diff --git a/Phase 2/task_3.ipynb b/Phase 2/task_3.ipynb index f56d892..a559156 100644 --- a/Phase 2/task_3.ipynb +++ b/Phase 2/task_3.ipynb @@ -2,7 +2,7 @@ "cells": [ { "cell_type": "code", - "execution_count": 1, + "execution_count": 4, "metadata": {}, "outputs": [], "source": [ @@ -13,7 +13,7 @@ }, { "cell_type": "code", - "execution_count": 2, + "execution_count": 5, "metadata": {}, "outputs": [], "source": [ @@ -22,126 +22,134 @@ }, { "cell_type": "code", - "execution_count": 3, + "execution_count": 6, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "Applying kmeans on the cm_fd space to get 10 latent semantics (showing only top 10 image-weight pairs for each latent semantic)...\n", - "Initialized centroids\n", - "Note: for K-Means we display distances, in ascending order\n", + "Applying lda on the cm_fd space to get 10 latent semantics (showing only top 10 image-weight pairs for each latent semantic)...\n", + "iteration: 1 of max_iter: 10\n", + "iteration: 2 of max_iter: 10\n", + "iteration: 3 of max_iter: 10\n", + "iteration: 4 of max_iter: 10\n", + "iteration: 5 of max_iter: 10\n", + "iteration: 6 of max_iter: 10\n", + "iteration: 7 of max_iter: 10\n", + "iteration: 8 of max_iter: 10\n", + "iteration: 9 of max_iter: 10\n", + "iteration: 10 of max_iter: 10\n", "Latent semantic no. 0\n", - "Image_ID\t2406\t-\tDistance\t2.4329297906521914\n", - "Image_ID\t2624\t-\tDistance\t2.4610601036735282\n", - "Image_ID\t7112\t-\tDistance\t2.5837781069798633\n", - "Image_ID\t5390\t-\tDistance\t2.60890832624663\n", - "Image_ID\t4782\t-\tDistance\t2.6300363909906017\n", - "Image_ID\t4218\t-\tDistance\t2.6526211985836103\n", - "Image_ID\t4210\t-\tDistance\t2.6581936664893533\n", - "Image_ID\t944\t-\tDistance\t2.7472085431102213\n", - "Image_ID\t6600\t-\tDistance\t2.788716977448917\n", - "Image_ID\t2398\t-\tDistance\t2.797045487845613\n", + "Image_ID\t1710\t-\tWeight\t0.617458014268485\n", + "Image_ID\t1844\t-\tWeight\t0.6075822274686563\n", + "Image_ID\t1750\t-\tWeight\t0.6070573195345486\n", + "Image_ID\t1400\t-\tWeight\t0.6056680791985845\n", + "Image_ID\t1284\t-\tWeight\t0.6034453335599401\n", + "Image_ID\t1722\t-\tWeight\t0.6007621954380373\n", + "Image_ID\t1824\t-\tWeight\t0.5984109879793347\n", + "Image_ID\t1446\t-\tWeight\t0.5961120049400928\n", + "Image_ID\t1746\t-\tWeight\t0.5956438913483608\n", + "Image_ID\t1202\t-\tWeight\t0.5946144775162294\n", "Latent semantic no. 1\n", - "Image_ID\t5826\t-\tDistance\t1.7730956906058473\n", - "Image_ID\t3944\t-\tDistance\t1.8750448829509372\n", - "Image_ID\t968\t-\tDistance\t1.9655862567434115\n", - "Image_ID\t1068\t-\tDistance\t1.9677696006956515\n", - "Image_ID\t5664\t-\tDistance\t2.0908245587325114\n", - "Image_ID\t7392\t-\tDistance\t2.1187697478953686\n", - "Image_ID\t3304\t-\tDistance\t2.154265483459674\n", - "Image_ID\t1008\t-\tDistance\t2.2197924178276014\n", - "Image_ID\t908\t-\tDistance\t2.237300492325052\n", - "Image_ID\t2940\t-\tDistance\t2.2377555386247865\n", + "Image_ID\t902\t-\tWeight\t0.4728143111474456\n", + "Image_ID\t1002\t-\tWeight\t0.46041900831405763\n", + "Image_ID\t542\t-\tWeight\t0.4321682728103117\n", + "Image_ID\t6660\t-\tWeight\t0.43006737908416837\n", + "Image_ID\t7140\t-\tWeight\t0.41016099848189896\n", + "Image_ID\t7422\t-\tWeight\t0.4097197999004479\n", + "Image_ID\t1048\t-\tWeight\t0.40947159895773955\n", + "Image_ID\t5862\t-\tWeight\t0.40422818133221733\n", + "Image_ID\t920\t-\tWeight\t0.39918666593292523\n", + "Image_ID\t532\t-\tWeight\t0.39629998547607764\n", "Latent semantic no. 2\n", - "Image_ID\t2406\t-\tDistance\t2.1258319537256445\n", - "Image_ID\t6922\t-\tDistance\t2.2011613151345975\n", - "Image_ID\t2624\t-\tDistance\t2.2289354011778006\n", - "Image_ID\t6484\t-\tDistance\t2.2515469285749545\n", - "Image_ID\t5390\t-\tDistance\t2.451999872498352\n", - "Image_ID\t4222\t-\tDistance\t2.4690306175362067\n", - "Image_ID\t5038\t-\tDistance\t2.4722970669139785\n", - "Image_ID\t3196\t-\tDistance\t2.475614158419068\n", - "Image_ID\t462\t-\tDistance\t2.49778761746267\n", - "Image_ID\t7380\t-\tDistance\t2.5265238831399635\n", + "Image_ID\t6528\t-\tWeight\t0.3855361898894576\n", + "Image_ID\t7514\t-\tWeight\t0.3582051575013368\n", + "Image_ID\t8258\t-\tWeight\t0.34639902472175704\n", + "Image_ID\t3164\t-\tWeight\t0.34339034052442163\n", + "Image_ID\t7546\t-\tWeight\t0.338559827261986\n", + "Image_ID\t6328\t-\tWeight\t0.3368802586491903\n", + "Image_ID\t5932\t-\tWeight\t0.33651755972532976\n", + "Image_ID\t3834\t-\tWeight\t0.3356941112662742\n", + "Image_ID\t3894\t-\tWeight\t0.326576952326855\n", + "Image_ID\t5976\t-\tWeight\t0.3265670285062378\n", "Latent semantic no. 3\n", - "Image_ID\t2412\t-\tDistance\t1.9079653649524306\n", - "Image_ID\t2138\t-\tDistance\t1.9508782175940445\n", - "Image_ID\t2290\t-\tDistance\t1.9526171427482104\n", - "Image_ID\t2302\t-\tDistance\t1.9769105940849563\n", - "Image_ID\t2640\t-\tDistance\t2.0476236872823406\n", - "Image_ID\t2634\t-\tDistance\t2.058811198055415\n", - "Image_ID\t2648\t-\tDistance\t2.0779524915237726\n", - "Image_ID\t2628\t-\tDistance\t2.1411367238671497\n", - "Image_ID\t2630\t-\tDistance\t2.156701968346356\n", - "Image_ID\t2502\t-\tDistance\t2.1813059883906454\n", + "Image_ID\t1744\t-\tWeight\t0.7351741873912249\n", + "Image_ID\t1134\t-\tWeight\t0.7128486032496076\n", + "Image_ID\t7466\t-\tWeight\t0.698769590115999\n", + "Image_ID\t2068\t-\tWeight\t0.6926683477111293\n", + "Image_ID\t1136\t-\tWeight\t0.687502465317813\n", + "Image_ID\t1752\t-\tWeight\t0.6873052436914959\n", + "Image_ID\t1130\t-\tWeight\t0.6726394748460636\n", + "Image_ID\t6710\t-\tWeight\t0.6535155833423436\n", + "Image_ID\t1450\t-\tWeight\t0.6414894098300652\n", + "Image_ID\t2090\t-\tWeight\t0.6268387632803436\n", "Latent semantic no. 4\n", - "Image_ID\t2528\t-\tDistance\t1.985388167407023\n", - "Image_ID\t2570\t-\tDistance\t2.020441033596718\n", - "Image_ID\t7000\t-\tDistance\t2.0389617509774554\n", - "Image_ID\t2544\t-\tDistance\t2.0461546917978493\n", - "Image_ID\t6946\t-\tDistance\t2.087028769480915\n", - "Image_ID\t5070\t-\tDistance\t2.093563899781913\n", - "Image_ID\t3884\t-\tDistance\t2.12383247213783\n", - "Image_ID\t6662\t-\tDistance\t2.133611417276695\n", - "Image_ID\t5584\t-\tDistance\t2.134813594870179\n", - "Image_ID\t7592\t-\tDistance\t2.1350058409043253\n", + "Image_ID\t2128\t-\tWeight\t0.5077209986058677\n", + "Image_ID\t2106\t-\tWeight\t0.500806169746303\n", + "Image_ID\t2008\t-\tWeight\t0.43841799612309496\n", + "Image_ID\t1222\t-\tWeight\t0.41374797151946374\n", + "Image_ID\t1968\t-\tWeight\t0.41245647494147325\n", + "Image_ID\t5534\t-\tWeight\t0.40585942227940236\n", + "Image_ID\t1938\t-\tWeight\t0.40488816917923176\n", + "Image_ID\t5902\t-\tWeight\t0.39867524511561125\n", + "Image_ID\t2452\t-\tWeight\t0.39854396145813886\n", + "Image_ID\t1950\t-\tWeight\t0.39682871606211834\n", "Latent semantic no. 5\n", - "Image_ID\t2406\t-\tDistance\t1.7192989054765462\n", - "Image_ID\t7736\t-\tDistance\t1.8415960899814483\n", - "Image_ID\t2624\t-\tDistance\t1.890325981685572\n", - "Image_ID\t4782\t-\tDistance\t1.947887574583758\n", - "Image_ID\t2434\t-\tDistance\t2.012480907684106\n", - "Image_ID\t5658\t-\tDistance\t2.0159295631755936\n", - "Image_ID\t5632\t-\tDistance\t2.0209799503972894\n", - "Image_ID\t5390\t-\tDistance\t2.054049699587572\n", - "Image_ID\t3762\t-\tDistance\t2.0632381421057997\n", - "Image_ID\t6922\t-\tDistance\t2.1324100407425832\n", + "Image_ID\t3128\t-\tWeight\t0.9323262707996046\n", + "Image_ID\t3134\t-\tWeight\t0.9288511931662002\n", + "Image_ID\t3132\t-\tWeight\t0.9257512744018676\n", + "Image_ID\t3130\t-\tWeight\t0.9206321130935269\n", + "Image_ID\t6646\t-\tWeight\t0.9034536187267997\n", + "Image_ID\t7508\t-\tWeight\t0.8994767166493532\n", + "Image_ID\t6640\t-\tWeight\t0.8958687751792616\n", + "Image_ID\t8624\t-\tWeight\t0.8949244821453077\n", + "Image_ID\t6604\t-\tWeight\t0.8870653537915141\n", + "Image_ID\t6534\t-\tWeight\t0.8745989651487901\n", "Latent semantic no. 6\n", - "Image_ID\t7244\t-\tDistance\t2.0882730827827514\n", - "Image_ID\t7256\t-\tDistance\t2.2363345183902643\n", - "Image_ID\t6946\t-\tDistance\t2.2626049811136104\n", - "Image_ID\t7232\t-\tDistance\t2.3287228186618827\n", - "Image_ID\t7260\t-\tDistance\t2.432017355562297\n", - "Image_ID\t4942\t-\tDistance\t2.5360228464626915\n", - "Image_ID\t3194\t-\tDistance\t2.652196198820196\n", - "Image_ID\t4946\t-\tDistance\t2.707800015244559\n", - "Image_ID\t6972\t-\tDistance\t2.772167403532193\n", - "Image_ID\t3822\t-\tDistance\t2.7757540939652245\n", + "Image_ID\t7024\t-\tWeight\t0.49312095749280327\n", + "Image_ID\t7036\t-\tWeight\t0.4782214728796395\n", + "Image_ID\t8362\t-\tWeight\t0.4662358245148104\n", + "Image_ID\t7008\t-\tWeight\t0.46357467039194805\n", + "Image_ID\t7042\t-\tWeight\t0.46321550546683676\n", + "Image_ID\t7054\t-\tWeight\t0.4582577226968157\n", + "Image_ID\t4594\t-\tWeight\t0.45499885749453567\n", + "Image_ID\t8108\t-\tWeight\t0.4548808255388789\n", + "Image_ID\t4804\t-\tWeight\t0.4537641746485284\n", + "Image_ID\t7018\t-\tWeight\t0.4500954855531814\n", "Latent semantic no. 7\n", - "Image_ID\t1234\t-\tDistance\t2.5103511852585627\n", - "Image_ID\t1406\t-\tDistance\t2.5905943688502\n", - "Image_ID\t1582\t-\tDistance\t2.64691846983913\n", - "Image_ID\t1844\t-\tDistance\t2.741629768608531\n", - "Image_ID\t1638\t-\tDistance\t2.7657226276060536\n", - "Image_ID\t1154\t-\tDistance\t2.8386700997389043\n", - "Image_ID\t1286\t-\tDistance\t2.8446264818255877\n", - "Image_ID\t1848\t-\tDistance\t2.8793700988824398\n", - "Image_ID\t1284\t-\tDistance\t2.879846330398362\n", - "Image_ID\t1592\t-\tDistance\t2.8822966091246407\n", + "Image_ID\t3072\t-\tWeight\t0.5545755342145449\n", + "Image_ID\t7754\t-\tWeight\t0.4966261995365101\n", + "Image_ID\t3314\t-\tWeight\t0.48233428979251847\n", + "Image_ID\t7940\t-\tWeight\t0.4800400108197779\n", + "Image_ID\t8512\t-\tWeight\t0.47551348229445217\n", + "Image_ID\t6198\t-\tWeight\t0.47117452506086344\n", + "Image_ID\t322\t-\tWeight\t0.4663234778213565\n", + "Image_ID\t2010\t-\tWeight\t0.46573364328793904\n", + "Image_ID\t3076\t-\tWeight\t0.4431223382983598\n", + "Image_ID\t972\t-\tWeight\t0.4405628751432792\n", "Latent semantic no. 8\n", - "Image_ID\t7686\t-\tDistance\t2.3114266143360425\n", - "Image_ID\t4286\t-\tDistance\t2.3193670377796534\n", - "Image_ID\t7974\t-\tDistance\t2.410584599384146\n", - "Image_ID\t7668\t-\tDistance\t2.4392449505107026\n", - "Image_ID\t3262\t-\tDistance\t2.4432361382128236\n", - "Image_ID\t7856\t-\tDistance\t2.484388558904672\n", - "Image_ID\t6250\t-\tDistance\t2.5139181727884887\n", - "Image_ID\t6982\t-\tDistance\t2.522220046130116\n", - "Image_ID\t4032\t-\tDistance\t2.5671693188571254\n", - "Image_ID\t8610\t-\tDistance\t2.592334945993663\n", + "Image_ID\t5600\t-\tWeight\t0.39739725479916665\n", + "Image_ID\t670\t-\tWeight\t0.3875951018959884\n", + "Image_ID\t350\t-\tWeight\t0.3720086985545715\n", + "Image_ID\t6460\t-\tWeight\t0.36938723858403194\n", + "Image_ID\t5624\t-\tWeight\t0.364040853186806\n", + "Image_ID\t356\t-\tWeight\t0.3583579835975199\n", + "Image_ID\t7432\t-\tWeight\t0.3553306592859769\n", + "Image_ID\t7422\t-\tWeight\t0.354707905541325\n", + "Image_ID\t5084\t-\tWeight\t0.35365911426394\n", + "Image_ID\t1140\t-\tWeight\t0.3479134590934088\n", "Latent semantic no. 9\n", - "Image_ID\t8656\t-\tDistance\t0.0\n", - "Image_ID\t5314\t-\tDistance\t7.545361629760217\n", - "Image_ID\t7854\t-\tDistance\t7.706317148014618\n", - "Image_ID\t712\t-\tDistance\t7.812246024712053\n", - "Image_ID\t8170\t-\tDistance\t7.940921127343809\n", - "Image_ID\t496\t-\tDistance\t7.95303740274659\n", - "Image_ID\t662\t-\tDistance\t7.976573111687378\n", - "Image_ID\t3188\t-\tDistance\t7.9858733547811935\n", - "Image_ID\t3116\t-\tDistance\t8.012971090439164\n", - "Image_ID\t3078\t-\tDistance\t8.023521594743528\n" + "Image_ID\t7654\t-\tWeight\t0.5679206359746548\n", + "Image_ID\t5354\t-\tWeight\t0.5064858428524615\n", + "Image_ID\t2804\t-\tWeight\t0.49614015154469926\n", + "Image_ID\t2764\t-\tWeight\t0.4860908228174713\n", + "Image_ID\t5134\t-\tWeight\t0.47600763822211256\n", + "Image_ID\t5136\t-\tWeight\t0.4611545624641291\n", + "Image_ID\t3704\t-\tWeight\t0.43021905028205043\n", + "Image_ID\t7484\t-\tWeight\t0.42015058396503724\n", + "Image_ID\t6830\t-\tWeight\t0.3890006613191919\n", + "Image_ID\t5410\t-\tWeight\t0.3846047200608215\n" ] } ], diff --git a/Phase 2/task_4.ipynb b/Phase 2/task_4.ipynb index 25d660c..d1d1f73 100644 --- a/Phase 2/task_4.ipynb +++ b/Phase 2/task_4.ipynb @@ -29,109 +29,54 @@ "name": "stdout", "output_type": "stream", "text": [ - "Applying CP decomposition on the cm_fd space to get 10 latent semantics (showing only top 10 image-weight pairs for each latent semantic)...\n", - "(4339, 900, 101)\n", + "Applying CP decomposition on the resnet_fd space to get 5 latent semantics (showing only top 10 image-weight pairs for each latent semantic)...\n", + "(4339, 1000, 101)\n", "Showing image-weight latent semantic\n", "Latent semantic no. 0\n", - "image\t823\t-\tweight\t0.06101574157129977\n", - "image\t809\t-\tweight\t0.06062830674568429\n", - "image\t806\t-\tweight\t0.060448512391290884\n", - "image\t832\t-\tweight\t0.06044200170224582\n", - "image\t830\t-\tweight\t0.06028043498591822\n", - "image\t808\t-\tweight\t0.06026752408221666\n", - "image\t772\t-\tweight\t0.06021140705672949\n", - "image\t750\t-\tweight\t0.060162025437143496\n", - "image\t844\t-\tweight\t0.060101929899988096\n", - "image\t784\t-\tweight\t0.06003388853666149\n", + "image\t16\t-\tweight\t0.09457863290867145\n", + "image\t33\t-\tweight\t0.09431358165046931\n", + "image\t8\t-\tweight\t0.09383106409263509\n", + "image\t31\t-\tweight\t0.0909314099940096\n", + "image\t77\t-\tweight\t0.08944321537104273\n", + "image\t60\t-\tweight\t0.08919523673591125\n", + "image\t117\t-\tweight\t0.08863817716328135\n", + "image\t190\t-\tweight\t0.08742826964165426\n", + "image\t61\t-\tweight\t0.08740880468847693\n", + "image\t4\t-\tweight\t0.08658248985130698\n", "Latent semantic no. 1\n", - "image\t980\t-\tweight\t0.0754118902341204\n", - "image\t1084\t-\tweight\t0.07362125136812943\n", - "image\t1011\t-\tweight\t0.06967853969554338\n", - "image\t997\t-\tweight\t0.06873541509302017\n", - "image\t1065\t-\tweight\t0.06811244748351335\n", - "image\t1184\t-\tweight\t0.06715708987702379\n", - "image\t1053\t-\tweight\t0.06697645698011236\n", - "image\t962\t-\tweight\t0.06677715910430597\n", - "image\t1287\t-\tweight\t0.06650715541378867\n", - "image\t968\t-\tweight\t0.065552599099574\n", + "image\t0\t-\tweight\t0.0\n", + "image\t1\t-\tweight\t0.0\n", + "image\t2\t-\tweight\t0.0\n", + "image\t3\t-\tweight\t0.0\n", + "image\t4\t-\tweight\t0.0\n", + "image\t5\t-\tweight\t0.0\n", + "image\t6\t-\tweight\t0.0\n", + "image\t7\t-\tweight\t0.0\n", + "image\t8\t-\tweight\t0.0\n", + "image\t9\t-\tweight\t0.0\n", "Latent semantic no. 2\n", - "image\t0\t-\tweight\t0.0\n", - "image\t1\t-\tweight\t0.0\n", - "image\t2\t-\tweight\t0.0\n", - "image\t3\t-\tweight\t0.0\n", - "image\t4\t-\tweight\t0.0\n", - "image\t5\t-\tweight\t0.0\n", - "image\t6\t-\tweight\t0.0\n", - "image\t7\t-\tweight\t0.0\n", - "image\t8\t-\tweight\t0.0\n", - "image\t9\t-\tweight\t0.0\n", + "image\t901\t-\tweight\t0.06704958761044195\n", + "image\t821\t-\tweight\t0.06679275183308425\n", + "image\t560\t-\tweight\t0.0664275386647296\n", + "image\t617\t-\tweight\t0.0662151403988761\n", + "image\t797\t-\tweight\t0.06443320486788845\n", + "image\t899\t-\tweight\t0.06434223110660761\n", + "image\t892\t-\tweight\t0.06428385401777054\n", + "image\t893\t-\tweight\t0.064267819006683\n", + "image\t553\t-\tweight\t0.06396933419584953\n", + "image\t688\t-\tweight\t0.06322044784443977\n", "Latent semantic no. 3\n", - "image\t218\t-\tweight\t0.0\n", - "image\t219\t-\tweight\t0.0\n", - "image\t220\t-\tweight\t0.0\n", - "image\t221\t-\tweight\t0.0\n", - "image\t222\t-\tweight\t0.0\n", - "image\t223\t-\tweight\t0.0\n", - "image\t224\t-\tweight\t0.0\n", - "image\t225\t-\tweight\t0.0\n", - "image\t226\t-\tweight\t0.0\n", - "image\t227\t-\tweight\t0.0\n", + "image\t0\t-\tweight\t0.0\n", + "image\t1\t-\tweight\t0.0\n", + "image\t2\t-\tweight\t0.0\n", + "image\t3\t-\tweight\t0.0\n", + "image\t4\t-\tweight\t0.0\n", + "image\t5\t-\tweight\t0.0\n", + "image\t6\t-\tweight\t0.0\n", + "image\t7\t-\tweight\t0.0\n", + "image\t8\t-\tweight\t0.0\n", + "image\t9\t-\tweight\t0.0\n", "Latent semantic no. 4\n", - "image\t4178\t-\tweight\t0.13411466061203375\n", - "image\t4133\t-\tweight\t0.13381869962849108\n", - "image\t4186\t-\tweight\t0.1328204635772519\n", - "image\t4112\t-\tweight\t0.13246858130287337\n", - "image\t4165\t-\tweight\t0.13047834274654035\n", - "image\t4096\t-\tweight\t0.12970904464417174\n", - "image\t4130\t-\tweight\t0.1276357487547854\n", - "image\t4163\t-\tweight\t0.12611220410021198\n", - "image\t4175\t-\tweight\t0.12609814994237703\n", - "image\t4125\t-\tweight\t0.12492475451893506\n", - "Latent semantic no. 5\n", - "image\t0\t-\tweight\t0.0\n", - "image\t1\t-\tweight\t0.0\n", - "image\t2\t-\tweight\t0.0\n", - "image\t3\t-\tweight\t0.0\n", - "image\t4\t-\tweight\t0.0\n", - "image\t5\t-\tweight\t0.0\n", - "image\t6\t-\tweight\t0.0\n", - "image\t7\t-\tweight\t0.0\n", - "image\t8\t-\tweight\t0.0\n", - "image\t9\t-\tweight\t0.0\n", - "Latent semantic no. 6\n", - "image\t0\t-\tweight\t0.0\n", - "image\t1\t-\tweight\t0.0\n", - "image\t2\t-\tweight\t0.0\n", - "image\t3\t-\tweight\t0.0\n", - "image\t4\t-\tweight\t0.0\n", - "image\t5\t-\tweight\t0.0\n", - "image\t6\t-\tweight\t0.0\n", - "image\t7\t-\tweight\t0.0\n", - "image\t8\t-\tweight\t0.0\n", - "image\t9\t-\tweight\t0.0\n", - "Latent semantic no. 7\n", - "image\t0\t-\tweight\t0.0\n", - "image\t1\t-\tweight\t0.0\n", - "image\t2\t-\tweight\t0.0\n", - "image\t3\t-\tweight\t0.0\n", - "image\t4\t-\tweight\t0.0\n", - "image\t5\t-\tweight\t0.0\n", - "image\t6\t-\tweight\t0.0\n", - "image\t7\t-\tweight\t0.0\n", - "image\t8\t-\tweight\t0.0\n", - "image\t9\t-\tweight\t0.0\n", - "Latent semantic no. 8\n", - "image\t0\t-\tweight\t0.0\n", - "image\t1\t-\tweight\t0.0\n", - "image\t2\t-\tweight\t0.0\n", - "image\t3\t-\tweight\t0.0\n", - "image\t4\t-\tweight\t0.0\n", - "image\t5\t-\tweight\t0.0\n", - "image\t6\t-\tweight\t0.0\n", - "image\t7\t-\tweight\t0.0\n", - "image\t8\t-\tweight\t0.0\n", - "image\t9\t-\tweight\t0.0\n", - "Latent semantic no. 9\n", "image\t0\t-\tweight\t0.0\n", "image\t1\t-\tweight\t0.0\n", "image\t2\t-\tweight\t0.0\n", @@ -144,121 +89,21 @@ "image\t9\t-\tweight\t0.0\n", "Showing feature-weight latent semantic\n", "Latent semantic no. 0\n", - "feature\t0\t-\tweight\t0.07577182824380883\n", - "feature\t9\t-\tweight\t0.07573677778472039\n", - "feature\t3\t-\tweight\t0.07557126037394385\n", - "feature\t6\t-\tweight\t0.0753781982199277\n", - "feature\t7\t-\tweight\t0.0001951950616295707\n", - "feature\t4\t-\tweight\t0.00017549416192999285\n", - "feature\t1\t-\tweight\t0.00012194961415249631\n", - "feature\t2\t-\tweight\t4.287652912002155e-06\n", - "feature\t8\t-\tweight\t-2.314815116961173e-06\n", - "feature\t5\t-\tweight\t-5.197417109414247e-06\n", + "feature\t0\t-\tweight\t0.011984002180022709\n", "Latent semantic no. 1\n", - "feature\t9\t-\tweight\t0.09115512060365509\n", - "feature\t0\t-\tweight\t0.09113096158559393\n", - "feature\t3\t-\tweight\t0.09044159243667037\n", - "feature\t6\t-\tweight\t0.09018059343754826\n", - "feature\t7\t-\tweight\t0.0021130646053269977\n", - "feature\t4\t-\tweight\t0.002030234496532767\n", - "feature\t1\t-\tweight\t0.002009281088063933\n", - "feature\t5\t-\tweight\t-0.0006594073704548895\n", - "feature\t2\t-\tweight\t-0.0006852646011520126\n", - "feature\t8\t-\tweight\t-0.0007029010314333884\n", + "feature\t0\t-\tweight\t-0.015847730845197867\n", "Latent semantic no. 2\n", - "feature\t2\t-\tweight\t0.0017202269882332225\n", - "feature\t5\t-\tweight\t0.0012782693995776035\n", - "feature\t8\t-\tweight\t0.0011056757480729573\n", - "feature\t4\t-\tweight\t-0.008186797881888055\n", - "feature\t1\t-\tweight\t-0.008219352401356154\n", - "feature\t7\t-\tweight\t-0.0082326697588083\n", - "feature\t6\t-\tweight\t-0.052967486759999564\n", - "feature\t0\t-\tweight\t-0.053269849112101635\n", - "feature\t3\t-\tweight\t-0.053314794168011104\n", - "feature\t9\t-\tweight\t-0.054790922702571875\n", + "feature\t0\t-\tweight\t0.003755764372246337\n", "Latent semantic no. 3\n", - "feature\t8\t-\tweight\t0.0012457435033955949\n", - "feature\t5\t-\tweight\t0.0011302318267326496\n", - "feature\t2\t-\tweight\t0.0008915556276299796\n", - "feature\t1\t-\tweight\t-0.0067143893348969585\n", - "feature\t7\t-\tweight\t-0.006979411165292033\n", - "feature\t4\t-\tweight\t-0.007115085250947199\n", - "feature\t9\t-\tweight\t-0.04627063193585373\n", - "feature\t0\t-\tweight\t-0.04669584380231813\n", - "feature\t3\t-\tweight\t-0.05358789010258499\n", - "feature\t6\t-\tweight\t-0.05372707309592606\n", + "feature\t0\t-\tweight\t-0.015820605365729715\n", "Latent semantic no. 4\n", - "feature\t9\t-\tweight\t0.06636728404803105\n", - "feature\t0\t-\tweight\t0.06602164959781295\n", - "feature\t6\t-\tweight\t0.0658680657426211\n", - "feature\t3\t-\tweight\t0.0658246292439607\n", - "feature\t7\t-\tweight\t0.0024698135167617423\n", - "feature\t1\t-\tweight\t0.0024642047114514965\n", - "feature\t4\t-\tweight\t0.002441605516788918\n", - "feature\t2\t-\tweight\t3.412235539925601e-05\n", - "feature\t8\t-\tweight\t3.0388889414075837e-05\n", - "feature\t5\t-\tweight\t-3.5221294849889635e-05\n", - "Latent semantic no. 5\n", - "feature\t2\t-\tweight\t-0.0004406092931454461\n", - "feature\t8\t-\tweight\t-0.0004885796160427777\n", - "feature\t5\t-\tweight\t-0.00061257112416781\n", - "feature\t1\t-\tweight\t-0.007155350004314086\n", - "feature\t4\t-\tweight\t-0.007165462449854097\n", - "feature\t7\t-\tweight\t-0.007444856783482605\n", - "feature\t6\t-\tweight\t-0.06042702105743578\n", - "feature\t3\t-\tweight\t-0.06082664033553194\n", - "feature\t0\t-\tweight\t-0.061400505754596324\n", - "feature\t9\t-\tweight\t-0.06196505846576572\n", - "Latent semantic no. 6\n", - "feature\t8\t-\tweight\t0.001098350913411075\n", - "feature\t2\t-\tweight\t0.0010016779555276794\n", - "feature\t5\t-\tweight\t0.0005821006414327626\n", - "feature\t4\t-\tweight\t-0.005900355271379414\n", - "feature\t1\t-\tweight\t-0.00598284109579637\n", - "feature\t7\t-\tweight\t-0.0061876362657868585\n", - "feature\t0\t-\tweight\t-0.06848064266828655\n", - "feature\t3\t-\tweight\t-0.06851566211382039\n", - "feature\t6\t-\tweight\t-0.0686464268816822\n", - "feature\t9\t-\tweight\t-0.0692640377395642\n", - "Latent semantic no. 7\n", - "feature\t5\t-\tweight\t0.0017254022262197148\n", - "feature\t8\t-\tweight\t0.001702794313355738\n", - "feature\t2\t-\tweight\t0.0003159487432469688\n", - "feature\t1\t-\tweight\t-0.0020164365697178\n", - "feature\t4\t-\tweight\t-0.0027621541654151115\n", - "feature\t7\t-\tweight\t-0.002853145862649653\n", - "feature\t0\t-\tweight\t-0.06195980356747699\n", - "feature\t9\t-\tweight\t-0.06199428708500771\n", - "feature\t6\t-\tweight\t-0.06368714708105448\n", - "feature\t3\t-\tweight\t-0.06385832819997592\n", - "Latent semantic no. 8\n", - "feature\t5\t-\tweight\t0.000579681022086685\n", - "feature\t8\t-\tweight\t0.00023776162317446615\n", - "feature\t2\t-\tweight\t-8.903068121134156e-05\n", - "feature\t1\t-\tweight\t-0.003628410033754683\n", - "feature\t4\t-\tweight\t-0.004042182279091933\n", - "feature\t7\t-\tweight\t-0.004079610197989652\n", - "feature\t0\t-\tweight\t-0.07078512499474116\n", - "feature\t9\t-\tweight\t-0.07090128668558571\n", - "feature\t6\t-\tweight\t-0.07284859530849022\n", - "feature\t3\t-\tweight\t-0.07317257962730919\n", - "Latent semantic no. 9\n", - "feature\t5\t-\tweight\t8.414336905221735e-05\n", - "feature\t8\t-\tweight\t5.6427744439484355e-05\n", - "feature\t2\t-\tweight\t-0.00016083066069906443\n", - "feature\t1\t-\tweight\t-0.0028491737945443647\n", - "feature\t4\t-\tweight\t-0.003057268122115886\n", - "feature\t7\t-\tweight\t-0.003069397622655647\n", - "feature\t0\t-\tweight\t-0.06533602471133236\n", - "feature\t3\t-\tweight\t-0.06579569084919401\n", - "feature\t6\t-\tweight\t-0.06579792129352352\n", - "feature\t9\t-\tweight\t-0.06583901427338712\n", + "feature\t0\t-\tweight\t0.006783847616503207\n", "Showing label-weight latent semantic\n", "Latent semantic no. 0\n", - "label\t3\t-\tweight\t1.0\n", - "label\t0\t-\tweight\t0.0\n", + "label\t0\t-\tweight\t0.9999999999999998\n", "label\t1\t-\tweight\t0.0\n", "label\t2\t-\tweight\t0.0\n", + "label\t3\t-\tweight\t0.0\n", "label\t4\t-\tweight\t0.0\n", "label\t5\t-\tweight\t0.0\n", "label\t6\t-\tweight\t0.0\n", @@ -266,21 +111,21 @@ "label\t8\t-\tweight\t0.0\n", "label\t9\t-\tweight\t0.0\n", "Latent semantic no. 1\n", - "label\t5\t-\tweight\t0.9999999999999999\n", + "label\t1\t-\tweight\t1.0000000000000004\n", "label\t0\t-\tweight\t0.0\n", - "label\t1\t-\tweight\t0.0\n", "label\t2\t-\tweight\t0.0\n", "label\t3\t-\tweight\t0.0\n", "label\t4\t-\tweight\t0.0\n", + "label\t5\t-\tweight\t0.0\n", "label\t6\t-\tweight\t0.0\n", "label\t7\t-\tweight\t0.0\n", "label\t8\t-\tweight\t0.0\n", "label\t9\t-\tweight\t0.0\n", "Latent semantic no. 2\n", - "label\t1\t-\tweight\t0.9999999999999998\n", + "label\t3\t-\tweight\t1.0000000000000009\n", "label\t0\t-\tweight\t0.0\n", + "label\t1\t-\tweight\t0.0\n", "label\t2\t-\tweight\t0.0\n", - "label\t3\t-\tweight\t0.0\n", "label\t4\t-\tweight\t0.0\n", "label\t5\t-\tweight\t0.0\n", "label\t6\t-\tweight\t0.0\n", @@ -288,73 +133,18 @@ "label\t8\t-\tweight\t0.0\n", "label\t9\t-\tweight\t0.0\n", "Latent semantic no. 3\n", - "label\t0\t-\tweight\t0.9999999999999994\n", + "label\t5\t-\tweight\t0.9999999999999998\n", + "label\t0\t-\tweight\t0.0\n", "label\t1\t-\tweight\t0.0\n", "label\t2\t-\tweight\t0.0\n", "label\t3\t-\tweight\t0.0\n", "label\t4\t-\tweight\t0.0\n", - "label\t5\t-\tweight\t0.0\n", "label\t6\t-\tweight\t0.0\n", "label\t7\t-\tweight\t0.0\n", "label\t8\t-\tweight\t0.0\n", "label\t9\t-\tweight\t0.0\n", "Latent semantic no. 4\n", - "label\t94\t-\tweight\t1.0000000000000007\n", - "label\t0\t-\tweight\t0.0\n", - "label\t1\t-\tweight\t0.0\n", - "label\t2\t-\tweight\t0.0\n", - "label\t3\t-\tweight\t0.0\n", - "label\t4\t-\tweight\t0.0\n", - "label\t5\t-\tweight\t0.0\n", - "label\t6\t-\tweight\t0.0\n", - "label\t7\t-\tweight\t0.0\n", - "label\t8\t-\tweight\t0.0\n", - "Latent semantic no. 5\n", - "label\t55\t-\tweight\t1.0\n", - "label\t0\t-\tweight\t0.0\n", - "label\t1\t-\tweight\t0.0\n", - "label\t2\t-\tweight\t0.0\n", - "label\t3\t-\tweight\t0.0\n", - "label\t4\t-\tweight\t0.0\n", - "label\t5\t-\tweight\t0.0\n", - "label\t6\t-\tweight\t0.0\n", - "label\t7\t-\tweight\t0.0\n", - "label\t8\t-\tweight\t0.0\n", - "Latent semantic no. 6\n", - "label\t12\t-\tweight\t0.9999999999999998\n", - "label\t0\t-\tweight\t0.0\n", - "label\t1\t-\tweight\t0.0\n", - "label\t2\t-\tweight\t0.0\n", - "label\t3\t-\tweight\t0.0\n", - "label\t4\t-\tweight\t0.0\n", - "label\t5\t-\tweight\t0.0\n", - "label\t6\t-\tweight\t0.0\n", - "label\t7\t-\tweight\t0.0\n", - "label\t8\t-\tweight\t0.0\n", - "Latent semantic no. 7\n", - "label\t63\t-\tweight\t0.9999999999999997\n", - "label\t0\t-\tweight\t0.0\n", - "label\t1\t-\tweight\t0.0\n", - "label\t2\t-\tweight\t0.0\n", - "label\t3\t-\tweight\t0.0\n", - "label\t4\t-\tweight\t0.0\n", - "label\t5\t-\tweight\t0.0\n", - "label\t6\t-\tweight\t0.0\n", - "label\t7\t-\tweight\t0.0\n", - "label\t8\t-\tweight\t0.0\n", - "Latent semantic no. 8\n", - "label\t46\t-\tweight\t1.0\n", - "label\t0\t-\tweight\t0.0\n", - "label\t1\t-\tweight\t0.0\n", - "label\t2\t-\tweight\t0.0\n", - "label\t3\t-\tweight\t0.0\n", - "label\t4\t-\tweight\t0.0\n", - "label\t5\t-\tweight\t0.0\n", - "label\t6\t-\tweight\t0.0\n", - "label\t7\t-\tweight\t0.0\n", - "label\t8\t-\tweight\t0.0\n", - "Latent semantic no. 9\n", - "label\t93\t-\tweight\t1.0000000000000002\n", + "label\t94\t-\tweight\t1.0000000000000004\n", "label\t0\t-\tweight\t0.0\n", "label\t1\t-\tweight\t0.0\n", "label\t2\t-\tweight\t0.0\n", diff --git a/Phase 2/task_5.ipynb b/Phase 2/task_5.ipynb index 460d6ba..762cd51 100644 --- a/Phase 2/task_5.ipynb +++ b/Phase 2/task_5.ipynb @@ -29,119 +29,127 @@ "name": "stdout", "output_type": "stream", "text": [ - "Applying kmeans on the given similarity matrix to get 10 latent semantics (showing only top 10 label-weight pairs for each latent semantic)...\n", - "Initialized centroids\n", - "Note: for K-Means we display distances, in ascending order\n", + "Applying lda on the given similarity matrix to get 10 latent semantics (showing only top 10 label-weight pairs for each latent semantic)...\n", + "iteration: 1 of max_iter: 10\n", + "iteration: 2 of max_iter: 10\n", + "iteration: 3 of max_iter: 10\n", + "iteration: 4 of max_iter: 10\n", + "iteration: 5 of max_iter: 10\n", + "iteration: 6 of max_iter: 10\n", + "iteration: 7 of max_iter: 10\n", + "iteration: 8 of max_iter: 10\n", + "iteration: 9 of max_iter: 10\n", + "iteration: 10 of max_iter: 10\n", "Latent semantic no. 0\n", - "label\t38\t-\tDistance\t2.0070855260713345\n", - "label\t71\t-\tDistance\t2.224974820168396\n", - "label\t94\t-\tDistance\t2.341857909278956\n", - "label\t45\t-\tDistance\t2.99059339026617\n", - "label\t34\t-\tDistance\t3.2010802901998034\n", - "label\t57\t-\tDistance\t3.248469772417219\n", - "label\t77\t-\tDistance\t3.5731245496083677\n", - "label\t84\t-\tDistance\t4.026791789923078\n", - "label\t50\t-\tDistance\t4.144496651017247\n", - "label\t74\t-\tDistance\t4.614517493407895\n", + "label\t86\t-\tWeight\t0.0004531654159359732\n", + "label\t81\t-\tWeight\t0.0004417802626698606\n", + "label\t20\t-\tWeight\t0.00043909085561082503\n", + "label\t37\t-\tWeight\t0.0004366108274701382\n", + "label\t23\t-\tWeight\t0.00043457527167984727\n", + "label\t30\t-\tWeight\t0.00043324186605595916\n", + "label\t25\t-\tWeight\t0.00043274706213965473\n", + "label\t24\t-\tWeight\t0.0004290312838498227\n", + "label\t26\t-\tWeight\t0.0004290127071576239\n", + "label\t58\t-\tWeight\t0.0004280705463204183\n", "Latent semantic no. 1\n", - "label\t92\t-\tDistance\t3.230292112512146\n", - "label\t4\t-\tDistance\t3.5335656340201087\n", - "label\t2\t-\tDistance\t4.905027845590568\n", - "label\t69\t-\tDistance\t4.993399423965622\n", - "label\t65\t-\tDistance\t6.275170101152081\n", - "label\t21\t-\tDistance\t6.792963383606834\n", - "label\t95\t-\tDistance\t9.460863854781731\n", - "label\t60\t-\tDistance\t10.659440914917885\n", - "label\t82\t-\tDistance\t14.23961431596092\n", - "label\t51\t-\tDistance\t14.308250416010853\n", + "label\t86\t-\tWeight\t0.00045317505419918263\n", + "label\t81\t-\tWeight\t0.0004417890180969132\n", + "label\t20\t-\tWeight\t0.0004391003128445388\n", + "label\t37\t-\tWeight\t0.00043662070169061585\n", + "label\t23\t-\tWeight\t0.0004345844126142611\n", + "label\t30\t-\tWeight\t0.00043325103891919523\n", + "label\t25\t-\tWeight\t0.00043275655078268234\n", + "label\t24\t-\tWeight\t0.0004290408792180107\n", + "label\t26\t-\tWeight\t0.00042902109696286967\n", + "label\t58\t-\tWeight\t0.0004280807127762838\n", "Latent semantic no. 2\n", - "label\t98\t-\tDistance\t4.084187568594383\n", - "label\t75\t-\tDistance\t4.208154727653996\n", - "label\t59\t-\tDistance\t4.267012427049042\n", - "label\t11\t-\tDistance\t4.3719751047928685\n", - "label\t63\t-\tDistance\t4.389793026579887\n", - "label\t64\t-\tDistance\t4.534510062334466\n", - "label\t32\t-\tDistance\t4.596340579479344\n", - "label\t79\t-\tDistance\t4.97413168034284\n", - "label\t55\t-\tDistance\t5.180445076965457\n", - "label\t84\t-\tDistance\t5.321702524477488\n", + "label\t86\t-\tWeight\t0.00045312072900256355\n", + "label\t81\t-\tWeight\t0.0004417364497245229\n", + "label\t20\t-\tWeight\t0.0004390475331611943\n", + "label\t37\t-\tWeight\t0.0004365681611562296\n", + "label\t23\t-\tWeight\t0.0004345323157784398\n", + "label\t30\t-\tWeight\t0.00043319901917670715\n", + "label\t25\t-\tWeight\t0.0004327044844270213\n", + "label\t24\t-\tWeight\t0.00042898930777452614\n", + "label\t26\t-\tWeight\t0.000428970107413019\n", + "label\t58\t-\tWeight\t0.00042802908762740616\n", "Latent semantic no. 3\n", - "label\t73\t-\tDistance\t2.2337776135986673\n", - "label\t77\t-\tDistance\t2.446394227315699\n", - "label\t22\t-\tDistance\t2.8266085928002305\n", - "label\t96\t-\tDistance\t2.951528289863372\n", - "label\t72\t-\tDistance\t3.0039788225292554\n", - "label\t45\t-\tDistance\t3.109522101340006\n", - "label\t74\t-\tDistance\t3.519269143632249\n", - "label\t57\t-\tDistance\t3.589490130921498\n", - "label\t50\t-\tDistance\t3.6391055564874\n", - "label\t18\t-\tDistance\t4.109290572000071\n", + "label\t86\t-\tWeight\t0.00045318195164987813\n", + "label\t81\t-\tWeight\t0.00044179608840518193\n", + "label\t20\t-\tWeight\t0.0004391067775271899\n", + "label\t37\t-\tWeight\t0.000436626468446809\n", + "label\t23\t-\tWeight\t0.00043459099827651484\n", + "label\t30\t-\tWeight\t0.00043325754714432983\n", + "label\t25\t-\tWeight\t0.0004327625151138594\n", + "label\t24\t-\tWeight\t0.00042904668099729267\n", + "label\t26\t-\tWeight\t0.00042902773613974173\n", + "label\t58\t-\tWeight\t0.0004280860358219467\n", "Latent semantic no. 4\n", - "label\t78\t-\tDistance\t1.8064076815500691\n", - "label\t6\t-\tDistance\t1.960264623688121\n", - "label\t7\t-\tDistance\t2.1426433652644246\n", - "label\t61\t-\tDistance\t2.211884975823563\n", - "label\t67\t-\tDistance\t2.2819452598845484\n", - "label\t20\t-\tDistance\t2.3104854768313308\n", - "label\t62\t-\tDistance\t2.4074452247279643\n", - "label\t23\t-\tDistance\t2.4123612373578465\n", - "label\t27\t-\tDistance\t2.5964084026274183\n", - "label\t26\t-\tDistance\t2.6484422926018762\n", + "label\t86\t-\tWeight\t0.0004532012230924254\n", + "label\t81\t-\tWeight\t0.0004418145591898838\n", + "label\t20\t-\tWeight\t0.0004391246602233907\n", + "label\t37\t-\tWeight\t0.00043664360658210823\n", + "label\t23\t-\tWeight\t0.0004346094906288087\n", + "label\t30\t-\tWeight\t0.0004332756310469352\n", + "label\t25\t-\tWeight\t0.00043277963540597756\n", + "label\t24\t-\tWeight\t0.0004290633871096734\n", + "label\t26\t-\tWeight\t0.0004290459466564114\n", + "label\t58\t-\tWeight\t0.00042810235322099204\n", "Latent semantic no. 5\n", - "label\t1\t-\tDistance\t0.0\n", - "label\t66\t-\tDistance\t6.283884339485376\n", - "label\t0\t-\tDistance\t7.134186839941345\n", - "label\t68\t-\tDistance\t7.6014631552864165\n", - "label\t42\t-\tDistance\t7.699614640935743\n", - "label\t90\t-\tDistance\t7.745628525155249\n", - "label\t35\t-\tDistance\t7.888542444783939\n", - "label\t89\t-\tDistance\t8.296957431371565\n", - "label\t19\t-\tDistance\t8.389232149750157\n", - "label\t70\t-\tDistance\t8.416181651996403\n", + "label\t86\t-\tWeight\t0.0004531814522875912\n", + "label\t81\t-\tWeight\t0.00044179547980990153\n", + "label\t20\t-\tWeight\t0.00043910615276579\n", + "label\t37\t-\tWeight\t0.0004366251198908978\n", + "label\t23\t-\tWeight\t0.0004345904089672849\n", + "label\t30\t-\tWeight\t0.0004332568886788472\n", + "label\t25\t-\tWeight\t0.0004327609475184491\n", + "label\t24\t-\tWeight\t0.00042904496501344676\n", + "label\t26\t-\tWeight\t0.0004290273924817515\n", + "label\t58\t-\tWeight\t0.0004280843616517628\n", "Latent semantic no. 6\n", - "label\t58\t-\tDistance\t1.4491641647189777\n", - "label\t37\t-\tDistance\t1.5439214839372046\n", - "label\t24\t-\tDistance\t1.5452615348627594\n", - "label\t8\t-\tDistance\t1.7715264047899464\n", - "label\t25\t-\tDistance\t1.86516161648985\n", - "label\t87\t-\tDistance\t2.077478215700691\n", - "label\t15\t-\tDistance\t2.225120843217057\n", - "label\t16\t-\tDistance\t2.267782774837321\n", - "label\t39\t-\tDistance\t2.395932754700218\n", - "label\t36\t-\tDistance\t2.6959359474526083\n", + "label\t2\t-\tWeight\t0.9979457923349433\n", + "label\t95\t-\tWeight\t0.9975714512001539\n", + "label\t60\t-\tWeight\t0.9974934163989678\n", + "label\t82\t-\tWeight\t0.9971947522049759\n", + "label\t51\t-\tWeight\t0.9971885301157567\n", + "label\t66\t-\tWeight\t0.9970754925406659\n", + "label\t29\t-\tWeight\t0.9970572171294957\n", + "label\t42\t-\tWeight\t0.9969819309782944\n", + "label\t47\t-\tWeight\t0.9969577461454074\n", + "label\t35\t-\tWeight\t0.9969023226836516\n", "Latent semantic no. 7\n", - "label\t44\t-\tDistance\t2.2303295853566074\n", - "label\t19\t-\tDistance\t2.233360628309259\n", - "label\t76\t-\tDistance\t2.2873290684053234\n", - "label\t49\t-\tDistance\t2.4188703660528543\n", - "label\t9\t-\tDistance\t2.4470406114525685\n", - "label\t54\t-\tDistance\t2.4930648472372385\n", - "label\t10\t-\tDistance\t2.5342743763741615\n", - "label\t33\t-\tDistance\t2.6761306270075935\n", - "label\t28\t-\tDistance\t2.76245021657484\n", - "label\t36\t-\tDistance\t2.8111765962163813\n", + "label\t86\t-\tWeight\t0.0004531931222370423\n", + "label\t81\t-\tWeight\t0.0004418065816432295\n", + "label\t20\t-\tWeight\t0.0004391176224740742\n", + "label\t37\t-\tWeight\t0.00043663627448884573\n", + "label\t23\t-\tWeight\t0.0004346018291120466\n", + "label\t30\t-\tWeight\t0.00043326792763734024\n", + "label\t25\t-\tWeight\t0.0004327723354289989\n", + "label\t24\t-\tWeight\t0.0004290562269897544\n", + "label\t26\t-\tWeight\t0.000429038285361369\n", + "label\t58\t-\tWeight\t0.0004280951952808515\n", "Latent semantic no. 8\n", - "label\t48\t-\tDistance\t3.1737547288361596\n", - "label\t85\t-\tDistance\t4.021946100259249\n", - "label\t91\t-\tDistance\t5.424003509894085\n", - "label\t52\t-\tDistance\t5.537608967567619\n", - "label\t43\t-\tDistance\t5.53813149000202\n", - "label\t80\t-\tDistance\t5.6425678719484225\n", - "label\t14\t-\tDistance\t5.87213105210823\n", - "label\t83\t-\tDistance\t7.001763109529681\n", - "label\t93\t-\tDistance\t7.563499549838895\n", - "label\t3\t-\tDistance\t8.036164382755217\n", + "label\t86\t-\tWeight\t0.0004531025037746746\n", + "label\t81\t-\tWeight\t0.00044171873000539025\n", + "label\t20\t-\tWeight\t0.0004390298979822301\n", + "label\t37\t-\tWeight\t0.0004365513222341559\n", + "label\t23\t-\tWeight\t0.00043451495489625614\n", + "label\t30\t-\tWeight\t0.0004331818006977396\n", + "label\t25\t-\tWeight\t0.0004326876783366398\n", + "label\t24\t-\tWeight\t0.00042897279004515285\n", + "label\t26\t-\tWeight\t0.00042895311102269417\n", + "label\t58\t-\tWeight\t0.000428012558440153\n", "Latent semantic no. 9\n", - "label\t51\t-\tDistance\t1.871618718249688\n", - "label\t82\t-\tDistance\t2.0311106628896\n", - "label\t29\t-\tDistance\t2.6509535626831533\n", - "label\t42\t-\tDistance\t3.083958153652753\n", - "label\t47\t-\tDistance\t3.198020753679005\n", - "label\t66\t-\tDistance\t3.5690360028582857\n", - "label\t35\t-\tDistance\t4.033659067172662\n", - "label\t60\t-\tDistance\t4.979629225985197\n", - "label\t33\t-\tDistance\t6.016698032150541\n", - "label\t95\t-\tDistance\t6.119613727077633\n" + "label\t80\t-\tWeight\t0.9980799926585355\n", + "label\t48\t-\tWeight\t0.9978481535222623\n", + "label\t93\t-\tWeight\t0.9975103137028881\n", + "label\t14\t-\tWeight\t0.99609327389133\n", + "label\t99\t-\tWeight\t0.9921318122895414\n", + "label\t91\t-\tWeight\t0.9827860773066165\n", + "label\t85\t-\tWeight\t0.9762723996945643\n", + "label\t75\t-\tWeight\t0.9476213255769989\n", + "label\t3\t-\tWeight\t0.9401709016743883\n", + "label\t98\t-\tWeight\t0.9244947049183805\n" ] } ], diff --git a/Phase 2/task_6.ipynb b/Phase 2/task_6.ipynb index c10883f..5524d66 100644 --- a/Phase 2/task_6.ipynb +++ b/Phase 2/task_6.ipynb @@ -29,120 +29,127 @@ "name": "stdout", "output_type": "stream", "text": [ - "Applying kmeans on the given similarity matrix to get 10 latent semantics (showing only top 10 image-weight pairs for each latent semantic)...\n", - "Initialized centroids\n", - "Iteration 78 - Converged\n", - "Note: for K-Means we display distances, in ascending order\n", + "Applying lda on the given similarity matrix to get 10 latent semantics (showing only top 10 image-weight pairs for each latent semantic)...\n", + "iteration: 1 of max_iter: 10\n", + "iteration: 2 of max_iter: 10\n", + "iteration: 3 of max_iter: 10\n", + "iteration: 4 of max_iter: 10\n", + "iteration: 5 of max_iter: 10\n", + "iteration: 6 of max_iter: 10\n", + "iteration: 7 of max_iter: 10\n", + "iteration: 8 of max_iter: 10\n", + "iteration: 9 of max_iter: 10\n", + "iteration: 10 of max_iter: 10\n", "Latent semantic no. 0\n", - "image\t2035\t-\tDistance\t15.193245192997269\n", - "image\t3813\t-\tDistance\t16.04888912166159\n", - "image\t3846\t-\tDistance\t16.9147608871532\n", - "image\t2925\t-\tDistance\t17.10454309878603\n", - "image\t3455\t-\tDistance\t18.102307562986407\n", - "image\t2410\t-\tDistance\t18.94942620886487\n", - "image\t2107\t-\tDistance\t19.47309707424604\n", - "image\t169\t-\tDistance\t19.533352544481723\n", - "image\t2584\t-\tDistance\t20.078954258235058\n", - "image\t2554\t-\tDistance\t20.31870945722174\n", + "image\t1320\t-\tWeight\t0.17206070988966676\n", + "image\t1145\t-\tWeight\t0.17179943626356087\n", + "image\t3461\t-\tWeight\t0.17154666587650064\n", + "image\t1324\t-\tWeight\t0.1714916836186797\n", + "image\t1069\t-\tWeight\t0.17141323253822324\n", + "image\t3690\t-\tWeight\t0.16959779587188872\n", + "image\t1206\t-\tWeight\t0.1694328485890043\n", + "image\t1314\t-\tWeight\t0.16852671831005397\n", + "image\t3868\t-\tWeight\t0.16772530255560464\n", + "image\t1315\t-\tWeight\t0.1676951554917541\n", "Latent semantic no. 1\n", - "image\t4287\t-\tDistance\t19.736469352294893\n", - "image\t1903\t-\tDistance\t20.625366718297947\n", - "image\t4283\t-\tDistance\t21.293764261460364\n", - "image\t2020\t-\tDistance\t21.439372707924147\n", - "image\t2216\t-\tDistance\t21.50575404583331\n", - "image\t4272\t-\tDistance\t22.731747308700246\n", - "image\t73\t-\tDistance\t22.984525532773183\n", - "image\t3118\t-\tDistance\t23.05742728400208\n", - "image\t622\t-\tDistance\t23.38211853588565\n", - "image\t4257\t-\tDistance\t23.952073196825147\n", + "image\t3461\t-\tWeight\t0.17897274174404698\n", + "image\t1069\t-\tWeight\t0.17739080866155166\n", + "image\t3690\t-\tWeight\t0.17715023009170783\n", + "image\t3868\t-\tWeight\t0.1765583750227632\n", + "image\t1151\t-\tWeight\t0.17552646878633446\n", + "image\t3677\t-\tWeight\t0.17491121915496274\n", + "image\t1145\t-\tWeight\t0.17444522065197465\n", + "image\t1206\t-\tWeight\t0.17347707411460248\n", + "image\t1702\t-\tWeight\t0.17323349506823651\n", + "image\t3236\t-\tWeight\t0.17259361731395684\n", "Latent semantic no. 2\n", - "image\t1607\t-\tDistance\t19.475143670438978\n", - "image\t1946\t-\tDistance\t21.51656357453921\n", - "image\t2356\t-\tDistance\t21.828572283680128\n", - "image\t3908\t-\tDistance\t22.05022203753488\n", - "image\t3547\t-\tDistance\t22.443143797259534\n", - "image\t2199\t-\tDistance\t22.571833277582463\n", - "image\t3519\t-\tDistance\t22.86028550513413\n", - "image\t1890\t-\tDistance\t23.30071966551519\n", - "image\t173\t-\tDistance\t23.303977110625112\n", - "image\t4270\t-\tDistance\t23.49369113941158\n", + "image\t2913\t-\tWeight\t0.24915169806958332\n", + "image\t1419\t-\tWeight\t0.24873364607633072\n", + "image\t3823\t-\tWeight\t0.24765439539815443\n", + "image\t3914\t-\tWeight\t0.24722108746353014\n", + "image\t1978\t-\tWeight\t0.24717924801135982\n", + "image\t2277\t-\tWeight\t0.24716600575687775\n", + "image\t3278\t-\tWeight\t0.24665320113150327\n", + "image\t516\t-\tWeight\t0.2458587523178849\n", + "image\t936\t-\tWeight\t0.24566413261838727\n", + "image\t3170\t-\tWeight\t0.24563727684846276\n", "Latent semantic no. 3\n", - "image\t3877\t-\tDistance\t26.69192882188752\n", - "image\t3763\t-\tDistance\t30.515760593946236\n", - "image\t3788\t-\tDistance\t32.71038293371164\n", - "image\t2735\t-\tDistance\t33.09699801502328\n", - "image\t1506\t-\tDistance\t36.057724149884244\n", - "image\t1686\t-\tDistance\t36.473691930187435\n", - "image\t3485\t-\tDistance\t36.49488863581563\n", - "image\t3920\t-\tDistance\t36.56582383384961\n", - "image\t3403\t-\tDistance\t37.44068139304385\n", - "image\t3762\t-\tDistance\t37.70577701904375\n", + "image\t2913\t-\tWeight\t0.3266523053746904\n", + "image\t534\t-\tWeight\t0.3212648440986947\n", + "image\t484\t-\tWeight\t0.3203437955249965\n", + "image\t1419\t-\tWeight\t0.31664090320889127\n", + "image\t1978\t-\tWeight\t0.31547212997691076\n", + "image\t3191\t-\tWeight\t0.3153671627412605\n", + "image\t1470\t-\tWeight\t0.31421423272112303\n", + "image\t3823\t-\tWeight\t0.3141460953426758\n", + "image\t533\t-\tWeight\t0.3138441729808489\n", + "image\t3914\t-\tWeight\t0.3137452844226845\n", "Latent semantic no. 4\n", - "image\t1783\t-\tDistance\t16.117313734508425\n", - "image\t1395\t-\tDistance\t16.95429167145128\n", - "image\t1784\t-\tDistance\t17.57009310160933\n", - "image\t1789\t-\tDistance\t17.973453810738004\n", - "image\t1765\t-\tDistance\t18.610362195798043\n", - "image\t1773\t-\tDistance\t19.041096692299885\n", - "image\t2926\t-\tDistance\t19.11502996606766\n", - "image\t1685\t-\tDistance\t19.414760349222448\n", - "image\t2841\t-\tDistance\t19.81113964538446\n", - "image\t1460\t-\tDistance\t19.898834382884864\n", + "image\t2581\t-\tWeight\t0.14803042765338018\n", + "image\t2427\t-\tWeight\t0.14787119654742203\n", + "image\t235\t-\tWeight\t0.14725550675790816\n", + "image\t3318\t-\tWeight\t0.1470958239116371\n", + "image\t529\t-\tWeight\t0.1464149769906216\n", + "image\t2502\t-\tWeight\t0.14596833327118602\n", + "image\t1974\t-\tWeight\t0.1458992530542452\n", + "image\t479\t-\tWeight\t0.14583345959587438\n", + "image\t3300\t-\tWeight\t0.14516588137746167\n", + "image\t2759\t-\tWeight\t0.1446833200007853\n", "Latent semantic no. 5\n", - "image\t3303\t-\tDistance\t20.969885324908756\n", - "image\t2045\t-\tDistance\t21.631692888420304\n", - "image\t3825\t-\tDistance\t21.716033288921732\n", - "image\t3929\t-\tDistance\t22.774521397811917\n", - "image\t1859\t-\tDistance\t23.372667860565386\n", - "image\t3232\t-\tDistance\t26.60481926894494\n", - "image\t3149\t-\tDistance\t26.715214213345696\n", - "image\t1502\t-\tDistance\t27.72700742629819\n", - "image\t1579\t-\tDistance\t28.000908326829553\n", - "image\t3021\t-\tDistance\t28.227049715323034\n", + "image\t3473\t-\tWeight\t0.16653860528182776\n", + "image\t1204\t-\tWeight\t0.16305223733127827\n", + "image\t3551\t-\tWeight\t0.16189112109250273\n", + "image\t2220\t-\tWeight\t0.16159567829951746\n", + "image\t1231\t-\tWeight\t0.16159001222843358\n", + "image\t1253\t-\tWeight\t0.1613447857090851\n", + "image\t3204\t-\tWeight\t0.1610615712011389\n", + "image\t3331\t-\tWeight\t0.1609424410565923\n", + "image\t1237\t-\tWeight\t0.16034096468940268\n", + "image\t3622\t-\tWeight\t0.15993886160572018\n", "Latent semantic no. 6\n", - "image\t1576\t-\tDistance\t18.87169047631405\n", - "image\t2858\t-\tDistance\t20.03847155817962\n", - "image\t1586\t-\tDistance\t20.080662203948876\n", - "image\t2850\t-\tDistance\t20.838413387796493\n", - "image\t2028\t-\tDistance\t21.169189788615924\n", - "image\t2716\t-\tDistance\t21.48136423054197\n", - "image\t4102\t-\tDistance\t21.660099255138686\n", - "image\t3457\t-\tDistance\t21.769184940550623\n", - "image\t1736\t-\tDistance\t21.85959261306364\n", - "image\t4314\t-\tDistance\t22.54861914619658\n", + "image\t599\t-\tWeight\t0.2198899760317277\n", + "image\t639\t-\tWeight\t0.21846435872932818\n", + "image\t640\t-\tWeight\t0.21776591339133608\n", + "image\t702\t-\tWeight\t0.2174138488317365\n", + "image\t704\t-\tWeight\t0.2166738332332963\n", + "image\t711\t-\tWeight\t0.21662045479027403\n", + "image\t703\t-\tWeight\t0.21661091222997475\n", + "image\t617\t-\tWeight\t0.2163479764382222\n", + "image\t589\t-\tWeight\t0.21631401416260512\n", + "image\t642\t-\tWeight\t0.21630913014866476\n", "Latent semantic no. 7\n", - "image\t3950\t-\tDistance\t25.18109439269185\n", - "image\t2023\t-\tDistance\t25.789279523766343\n", - "image\t3932\t-\tDistance\t27.90805288360532\n", - "image\t1434\t-\tDistance\t28.944408149134258\n", - "image\t2330\t-\tDistance\t29.442864276116474\n", - "image\t2349\t-\tDistance\t30.24950272216615\n", - "image\t3252\t-\tDistance\t30.39413795688458\n", - "image\t3526\t-\tDistance\t30.998757072825036\n", - "image\t1504\t-\tDistance\t31.665045303749636\n", - "image\t3117\t-\tDistance\t32.420320427638046\n", + "image\t3928\t-\tWeight\t0.6634818538599493\n", + "image\t3801\t-\tWeight\t0.6573450633183574\n", + "image\t1701\t-\tWeight\t0.6480471204807624\n", + "image\t3840\t-\tWeight\t0.6456662415349316\n", + "image\t4062\t-\tWeight\t0.6439791662614557\n", + "image\t4186\t-\tWeight\t0.641220476711286\n", + "image\t830\t-\tWeight\t0.6384302481021613\n", + "image\t784\t-\tWeight\t0.6374058630564187\n", + "image\t3659\t-\tWeight\t0.636175407817677\n", + "image\t4042\t-\tWeight\t0.6322635857453663\n", "Latent semantic no. 8\n", - "image\t2077\t-\tDistance\t13.954066038827099\n", - "image\t3402\t-\tDistance\t14.458733182318412\n", - "image\t1563\t-\tDistance\t16.656651855034323\n", - "image\t1846\t-\tDistance\t17.052974589353724\n", - "image\t730\t-\tDistance\t17.25680776558567\n", - "image\t3503\t-\tDistance\t17.367570425682572\n", - "image\t3405\t-\tDistance\t18.378448265500502\n", - "image\t4284\t-\tDistance\t19.017406411077424\n", - "image\t3809\t-\tDistance\t19.162266095814548\n", - "image\t2510\t-\tDistance\t19.361042141304708\n", + "image\t1580\t-\tWeight\t0.28575545742878244\n", + "image\t1419\t-\tWeight\t0.28332419763850997\n", + "image\t3914\t-\tWeight\t0.28232175164293977\n", + "image\t936\t-\tWeight\t0.2823216465790576\n", + "image\t3859\t-\tWeight\t0.28189499418627034\n", + "image\t3861\t-\tWeight\t0.2801815894641137\n", + "image\t1592\t-\tWeight\t0.27958765520327383\n", + "image\t3823\t-\tWeight\t0.2793916278176494\n", + "image\t2692\t-\tWeight\t0.27938679856587517\n", + "image\t1919\t-\tWeight\t0.2786505567477107\n", "Latent semantic no. 9\n", - "image\t3393\t-\tDistance\t18.57180005298004\n", - "image\t2544\t-\tDistance\t20.113218222781388\n", - "image\t1930\t-\tDistance\t20.383444354935005\n", - "image\t1682\t-\tDistance\t21.019603660594967\n", - "image\t3155\t-\tDistance\t21.019680109622932\n", - "image\t4000\t-\tDistance\t21.85089581447219\n", - "image\t2815\t-\tDistance\t21.85923223224687\n", - "image\t2524\t-\tDistance\t22.415510254934645\n", - "image\t2907\t-\tDistance\t22.896560385522896\n", - "image\t2434\t-\tDistance\t22.9031446197451\n" + "image\t1272\t-\tWeight\t0.1837953952807028\n", + "image\t1274\t-\tWeight\t0.1794627699707628\n", + "image\t1942\t-\tWeight\t0.17899500770197288\n", + "image\t3500\t-\tWeight\t0.17707556817302403\n", + "image\t3192\t-\tWeight\t0.17705287616822626\n", + "image\t2818\t-\tWeight\t0.17660356031482674\n", + "image\t1285\t-\tWeight\t0.17617394226847666\n", + "image\t2587\t-\tWeight\t0.17562936196517273\n", + "image\t2801\t-\tWeight\t0.17495390468365793\n", + "image\t3331\t-\tWeight\t0.17343968962278572\n" ] } ], diff --git a/Phase 2/task_7.ipynb b/Phase 2/task_7.ipynb index 3a72b77..90cd935 100644 --- a/Phase 2/task_7.ipynb +++ b/Phase 2/task_7.ipynb @@ -2,18 +2,9 @@ "cells": [ { "cell_type": "code", - "execution_count": 102, + "execution_count": 1, "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "The autoreload extension is already loaded. To reload it, use:\n", - " %reload_ext autoreload\n" - ] - } - ], + "outputs": [], "source": [ "%load_ext autoreload\n", "%autoreload 2" @@ -21,7 +12,7 @@ }, { "cell_type": "code", - "execution_count": 103, + "execution_count": 2, "metadata": {}, "outputs": [], "source": [ @@ -36,7 +27,7 @@ }, { "cell_type": "code", - "execution_count": 104, + "execution_count": 3, "metadata": {}, "outputs": [], "source": [ @@ -46,14 +37,14 @@ }, { "cell_type": "code", - "execution_count": 105, + "execution_count": 4, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "label_sim-cm_fd-lda-10-model.joblib loaded\n" + "resnet_fd-cp-5-semantics.json loaded\n" ] } ], @@ -125,7 +116,7 @@ }, { "cell_type": "code", - "execution_count": 106, + "execution_count": 5, "metadata": {}, "outputs": [], "source": [ @@ -181,7 +172,6 @@ " comparison_vector = model.transform(feature_vectors_shifted.flatten().reshape(1, -1)).flatten()\n", " print(comparison_feature_space.shape)\n", " print(comparison_vector.shape)\n", - " # print(retValue)\n", "\n", " n = len(comparison_feature_space)\n", "\n", @@ -198,7 +188,7 @@ }, { "cell_type": "code", - "execution_count": 107, + "execution_count": 6, "metadata": {}, "outputs": [], "source": [ @@ -228,7 +218,7 @@ }, { "cell_type": "code", - "execution_count": 108, + "execution_count": 7, "metadata": {}, "outputs": [], "source": [ @@ -278,24 +268,23 @@ }, { "cell_type": "code", - "execution_count": 109, + "execution_count": 8, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "Most similar label to 0 is 19\n", - "3634\n", - "3600\n", - "3562\n", - "3618\n", - "3574\n", - "3604\n", - "3550\n", - "3542\n", - "3564\n", - "3538\n" + "{'image_id': 870, 'distance': 0.0}\n", + "{'image_id': 872, 'distance': 0.0}\n", + "{'image_id': 874, 'distance': 0.0}\n", + "{'image_id': 876, 'distance': 0.0}\n", + "{'image_id': 878, 'distance': 0.0}\n", + "{'image_id': 880, 'distance': 0.0}\n", + "{'image_id': 882, 'distance': 0.0}\n", + "{'image_id': 884, 'distance': 0.0}\n", + "{'image_id': 886, 'distance': 0.0}\n", + "{'image_id': 888, 'distance': 0.0}\n" ] } ], diff --git a/Phase 2/task_8.ipynb b/Phase 2/task_8.ipynb index 59b7a72..58b0f57 100644 --- a/Phase 2/task_8.ipynb +++ b/Phase 2/task_8.ipynb @@ -118,7 +118,7 @@ " else:\n", " print(f\"{selected_latent_space}-{selected_feature_model}-{selected_dim_reduction_method}-{k}-model.joblib does not exist\")\n", " else:\n", - " if os.path.exists(f\"{selected_latent_space}-{selected_feature_model}-{selected_dim_reduction_method}-{k}-semantics.json\"):\n", + " if os.path.exists(f\"{selected_latent_space}-{selected_feature_model}-{selected_dim_reduction_method}img-{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",