
"%autoreload 2"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [],
"source": [
"from utils import *\n",
"warnings.filterwarnings('ignore')\n",
"%matplotlib inline"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [],
"source": [
"fd_collection = getCollection(\"team_5_mwdb_phase_2\", \"fd_collection\")\n"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Applying svd on the given similarity matrix to get 10 latent semantics (showing only top 10 image-weight pairs for each latent semantic)...\n",
"(209, 10, 10, 3, 3)\n"
]
},
{
"ename": "ValueError",
"evalue": "array must have ndim <= 2",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mValueError\u001b[0m Traceback (most recent call last)",
"\u001b[1;32m/Users/pavanrathnakarshetty/Documents/Multimedia and Web Databases/Phase 2/CSE515_MWDB_Project/Phase 2/task_3.ipynb Cell 4\u001b[0m line \u001b[0;36m1\n\u001b[1;32m 7\u001b[0m \u001b[39mraise\u001b[39;00m \u001b[39mValueError\u001b[39;00m(\u001b[39m\"\u001b[39m\u001b[39mk should be a positive integer\u001b[39m\u001b[39m\"\u001b[39m)\n\u001b[1;32m 9\u001b[0m selected_dim_reduction_method \u001b[39m=\u001b[39m \u001b[39mstr\u001b[39m(\n\u001b[1;32m 10\u001b[0m \u001b[39minput\u001b[39m(\n\u001b[1;32m 11\u001b[0m \u001b[39m\"\u001b[39m\u001b[39mEnter dimensionality reduction method - one of \u001b[39m\u001b[39m\"\u001b[39m\n\u001b[1;32m 12\u001b[0m \u001b[39m+\u001b[39m \u001b[39mstr\u001b[39m(\u001b[39mlist\u001b[39m(valid_dim_reduction_methods\u001b[39m.\u001b[39mkeys()))\n\u001b[1;32m 13\u001b[0m )\n\u001b[1;32m 14\u001b[0m )\n\u001b[0;32m---> 16\u001b[0m extract_latent_semantics(\n\u001b[1;32m 17\u001b[0m fd_collection,\n\u001b[1;32m 18\u001b[0m k,\n\u001b[1;32m 19\u001b[0m selected_feature_model,\n\u001b[1;32m 20\u001b[0m selected_dim_reduction_method,\n\u001b[1;32m 21\u001b[0m top_images\u001b[39m=\u001b[39;49m\u001b[39m10\u001b[39;49m,\n\u001b[1;32m 22\u001b[0m )\n",
"File \u001b[0;32m~/Documents/Multimedia and Web Databases/Phase 2/CSE515_MWDB_Project/Phase 2/utils.py:865\u001b[0m, in \u001b[0;36mextract_latent_semantics\u001b[0;34m(fd_collection, k, feature_model, dim_reduction_method, sim_matrix, top_images, fn_prefix)\u001b[0m\n\u001b[1;32m 861\u001b[0m \u001b[39mmatch\u001b[39;00m valid_dim_reduction_methods[dim_reduction_method]:\n\u001b[1;32m 862\u001b[0m \u001b[39m# singular value decomposition\u001b[39;00m\n\u001b[1;32m 863\u001b[0m \u001b[39m# sparse version of SVD to get only k singular values\u001b[39;00m\n\u001b[1;32m 864\u001b[0m \u001b[39mcase\u001b[39;00m \u001b[39m1\u001b[39m:\n\u001b[0;32m--> 865\u001b[0m U, S, V_T \u001b[39m=\u001b[39m svds(feature_vectors, k\u001b[39m=\u001b[39;49mk)\n\u001b[1;32m 867\u001b[0m all_latent_semantics \u001b[39m=\u001b[39m {\n\u001b[1;32m 868\u001b[0m \u001b[39m\"\u001b[39m\u001b[39mimage-semantic\u001b[39m\u001b[39m\"\u001b[39m: U\u001b[39m.\u001b[39mtolist(),\n\u001b[1;32m 869\u001b[0m \u001b[39m\"\u001b[39m\u001b[39msemantics-core\u001b[39m\u001b[39m\"\u001b[39m: S\u001b[39m.\u001b[39mtolist(),\n\u001b[1;32m 870\u001b[0m \u001b[39m\"\u001b[39m\u001b[39msemantic-feature\u001b[39m\u001b[39m\"\u001b[39m: V_T\u001b[39m.\u001b[39mtolist(),\n\u001b[1;32m 871\u001b[0m }\n\u001b[1;32m 873\u001b[0m \u001b[39m# for each latent semantic, sort imageID-weight pairs by weights in descending order\u001b[39;00m\n",
"File \u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/scipy/sparse/linalg/_eigen/_svds.py:443\u001b[0m, in \u001b[0;36msvds\u001b[0;34m(A, k, ncv, tol, which, v0, maxiter, return_singular_vectors, solver, random_state, options)\u001b[0m\n\u001b[1;32m 104\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39msvds\u001b[39m(A, k\u001b[39m=\u001b[39m\u001b[39m6\u001b[39m, ncv\u001b[39m=\u001b[39m\u001b[39mNone\u001b[39;00m, tol\u001b[39m=\u001b[39m\u001b[39m0\u001b[39m, which\u001b[39m=\u001b[39m\u001b[39m'\u001b[39m\u001b[39mLM\u001b[39m\u001b[39m'\u001b[39m, v0\u001b[39m=\u001b[39m\u001b[39mNone\u001b[39;00m,\n\u001b[1;32m 105\u001b[0m maxiter\u001b[39m=\u001b[39m\u001b[39mNone\u001b[39;00m, return_singular_vectors\u001b[39m=\u001b[39m\u001b[39mTrue\u001b[39;00m,\n\u001b[1;32m 106\u001b[0m solver\u001b[39m=\u001b[39m\u001b[39m'\u001b[39m\u001b[39marpack\u001b[39m\u001b[39m'\u001b[39m, random_state\u001b[39m=\u001b[39m\u001b[39mNone\u001b[39;00m, options\u001b[39m=\u001b[39m\u001b[39mNone\u001b[39;00m):\n\u001b[1;32m 107\u001b[0m \u001b[39m \u001b[39m\u001b[39m\"\"\"\u001b[39;00m\n\u001b[1;32m 108\u001b[0m \u001b[39m Partial singular value decomposition of a sparse matrix.\u001b[39;00m\n\u001b[1;32m 109\u001b[0m \n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 441\u001b[0m \n\u001b[1;32m 442\u001b[0m \u001b[39m \"\"\"\u001b[39;00m\n\u001b[0;32m--> 443\u001b[0m args \u001b[39m=\u001b[39m _iv(A, k, ncv, tol, which, v0, maxiter, return_singular_vectors,\n\u001b[1;32m 444\u001b[0m solver, random_state)\n\u001b[1;32m 445\u001b[0m (A, k, ncv, tol, which, v0, maxiter,\n\u001b[1;32m 446\u001b[0m return_singular_vectors, solver, random_state) \u001b[39m=\u001b[39m args\n\u001b[1;32m 448\u001b[0m largest \u001b[39m=\u001b[39m (which \u001b[39m==\u001b[39m \u001b[39m'\u001b[39m\u001b[39mLM\u001b[39m\u001b[39m'\u001b[39m)\n",
"File \u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/scipy/sparse/linalg/_eigen/_svds.py:36\u001b[0m, in \u001b[0;36m_iv\u001b[0;34m(A, k, ncv, tol, which, v0, maxiter, return_singular, solver, random_state)\u001b[0m\n\u001b[1;32m 33\u001b[0m \u001b[39mraise\u001b[39;00m \u001b[39mValueError\u001b[39;00m(\u001b[39mf\u001b[39m\u001b[39m\"\u001b[39m\u001b[39msolver must be one of \u001b[39m\u001b[39m{\u001b[39;00msolvers\u001b[39m}\u001b[39;00m\u001b[39m.\u001b[39m\u001b[39m\"\u001b[39m)\n\u001b[1;32m 35\u001b[0m \u001b[39m# input validation/standardization for `A`\u001b[39;00m\n\u001b[0;32m---> 36\u001b[0m A \u001b[39m=\u001b[39m aslinearoperator(A) \u001b[39m# this takes care of some input validation\u001b[39;00m\n\u001b[1;32m 37\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mnot\u001b[39;00m (np\u001b[39m.\u001b[39missubdtype(A\u001b[39m.\u001b[39mdtype, np\u001b[39m.\u001b[39mcomplexfloating)\n\u001b[1;32m 38\u001b[0m \u001b[39mor\u001b[39;00m np\u001b[39m.\u001b[39missubdtype(A\u001b[39m.\u001b[39mdtype, np\u001b[39m.\u001b[39mfloating)):\n\u001b[1;32m 39\u001b[0m message \u001b[39m=\u001b[39m \u001b[39m\"\u001b[39m\u001b[39m`A` must be of floating or complex floating data type.\u001b[39m\u001b[39m\"\u001b[39m\n",
"File \u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/scipy/sparse/linalg/_interface.py:871\u001b[0m, in \u001b[0;36maslinearoperator\u001b[0;34m(A)\u001b[0m\n\u001b[1;32m 869\u001b[0m \u001b[39melif\u001b[39;00m \u001b[39misinstance\u001b[39m(A, np\u001b[39m.\u001b[39mndarray) \u001b[39mor\u001b[39;00m \u001b[39misinstance\u001b[39m(A, np\u001b[39m.\u001b[39mmatrix):\n\u001b[1;32m 870\u001b[0m \u001b[39mif\u001b[39;00m A\u001b[39m.\u001b[39mndim \u001b[39m>\u001b[39m \u001b[39m2\u001b[39m:\n\u001b[0;32m--> 871\u001b[0m \u001b[39mraise\u001b[39;00m \u001b[39mValueError\u001b[39;00m(\u001b[39m'\u001b[39m\u001b[39marray must have ndim <= 2\u001b[39m\u001b[39m'\u001b[39m)\n\u001b[1;32m 872\u001b[0m A \u001b[39m=\u001b[39m np\u001b[39m.\u001b[39matleast_2d(np\u001b[39m.\u001b[39masarray(A))\n\u001b[1;32m 873\u001b[0m \u001b[39mreturn\u001b[39;00m MatrixLinearOperator(A)\n",
"\u001b[0;31mValueError\u001b[0m: array must have ndim <= 2"
]
}
],
"source": [
"selected_feature_model = valid_feature_models[\n",
" str(input(\"Enter feature model - one of \" + str(list(valid_feature_models.keys()))))\n",
"]\n",
"\n",
"k = int(input(\"Enter value of k: \"))\n",
"if k < 1:\n",
" raise ValueError(\"k should be a positive integer\")\n",
"\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",
"extract_latent_semantics(\n",
" fd_collection,\n",
" k,\n",
" selected_feature_model,\n",
" selected_dim_reduction_method,\n",
" top_images=10,\n",
")\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": "3.11.5"
}
},
"nbformat": 4,
"nbformat_minor": 2
}