{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# Self made SVD" ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "import helpers\n", "import pandas as pd\n", "import numpy as np\n", "import scipy.sparse as sparse\n", "from collections import defaultdict\n", "from itertools import chain\n", "import random\n", "\n", "train_read=pd.read_csv('./Datasets/ml-100k/train.csv', sep='\\t', header=None)\n", "test_read=pd.read_csv('./Datasets/ml-100k/test.csv', sep='\\t', header=None)\n", "train_ui, test_ui, user_code_id, user_id_code, item_code_id, item_id_code = helpers.data_to_csr(train_read, test_read)" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [], "source": [ "# Done similarly to https://github.com/albertauyeung/matrix-factorization-in-python\n", "from tqdm import tqdm\n", "\n", "class SVD():\n", " \n", " def __init__(self, train_ui, learning_rate, regularization, nb_factors, iterations):\n", " self.train_ui=train_ui\n", " self.uir=list(zip(*[train_ui.nonzero()[0],train_ui.nonzero()[1], train_ui.data]))\n", " \n", " self.learning_rate=learning_rate\n", " self.regularization=regularization\n", " self.iterations=iterations\n", " self.nb_users, self.nb_items=train_ui.shape\n", " self.nb_ratings=train_ui.nnz\n", " self.nb_factors=nb_factors\n", " \n", " self.Pu=np.random.normal(loc=0, scale=1./self.nb_factors, size=(self.nb_users, self.nb_factors))\n", " self.Qi=np.random.normal(loc=0, scale=1./self.nb_factors, size=(self.nb_items, self.nb_factors))\n", "\n", " def train(self, test_ui=None):\n", " if test_ui!=None:\n", " self.test_uir=list(zip(*[test_ui.nonzero()[0],test_ui.nonzero()[1], test_ui.data]))\n", " \n", " self.learning_process=[]\n", " pbar = tqdm(range(self.iterations))\n", " for i in pbar:\n", " pbar.set_description(f'Epoch {i} RMSE: {self.learning_process[-1][1] if i>0 else 0}. Training epoch {i+1}...')\n", " np.random.shuffle(self.uir)\n", " self.sgd(self.uir)\n", " if test_ui==None:\n", " self.learning_process.append([i+1, self.RMSE_total(self.uir)])\n", " else:\n", " self.learning_process.append([i+1, self.RMSE_total(self.uir), self.RMSE_total(self.test_uir)])\n", " \n", " def sgd(self, uir):\n", " \n", " for u, i, score in uir:\n", " # Computer prediction and error\n", " prediction = self.get_rating(u,i)\n", " e = (score - prediction)\n", " \n", " # Update user and item latent feature matrices\n", " Pu_update=self.learning_rate * (e * self.Qi[i] - self.regularization * self.Pu[u])\n", " Qi_update=self.learning_rate * (e * self.Pu[u] - self.regularization * self.Qi[i])\n", " \n", " self.Pu[u] += Pu_update\n", " self.Qi[i] += Qi_update\n", " \n", " def get_rating(self, u, i):\n", " prediction = self.Pu[u].dot(self.Qi[i].T)\n", " return prediction\n", " \n", " def RMSE_total(self, uir):\n", " RMSE=0\n", " for u,i, score in uir:\n", " prediction = self.get_rating(u,i)\n", " RMSE+=(score - prediction)**2\n", " return np.sqrt(RMSE/len(uir))\n", " \n", " def estimations(self):\n", " self.estimations=\\\n", " np.dot(self.Pu,self.Qi.T)\n", "\n", " def recommend(self, user_code_id, item_code_id, topK=10):\n", " \n", " top_k = defaultdict(list)\n", " for nb_user, user in enumerate(self.estimations):\n", " \n", " user_rated=self.train_ui.indices[self.train_ui.indptr[nb_user]:self.train_ui.indptr[nb_user+1]]\n", " for item, score in enumerate(user):\n", " if item not in user_rated and not np.isnan(score):\n", " top_k[user_code_id[nb_user]].append((item_code_id[item], score))\n", " result=[]\n", " # Let's choose k best items in the format: (user, item1, score1, item2, score2, ...)\n", " for uid, item_scores in top_k.items():\n", " item_scores.sort(key=lambda x: x[1], reverse=True)\n", " result.append([uid]+list(chain(*item_scores[:topK])))\n", " return result\n", " \n", " def estimate(self, user_code_id, item_code_id, test_ui):\n", " result=[]\n", " for user, item in zip(*test_ui.nonzero()):\n", " result.append([user_code_id[user], item_code_id[item], \n", " self.estimations[user,item] if not np.isnan(self.estimations[user,item]) else 1])\n", " return result" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "Epoch 39 RMSE: 0.7486867798606991. Training epoch 40...: 100%|██████████| 40/40 [02:44<00:00, 4.12s/it]\n" ] } ], "source": [ "model=SVD(train_ui, learning_rate=0.005, regularization=0.02, nb_factors=100, iterations=40)\n", "model.train(test_ui)" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "import matplotlib.pyplot as plt\n", "\n", "df=pd.DataFrame(model.learning_process).iloc[:,:2]\n", "df.columns=['epoch', 'train_RMSE']\n", "plt.plot('epoch', 'train_RMSE', data=df, color='blue')\n", "plt.legend()" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "import matplotlib.pyplot as plt\n", "\n", "df=pd.DataFrame(model.learning_process[10:], columns=['epoch', 'train_RMSE', 'test_RMSE'])\n", "plt.plot('epoch', 'train_RMSE', data=df, color='blue')\n", "plt.plot('epoch', 'test_RMSE', data=df, color='yellow', linestyle='dashed')\n", "plt.legend()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### Saving and evaluating recommendations" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [], "source": [ "model.estimations()\n", "\n", "top_n=pd.DataFrame(model.recommend(user_code_id, item_code_id, topK=10))\n", "\n", "top_n.to_csv('Recommendations generated/ml-100k/Self_SVD_reco.csv', index=False, header=False)\n", "\n", "estimations=pd.DataFrame(model.estimate(user_code_id, item_code_id, test_ui))\n", "estimations.to_csv('Recommendations generated/ml-100k/Self_SVD_estimations.csv', index=False, header=False)" ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "943it [00:00, 4196.25it/s]\n" ] }, { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
RMSEMAEprecisionrecallF_1F_05precision_superrecall_superNDCGmAPMRRLAUCHRF_2Whole_averageReco in testTest coverageShannonGini
00.9140240.7171810.1044540.0438360.0533310.0707160.0945280.0767510.1067110.0505320.1943660.5186470.4793210.0459410.1532610.8537650.1486293.8363340.973007
\n", "
" ], "text/plain": [ " RMSE MAE precision recall F_1 F_05 \\\n", "0 0.914024 0.717181 0.104454 0.043836 0.053331 0.070716 \n", "\n", " precision_super recall_super NDCG mAP MRR LAUC \\\n", "0 0.094528 0.076751 0.106711 0.050532 0.194366 0.518647 \n", "\n", " HR F_2 Whole_average Reco in test Test coverage Shannon \\\n", "0 0.479321 0.045941 0.153261 0.853765 0.148629 3.836334 \n", "\n", " Gini \n", "0 0.973007 " ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ "import evaluation_measures as ev\n", "\n", "estimations_df=pd.read_csv('Recommendations generated/ml-100k/Self_SVD_estimations.csv', header=None)\n", "reco=np.loadtxt('Recommendations generated/ml-100k/Self_SVD_reco.csv', delimiter=',')\n", "\n", "ev.evaluate(test=pd.read_csv('./Datasets/ml-100k/test.csv', sep='\\t', header=None),\n", " estimations_df=estimations_df, \n", " reco=reco,\n", " super_reactions=[4,5])" ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "943it [00:00, 4120.95it/s]\n", "943it [00:00, 4286.76it/s]\n", "943it [00:00, 4253.65it/s]\n", "943it [00:00, 4386.02it/s]\n", "943it [00:00, 4497.82it/s]\n", "943it [00:00, 4289.74it/s]\n", "943it [00:00, 4682.40it/s]\n", "943it [00:00, 4255.79it/s]\n", "943it [00:00, 3942.08it/s]\n", "943it [00:00, 4136.45it/s]\n", "943it [00:00, 3908.85it/s]\n", "943it [00:00, 3779.61it/s]\n", "943it [00:00, 4456.49it/s]\n", "943it [00:00, 3504.99it/s]\n", "943it [00:00, 3182.20it/s]\n", "943it [00:00, 3850.55it/s]\n", "943it [00:00, 3881.66it/s]\n", "943it [00:00, 4822.70it/s]\n" ] }, { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
ModelRMSEMAEprecisionrecallF_1F_05precision_superrecall_superNDCGmAPMRRLAUCHRF_2Whole_averageReco in testTest coverageShannonGini
0Self_RP3Beta3.7029283.5277130.3226940.2160690.2121520.2475380.2452790.2849830.3882710.2482390.6363180.6056830.9109230.2054500.3769670.9997880.1789324.5496630.950182
0Self_P33.7024463.5272730.2821850.1920920.1867490.2169800.2041850.2400960.3391140.2049050.5721570.5935440.8759280.1817020.3408031.0000000.0772013.8758920.974947
0Self_TopPop2.5082582.2179090.1888650.1169190.1187320.1415840.1304720.1374730.2146510.1117070.4009390.5555460.7656420.1127500.2496071.0000000.0389613.1590790.987317
0Self_SVDBaseline3.6456663.4802460.1378580.0823980.0841510.1010630.1079400.1093930.1644770.0829730.3423740.5380970.6383880.0798600.2057480.9998940.2792215.1590760.907220
0Ready_SVD0.9525630.7501580.0944860.0462740.0513890.0656250.0826180.0741500.1093200.0513830.2406930.5198490.4750800.0462370.1547590.9934250.2063494.4429960.952832
0Self_SVD0.9140240.7171810.1044540.0438360.0533310.0707160.0945280.0767510.1067110.0505320.1943660.5186470.4793210.0459410.1532610.8537650.1486293.8363340.973007
0Ready_Baseline0.9494590.7524870.0914100.0376520.0460300.0612860.0796140.0564630.0959570.0431780.1981930.5155010.4379640.0395490.1419001.0000000.0339112.8365130.991139
0Self_KNNSurprisetask0.9462550.7452090.0834570.0328480.0412270.0554930.0747850.0488900.0895770.0409020.1890570.5130760.4178150.0349960.1351770.8885470.1305923.6118060.978659
0Self_TopRated2.5082582.2179090.0793210.0326670.0399830.0531700.0688840.0485820.0707660.0276020.1147900.5129430.4114530.0343850.1245461.0000000.0245312.7612380.991660
0Ready_SVDBiased0.9421410.7427600.0812300.0323440.0403020.0539320.0726390.0511260.0875520.0393460.1912850.5128180.4167550.0344050.1344780.9976670.1652244.1475790.964690
0Self_GlobalAvg1.1257600.9435340.0611880.0259680.0313830.0413430.0405580.0321070.0676950.0274700.1711870.5095460.3849420.0272130.1183831.0000000.0259742.7117720.992003
0Ready_Random1.5256331.2257140.0477200.0220490.0254940.0328450.0290770.0250150.0517570.0192420.1281810.5075430.3276780.0226280.1032690.9872750.1847045.1051220.906561
0Ready_I-KNN1.0303860.8130670.0260870.0069080.0105930.0160460.0211370.0095220.0242140.0089580.0480680.4998850.1548250.0080070.0695210.4023330.4343435.1336500.877999
0Ready_I-KNNBaseline0.9353270.7374240.0025450.0007550.0011050.0016020.0022530.0009300.0034440.0013620.0117600.4967240.0212090.0008620.0453790.4828210.0598852.2325780.994487
0Ready_U-KNN1.0234950.8079130.0007420.0002050.0003050.0004490.0005360.0001980.0008450.0002740.0027440.4964410.0074230.0002350.0425330.6021210.0108232.0891860.995706
0Self_BaselineIU0.9581360.7540510.0009540.0001880.0002980.0004810.0006440.0002230.0010430.0003350.0033480.4964330.0095440.0002200.0428090.6990460.0050511.9459100.995669
0Self_BaselineUI0.9675850.7627400.0009540.0001700.0002780.0004630.0006440.0001890.0007520.0001680.0016770.4964240.0095440.0002010.0426220.6005300.0050511.8031260.996380
0Self_IKNN1.0183630.8087930.0003180.0001080.0001400.0001890.0000000.0000000.0002140.0000370.0003680.4963910.0031810.0001180.0417550.3921530.1154404.1747410.965327
\n", "
" ], "text/plain": [ " Model RMSE MAE precision recall F_1 \\\n", "0 Self_RP3Beta 3.702928 3.527713 0.322694 0.216069 0.212152 \n", "0 Self_P3 3.702446 3.527273 0.282185 0.192092 0.186749 \n", "0 Self_TopPop 2.508258 2.217909 0.188865 0.116919 0.118732 \n", "0 Self_SVDBaseline 3.645666 3.480246 0.137858 0.082398 0.084151 \n", "0 Ready_SVD 0.952563 0.750158 0.094486 0.046274 0.051389 \n", "0 Self_SVD 0.914024 0.717181 0.104454 0.043836 0.053331 \n", "0 Ready_Baseline 0.949459 0.752487 0.091410 0.037652 0.046030 \n", "0 Self_KNNSurprisetask 0.946255 0.745209 0.083457 0.032848 0.041227 \n", "0 Self_TopRated 2.508258 2.217909 0.079321 0.032667 0.039983 \n", "0 Ready_SVDBiased 0.942141 0.742760 0.081230 0.032344 0.040302 \n", "0 Self_GlobalAvg 1.125760 0.943534 0.061188 0.025968 0.031383 \n", "0 Ready_Random 1.525633 1.225714 0.047720 0.022049 0.025494 \n", "0 Ready_I-KNN 1.030386 0.813067 0.026087 0.006908 0.010593 \n", "0 Ready_I-KNNBaseline 0.935327 0.737424 0.002545 0.000755 0.001105 \n", "0 Ready_U-KNN 1.023495 0.807913 0.000742 0.000205 0.000305 \n", "0 Self_BaselineIU 0.958136 0.754051 0.000954 0.000188 0.000298 \n", "0 Self_BaselineUI 0.967585 0.762740 0.000954 0.000170 0.000278 \n", "0 Self_IKNN 1.018363 0.808793 0.000318 0.000108 0.000140 \n", "\n", " F_05 precision_super recall_super NDCG mAP MRR \\\n", "0 0.247538 0.245279 0.284983 0.388271 0.248239 0.636318 \n", "0 0.216980 0.204185 0.240096 0.339114 0.204905 0.572157 \n", "0 0.141584 0.130472 0.137473 0.214651 0.111707 0.400939 \n", "0 0.101063 0.107940 0.109393 0.164477 0.082973 0.342374 \n", "0 0.065625 0.082618 0.074150 0.109320 0.051383 0.240693 \n", "0 0.070716 0.094528 0.076751 0.106711 0.050532 0.194366 \n", "0 0.061286 0.079614 0.056463 0.095957 0.043178 0.198193 \n", "0 0.055493 0.074785 0.048890 0.089577 0.040902 0.189057 \n", "0 0.053170 0.068884 0.048582 0.070766 0.027602 0.114790 \n", "0 0.053932 0.072639 0.051126 0.087552 0.039346 0.191285 \n", "0 0.041343 0.040558 0.032107 0.067695 0.027470 0.171187 \n", "0 0.032845 0.029077 0.025015 0.051757 0.019242 0.128181 \n", "0 0.016046 0.021137 0.009522 0.024214 0.008958 0.048068 \n", "0 0.001602 0.002253 0.000930 0.003444 0.001362 0.011760 \n", "0 0.000449 0.000536 0.000198 0.000845 0.000274 0.002744 \n", "0 0.000481 0.000644 0.000223 0.001043 0.000335 0.003348 \n", "0 0.000463 0.000644 0.000189 0.000752 0.000168 0.001677 \n", "0 0.000189 0.000000 0.000000 0.000214 0.000037 0.000368 \n", "\n", " LAUC HR F_2 Whole_average Reco in test Test coverage \\\n", "0 0.605683 0.910923 0.205450 0.376967 0.999788 0.178932 \n", "0 0.593544 0.875928 0.181702 0.340803 1.000000 0.077201 \n", "0 0.555546 0.765642 0.112750 0.249607 1.000000 0.038961 \n", "0 0.538097 0.638388 0.079860 0.205748 0.999894 0.279221 \n", "0 0.519849 0.475080 0.046237 0.154759 0.993425 0.206349 \n", "0 0.518647 0.479321 0.045941 0.153261 0.853765 0.148629 \n", "0 0.515501 0.437964 0.039549 0.141900 1.000000 0.033911 \n", "0 0.513076 0.417815 0.034996 0.135177 0.888547 0.130592 \n", "0 0.512943 0.411453 0.034385 0.124546 1.000000 0.024531 \n", "0 0.512818 0.416755 0.034405 0.134478 0.997667 0.165224 \n", "0 0.509546 0.384942 0.027213 0.118383 1.000000 0.025974 \n", "0 0.507543 0.327678 0.022628 0.103269 0.987275 0.184704 \n", "0 0.499885 0.154825 0.008007 0.069521 0.402333 0.434343 \n", "0 0.496724 0.021209 0.000862 0.045379 0.482821 0.059885 \n", "0 0.496441 0.007423 0.000235 0.042533 0.602121 0.010823 \n", "0 0.496433 0.009544 0.000220 0.042809 0.699046 0.005051 \n", "0 0.496424 0.009544 0.000201 0.042622 0.600530 0.005051 \n", "0 0.496391 0.003181 0.000118 0.041755 0.392153 0.115440 \n", "\n", " Shannon Gini \n", "0 4.549663 0.950182 \n", "0 3.875892 0.974947 \n", "0 3.159079 0.987317 \n", "0 5.159076 0.907220 \n", "0 4.442996 0.952832 \n", "0 3.836334 0.973007 \n", "0 2.836513 0.991139 \n", "0 3.611806 0.978659 \n", "0 2.761238 0.991660 \n", "0 4.147579 0.964690 \n", "0 2.711772 0.992003 \n", "0 5.105122 0.906561 \n", "0 5.133650 0.877999 \n", "0 2.232578 0.994487 \n", "0 2.089186 0.995706 \n", "0 1.945910 0.995669 \n", "0 1.803126 0.996380 \n", "0 4.174741 0.965327 " ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "import imp\n", "imp.reload(ev)\n", "\n", "import evaluation_measures as ev\n", "dir_path=\"Recommendations generated/ml-100k/\"\n", "super_reactions=[4,5]\n", "test=pd.read_csv('./Datasets/ml-100k/test.csv', sep='\\t', header=None)\n", "\n", "ev.evaluate_all(test, dir_path, super_reactions)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Embeddings" ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([[1, 2],\n", " [3, 4]])" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/plain": [ "array([[0.4472136 , 0.89442719],\n", " [0.6 , 0.8 ]])" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "x=np.array([[1,2],[3,4]])\n", "display(x)\n", "x/np.linalg.norm(x, axis=1)[:,None]" ] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
codescoreitem_ididtitlegenres
015061.00000015071507Three Lives and Only One Death (1996)Comedy
113210.98100313221322Metisse (Café au Lait) (1993)Comedy
212220.98076112231223King of the Hill (1993)Drama
39690.979522970970Hear My Song (1991)Comedy
415540.97866915551555Secret Adventures of Tom Thumb, The (1993)Adventure, Children's
51180.977169119119Maya Lin: A Strong Clear Vision (1994)Documentary
613710.97693813721372Stranger, The (1994)Action
713780.97671813791379Love and Other Catastrophes (1996)Romance
811680.97643511691169Fresh (1994)Drama
98210.976383822822Faces (1968)Drama
\n", "
" ], "text/plain": [ " code score item_id id title \\\n", "0 1506 1.000000 1507 1507 Three Lives and Only One Death (1996) \n", "1 1321 0.981003 1322 1322 Metisse (Café au Lait) (1993) \n", "2 1222 0.980761 1223 1223 King of the Hill (1993) \n", "3 969 0.979522 970 970 Hear My Song (1991) \n", "4 1554 0.978669 1555 1555 Secret Adventures of Tom Thumb, The (1993) \n", "5 118 0.977169 119 119 Maya Lin: A Strong Clear Vision (1994) \n", "6 1371 0.976938 1372 1372 Stranger, The (1994) \n", "7 1378 0.976718 1379 1379 Love and Other Catastrophes (1996) \n", "8 1168 0.976435 1169 1169 Fresh (1994) \n", "9 821 0.976383 822 822 Faces (1968) \n", "\n", " genres \n", "0 Comedy \n", "1 Comedy \n", "2 Drama \n", "3 Comedy \n", "4 Adventure, Children's \n", "5 Documentary \n", "6 Action \n", "7 Romance \n", "8 Drama \n", "9 Drama " ] }, "execution_count": 10, "metadata": {}, "output_type": "execute_result" } ], "source": [ "item=random.choice(list(set(train_ui.indices)))\n", "\n", "embeddings_norm=model.Qi/np.linalg.norm(model.Qi, axis=1)[:,None] # we do not mean-center here\n", "# omitting normalization also makes sense, but items with a greater magnitude will be recommended more often\n", "\n", "similarity_scores=np.dot(embeddings_norm,embeddings_norm[item].T)\n", "top_similar_items=pd.DataFrame(enumerate(similarity_scores), columns=['code', 'score'])\\\n", ".sort_values(by=['score'], ascending=[False])[:10]\n", "\n", "top_similar_items['item_id']=top_similar_items['code'].apply(lambda x: item_code_id[x])\n", "\n", "items=pd.read_csv('./Datasets/ml-100k/movies.csv')\n", "\n", "result=pd.merge(top_similar_items, items, left_on='item_id', right_on='id')\n", "\n", "result" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# project task 5: implement SVD on top baseline (as it is in Surprise library)" ] }, { "cell_type": "code", "execution_count": 11, "metadata": {}, "outputs": [], "source": [ "# making changes to our implementation by considering additional parameters in the gradient descent procedure \n", "# seems to be the fastest option\n", "# please save the output in 'Recommendations generated/ml-100k/Self_SVDBaseline_reco.csv' and\n", "# 'Recommendations generated/ml-100k/Self_SVDBaseline_estimations.csv'\n", "# Done similarly to https://github.com/albertauyeung/matrix-factorization-in-python\n", "\n", "## SOLUTION TASK 5\n", "\n", "from tqdm import tqdm\n", "\n", "\n", "class SVDbaseline():\n", " def __init__(self, train_ui, learning_rate, regularization, nb_factors, iterations):\n", " self.train_ui = train_ui\n", " self.uir = list(zip(*[train_ui.nonzero()[0], train_ui.nonzero()[1], train_ui.data]))\n", " \n", " self.learning_rate = learning_rate\n", " self.regularization = regularization\n", " self.iterations = iterations\n", " self.nb_users, self.nb_items = train_ui.shape\n", " self.nb_ratings = train_ui.nnz\n", " self.nb_factors = nb_factors\n", " \n", " self.Bu = np.random.normal(loc = 0, scale = 1./self.nb_factors, size = (self.nb_users, self.nb_factors))\n", " self.Bi = np.random.normal(loc = 0, scale = 1./self.nb_factors, size = (self.nb_items, self.nb_factors))\n", " \n", " self.Pu = np.random.normal(loc = 0, scale = 1./self.nb_factors, size = (self.nb_users, self.nb_factors))\n", " self.Qi = np.random.normal(loc = 0, scale = 1./self.nb_factors, size = (self.nb_items, self.nb_factors))\n", " \n", " self.bias_i = np.zeros(self.nb_items)\n", " self.bias_u = np.zeros(self.nb_users)\n", "\n", " \n", " def train(self, test_ui = None):\n", " if test_ui != None:\n", " self.test_uir = list(zip(*[test_ui.nonzero()[0],test_ui.nonzero()[1], test_ui.data]))\n", " \n", " self.learning_process = []\n", " pbar = tqdm(range(self.iterations))\n", " \n", " for i in pbar:\n", " pbar.set_description(f'Epoch {i} RMSE: {self.learning_process[-1][1] if i > 0 else 0}. Training epoch {i + 1}...')\n", " np.random.shuffle(self.uir)\n", " self.sgd(self.uir)\n", " \n", " if test_ui == None:\n", " self.learning_process.append([i + 1, self.RMSE_total(self.uir)])\n", " else:\n", " self.learning_process.append([i + 1, self.RMSE_total(self.uir), self.RMSE_total(self.test_uir)])\n", " \n", " \n", " def sgd(self, uir):\n", " for u, i, score in uir:\n", " prediction = self.get_rating(u,i)\n", " e = (score - prediction)\n", " \n", " Pu_update = self.learning_rate * (e * self.Qi[i] - self.regularization * self.Pu[u])\n", " Qi_update = self.learning_rate * (e * self.Pu[u] - self.regularization * self.Qi[i])\n", " \n", " Bu_update = self.learning_rate * (e - self.regularization * self.Bu[u])\n", " Bi_update = self.learning_rate * (e - self.regularization * self.Bi[i])\n", " \n", " self.Bu[u] += Bu_update\n", " self.Bi[i] += Bi_update\n", "\n", " self.Pu[u] += Pu_update\n", " self.Qi[i] += Qi_update\n", " \n", " \n", " def get_rating(self, u, i):\n", " prediction = self.Bu[u] + self.Bi[i] + self.Pu[u].dot(self.Qi[i].T)\n", " return prediction\n", " \n", " \n", " def RMSE_total(self, uir):\n", " RMSE = 0\n", " for u,i, score in uir:\n", " prediction = self.get_rating(u,i)\n", " RMSE += (score - prediction) ** 2\n", " return np.sqrt(RMSE / len(uir))\n", " \n", " \n", " def estimations(self):\n", " self.estimations=\\\n", " self.bias_u[:, np.newaxis] + self.bias_i[np.newaxis:,] + np.dot(self.Pu, self.Qi.T)\n", "\n", " \n", " def recommend(self, user_code_id, item_code_id, topK = 10):\n", " top_k = defaultdict(list)\n", " for nb_user, user in enumerate(self.estimations):\n", " user_rated = self.train_ui.indices[self.train_ui.indptr[nb_user]:self.train_ui.indptr[nb_user + 1]]\n", " for item, score in enumerate(user):\n", " if item not in user_rated and not np.isnan(score):\n", " top_k[user_code_id[nb_user]].append((item_code_id[item], score))\n", " result = []\n", " for uid, item_scores in top_k.items():\n", " item_scores.sort(key = lambda x: x[1], reverse = True)\n", " result.append([uid] + list(chain(*item_scores[:topK])))\n", " return result\n", " \n", " \n", " def estimate(self, user_code_id, item_code_id, test_ui):\n", " result = []\n", " for user, item in zip(*test_ui.nonzero()):\n", " result.append([user_code_id[user], item_code_id[item], \n", " self.estimations[user, item] if not np.isnan(self.estimations[user, item]) else 1])\n", " return result\n" ] }, { "cell_type": "code", "execution_count": 12, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "Epoch 1 RMSE: [1.56608586 1.56623479 1.56621037 1.56632553 1.56623458 1.56635299/it]\n", " 1.56619416 1.56628788 1.56607805 1.56610718 1.5661098 1.56609704\n", " 1.566004 1.56635197 1.56629583 1.56637115 1.56612989 1.56611816\n", " 1.56608223 1.56620134 1.56614774 1.56600187 1.56606093 1.56632669\n", " 1.56606789 1.56604036 1.56625598 1.56613531 1.56633648 1.56600872\n", " 1.56593977 1.56626981 1.56613995 1.5660633 1.56606053 1.56622139\n", " 1.56613882 1.56602313 1.56648528 1.56610116 1.56656389 1.56608295\n", " 1.56625392 1.56620991 1.56619335 1.56639951 1.56619406 1.56632219\n", " 1.56615928 1.56610521 1.5663387 1.56590644 1.56619503 1.56621932\n", " 1.56632845 1.56634084 1.56622762 1.56632436 1.56645543 1.56621592\n", " 1.56602816 1.56626736 1.56624728 1.56613085 1.56611973 1.56632436\n", " 1.56616877 1.56618865 1.56609637 1.56619961 1.56622677 1.5663226\n", " 1.56617601 1.56629154 1.56614605 1.56628346 1.56615301 1.56624603\n", " 1.56635585 1.56632165 1.5663433 1.56628036 1.56619891 1.56619768\n", " 1.56590739 1.56620672 1.56625369 1.56612506 1.5659569 1.56588453\n", " 1.56651464 1.5662788 1.56625525 1.566122 1.56609851 1.5663006\n", "Epoch 1 RMSE: [1.56608586 1.56623479 1.56621037 1.56632553 1.56623458 1.56635299 | 1/40 [00:05<03:32, 5.44s/it]\n", " 1.56619416 1.56628788 1.56607805 1.56610718 1.5661098 1.56609704\n", " 1.566004 1.56635197 1.56629583 1.56637115 1.56612989 1.56611816\n", " 1.56608223 1.56620134 1.56614774 1.56600187 1.56606093 1.56632669\n", " 1.56606789 1.56604036 1.56625598 1.56613531 1.56633648 1.56600872\n", " 1.56593977 1.56626981 1.56613995 1.5660633 1.56606053 1.56622139\n", " 1.56613882 1.56602313 1.56648528 1.56610116 1.56656389 1.56608295\n", " 1.56625392 1.56620991 1.56619335 1.56639951 1.56619406 1.56632219\n", " 1.56615928 1.56610521 1.5663387 1.56590644 1.56619503 1.56621932\n", " 1.56632845 1.56634084 1.56622762 1.56632436 1.56645543 1.56621592\n", " 1.56602816 1.56626736 1.56624728 1.56613085 1.56611973 1.56632436\n", " 1.56616877 1.56618865 1.56609637 1.56619961 1.56622677 1.5663226\n", " 1.56617601 1.56629154 1.56614605 1.56628346 1.56615301 1.56624603\n", " 1.56635585 1.56632165 1.5663433 1.56628036 1.56619891 1.56619768\n", " 1.56590739 1.56620672 1.56625369 1.56612506 1.5659569 1.56588453\n", " 1.56651464 1.5662788 1.56625525 1.566122 1.56609851 1.5663006\n", "Epoch 2 RMSE: [1.24155256 1.24161211 1.24160099 1.24167888 1.24172228 1.2417441 | 2/40 [00:10<03:25, 5.42s/it]\n", " 1.24165504 1.24175179 1.24155206 1.2415503 1.24154766 1.24165204\n", " 1.24151588 1.24175578 1.24168565 1.24174765 1.24165319 1.24164559\n", " 1.24154743 1.24165309 1.24161726 1.24154997 1.24159932 1.24172956\n", " 1.24156102 1.24148321 1.24170529 1.24160801 1.24170631 1.24156325\n", " 1.24146188 1.2416245 1.24160268 1.24154123 1.24154621 1.24159064\n", " 1.24162574 1.24147559 1.24180757 1.2415933 1.24186149 1.24156608\n", " 1.24163722 1.2416763 1.24158823 1.24172209 1.24162708 1.24166432\n", " 1.24165274 1.24154747 1.2417554 1.24148976 1.24161473 1.24160402\n", " 1.24175115 1.24161673 1.24159559 1.24172175 1.24183389 1.24161557\n", " 1.24160484 1.24161826 1.24167579 1.24158516 1.24162002 1.24171992\n", " 1.24154326 1.24161618 1.24152588 1.24164272 1.24159967 1.2416287\n", " 1.24160281 1.24171739 1.24167929 1.24169227 1.24164622 1.24168539\n", " 1.24171969 1.24165194 1.24177983 1.2416788 1.24168927 1.24166932\n", " 1.24151294 1.24171813 1.24164837 1.24155666 1.24164055 1.24142973\n", " 1.24181492 1.24172122 1.24164756 1.24160732 1.24163821 1.24175878\n", "Epoch 2 RMSE: [1.24155256 1.24161211 1.24160099 1.24167888 1.24172228 1.2417441 | 2/40 [00:10<03:25, 5.42s/it]\n", " 1.24165504 1.24175179 1.24155206 1.2415503 1.24154766 1.24165204\n", " 1.24151588 1.24175578 1.24168565 1.24174765 1.24165319 1.24164559\n", " 1.24154743 1.24165309 1.24161726 1.24154997 1.24159932 1.24172956\n", " 1.24156102 1.24148321 1.24170529 1.24160801 1.24170631 1.24156325\n", " 1.24146188 1.2416245 1.24160268 1.24154123 1.24154621 1.24159064\n", " 1.24162574 1.24147559 1.24180757 1.2415933 1.24186149 1.24156608\n", " 1.24163722 1.2416763 1.24158823 1.24172209 1.24162708 1.24166432\n", " 1.24165274 1.24154747 1.2417554 1.24148976 1.24161473 1.24160402\n", " 1.24175115 1.24161673 1.24159559 1.24172175 1.24183389 1.24161557\n", " 1.24160484 1.24161826 1.24167579 1.24158516 1.24162002 1.24171992\n", " 1.24154326 1.24161618 1.24152588 1.24164272 1.24159967 1.2416287\n", " 1.24160281 1.24171739 1.24167929 1.24169227 1.24164622 1.24168539\n", " 1.24171969 1.24165194 1.24177983 1.2416788 1.24168927 1.24166932\n", " 1.24151294 1.24171813 1.24164837 1.24155666 1.24164055 1.24142973\n", " 1.24181492 1.24172122 1.24164756 1.24160732 1.24163821 1.24175878\n", "Epoch 3 RMSE: [1.13235324 1.13239666 1.13237121 1.13244671 1.13249999 1.13250893 | 3/40 [00:16<03:19, 5.40s/it]\n", " 1.13245269 1.13252979 1.13237173 1.1323637 1.13236973 1.13245652\n", " 1.13234872 1.13249684 1.13244719 1.13248902 1.13245581 1.13246051\n", " 1.13235226 1.13245104 1.132409 1.13239075 1.13238513 1.1324869\n", " 1.13238241 1.13230899 1.13249222 1.13241522 1.13245359 1.13237399\n", " 1.1323043 1.13238487 1.13241407 1.13235769 1.1323626 1.13238431\n", " 1.13239682 1.13229717 1.13253777 1.13239335 1.13256654 1.1324005\n", " 1.13240486 1.13246688 1.13238527 1.13247623 1.13242954 1.13242152\n", " 1.13244674 1.13234966 1.13251425 1.13234824 1.13238395 1.13240939\n", " 1.13251224 1.1323703 1.13236787 1.13244705 1.13256574 1.13239854\n", " 1.13242093 1.13239679 1.13246282 1.13237115 1.13242647 1.13247069\n", " 1.13233879 1.1324038 1.13233569 1.13244437 1.13238154 1.13239616\n", " 1.13238994 1.13248695 1.13246892 1.13244241 1.13243931 1.132471\n", " 1.13246322 1.13242626 1.13254761 1.13241684 1.1324755 1.13243697\n", " 1.13236307 1.13249072 1.13242897 1.13235873 1.1324652 1.13230258\n", " 1.13254552 1.13249112 1.1324098 1.13242447 1.13243183 1.13251215\n", "Epoch 3 RMSE: [1.13235324 1.13239666 1.13237121 1.13244671 1.13249999 1.13250893 | 3/40 [00:16<03:19, 5.40s/it] \n", " 1.13245269 1.13252979 1.13237173 1.1323637 1.13236973 1.13245652\n", " 1.13234872 1.13249684 1.13244719 1.13248902 1.13245581 1.13246051\n", " 1.13235226 1.13245104 1.132409 1.13239075 1.13238513 1.1324869\n", " 1.13238241 1.13230899 1.13249222 1.13241522 1.13245359 1.13237399\n", " 1.1323043 1.13238487 1.13241407 1.13235769 1.1323626 1.13238431\n", " 1.13239682 1.13229717 1.13253777 1.13239335 1.13256654 1.1324005\n", " 1.13240486 1.13246688 1.13238527 1.13247623 1.13242954 1.13242152\n", " 1.13244674 1.13234966 1.13251425 1.13234824 1.13238395 1.13240939\n", " 1.13251224 1.1323703 1.13236787 1.13244705 1.13256574 1.13239854\n", " 1.13242093 1.13239679 1.13246282 1.13237115 1.13242647 1.13247069\n", " 1.13233879 1.1324038 1.13233569 1.13244437 1.13238154 1.13239616\n", " 1.13238994 1.13248695 1.13246892 1.13244241 1.13243931 1.132471\n", " 1.13246322 1.13242626 1.13254761 1.13241684 1.1324755 1.13243697\n", " 1.13236307 1.13249072 1.13242897 1.13235873 1.1324652 1.13230258\n", " 1.13254552 1.13249112 1.1324098 1.13242447 1.13243183 1.13251215\n", "Epoch 4 RMSE: [1.07466271 1.07470131 1.07467036 1.07473805 1.07478455 1.07479521 | 4/40 [00:21<03:13, 5.38s/it]\n", " 1.07475274 1.07481765 1.07468793 1.07468635 1.07468858 1.07475369\n", " 1.07467302 1.07476789 1.0747385 1.07475847 1.07475363 1.07476699\n", " 1.07466799 1.07475411 1.07471104 1.07470939 1.07467998 1.07476577\n", " 1.07469556 1.07464409 1.07478016 1.07472552 1.07473274 1.07467987\n", " 1.07463446 1.07468298 1.07472237 1.07467416 1.0746728 1.0746933\n", " 1.07468608 1.07462385 1.07480877 1.07469741 1.07481973 1.07472909\n", " 1.07470395 1.07476503 1.07469568 1.07475898 1.07473831 1.07471373\n", " 1.07473638 1.07466193 1.07479406 1.07468483 1.07467646 1.07472319\n", " 1.07478447 1.07466565 1.07466693 1.07471768 1.07482993 1.07469847\n", " 1.07472755 1.07469956 1.07476093 1.07467442 1.07473166 1.07475135\n", " 1.07465189 1.07470357 1.0746559 1.07474962 1.0746867 1.07469728\n", " 1.07469303 1.0747795 1.07475936 1.07472422 1.07473684 1.07476557\n", " 1.07474013 1.07472305 1.07482831 1.07469053 1.07476533 1.07472113\n", " 1.07468452 1.07477478 1.0747232 1.07467407 1.07476302 1.07464822\n", " 1.07481145 1.07477654 1.07470011 1.07473805 1.07472823 1.0747846\n", "Epoch 4 RMSE: [1.07466271 1.07470131 1.07467036 1.07473805 1.07478455 1.07479521 | 4/40 [00:21<03:13, 5.38s/it]\n", " 1.07475274 1.07481765 1.07468793 1.07468635 1.07468858 1.07475369\n", " 1.07467302 1.07476789 1.0747385 1.07475847 1.07475363 1.07476699\n", " 1.07466799 1.07475411 1.07471104 1.07470939 1.07467998 1.07476577\n", " 1.07469556 1.07464409 1.07478016 1.07472552 1.07473274 1.07467987\n", " 1.07463446 1.07468298 1.07472237 1.07467416 1.0746728 1.0746933\n", " 1.07468608 1.07462385 1.07480877 1.07469741 1.07481973 1.07472909\n", " 1.07470395 1.07476503 1.07469568 1.07475898 1.07473831 1.07471373\n", " 1.07473638 1.07466193 1.07479406 1.07468483 1.07467646 1.07472319\n", " 1.07478447 1.07466565 1.07466693 1.07471768 1.07482993 1.07469847\n", " 1.07472755 1.07469956 1.07476093 1.07467442 1.07473166 1.07475135\n", " 1.07465189 1.07470357 1.0746559 1.07474962 1.0746867 1.07469728\n", " 1.07469303 1.0747795 1.07475936 1.07472422 1.07473684 1.07476557\n", " 1.07474013 1.07472305 1.07482831 1.07469053 1.07476533 1.07472113\n", " 1.07468452 1.07477478 1.0747232 1.07467407 1.07476302 1.07464822\n", " 1.07481145 1.07477654 1.07470011 1.07473805 1.07472823 1.0747846\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Epoch 5 RMSE: [1.03800929 1.03804486 1.03801185 1.03807031 1.0381086 1.03812164 | 5/40 [00:26<03:07, 5.34s/it]\n", " 1.03808771 1.03814441 1.03803487 1.03803894 1.03803719 1.03808587\n", " 1.03802608 1.03809077 1.03807425 1.03807796 1.03808644 1.0381037\n", " 1.03802003 1.03809093 1.03805006 1.03805359 1.0380156 1.03809042\n", " 1.03803814 1.03800851 1.03810592 1.03806769 1.03806038 1.03802149\n", " 1.03799068 1.03802478 1.03806144 1.03802258 1.03801665 1.03803593\n", " 1.03802005 1.03798216 1.03813007 1.0380375 1.03812924 1.03808126\n", " 1.03804579 1.03809947 1.0380401 1.03808686 1.0380806 1.0380505\n", " 1.03806356 1.03801063 1.03811893 1.03804337 1.03801334 1.03806814\n", " 1.03810191 1.03800634 1.03800741 1.03804284 1.03814404 1.03803731\n", " 1.03806659 1.03804163 1.03809557 1.03801779 1.03807147 1.0380792\n", " 1.03800162 1.03804299 1.03800969 1.03808695 1.03803135 1.038039\n", " 1.03803494 1.0381119 1.03808788 1.0380544 1.038071 1.03809686\n", " 1.03806571 1.03805986 1.03814968 1.03801752 1.03809431 1.03804918\n", " 1.03803067 1.03809979 1.0380565 1.03802518 1.03809234 1.03801116\n", " 1.03812669 1.03810362 1.03803495 1.03808056 1.03806172 1.03810283\n", "Epoch 5 RMSE: [1.03800929 1.03804486 1.03801185 1.03807031 1.0381086 1.03812164 | 5/40 [00:26<03:07, 5.34s/it] \n", " 1.03808771 1.03814441 1.03803487 1.03803894 1.03803719 1.03808587\n", " 1.03802608 1.03809077 1.03807425 1.03807796 1.03808644 1.0381037\n", " 1.03802003 1.03809093 1.03805006 1.03805359 1.0380156 1.03809042\n", " 1.03803814 1.03800851 1.03810592 1.03806769 1.03806038 1.03802149\n", " 1.03799068 1.03802478 1.03806144 1.03802258 1.03801665 1.03803593\n", " 1.03802005 1.03798216 1.03813007 1.0380375 1.03812924 1.03808126\n", " 1.03804579 1.03809947 1.0380401 1.03808686 1.0380806 1.0380505\n", " 1.03806356 1.03801063 1.03811893 1.03804337 1.03801334 1.03806814\n", " 1.03810191 1.03800634 1.03800741 1.03804284 1.03814404 1.03803731\n", " 1.03806659 1.03804163 1.03809557 1.03801779 1.03807147 1.0380792\n", " 1.03800162 1.03804299 1.03800969 1.03808695 1.03803135 1.038039\n", " 1.03803494 1.0381119 1.03808788 1.0380544 1.038071 1.03809686\n", " 1.03806571 1.03805986 1.03814968 1.03801752 1.03809431 1.03804918\n", " 1.03803067 1.03809979 1.0380565 1.03802518 1.03809234 1.03801116\n", " 1.03812669 1.03810362 1.03803495 1.03808056 1.03806172 1.03810283\n", "Epoch 6 RMSE: [1.01278106 1.01281346 1.01278068 1.01283119 1.01286253 1.01287725 | 6/40 [00:32<03:01, 5.34s/it]\n", " 1.01284813 1.01289844 1.01280524 1.01281318 1.01280764 1.01284597\n", " 1.0128004 1.01284775 1.01283798 1.01283157 1.01284598 1.01286571\n", " 1.01279572 1.01285386 1.01281524 1.01281951 1.01278064 1.01284734\n", " 1.01280344 1.01279181 1.01286024 1.01283408 1.01282006 1.01278895\n", " 1.01276798 1.0127944 1.01282596 1.01279438 1.01278651 1.01280405\n", " 1.01278447 1.01276186 1.01288362 1.01280432 1.01287541 1.01285337\n", " 1.01281475 1.01286091 1.01280873 1.01284521 1.01284636 1.01281644\n", " 1.01282038 1.01278519 1.01287396 1.01281957 1.01277949 1.01283511\n", " 1.01285294 1.01277564 1.01277606 1.01280241 1.01289215 1.01280229\n", " 1.01283142 1.01280953 1.01285489 1.01278901 1.01283634 1.01283779\n", " 1.01277714 1.01280965 1.01278649 1.01284963 1.01280238 1.01280733\n", " 1.01280404 1.01287196 1.01284502 1.01281565 1.01283226 1.01285444\n", " 1.0128232 1.01282363 1.01290081 1.01277807 1.01285255 1.0128091\n", " 1.01279976 1.01285455 1.01281843 1.01279979 1.01284806 1.01279096\n", " 1.01287528 1.01286024 1.01279983 1.01284487 1.01282365 1.01285443\n", "Epoch 6 RMSE: [1.01278106 1.01281346 1.01278068 1.01283119 1.01286253 1.01287725 | 6/40 [00:32<03:01, 5.34s/it]\n", " 1.01284813 1.01289844 1.01280524 1.01281318 1.01280764 1.01284597\n", " 1.0128004 1.01284775 1.01283798 1.01283157 1.01284598 1.01286571\n", " 1.01279572 1.01285386 1.01281524 1.01281951 1.01278064 1.01284734\n", " 1.01280344 1.01279181 1.01286024 1.01283408 1.01282006 1.01278895\n", " 1.01276798 1.0127944 1.01282596 1.01279438 1.01278651 1.01280405\n", " 1.01278447 1.01276186 1.01288362 1.01280432 1.01287541 1.01285337\n", " 1.01281475 1.01286091 1.01280873 1.01284521 1.01284636 1.01281644\n", " 1.01282038 1.01278519 1.01287396 1.01281957 1.01277949 1.01283511\n", " 1.01285294 1.01277564 1.01277606 1.01280241 1.01289215 1.01280229\n", " 1.01283142 1.01280953 1.01285489 1.01278901 1.01283634 1.01283779\n", " 1.01277714 1.01280965 1.01278649 1.01284963 1.01280238 1.01280733\n", " 1.01280404 1.01287196 1.01284502 1.01281565 1.01283226 1.01285444\n", " 1.0128232 1.01282363 1.01290081 1.01277807 1.01285255 1.0128091\n", " 1.01279976 1.01285455 1.01281843 1.01279979 1.01284806 1.01279096\n", " 1.01287528 1.01286024 1.01279983 1.01284487 1.01282365 1.01285443\n", "Epoch 7 RMSE: [0.99426685 0.99429572 0.99426321 0.99430772 0.99433392 0.99434846 | 7/40 [00:37<02:55, 5.32s/it]\n", " 0.99432325 0.99436813 0.99428813 0.99429818 0.99429055 0.99432117\n", " 0.99428649 0.99432252 0.99431576 0.9943039 0.99432044 0.99434125\n", " 0.99428292 0.9943309 0.99429504 0.99429871 0.99426144 0.99432172\n", " 0.99428245 0.99428387 0.99433104 0.99431362 0.99429617 0.99427082\n", " 0.99425688 0.99427838 0.99430429 0.99427835 0.99427015 0.99428558\n", " 0.99426474 0.99425276 0.99435449 0.9942857 0.9943422 0.9943355\n", " 0.99429719 0.99433638 0.9942905 0.9943203 0.99432589 0.99429669\n", " 0.99429491 0.99427262 0.99434599 0.99430542 0.99426183 0.9943147\n", " 0.99432265 0.99426017 0.99425968 0.99427974 0.99435904 0.99428242\n", " 0.99431024 0.99429114 0.99432892 0.99427363 0.9943143 0.99431342\n", " 0.9942645 0.99429132 0.99427521 0.99432601 0.99428714 0.9942887\n", " 0.99428658 0.99434702 0.99431826 0.99429346 0.99430848 0.99432786\n", " 0.99429779 0.99430248 0.99436866 0.99425719 0.99432654 0.9942863\n", " 0.99428098 0.99432623 0.9942954 0.99428635 0.9943206 0.99427945\n", " 0.99434296 0.99433319 0.99428054 0.99432182 0.99430013 0.99432376\n", "Epoch 7 RMSE: [0.99426685 0.99429572 0.99426321 0.99430772 0.99433392 0.99434846 | 7/40 [00:37<02:55, 5.32s/it] \n", " 0.99432325 0.99436813 0.99428813 0.99429818 0.99429055 0.99432117\n", " 0.99428649 0.99432252 0.99431576 0.9943039 0.99432044 0.99434125\n", " 0.99428292 0.9943309 0.99429504 0.99429871 0.99426144 0.99432172\n", " 0.99428245 0.99428387 0.99433104 0.99431362 0.99429617 0.99427082\n", " 0.99425688 0.99427838 0.99430429 0.99427835 0.99427015 0.99428558\n", " 0.99426474 0.99425276 0.99435449 0.9942857 0.9943422 0.9943355\n", " 0.99429719 0.99433638 0.9942905 0.9943203 0.99432589 0.99429669\n", " 0.99429491 0.99427262 0.99434599 0.99430542 0.99426183 0.9943147\n", " 0.99432265 0.99426017 0.99425968 0.99427974 0.99435904 0.99428242\n", " 0.99431024 0.99429114 0.99432892 0.99427363 0.9943143 0.99431342\n", " 0.9942645 0.99429132 0.99427521 0.99432601 0.99428714 0.9942887\n", " 0.99428658 0.99434702 0.99431826 0.99429346 0.99430848 0.99432786\n", " 0.99429779 0.99430248 0.99436866 0.99425719 0.99432654 0.9942863\n", " 0.99428098 0.99432623 0.9942954 0.99428635 0.9943206 0.99427945\n", " 0.99434296 0.99433319 0.99428054 0.99432182 0.99430013 0.99432376\n", "Epoch 8 RMSE: [0.98032841 0.98035351 0.98032262 0.98036189 0.98038399 0.98039754 | 8/40 [00:42<02:50, 5.32s/it]\n", " 0.98037568 0.98041579 0.98034677 0.98035787 0.98034877 0.98037456\n", " 0.98034705 0.98037687 0.98037041 0.98035616 0.98037272 0.98039435\n", " 0.98034519 0.98038506 0.98035139 0.98035463 0.98031996 0.98037481\n", " 0.98033782 0.9803488 0.98038092 0.98036887 0.9803511 0.98032956\n", " 0.98032061 0.98033857 0.98035925 0.98033791 0.9803305 0.9803432\n", " 0.980323 0.98031789 0.98040359 0.98034402 0.98038948 0.98039226\n", " 0.98035571 0.98038895 0.98034794 0.98037323 0.98038169 0.98035356\n", " 0.98034802 0.98033558 0.98039613 0.9803653 0.98032118 0.98037004\n", " 0.9803722 0.98032129 0.98032048 0.98033548 0.98040586 0.98033933\n", " 0.9803661 0.98034865 0.98038025 0.98033444 0.980369 0.98036679\n", " 0.980327 0.98034959 0.98033851 0.98037913 0.98034745 0.98034623\n", " 0.98034566 0.9803988 0.98037013 0.98034868 0.98036169 0.98037883\n", " 0.9803517 0.98035807 0.98041573 0.98031508 0.98037873 0.98034165\n", " 0.9803389 0.98037641 0.98035089 0.98034798 0.98037176 0.98034142\n", " 0.98039063 0.98038458 0.98033873 0.98037451 0.98035442 0.98037335\n", "Epoch 8 RMSE: [0.98032841 0.98035351 0.98032262 0.98036189 0.98038399 0.98039754 | 8/40 [00:42<02:50, 5.32s/it]\n", " 0.98037568 0.98041579 0.98034677 0.98035787 0.98034877 0.98037456\n", " 0.98034705 0.98037687 0.98037041 0.98035616 0.98037272 0.98039435\n", " 0.98034519 0.98038506 0.98035139 0.98035463 0.98031996 0.98037481\n", " 0.98033782 0.9803488 0.98038092 0.98036887 0.9803511 0.98032956\n", " 0.98032061 0.98033857 0.98035925 0.98033791 0.9803305 0.9803432\n", " 0.980323 0.98031789 0.98040359 0.98034402 0.98038948 0.98039226\n", " 0.98035571 0.98038895 0.98034794 0.98037323 0.98038169 0.98035356\n", " 0.98034802 0.98033558 0.98039613 0.9803653 0.98032118 0.98037004\n", " 0.9803722 0.98032129 0.98032048 0.98033548 0.98040586 0.98033933\n", " 0.9803661 0.98034865 0.98038025 0.98033444 0.980369 0.98036679\n", " 0.980327 0.98034959 0.98033851 0.98037913 0.98034745 0.98034623\n", " 0.98034566 0.9803988 0.98037013 0.98034868 0.98036169 0.98037883\n", " 0.9803517 0.98035807 0.98041573 0.98031508 0.98037873 0.98034165\n", " 0.9803389 0.98037641 0.98035089 0.98034798 0.98037176 0.98034142\n", " 0.98039063 0.98038458 0.98033873 0.98037451 0.98035442 0.98037335\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Epoch 9 RMSE: [0.9694492 0.96947007 0.96944108 0.9694767 0.96949523 0.9695074 | 9/40 [00:47<02:44, 5.30s/it]\n", " 0.9694882 0.96952424 0.96946422 0.96947599 0.96946601 0.96948819\n", " 0.96946618 0.96949149 0.9694846 0.96946943 0.96948569 0.96950732\n", " 0.96946534 0.96949901 0.96946766 0.96947022 0.9694381 0.96948868\n", " 0.96945359 0.96947024 0.96949185 0.96948388 0.96946674 0.96944816\n", " 0.96944223 0.96945801 0.96947428 0.96945628 0.96944982 0.96946021\n", " 0.96944124 0.969441 0.96951416 0.96946196 0.96949921 0.96950764\n", " 0.96947305 0.96950168 0.96946441 0.96948692 0.96949659 0.96946984\n", " 0.96946248 0.96945644 0.96950706 0.96948278 0.96944039 0.96948504\n", " 0.96948394 0.96944163 0.96944026 0.96945154 0.96951425 0.96945632\n", " 0.96948171 0.96946562 0.96949195 0.96945461 0.96948294 0.96948093\n", " 0.96944749 0.96946766 0.96945944 0.96949223 0.96946654 0.96946313\n", " 0.96946376 0.96951044 0.96948237 0.96946441 0.96947514 0.96949051\n", " 0.96946559 0.9694736 0.96952395 0.96943319 0.96949175 0.96945789\n", " 0.96945613 0.9694875 0.96946644 0.96946757 0.9694842 0.96946167\n", " 0.96949991 0.96949691 0.96945647 0.96948745 0.96946921 0.96948448\n", "Epoch 9 RMSE: [0.9694492 0.96947007 0.96944108 0.9694767 0.96949523 0.9695074 | 9/40 [00:47<02:44, 5.30s/it]\n", " 0.9694882 0.96952424 0.96946422 0.96947599 0.96946601 0.96948819\n", " 0.96946618 0.96949149 0.9694846 0.96946943 0.96948569 0.96950732\n", " 0.96946534 0.96949901 0.96946766 0.96947022 0.9694381 0.96948868\n", " 0.96945359 0.96947024 0.96949185 0.96948388 0.96946674 0.96944816\n", " 0.96944223 0.96945801 0.96947428 0.96945628 0.96944982 0.96946021\n", " 0.96944124 0.969441 0.96951416 0.96946196 0.96949921 0.96950764\n", " 0.96947305 0.96950168 0.96946441 0.96948692 0.96949659 0.96946984\n", " 0.96946248 0.96945644 0.96950706 0.96948278 0.96944039 0.96948504\n", " 0.96948394 0.96944163 0.96944026 0.96945154 0.96951425 0.96945632\n", " 0.96948171 0.96946562 0.96949195 0.96945461 0.96948294 0.96948093\n", " 0.96944749 0.96946766 0.96945944 0.96949223 0.96946654 0.96946313\n", " 0.96946376 0.96951044 0.96948237 0.96946441 0.96947514 0.96949051\n", " 0.96946559 0.9694736 0.96952395 0.96943319 0.96949175 0.96945789\n", " 0.96945613 0.9694875 0.96946644 0.96946757 0.9694842 0.96946167\n", " 0.96949991 0.96949691 0.96945647 0.96948745 0.96946921 0.96948448\n", "Epoch 10 RMSE: [0.96069644 0.96071369 0.96068629 0.96071866 0.96073453 0.96074565 | 10/40 [00:53<02:39, 5.33s/it]\n", " 0.96072891 0.9607607 0.96070909 0.96072049 0.96071018 0.96073019\n", " 0.96071215 0.96073435 0.96072659 0.96071167 0.96072647 0.96074826\n", " 0.960712 0.96074059 0.96071141 0.96071321 0.96068387 0.96073057\n", " 0.96069694 0.96071751 0.96073128 0.96072665 0.96071027 0.96069396\n", " 0.96069037 0.96070451 0.9607168 0.9607018 0.96069658 0.96070475\n", " 0.96068715 0.96069004 0.96075274 0.96070714 0.9607381 0.96074965\n", " 0.96071718 0.96074202 0.96070836 0.96072835 0.96073855 0.96071347\n", " 0.96070484 0.96070427 0.96074646 0.96072675 0.96068734 0.96072739\n", " 0.96072377 0.96068881 0.96068735 0.96069571 0.96075138 0.96070094\n", " 0.96072483 0.96070974 0.96073153 0.96070112 0.96072459 0.96072312\n", " 0.9606946 0.96071269 0.96070658 0.96073322 0.96071228 0.96070711\n", " 0.96070885 0.96074969 0.96072308 0.96070752 0.9607166 0.96073044\n", " 0.96070855 0.96071651 0.96076101 0.96067945 0.96073295 0.96070218\n", " 0.96070069 0.96072713 0.96070969 0.96071358 0.96072465 0.96070806\n", " 0.96073813 0.9607371 0.96070178 0.9607277 0.96071176 0.96072425\n", "Epoch 10 RMSE: [0.96069644 0.96071369 0.96068629 0.96071866 0.96073453 0.96074565 | 10/40 [00:53<02:39, 5.33s/it]\n", " 0.96072891 0.9607607 0.96070909 0.96072049 0.96071018 0.96073019\n", " 0.96071215 0.96073435 0.96072659 0.96071167 0.96072647 0.96074826\n", " 0.960712 0.96074059 0.96071141 0.96071321 0.96068387 0.96073057\n", " 0.96069694 0.96071751 0.96073128 0.96072665 0.96071027 0.96069396\n", " 0.96069037 0.96070451 0.9607168 0.9607018 0.96069658 0.96070475\n", " 0.96068715 0.96069004 0.96075274 0.96070714 0.9607381 0.96074965\n", " 0.96071718 0.96074202 0.96070836 0.96072835 0.96073855 0.96071347\n", " 0.96070484 0.96070427 0.96074646 0.96072675 0.96068734 0.96072739\n", " 0.96072377 0.96068881 0.96068735 0.96069571 0.96075138 0.96070094\n", " 0.96072483 0.96070974 0.96073153 0.96070112 0.96072459 0.96072312\n", " 0.9606946 0.96071269 0.96070658 0.96073322 0.96071228 0.96070711\n", " 0.96070885 0.96074969 0.96072308 0.96070752 0.9607166 0.96073044\n", " 0.96070855 0.96071651 0.96076101 0.96067945 0.96073295 0.96070218\n", " 0.96070069 0.96072713 0.96070969 0.96071358 0.96072465 0.96070806\n", " 0.96073813 0.9607371 0.96070178 0.9607277 0.96071176 0.96072425\n", "Epoch 11 RMSE: [0.95355938 0.95357278 0.95354808 0.95357698 0.95359097 0.95360068 | 11/40 [00:58<02:35, 5.35s/it]\n", " 0.95358614 0.95361422 0.95356927 0.9535803 0.95357015 0.9535882\n", " 0.95357319 0.95359291 0.95358431 0.9535702 0.95358364 0.95360555\n", " 0.95357351 0.95359801 0.95357109 0.95357231 0.95354613 0.95358883\n", " 0.95355681 0.95357905 0.95358773 0.95358514 0.95357018 0.95355558\n", " 0.95355366 0.95356612 0.9535756 0.95356257 0.95355855 0.95356523\n", " 0.95354888 0.95355379 0.95360803 0.95356794 0.95359406 0.95360724\n", " 0.95357679 0.95359892 0.9535678 0.953586 0.95359621 0.95357294\n", " 0.95356397 0.95356679 0.95360226 0.953586 0.95354944 0.95358578\n", " 0.95358091 0.95355168 0.95355014 0.95355603 0.95360613 0.9535614\n", " 0.95358404 0.95356969 0.95358771 0.95356319 0.95358236 0.9535817\n", " 0.95355692 0.95357342 0.95356858 0.95359029 0.95357357 0.95356678\n", " 0.95356958 0.95360547 0.95358004 0.95356694 0.95357409 0.95358682\n", " 0.95356711 0.95357535 0.95361502 0.95354186 0.95358997 0.95356258\n", " 0.95356117 0.95358343 0.95356932 0.95357491 0.95358221 0.95356947\n", " 0.95359337 0.95359393 0.95356266 0.95358437 0.95357061 0.95358076\n", "Epoch 11 RMSE: [0.95355938 0.95357278 0.95354808 0.95357698 0.95359097 0.95360068 | 11/40 [00:58<02:35, 5.35s/it] \n", " 0.95358614 0.95361422 0.95356927 0.9535803 0.95357015 0.9535882\n", " 0.95357319 0.95359291 0.95358431 0.9535702 0.95358364 0.95360555\n", " 0.95357351 0.95359801 0.95357109 0.95357231 0.95354613 0.95358883\n", " 0.95355681 0.95357905 0.95358773 0.95358514 0.95357018 0.95355558\n", " 0.95355366 0.95356612 0.9535756 0.95356257 0.95355855 0.95356523\n", " 0.95354888 0.95355379 0.95360803 0.95356794 0.95359406 0.95360724\n", " 0.95357679 0.95359892 0.9535678 0.953586 0.95359621 0.95357294\n", " 0.95356397 0.95356679 0.95360226 0.953586 0.95354944 0.95358578\n", " 0.95358091 0.95355168 0.95355014 0.95355603 0.95360613 0.9535614\n", " 0.95358404 0.95356969 0.95358771 0.95356319 0.95358236 0.9535817\n", " 0.95355692 0.95357342 0.95356858 0.95359029 0.95357357 0.95356678\n", " 0.95356958 0.95360547 0.95358004 0.95356694 0.95357409 0.95358682\n", " 0.95356711 0.95357535 0.95361502 0.95354186 0.95358997 0.95356258\n", " 0.95356117 0.95358343 0.95356932 0.95357491 0.95358221 0.95356947\n", " 0.95359337 0.95359393 0.95356266 0.95358437 0.95357061 0.95358076\n", "Epoch 12 RMSE: [0.94762464 0.94763434 0.94761214 0.94763842 0.94765098 0.94765922 | 12/40 [01:04<02:34, 5.50s/it]\n", " 0.94764632 0.94767125 0.94763215 0.94764233 0.9476331 0.9476496\n", " 0.94763679 0.9476547 0.947645 0.94763224 0.94764431 0.94766595\n", " 0.94763762 0.94765851 0.94763371 0.94763451 0.94761027 0.94765038\n", " 0.94761978 0.94764277 0.94764766 0.94764674 0.9476331 0.94762025\n", " 0.94761923 0.94763032 0.94763753 0.94762615 0.94762322 0.94762832\n", " 0.94761375 0.94762016 0.94766708 0.94763166 0.94765359 0.94766761\n", " 0.94763909 0.9476585 0.9476303 0.94764697 0.94765692 0.94763502\n", " 0.94762597 0.94763179 0.94766158 0.94764789 0.94761432 0.94764702\n", " 0.94764131 0.94761675 0.94761562 0.94761929 0.94766425 0.9476249\n", " 0.94764622 0.94763286 0.94764731 0.94762761 0.9476432 0.9476433\n", " 0.94762154 0.94763687 0.94763272 0.94765063 0.94763754 0.94762912\n", " 0.94763314 0.94766451 0.94764053 0.94762926 0.94763502 0.9476469\n", " 0.94762933 0.94763735 0.94767281 0.94760695 0.94765069 0.94762589\n", " 0.94762436 0.9476433 0.94763175 0.94763864 0.94764304 0.9476333\n", " 0.94765225 0.94765414 0.94762648 0.9476444 0.94763244 0.94764101\n", "Epoch 12 RMSE: [0.94762464 0.94763434 0.94761214 0.94763842 0.94765098 0.94765922 | 12/40 [01:04<02:34, 5.50s/it] \n", " 0.94764632 0.94767125 0.94763215 0.94764233 0.9476331 0.9476496\n", " 0.94763679 0.9476547 0.947645 0.94763224 0.94764431 0.94766595\n", " 0.94763762 0.94765851 0.94763371 0.94763451 0.94761027 0.94765038\n", " 0.94761978 0.94764277 0.94764766 0.94764674 0.9476331 0.94762025\n", " 0.94761923 0.94763032 0.94763753 0.94762615 0.94762322 0.94762832\n", " 0.94761375 0.94762016 0.94766708 0.94763166 0.94765359 0.94766761\n", " 0.94763909 0.9476585 0.9476303 0.94764697 0.94765692 0.94763502\n", " 0.94762597 0.94763179 0.94766158 0.94764789 0.94761432 0.94764702\n", " 0.94764131 0.94761675 0.94761562 0.94761929 0.94766425 0.9476249\n", " 0.94764622 0.94763286 0.94764731 0.94762761 0.9476432 0.9476433\n", " 0.94762154 0.94763687 0.94763272 0.94765063 0.94763754 0.94762912\n", " 0.94763314 0.94766451 0.94764053 0.94762926 0.94763502 0.9476469\n", " 0.94762933 0.94763735 0.94767281 0.94760695 0.94765069 0.94762589\n", " 0.94762436 0.9476433 0.94763175 0.94763864 0.94764304 0.9476333\n", " 0.94765225 0.94765414 0.94762648 0.9476444 0.94763244 0.94764101\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Epoch 13 RMSE: [0.94250355 0.94251 0.94249004 0.94251424 0.94252492 0.94253214 | 13/40 [01:09<02:27, 5.47s/it]\n", " 0.94252126 0.94254282 0.94250924 0.94251867 0.94250963 0.94252498\n", " 0.9425141 0.94253041 0.94251997 0.9425084 0.94251923 0.94254045\n", " 0.94251483 0.94253318 0.94251044 0.94251076 0.94248893 0.9425257\n", " 0.9424967 0.9425198 0.94252196 0.94252218 0.94251019 0.94249833\n", " 0.94249833 0.94250832 0.94251331 0.94250359 0.9425015 0.94250558\n", " 0.94249227 0.94249932 0.9425401 0.94250916 0.94252765 0.94254207\n", " 0.94251521 0.94253293 0.94250672 0.94252199 0.9425315 0.94251133\n", " 0.94250243 0.94250991 0.94253504 0.94252347 0.94249281 0.94252258\n", " 0.94251625 0.94249575 0.94249447 0.94249627 0.94253718 0.9425021\n", " 0.94252222 0.94250936 0.94252149 0.94250569 0.94251802 0.94251918\n", " 0.9424994 0.94251436 0.94251051 0.94252501 0.94251518 0.94250555\n", " 0.9425103 0.94253793 0.94251515 0.94250544 0.94251047 0.9425212\n", " 0.94250546 0.94251334 0.94254524 0.94248572 0.94252542 0.94250341\n", " 0.94250169 0.94251769 0.94250879 0.94251611 0.94251834 0.9425109\n", " 0.94252582 0.94252845 0.94250394 0.94251885 0.94250869 0.94251583\n", "Epoch 13 RMSE: [0.94250355 0.94251 0.94249004 0.94251424 0.94252492 0.94253214 | 13/40 [01:09<02:27, 5.47s/it]\n", " 0.94252126 0.94254282 0.94250924 0.94251867 0.94250963 0.94252498\n", " 0.9425141 0.94253041 0.94251997 0.9425084 0.94251923 0.94254045\n", " 0.94251483 0.94253318 0.94251044 0.94251076 0.94248893 0.9425257\n", " 0.9424967 0.9425198 0.94252196 0.94252218 0.94251019 0.94249833\n", " 0.94249833 0.94250832 0.94251331 0.94250359 0.9425015 0.94250558\n", " 0.94249227 0.94249932 0.9425401 0.94250916 0.94252765 0.94254207\n", " 0.94251521 0.94253293 0.94250672 0.94252199 0.9425315 0.94251133\n", " 0.94250243 0.94250991 0.94253504 0.94252347 0.94249281 0.94252258\n", " 0.94251625 0.94249575 0.94249447 0.94249627 0.94253718 0.9425021\n", " 0.94252222 0.94250936 0.94252149 0.94250569 0.94251802 0.94251918\n", " 0.9424994 0.94251436 0.94251051 0.94252501 0.94251518 0.94250555\n", " 0.9425103 0.94253793 0.94251515 0.94250544 0.94251047 0.9425212\n", " 0.94250546 0.94251334 0.94254524 0.94248572 0.94252542 0.94250341\n", " 0.94250169 0.94251769 0.94250879 0.94251611 0.94251834 0.9425109\n", " 0.94252582 0.94252845 0.94250394 0.94251885 0.94250869 0.94251583\n", "Epoch 14 RMSE: [0.93798076 0.93798437 0.93796693 0.9379891 0.93799854 0.93800461 | 14/40 [01:15<02:21, 5.43s/it]\n", " 0.93799533 0.93801408 0.93798501 0.93799373 0.93798536 0.93799954\n", " 0.93799004 0.93800529 0.93799412 0.9379837 0.93799326 0.93801418\n", " 0.93799101 0.93800713 0.93798609 0.93798598 0.93796628 0.9380003\n", " 0.93797297 0.93799535 0.93799583 0.93799682 0.9379862 0.93797543\n", " 0.93797584 0.93798491 0.93798849 0.93797985 0.93797869 0.93798162\n", " 0.93796949 0.93797718 0.93801296 0.93798512 0.93800125 0.93801539\n", " 0.93799016 0.93800621 0.93798216 0.93799629 0.93800518 0.93798651\n", " 0.93797791 0.93798688 0.93800812 0.93799799 0.93797028 0.9379971\n", " 0.93799052 0.93797319 0.93797204 0.93797251 0.93800985 0.93797854\n", " 0.93799726 0.93798526 0.93799513 0.93798247 0.93799221 0.93799416\n", " 0.93797625 0.93799032 0.93798676 0.93799882 0.93799135 0.93798097\n", " 0.93798645 0.93801038 0.93798914 0.93798081 0.93798517 0.93799518\n", " 0.93798079 0.93798842 0.93801718 0.9379633 0.9379996 0.93797977\n", " 0.93797768 0.93799121 0.9379846 0.93799218 0.93799281 0.93798726\n", " 0.93799863 0.93800195 0.93798054 0.93799249 0.93798406 0.93798985\n", "Epoch 14 RMSE: [0.93798076 0.93798437 0.93796693 0.9379891 0.93799854 0.93800461 | 14/40 [01:15<02:21, 5.43s/it]\n", " 0.93799533 0.93801408 0.93798501 0.93799373 0.93798536 0.93799954\n", " 0.93799004 0.93800529 0.93799412 0.9379837 0.93799326 0.93801418\n", " 0.93799101 0.93800713 0.93798609 0.93798598 0.93796628 0.9380003\n", " 0.93797297 0.93799535 0.93799583 0.93799682 0.9379862 0.93797543\n", " 0.93797584 0.93798491 0.93798849 0.93797985 0.93797869 0.93798162\n", " 0.93796949 0.93797718 0.93801296 0.93798512 0.93800125 0.93801539\n", " 0.93799016 0.93800621 0.93798216 0.93799629 0.93800518 0.93798651\n", " 0.93797791 0.93798688 0.93800812 0.93799799 0.93797028 0.9379971\n", " 0.93799052 0.93797319 0.93797204 0.93797251 0.93800985 0.93797854\n", " 0.93799726 0.93798526 0.93799513 0.93798247 0.93799221 0.93799416\n", " 0.93797625 0.93799032 0.93798676 0.93799882 0.93799135 0.93798097\n", " 0.93798645 0.93801038 0.93798914 0.93798081 0.93798517 0.93799518\n", " 0.93798079 0.93798842 0.93801718 0.9379633 0.9379996 0.93797977\n", " 0.93797768 0.93799121 0.9379846 0.93799218 0.93799281 0.93798726\n", " 0.93799863 0.93800195 0.93798054 0.93799249 0.93798406 0.93798985\n", "Epoch 15 RMSE: [0.93398928 0.93399056 0.93397506 0.93399548 0.93400396 0.9340091 | 15/40 [01:20<02:15, 5.40s/it]\n", " 0.93400102 0.93401733 0.93399189 0.93399998 0.93399231 0.93400579\n", " 0.93399741 0.93401133 0.9339997 0.93399032 0.93399897 0.93401929\n", " 0.93399826 0.93401242 0.93399297 0.93399285 0.93397483 0.93400631\n", " 0.93398069 0.93400214 0.93400115 0.93400292 0.93399373 0.93398363\n", " 0.93398453 0.93399267 0.93399499 0.93398727 0.93398691 0.93398891\n", " 0.93397804 0.93398596 0.9340175 0.93399267 0.93400663 0.93402026\n", " 0.93399664 0.93401128 0.93398916 0.93400218 0.93401032 0.93399291\n", " 0.93398512 0.93399469 0.93401287 0.93400412 0.93397885 0.93400312\n", " 0.93399637 0.93398184 0.93398086 0.93398001 0.93401387 0.93398599\n", " 0.93400372 0.93399243 0.93400024 0.93399044 0.93399796 0.93400065\n", " 0.93398425 0.9339976 0.93399424 0.93400442 0.93399891 0.93398768\n", " 0.93399366 0.93401464 0.93399497 0.9339878 0.93399139 0.93400064\n", " 0.93398764 0.93399508 0.93402106 0.9339724 0.93400506 0.93398751\n", " 0.93398521 0.93399692 0.93399176 0.93399928 0.9339989 0.93399464\n", " 0.93400337 0.93400736 0.93398835 0.93399786 0.93399088 0.93399557\n", "Epoch 15 RMSE: [0.93398928 0.93399056 0.93397506 0.93399548 0.93400396 0.9340091 | 15/40 [01:20<02:15, 5.40s/it]\n", " 0.93400102 0.93401733 0.93399189 0.93399998 0.93399231 0.93400579\n", " 0.93399741 0.93401133 0.9339997 0.93399032 0.93399897 0.93401929\n", " 0.93399826 0.93401242 0.93399297 0.93399285 0.93397483 0.93400631\n", " 0.93398069 0.93400214 0.93400115 0.93400292 0.93399373 0.93398363\n", " 0.93398453 0.93399267 0.93399499 0.93398727 0.93398691 0.93398891\n", " 0.93397804 0.93398596 0.9340175 0.93399267 0.93400663 0.93402026\n", " 0.93399664 0.93401128 0.93398916 0.93400218 0.93401032 0.93399291\n", " 0.93398512 0.93399469 0.93401287 0.93400412 0.93397885 0.93400312\n", " 0.93399637 0.93398184 0.93398086 0.93398001 0.93401387 0.93398599\n", " 0.93400372 0.93399243 0.93400024 0.93399044 0.93399796 0.93400065\n", " 0.93398425 0.9339976 0.93399424 0.93400442 0.93399891 0.93398768\n", " 0.93399366 0.93401464 0.93399497 0.9339878 0.93399139 0.93400064\n", " 0.93398764 0.93399508 0.93402106 0.9339724 0.93400506 0.93398751\n", " 0.93398521 0.93399692 0.93399176 0.93399928 0.9339989 0.93399464\n", " 0.93400337 0.93400736 0.93398835 0.93399786 0.93399088 0.93399557\n", "Epoch 16 RMSE: [0.93042093 0.93042015 0.93040655 0.93042527 0.93043286 0.93043727 | 16/40 [01:26<02:09, 5.41s/it]\n", " 0.93043041 0.93044445 0.93042238 0.93042974 0.93042288 0.93043552\n", " 0.93042784 0.93044086 0.93042916 0.93042058 0.93042842 0.93044836\n", " 0.93042894 0.93044149 0.93042365 0.93042324 0.93040678 0.93043597\n", " 0.9304118 0.93043223 0.93043048 0.93043253 0.93042468 0.93041534\n", " 0.93041628 0.93042401 0.93042486 0.93041796 0.93041837 0.93041988\n", " 0.93041002 0.93041795 0.93044559 0.93042359 0.9304357 0.9304487\n", " 0.93042638 0.93043997 0.9304195 0.93043162 0.9304391 0.93042313\n", " 0.93041562 0.93042584 0.93044147 0.93043342 0.93041079 0.93043265\n", " 0.93042586 0.93041375 0.9304129 0.9304109 0.93044197 0.93041686\n", " 0.9304336 0.93042296 0.93042911 0.93042181 0.93042738 0.93043063\n", " 0.93041565 0.93042823 0.93042496 0.93043338 0.93042973 0.93041794\n", " 0.93042433 0.9304427 0.93042455 0.93041802 0.93042136 0.93042983\n", " 0.93041796 0.93042522 0.9304489 0.93040451 0.93043423 0.93041856\n", " 0.93041611 0.93042624 0.93042245 0.93042987 0.93042875 0.93042551\n", " 0.93043183 0.93043633 0.93041954 0.93042684 0.93042105 0.93042486\n", "Epoch 16 RMSE: [0.93042093 0.93042015 0.93040655 0.93042527 0.93043286 0.93043727 | 16/40 [01:26<02:09, 5.41s/it]\n", " 0.93043041 0.93044445 0.93042238 0.93042974 0.93042288 0.93043552\n", " 0.93042784 0.93044086 0.93042916 0.93042058 0.93042842 0.93044836\n", " 0.93042894 0.93044149 0.93042365 0.93042324 0.93040678 0.93043597\n", " 0.9304118 0.93043223 0.93043048 0.93043253 0.93042468 0.93041534\n", " 0.93041628 0.93042401 0.93042486 0.93041796 0.93041837 0.93041988\n", " 0.93041002 0.93041795 0.93044559 0.93042359 0.9304357 0.9304487\n", " 0.93042638 0.93043997 0.9304195 0.93043162 0.9304391 0.93042313\n", " 0.93041562 0.93042584 0.93044147 0.93043342 0.93041079 0.93043265\n", " 0.93042586 0.93041375 0.9304129 0.9304109 0.93044197 0.93041686\n", " 0.9304336 0.93042296 0.93042911 0.93042181 0.93042738 0.93043063\n", " 0.93041565 0.93042823 0.93042496 0.93043338 0.93042973 0.93041794\n", " 0.93042433 0.9304427 0.93042455 0.93041802 0.93042136 0.93042983\n", " 0.93041796 0.93042522 0.9304489 0.93040451 0.93043423 0.93041856\n", " 0.93041611 0.93042624 0.93042245 0.93042987 0.93042875 0.93042551\n", " 0.93043183 0.93043633 0.93041954 0.93042684 0.93042105 0.93042486\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Epoch 17 RMSE: [0.92698472 0.92698189 0.92697029 0.92698759 0.92699418 0.92699818 | 17/40 [01:31<02:05, 5.46s/it]\n", " 0.92699221 0.92700424 0.92698509 0.92699188 0.92698567 0.92699737\n", " 0.9269906 0.92700279 0.92699082 0.92698323 0.92699036 0.92700964\n", " 0.92699157 0.92700278 0.9269865 0.92698585 0.92697084 0.92699785\n", " 0.92697549 0.92699443 0.92699201 0.9269943 0.9269878 0.92697917\n", " 0.92698027 0.92698719 0.92698728 0.92698103 0.92698189 0.92698295\n", " 0.92697412 0.92698176 0.9270063 0.92698655 0.92699721 0.92700975\n", " 0.92698851 0.92700131 0.92698213 0.92699329 0.92700012 0.92698532\n", " 0.92697867 0.92698893 0.9270026 0.92699526 0.92697461 0.92699453\n", " 0.92698782 0.92697772 0.926977 0.92697401 0.92700286 0.92698005\n", " 0.92699588 0.9269857 0.92699051 0.92698505 0.92698915 0.92699334\n", " 0.92697904 0.926991 0.92698767 0.92699497 0.92699268 0.92698034\n", " 0.92698725 0.92700337 0.92698655 0.92698071 0.92698357 0.92699151\n", " 0.92698051 0.92698746 0.92700935 0.92696875 0.92699563 0.92698192\n", " 0.92697911 0.92698793 0.92698517 0.9269926 0.92699082 0.92698846\n", " 0.92699289 0.92699772 0.92698279 0.92698859 0.92698379 0.92698658\n", "Epoch 17 RMSE: [0.92698472 0.92698189 0.92697029 0.92698759 0.92699418 0.92699818 | 17/40 [01:31<02:05, 5.46s/it]\n", " 0.92699221 0.92700424 0.92698509 0.92699188 0.92698567 0.92699737\n", " 0.9269906 0.92700279 0.92699082 0.92698323 0.92699036 0.92700964\n", " 0.92699157 0.92700278 0.9269865 0.92698585 0.92697084 0.92699785\n", " 0.92697549 0.92699443 0.92699201 0.9269943 0.9269878 0.92697917\n", " 0.92698027 0.92698719 0.92698728 0.92698103 0.92698189 0.92698295\n", " 0.92697412 0.92698176 0.9270063 0.92698655 0.92699721 0.92700975\n", " 0.92698851 0.92700131 0.92698213 0.92699329 0.92700012 0.92698532\n", " 0.92697867 0.92698893 0.9270026 0.92699526 0.92697461 0.92699453\n", " 0.92698782 0.92697772 0.926977 0.92697401 0.92700286 0.92698005\n", " 0.92699588 0.9269857 0.92699051 0.92698505 0.92698915 0.92699334\n", " 0.92697904 0.926991 0.92698767 0.92699497 0.92699268 0.92698034\n", " 0.92698725 0.92700337 0.92698655 0.92698071 0.92698357 0.92699151\n", " 0.92698051 0.92698746 0.92700935 0.92696875 0.92699563 0.92698192\n", " 0.92697911 0.92698793 0.92698517 0.9269926 0.92699082 0.92698846\n", " 0.92699289 0.92699772 0.92698279 0.92698859 0.92698379 0.92698658\n", "Epoch 18 RMSE: [0.92362926 0.92362489 0.92361492 0.92363082 0.92363679 0.92364012 | 18/40 [01:37<02:00, 5.48s/it]\n", " 0.92363518 0.92364557 0.92362881 0.92363496 0.92362938 0.92364061\n", " 0.92363423 0.92364591 0.92363376 0.92362695 0.92363327 0.92365196\n", " 0.92363535 0.92364531 0.92363039 0.92362945 0.92361549 0.92364085\n", " 0.92361968 0.92363758 0.92363499 0.92363735 0.92363191 0.92362378\n", " 0.92362507 0.92363132 0.92363078 0.92362495 0.92362642 0.92362715\n", " 0.92361891 0.9236264 0.92364824 0.92363049 0.92363992 0.92365173\n", " 0.92363177 0.92364356 0.92362588 0.92363617 0.92364242 0.92362883\n", " 0.9236225 0.92363297 0.92364479 0.92363799 0.92361949 0.92363751\n", " 0.92363077 0.92362254 0.9236219 0.92361828 0.92364459 0.92362415\n", " 0.92363908 0.9236297 0.92363321 0.92362939 0.92363225 0.92363668\n", " 0.92362338 0.92363479 0.92363149 0.92363763 0.92363657 0.92362393\n", " 0.92363112 0.9236452 0.92362948 0.92362444 0.92362703 0.92363438\n", " 0.92362435 0.92363111 0.92365086 0.92361401 0.92363836 0.92362616\n", " 0.92362323 0.92363094 0.92362919 0.92363638 0.92363398 0.92363232\n", " 0.92363498 0.92364038 0.92362689 0.92363114 0.92362751 0.92362984\n", "Epoch 18 RMSE: [0.92362926 0.92362489 0.92361492 0.92363082 0.92363679 0.92364012 | 18/40 [01:37<02:00, 5.48s/it]\n", " 0.92363518 0.92364557 0.92362881 0.92363496 0.92362938 0.92364061\n", " 0.92363423 0.92364591 0.92363376 0.92362695 0.92363327 0.92365196\n", " 0.92363535 0.92364531 0.92363039 0.92362945 0.92361549 0.92364085\n", " 0.92361968 0.92363758 0.92363499 0.92363735 0.92363191 0.92362378\n", " 0.92362507 0.92363132 0.92363078 0.92362495 0.92362642 0.92362715\n", " 0.92361891 0.9236264 0.92364824 0.92363049 0.92363992 0.92365173\n", " 0.92363177 0.92364356 0.92362588 0.92363617 0.92364242 0.92362883\n", " 0.9236225 0.92363297 0.92364479 0.92363799 0.92361949 0.92363751\n", " 0.92363077 0.92362254 0.9236219 0.92361828 0.92364459 0.92362415\n", " 0.92363908 0.9236297 0.92363321 0.92362939 0.92363225 0.92363668\n", " 0.92362338 0.92363479 0.92363149 0.92363763 0.92363657 0.92362393\n", " 0.92363112 0.9236452 0.92362948 0.92362444 0.92362703 0.92363438\n", " 0.92362435 0.92363111 0.92365086 0.92361401 0.92363836 0.92362616\n", " 0.92362323 0.92363094 0.92362919 0.92363638 0.92363398 0.92363232\n", " 0.92363498 0.92364038 0.92362689 0.92363114 0.92362751 0.92362984\n", "Epoch 19 RMSE: [0.9202722 0.92026655 0.92025776 0.92027279 0.92027805 0.92028091 | 19/40 [01:42<01:55, 5.49s/it]\n", " 0.92027693 0.92028573 0.92027088 0.92027643 0.92027157 0.92028222\n", " 0.92027638 0.92028733 0.92027514 0.920269 0.92027464 0.92029287\n", " 0.9202775 0.9202864 0.92027258 0.92027147 0.92025877 0.92028233\n", " 0.92026266 0.92027929 0.92027637 0.92027888 0.92027439 0.9202669\n", " 0.92026812 0.92027377 0.92027256 0.92026754 0.92026922 0.92026963\n", " 0.92026225 0.92026929 0.9202889 0.92027268 0.92028133 0.92029215\n", " 0.92027367 0.92028458 0.9202681 0.9202776 0.92028315 0.92027072\n", " 0.92026489 0.92027528 0.92028567 0.92027947 0.92026279 0.92027904\n", " 0.92027232 0.92026576 0.92026525 0.92026096 0.92028552 0.92026678\n", " 0.92028081 0.92027199 0.92027431 0.92027208 0.92027388 0.92027868\n", " 0.92026621 0.92027692 0.92027373 0.92027892 0.92027891 0.92026608\n", " 0.92027341 0.92028568 0.9202713 0.92026672 0.92026915 0.92027597\n", " 0.92026659 0.92027319 0.92029131 0.92025732 0.92027982 0.92026883\n", " 0.92026578 0.92027255 0.92027135 0.92027837 0.92027576 0.92027461\n", " 0.92027606 0.9202818 0.92026966 0.92027279 0.9202698 0.92027134\n", "Epoch 19 RMSE: [0.9202722 0.92026655 0.92025776 0.92027279 0.92027805 0.92028091 | 19/40 [01:42<01:55, 5.49s/it] \n", " 0.92027693 0.92028573 0.92027088 0.92027643 0.92027157 0.92028222\n", " 0.92027638 0.92028733 0.92027514 0.920269 0.92027464 0.92029287\n", " 0.9202775 0.9202864 0.92027258 0.92027147 0.92025877 0.92028233\n", " 0.92026266 0.92027929 0.92027637 0.92027888 0.92027439 0.9202669\n", " 0.92026812 0.92027377 0.92027256 0.92026754 0.92026922 0.92026963\n", " 0.92026225 0.92026929 0.9202889 0.92027268 0.92028133 0.92029215\n", " 0.92027367 0.92028458 0.9202681 0.9202776 0.92028315 0.92027072\n", " 0.92026489 0.92027528 0.92028567 0.92027947 0.92026279 0.92027904\n", " 0.92027232 0.92026576 0.92026525 0.92026096 0.92028552 0.92026678\n", " 0.92028081 0.92027199 0.92027431 0.92027208 0.92027388 0.92027868\n", " 0.92026621 0.92027692 0.92027373 0.92027892 0.92027891 0.92026608\n", " 0.92027341 0.92028568 0.9202713 0.92026672 0.92026915 0.92027597\n", " 0.92026659 0.92027319 0.92029131 0.92025732 0.92027982 0.92026883\n", " 0.92026578 0.92027255 0.92027135 0.92027837 0.92027576 0.92027461\n", " 0.92027606 0.9202818 0.92026966 0.92027279 0.9202698 0.92027134\n", "Epoch 20 RMSE: [0.91666156 0.91665455 0.91664738 0.91666122 0.9166659 0.91666838 | 20/40 [01:48<01:50, 5.51s/it]\n", " 0.91666504 0.91667252 0.91665953 0.91666455 0.91666051 0.91667035\n", " 0.91666505 0.91667536 0.91666344 0.91665763 0.91666284 0.91668043\n", " 0.91666592 0.9166739 0.9166615 0.91666031 0.91664839 0.91667029\n", " 0.91665194 0.91666736 0.91666441 0.91666697 0.91666345 0.91665631\n", " 0.9166576 0.91666268 0.91666107 0.9166564 0.91665857 0.91665861\n", " 0.91665185 0.91665875 0.91667617 0.91666153 0.91666915 0.91667932\n", " 0.91666192 0.9166722 0.91665696 0.91666562 0.91667068 0.91665921\n", " 0.91665371 0.91666413 0.91667325 0.91666726 0.91665241 0.916667\n", " 0.91666047 0.91665533 0.91665473 0.91665018 0.91667274 0.9166559\n", " 0.91666898 0.91666083 0.91666236 0.91666103 0.91666202 0.91666718\n", " 0.91665535 0.91666549 0.9166623 0.91666687 0.91666767 0.91665461\n", " 0.91666194 0.91667289 0.91665935 0.91665533 0.91665786 0.91666408\n", " 0.91665529 0.9166617 0.91667848 0.91664732 0.91666755 0.9166579\n", " 0.91665467 0.91666073 0.91666025 0.91666701 0.91666428 0.91666323\n", " 0.9166637 0.91666939 0.9166586 0.91666086 0.91665847 0.91665946\n", "Epoch 20 RMSE: [0.91666156 0.91665455 0.91664738 0.91666122 0.9166659 0.91666838 | 20/40 [01:48<01:50, 5.51s/it] \n", " 0.91666504 0.91667252 0.91665953 0.91666455 0.91666051 0.91667035\n", " 0.91666505 0.91667536 0.91666344 0.91665763 0.91666284 0.91668043\n", " 0.91666592 0.9166739 0.9166615 0.91666031 0.91664839 0.91667029\n", " 0.91665194 0.91666736 0.91666441 0.91666697 0.91666345 0.91665631\n", " 0.9166576 0.91666268 0.91666107 0.9166564 0.91665857 0.91665861\n", " 0.91665185 0.91665875 0.91667617 0.91666153 0.91666915 0.91667932\n", " 0.91666192 0.9166722 0.91665696 0.91666562 0.91667068 0.91665921\n", " 0.91665371 0.91666413 0.91667325 0.91666726 0.91665241 0.916667\n", " 0.91666047 0.91665533 0.91665473 0.91665018 0.91667274 0.9166559\n", " 0.91666898 0.91666083 0.91666236 0.91666103 0.91666202 0.91666718\n", " 0.91665535 0.91666549 0.9166623 0.91666687 0.91666767 0.91665461\n", " 0.91666194 0.91667289 0.91665935 0.91665533 0.91665786 0.91666408\n", " 0.91665529 0.9166617 0.91667848 0.91664732 0.91666755 0.9166579\n", " 0.91665467 0.91666073 0.91666025 0.91666701 0.91666428 0.91666323\n", " 0.9166637 0.91666939 0.9166586 0.91666086 0.91665847 0.91665946\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Epoch 21 RMSE: [0.91283752 0.91282974 0.9128236 0.91283663 0.91284083 0.91284309 | 21/40 [01:53<01:44, 5.50s/it]\n", " 0.9128404 0.91284653 0.91283531 0.91283973 0.91283633 0.91284547\n", " 0.91284061 0.91285035 0.91283849 0.91283336 0.91283811 0.91285517\n", " 0.91284141 0.91284872 0.91283724 0.91283593 0.9128249 0.9128454\n", " 0.91282823 0.91284246 0.91283963 0.91284204 0.91283933 0.91283249\n", " 0.91283388 0.91283849 0.91283658 0.91283225 0.91283468 0.91283467\n", " 0.91282848 0.91283496 0.91285066 0.91283736 0.91284421 0.91285377\n", " 0.91283725 0.91284687 0.91283282 0.91284078 0.91284517 0.91283473\n", " 0.91282961 0.91283996 0.91284796 0.91284224 0.91282884 0.91284226\n", " 0.91283589 0.91283165 0.91283131 0.91282642 0.91284729 0.91283187\n", " 0.9128443 0.91283663 0.91283746 0.9128372 0.91283734 0.91284271\n", " 0.91283141 0.91284098 0.91283792 0.91284188 0.91284333 0.9128304\n", " 0.91283774 0.91284748 0.91283487 0.91283126 0.91283346 0.91283916\n", " 0.91283115 0.91283726 0.91285272 0.91282397 0.91284272 0.91283394\n", " 0.9128307 0.91283596 0.91283599 0.91284244 0.91283969 0.91283905\n", " 0.91283838 0.9128444 0.91283468 0.91283594 0.9128343 0.91283488\n", "Epoch 21 RMSE: [0.91283752 0.91282974 0.9128236 0.91283663 0.91284083 0.91284309 | 21/40 [01:53<01:44, 5.50s/it]\n", " 0.9128404 0.91284653 0.91283531 0.91283973 0.91283633 0.91284547\n", " 0.91284061 0.91285035 0.91283849 0.91283336 0.91283811 0.91285517\n", " 0.91284141 0.91284872 0.91283724 0.91283593 0.9128249 0.9128454\n", " 0.91282823 0.91284246 0.91283963 0.91284204 0.91283933 0.91283249\n", " 0.91283388 0.91283849 0.91283658 0.91283225 0.91283468 0.91283467\n", " 0.91282848 0.91283496 0.91285066 0.91283736 0.91284421 0.91285377\n", " 0.91283725 0.91284687 0.91283282 0.91284078 0.91284517 0.91283473\n", " 0.91282961 0.91283996 0.91284796 0.91284224 0.91282884 0.91284226\n", " 0.91283589 0.91283165 0.91283131 0.91282642 0.91284729 0.91283187\n", " 0.9128443 0.91283663 0.91283746 0.9128372 0.91283734 0.91284271\n", " 0.91283141 0.91284098 0.91283792 0.91284188 0.91284333 0.9128304\n", " 0.91283774 0.91284748 0.91283487 0.91283126 0.91283346 0.91283916\n", " 0.91283115 0.91283726 0.91285272 0.91282397 0.91284272 0.91283394\n", " 0.9128307 0.91283596 0.91283599 0.91284244 0.91283969 0.91283905\n", " 0.91283838 0.9128444 0.91283468 0.91283594 0.9128343 0.91283488\n", "Epoch 22 RMSE: [0.90862876 0.90862005 0.90861508 0.90862718 0.90863095 0.90863288 | 22/40 [01:59<01:37, 5.44s/it]\n", " 0.90863064 0.9086358 0.90862568 0.90862993 0.9086271 0.90863562\n", " 0.9086312 0.90864052 0.9086287 0.90862419 0.90862848 0.90864493\n", " 0.90863178 0.90863881 0.90862796 0.90862649 0.90861647 0.90863556\n", " 0.90861948 0.90863286 0.90862987 0.90863216 0.90863013 0.90862362\n", " 0.90862522 0.90862918 0.90862711 0.90862302 0.90862573 0.90862563\n", " 0.90861975 0.90862616 0.90864019 0.90862808 0.90863447 0.90864323\n", " 0.90862771 0.90863671 0.90862361 0.90863087 0.90863492 0.90862527\n", " 0.90862065 0.90863067 0.90863788 0.90863235 0.90862026 0.90863245\n", " 0.90862624 0.90862301 0.90862272 0.90861752 0.90863698 0.90862293\n", " 0.90863469 0.90862738 0.90862779 0.9086281 0.90862765 0.90863348\n", " 0.90862257 0.90863162 0.90862858 0.908632 0.90863408 0.90862118\n", " 0.90862819 0.90863686 0.90862546 0.90862185 0.90862422 0.90862952\n", " 0.90862179 0.90862795 0.90864228 0.90861564 0.90863277 0.90862511\n", " 0.90862163 0.90862635 0.90862695 0.90863294 0.90863001 0.90862984\n", " 0.90862832 0.90863447 0.90862573 0.90862639 0.90862504 0.90862545\n", "Epoch 22 RMSE: [0.90862876 0.90862005 0.90861508 0.90862718 0.90863095 0.90863288 | 22/40 [01:59<01:37, 5.44s/it]\n", " 0.90863064 0.9086358 0.90862568 0.90862993 0.9086271 0.90863562\n", " 0.9086312 0.90864052 0.9086287 0.90862419 0.90862848 0.90864493\n", " 0.90863178 0.90863881 0.90862796 0.90862649 0.90861647 0.90863556\n", " 0.90861948 0.90863286 0.90862987 0.90863216 0.90863013 0.90862362\n", " 0.90862522 0.90862918 0.90862711 0.90862302 0.90862573 0.90862563\n", " 0.90861975 0.90862616 0.90864019 0.90862808 0.90863447 0.90864323\n", " 0.90862771 0.90863671 0.90862361 0.90863087 0.90863492 0.90862527\n", " 0.90862065 0.90863067 0.90863788 0.90863235 0.90862026 0.90863245\n", " 0.90862624 0.90862301 0.90862272 0.90861752 0.90863698 0.90862293\n", " 0.90863469 0.90862738 0.90862779 0.9086281 0.90862765 0.90863348\n", " 0.90862257 0.90863162 0.90862858 0.908632 0.90863408 0.90862118\n", " 0.90862819 0.90863686 0.90862546 0.90862185 0.90862422 0.90862952\n", " 0.90862179 0.90862795 0.90864228 0.90861564 0.90863277 0.90862511\n", " 0.90862163 0.90862635 0.90862695 0.90863294 0.90863001 0.90862984\n", " 0.90862832 0.90863447 0.90862573 0.90862639 0.90862504 0.90862545\n", "Epoch 23 RMSE: [0.90413804 0.90412898 0.90412468 0.90413607 0.90413945 0.90414125 | 23/40 [02:04<01:32, 5.43s/it]\n", " 0.9041396 0.90414373 0.90413492 0.90413868 0.90413633 0.90414429\n", " 0.90414011 0.90414907 0.90413746 0.90413324 0.90413714 0.90415318\n", " 0.90414084 0.90414677 0.9041371 0.90413587 0.90412617 0.9041443\n", " 0.90412931 0.90414124 0.90413871 0.90414085 0.90413952 0.90413332\n", " 0.90413465 0.90413849 0.90413614 0.90413231 0.90413525 0.90413502\n", " 0.90412984 0.9041356 0.90414823 0.90413724 0.9041429 0.9041511\n", " 0.90413653 0.90414515 0.90413269 0.90413962 0.90414302 0.90413452\n", " 0.9041299 0.90413971 0.90414611 0.90414085 0.90413019 0.9041412\n", " 0.90413503 0.90413261 0.90413235 0.90412719 0.9041452 0.90413208\n", " 0.90414334 0.90413667 0.90413636 0.90413764 0.90413655 0.90414236\n", " 0.90413193 0.90414038 0.90413757 0.90414066 0.90414295 0.90413023\n", " 0.90413756 0.90414501 0.90413438 0.90413109 0.90413336 0.90413824\n", " 0.90413121 0.90413686 0.90415009 0.90412568 0.90414126 0.90413447\n", " 0.90413114 0.90413515 0.90413606 0.90414199 0.9041392 0.90413878\n", " 0.90413679 0.9041429 0.9041351 0.9041351 0.9041343 0.90413417\n", "Epoch 23 RMSE: [0.90413804 0.90412898 0.90412468 0.90413607 0.90413945 0.90414125 | 23/40 [02:04<01:32, 5.43s/it] \n", " 0.9041396 0.90414373 0.90413492 0.90413868 0.90413633 0.90414429\n", " 0.90414011 0.90414907 0.90413746 0.90413324 0.90413714 0.90415318\n", " 0.90414084 0.90414677 0.9041371 0.90413587 0.90412617 0.9041443\n", " 0.90412931 0.90414124 0.90413871 0.90414085 0.90413952 0.90413332\n", " 0.90413465 0.90413849 0.90413614 0.90413231 0.90413525 0.90413502\n", " 0.90412984 0.9041356 0.90414823 0.90413724 0.9041429 0.9041511\n", " 0.90413653 0.90414515 0.90413269 0.90413962 0.90414302 0.90413452\n", " 0.9041299 0.90413971 0.90414611 0.90414085 0.90413019 0.9041412\n", " 0.90413503 0.90413261 0.90413235 0.90412719 0.9041452 0.90413208\n", " 0.90414334 0.90413667 0.90413636 0.90413764 0.90413655 0.90414236\n", " 0.90413193 0.90414038 0.90413757 0.90414066 0.90414295 0.90413023\n", " 0.90413756 0.90414501 0.90413438 0.90413109 0.90413336 0.90413824\n", " 0.90413121 0.90413686 0.90415009 0.90412568 0.90414126 0.90413447\n", " 0.90413114 0.90413515 0.90413606 0.90414199 0.9041392 0.90413878\n", " 0.90413679 0.9041429 0.9041351 0.9041351 0.9041343 0.90413417\n", "Epoch 24 RMSE: [0.89907662 0.8990668 0.89906357 0.89907419 0.89907741 0.89907888 | 24/40 [02:09<01:26, 5.41s/it]\n", " 0.89907772 0.89908096 0.89907327 0.8990765 0.89907485 0.89908202\n", " 0.89907831 0.89908678 0.89907543 0.89907163 0.89907522 0.89909089\n", " 0.89907903 0.89908453 0.89907549 0.89907407 0.89906521 0.89908209\n", " 0.89906812 0.89907931 0.89907655 0.89907867 0.89907793 0.89907214\n", " 0.89907358 0.89907686 0.89907437 0.89907061 0.89907375 0.89907354\n", " 0.89906882 0.89907428 0.89908577 0.89907553 0.89908064 0.89908845\n", " 0.89907463 0.8990828 0.89907141 0.8990774 0.89908054 0.89907265\n", " 0.89906845 0.89907799 0.89908376 0.89907871 0.89906908 0.89907908\n", " 0.89907309 0.89907144 0.89907128 0.89906589 0.89908272 0.89907067\n", " 0.89908136 0.89907512 0.89907424 0.89907603 0.89907476 0.89908061\n", " 0.89907059 0.89907845 0.89907592 0.89907843 0.89908131 0.89906856\n", " 0.8990758 0.89908258 0.89907264 0.89906964 0.8990718 0.89907615\n", " 0.89906964 0.89907504 0.89908746 0.89906472 0.89907913 0.89907292\n", " 0.89906957 0.89907334 0.89907439 0.89908009 0.89907713 0.89907718\n", " 0.89907448 0.89908066 0.89907363 0.89907298 0.89907268 0.89907213\n", "Epoch 24 RMSE: [0.89907662 0.8990668 0.89906357 0.89907419 0.89907741 0.89907888 | 24/40 [02:09<01:26, 5.41s/it]\n", " 0.89907772 0.89908096 0.89907327 0.8990765 0.89907485 0.89908202\n", " 0.89907831 0.89908678 0.89907543 0.89907163 0.89907522 0.89909089\n", " 0.89907903 0.89908453 0.89907549 0.89907407 0.89906521 0.89908209\n", " 0.89906812 0.89907931 0.89907655 0.89907867 0.89907793 0.89907214\n", " 0.89907358 0.89907686 0.89907437 0.89907061 0.89907375 0.89907354\n", " 0.89906882 0.89907428 0.89908577 0.89907553 0.89908064 0.89908845\n", " 0.89907463 0.8990828 0.89907141 0.8990774 0.89908054 0.89907265\n", " 0.89906845 0.89907799 0.89908376 0.89907871 0.89906908 0.89907908\n", " 0.89907309 0.89907144 0.89907128 0.89906589 0.89908272 0.89907067\n", " 0.89908136 0.89907512 0.89907424 0.89907603 0.89907476 0.89908061\n", " 0.89907059 0.89907845 0.89907592 0.89907843 0.89908131 0.89906856\n", " 0.8990758 0.89908258 0.89907264 0.89906964 0.8990718 0.89907615\n", " 0.89906964 0.89907504 0.89908746 0.89906472 0.89907913 0.89907292\n", " 0.89906957 0.89907334 0.89907439 0.89908009 0.89907713 0.89907718\n", " 0.89907448 0.89908066 0.89907363 0.89907298 0.89907268 0.89907213\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Epoch 25 RMSE: [0.89370798 0.89369786 0.89369547 0.89370534 0.89370814 0.89370966 | 25/40 [02:15<01:21, 5.41s/it]\n", " 0.89370887 0.89371131 0.89370455 0.89370735 0.89370609 0.89371293\n", " 0.89370943 0.89371749 0.8937063 0.89370298 0.89370615 0.89372122\n", " 0.89371009 0.89371521 0.8937069 0.89370548 0.8936969 0.89371291\n", " 0.89369981 0.89371011 0.89370761 0.89370949 0.89370938 0.89370374\n", " 0.89370508 0.89370819 0.89370566 0.89370211 0.89370534 0.89370515\n", " 0.89370067 0.89370587 0.89371625 0.8937068 0.89371147 0.89371878\n", " 0.89370568 0.89371347 0.89370271 0.89370827 0.89371115 0.89370386\n", " 0.89369979 0.89370926 0.89371453 0.89370945 0.89370087 0.89371004\n", " 0.89370425 0.89370305 0.89370289 0.89369752 0.89371338 0.89370207\n", " 0.89371228 0.89370642 0.89370512 0.89370744 0.89370581 0.89371169\n", " 0.89370227 0.89370958 0.8937071 0.89370936 0.89371212 0.89369993\n", " 0.89370708 0.89371297 0.89370391 0.89370097 0.89370312 0.89370719\n", " 0.89370079 0.89370631 0.89371789 0.89369666 0.89371004 0.89370439\n", " 0.89370115 0.89370452 0.89370561 0.89371122 0.89370834 0.89370833\n", " 0.89370529 0.89371142 0.89370493 0.89370407 0.89370392 0.89370333\n", "Epoch 25 RMSE: [0.89370798 0.89369786 0.89369547 0.89370534 0.89370814 0.89370966 | 25/40 [02:15<01:21, 5.41s/it]\n", " 0.89370887 0.89371131 0.89370455 0.89370735 0.89370609 0.89371293\n", " 0.89370943 0.89371749 0.8937063 0.89370298 0.89370615 0.89372122\n", " 0.89371009 0.89371521 0.8937069 0.89370548 0.8936969 0.89371291\n", " 0.89369981 0.89371011 0.89370761 0.89370949 0.89370938 0.89370374\n", " 0.89370508 0.89370819 0.89370566 0.89370211 0.89370534 0.89370515\n", " 0.89370067 0.89370587 0.89371625 0.8937068 0.89371147 0.89371878\n", " 0.89370568 0.89371347 0.89370271 0.89370827 0.89371115 0.89370386\n", " 0.89369979 0.89370926 0.89371453 0.89370945 0.89370087 0.89371004\n", " 0.89370425 0.89370305 0.89370289 0.89369752 0.89371338 0.89370207\n", " 0.89371228 0.89370642 0.89370512 0.89370744 0.89370581 0.89371169\n", " 0.89370227 0.89370958 0.8937071 0.89370936 0.89371212 0.89369993\n", " 0.89370708 0.89371297 0.89370391 0.89370097 0.89370312 0.89370719\n", " 0.89370079 0.89370631 0.89371789 0.89369666 0.89371004 0.89370439\n", " 0.89370115 0.89370452 0.89370561 0.89371122 0.89370834 0.89370833\n", " 0.89370529 0.89371142 0.89370493 0.89370407 0.89370392 0.89370333\n", "Epoch 26 RMSE: [0.88777452 0.88776404 0.88776209 0.88777159 0.8877742 0.88777536 | 26/40 [02:20<01:15, 5.41s/it]\n", " 0.88777483 0.88777687 0.88777084 0.88777334 0.88777255 0.88777866\n", " 0.88777563 0.88778338 0.88777248 0.88776928 0.88777233 0.88778684\n", " 0.88777623 0.88778091 0.88777323 0.88777168 0.88776391 0.88777884\n", " 0.88776672 0.8877762 0.8877737 0.88777547 0.88777577 0.88777037\n", " 0.88777171 0.88777438 0.88777181 0.8877685 0.88777184 0.88777158\n", " 0.88776741 0.88777229 0.88778191 0.88777304 0.88777743 0.88778429\n", " 0.88777192 0.88777927 0.8877693 0.88777439 0.88777672 0.88777015\n", " 0.88776649 0.88777547 0.88778011 0.8877754 0.88776771 0.88777587\n", " 0.88777033 0.88776988 0.88776984 0.88776426 0.88777885 0.88776857\n", " 0.88777836 0.88777281 0.8877712 0.88777399 0.88777201 0.88777811\n", " 0.88776886 0.88777573 0.88777328 0.88777537 0.88777872 0.88776631\n", " 0.88777333 0.88777863 0.88777018 0.88776732 0.88776958 0.88777324\n", " 0.88776721 0.88777264 0.8877833 0.8877637 0.887776 0.88777094\n", " 0.88776767 0.88777068 0.88777194 0.88777734 0.88777446 0.88777454\n", " 0.88777107 0.88777733 0.88777152 0.88777029 0.8877705 0.88776943\n", "Epoch 26 RMSE: [0.88777452 0.88776404 0.88776209 0.88777159 0.8877742 0.88777536 | 26/40 [02:20<01:15, 5.41s/it]\n", " 0.88777483 0.88777687 0.88777084 0.88777334 0.88777255 0.88777866\n", " 0.88777563 0.88778338 0.88777248 0.88776928 0.88777233 0.88778684\n", " 0.88777623 0.88778091 0.88777323 0.88777168 0.88776391 0.88777884\n", " 0.88776672 0.8877762 0.8877737 0.88777547 0.88777577 0.88777037\n", " 0.88777171 0.88777438 0.88777181 0.8877685 0.88777184 0.88777158\n", " 0.88776741 0.88777229 0.88778191 0.88777304 0.88777743 0.88778429\n", " 0.88777192 0.88777927 0.8877693 0.88777439 0.88777672 0.88777015\n", " 0.88776649 0.88777547 0.88778011 0.8877754 0.88776771 0.88777587\n", " 0.88777033 0.88776988 0.88776984 0.88776426 0.88777885 0.88776857\n", " 0.88777836 0.88777281 0.8877712 0.88777399 0.88777201 0.88777811\n", " 0.88776886 0.88777573 0.88777328 0.88777537 0.88777872 0.88776631\n", " 0.88777333 0.88777863 0.88777018 0.88776732 0.88776958 0.88777324\n", " 0.88776721 0.88777264 0.8877833 0.8877637 0.887776 0.88777094\n", " 0.88776767 0.88777068 0.88777194 0.88777734 0.88777446 0.88777454\n", " 0.88777107 0.88777733 0.88777152 0.88777029 0.8877705 0.88776943\n", "Epoch 27 RMSE: [0.88166026 0.8816496 0.88164825 0.88165724 0.88165963 0.88166075 | 27/40 [02:26<01:10, 5.44s/it]\n", " 0.88166049 0.88166201 0.88165648 0.88165893 0.8816584 0.88166404\n", " 0.88166115 0.88166863 0.88165802 0.88165512 0.88165797 0.88167212\n", " 0.88166186 0.88166624 0.88165913 0.88165746 0.88165008 0.88166428\n", " 0.88165282 0.88166154 0.8816593 0.88166088 0.88166162 0.8816565\n", " 0.8816578 0.8816602 0.8816576 0.88165442 0.8816578 0.88165741\n", " 0.88165372 0.88165831 0.88166713 0.88165879 0.88166269 0.88166924\n", " 0.88165758 0.88166455 0.88165518 0.88165984 0.88166193 0.88165596\n", " 0.88165245 0.88166108 0.88166543 0.88166085 0.88165406 0.88166145\n", " 0.88165595 0.88165587 0.88165593 0.88165041 0.88166417 0.88165442\n", " 0.88166378 0.88165867 0.8816567 0.88165994 0.88165765 0.88166377\n", " 0.88165487 0.8816613 0.88165896 0.88166087 0.88166418 0.88165212\n", " 0.88165914 0.88166378 0.88165596 0.88165334 0.8816556 0.88165884\n", " 0.88165323 0.88165833 0.88166829 0.88164991 0.88166128 0.88165687\n", " 0.88165369 0.88165651 0.8816577 0.88166279 0.88166009 0.88166023\n", " 0.88165638 0.88166268 0.88165743 0.88165596 0.88165641 0.88165515\n", "Epoch 27 RMSE: [0.88166026 0.8816496 0.88164825 0.88165724 0.88165963 0.88166075 | 27/40 [02:26<01:10, 5.44s/it] \n", " 0.88166049 0.88166201 0.88165648 0.88165893 0.8816584 0.88166404\n", " 0.88166115 0.88166863 0.88165802 0.88165512 0.88165797 0.88167212\n", " 0.88166186 0.88166624 0.88165913 0.88165746 0.88165008 0.88166428\n", " 0.88165282 0.88166154 0.8816593 0.88166088 0.88166162 0.8816565\n", " 0.8816578 0.8816602 0.8816576 0.88165442 0.8816578 0.88165741\n", " 0.88165372 0.88165831 0.88166713 0.88165879 0.88166269 0.88166924\n", " 0.88165758 0.88166455 0.88165518 0.88165984 0.88166193 0.88165596\n", " 0.88165245 0.88166108 0.88166543 0.88166085 0.88165406 0.88166145\n", " 0.88165595 0.88165587 0.88165593 0.88165041 0.88166417 0.88165442\n", " 0.88166378 0.88165867 0.8816567 0.88165994 0.88165765 0.88166377\n", " 0.88165487 0.8816613 0.88165896 0.88166087 0.88166418 0.88165212\n", " 0.88165914 0.88166378 0.88165596 0.88165334 0.8816556 0.88165884\n", " 0.88165323 0.88165833 0.88166829 0.88164991 0.88166128 0.88165687\n", " 0.88165369 0.88165651 0.8816577 0.88166279 0.88166009 0.88166023\n", " 0.88165638 0.88166268 0.88165743 0.88165596 0.88165641 0.88165515\n", "Epoch 28 RMSE: [0.87510834 0.87509754 0.87509663 0.87510501 0.87510732 0.87510844 | 28/40 [02:31<01:04, 5.41s/it]\n", " 0.87510832 0.87510935 0.8751045 0.87510659 0.8751064 0.87511164\n", " 0.87510898 0.87511614 0.87510577 0.87510311 0.87510578 0.87511943\n", " 0.87510964 0.87511362 0.87510719 0.87510538 0.8750985 0.87511187\n", " 0.87510119 0.87510917 0.87510698 0.87510852 0.87510968 0.87510468\n", " 0.87510608 0.87510799 0.87510547 0.87510238 0.87510591 0.87510559\n", " 0.87510213 0.87510641 0.87511438 0.87510659 0.87511041 0.87511643\n", " 0.87510541 0.87511212 0.8751033 0.87510743 0.87510914 0.87510382\n", " 0.87510055 0.87510899 0.87511296 0.87510838 0.87510233 0.87510917\n", " 0.87510382 0.87510422 0.87510418 0.87509873 0.87511159 0.87510246\n", " 0.87511153 0.87510659 0.87510447 0.87510802 0.87510553 0.87511167\n", " 0.87510313 0.87510911 0.87510697 0.87510844 0.87511208 0.87510019\n", " 0.875107 0.87511121 0.8751039 0.87510128 0.87510373 0.87510653\n", " 0.87510125 0.87510633 0.8751156 0.87509846 0.87510891 0.87510498\n", " 0.87510189 0.87510428 0.87510558 0.87511057 0.87510792 0.8751081\n", " 0.87510402 0.87511035 0.87510553 0.87510394 0.87510449 0.87510294\n", "Epoch 28 RMSE: [0.87510834 0.87509754 0.87509663 0.87510501 0.87510732 0.87510844 | 28/40 [02:31<01:04, 5.41s/it]\n", " 0.87510832 0.87510935 0.8751045 0.87510659 0.8751064 0.87511164\n", " 0.87510898 0.87511614 0.87510577 0.87510311 0.87510578 0.87511943\n", " 0.87510964 0.87511362 0.87510719 0.87510538 0.8750985 0.87511187\n", " 0.87510119 0.87510917 0.87510698 0.87510852 0.87510968 0.87510468\n", " 0.87510608 0.87510799 0.87510547 0.87510238 0.87510591 0.87510559\n", " 0.87510213 0.87510641 0.87511438 0.87510659 0.87511041 0.87511643\n", " 0.87510541 0.87511212 0.8751033 0.87510743 0.87510914 0.87510382\n", " 0.87510055 0.87510899 0.87511296 0.87510838 0.87510233 0.87510917\n", " 0.87510382 0.87510422 0.87510418 0.87509873 0.87511159 0.87510246\n", " 0.87511153 0.87510659 0.87510447 0.87510802 0.87510553 0.87511167\n", " 0.87510313 0.87510911 0.87510697 0.87510844 0.87511208 0.87510019\n", " 0.875107 0.87511121 0.8751039 0.87510128 0.87510373 0.87510653\n", " 0.87510125 0.87510633 0.8751156 0.87509846 0.87510891 0.87510498\n", " 0.87510189 0.87510428 0.87510558 0.87511057 0.87510792 0.8751081\n", " 0.87510402 0.87511035 0.87510553 0.87510394 0.87510449 0.87510294\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Epoch 29 RMSE: [0.86823894 0.86822801 0.86822766 0.86823551 0.86823771 0.86823867▎ | 29/40 [02:37<01:00, 5.46s/it]\n", " 0.86823888 0.86823943 0.86823506 0.86823688 0.86823717 0.86824192\n", " 0.86823941 0.86824639 0.8682362 0.86823385 0.86823621 0.86824941\n", " 0.86824005 0.86824385 0.86823777 0.86823607 0.86822946 0.86824213\n", " 0.86823216 0.86823966 0.86823746 0.86823883 0.86824036 0.86823545\n", " 0.86823686 0.86823855 0.8682361 0.86823303 0.86823667 0.86823629\n", " 0.8682332 0.86823711 0.86824446 0.86823721 0.86824071 0.86824626\n", " 0.86823599 0.86824224 0.86823406 0.86823781 0.8682393 0.86823449\n", " 0.86823139 0.86823948 0.86824308 0.8682386 0.86823343 0.86823948\n", " 0.8682343 0.86823506 0.86823508 0.86822965 0.86824176 0.86823308\n", " 0.86824182 0.86823728 0.86823501 0.8682387 0.86823606 0.8682422\n", " 0.86823394 0.86823947 0.86823755 0.8682388 0.86824244 0.86823086\n", " 0.86823758 0.86824138 0.86823449 0.86823205 0.86823441 0.86823701\n", " 0.86823191 0.86823693 0.8682456 0.86822948 0.86823926 0.86823567\n", " 0.86823255 0.8682349 0.86823623 0.86824105 0.86823848 0.86823869\n", " 0.86823434 0.86824056 0.86823623 0.8682345 0.86823516 0.86823361\n", "Epoch 29 RMSE: [0.86823894 0.86822801 0.86822766 0.86823551 0.86823771 0.86823867▎ | 29/40 [02:37<01:00, 5.46s/it]\n", " 0.86823888 0.86823943 0.86823506 0.86823688 0.86823717 0.86824192\n", " 0.86823941 0.86824639 0.8682362 0.86823385 0.86823621 0.86824941\n", " 0.86824005 0.86824385 0.86823777 0.86823607 0.86822946 0.86824213\n", " 0.86823216 0.86823966 0.86823746 0.86823883 0.86824036 0.86823545\n", " 0.86823686 0.86823855 0.8682361 0.86823303 0.86823667 0.86823629\n", " 0.8682332 0.86823711 0.86824446 0.86823721 0.86824071 0.86824626\n", " 0.86823599 0.86824224 0.86823406 0.86823781 0.8682393 0.86823449\n", " 0.86823139 0.86823948 0.86824308 0.8682386 0.86823343 0.86823948\n", " 0.8682343 0.86823506 0.86823508 0.86822965 0.86824176 0.86823308\n", " 0.86824182 0.86823728 0.86823501 0.8682387 0.86823606 0.8682422\n", " 0.86823394 0.86823947 0.86823755 0.8682388 0.86824244 0.86823086\n", " 0.86823758 0.86824138 0.86823449 0.86823205 0.86823441 0.86823701\n", " 0.86823191 0.86823693 0.8682456 0.86822948 0.86823926 0.86823567\n", " 0.86823255 0.8682349 0.86823623 0.86824105 0.86823848 0.86823869\n", " 0.86823434 0.86824056 0.86823623 0.8682345 0.86823516 0.86823361\n", "Epoch 30 RMSE: [0.86110019 0.86108921 0.86108926 0.8610966 0.86109871 0.86109966▌ | 30/40 [02:42<00:54, 5.46s/it]\n", " 0.86109996 0.86110027 0.86109627 0.86109785 0.86109837 0.86110273\n", " 0.86110047 0.86110709 0.86109723 0.86109514 0.86109729 0.86111005\n", " 0.86110108 0.86110462 0.86109897 0.86109726 0.86109122 0.86110306\n", " 0.86109372 0.86110043 0.86109851 0.86109985 0.8611016 0.86109689\n", " 0.86109814 0.86109965 0.86109726 0.8610943 0.8610979 0.86109759\n", " 0.86109464 0.86109845 0.86110525 0.86109832 0.86110154 0.86110695\n", " 0.86109706 0.86110309 0.86109537 0.86109868 0.86109994 0.86109568\n", " 0.86109269 0.86110049 0.86110393 0.8610996 0.86109488 0.86110037\n", " 0.86109547 0.86109657 0.8610965 0.8610912 0.86110239 0.86109435\n", " 0.86110294 0.86109839 0.86109597 0.86109998 0.86109735 0.86110324\n", " 0.86109536 0.86110052 0.86109861 0.86109987 0.86110357 0.86109208\n", " 0.86109876 0.86110217 0.86109577 0.86109338 0.8610957 0.861098\n", " 0.86109327 0.86109804 0.86110613 0.86109114 0.86110013 0.86109695\n", " 0.86109409 0.86109602 0.86109743 0.86110196 0.8610996 0.8610997\n", " 0.86109523 0.86110151 0.86109746 0.86109567 0.86109655 0.86109468\n", "Epoch 30 RMSE: [0.86110019 0.86108921 0.86108926 0.8610966 0.86109871 0.86109966▌ | 30/40 [02:42<00:54, 5.46s/it] \n", " 0.86109996 0.86110027 0.86109627 0.86109785 0.86109837 0.86110273\n", " 0.86110047 0.86110709 0.86109723 0.86109514 0.86109729 0.86111005\n", " 0.86110108 0.86110462 0.86109897 0.86109726 0.86109122 0.86110306\n", " 0.86109372 0.86110043 0.86109851 0.86109985 0.8611016 0.86109689\n", " 0.86109814 0.86109965 0.86109726 0.8610943 0.8610979 0.86109759\n", " 0.86109464 0.86109845 0.86110525 0.86109832 0.86110154 0.86110695\n", " 0.86109706 0.86110309 0.86109537 0.86109868 0.86109994 0.86109568\n", " 0.86109269 0.86110049 0.86110393 0.8610996 0.86109488 0.86110037\n", " 0.86109547 0.86109657 0.8610965 0.8610912 0.86110239 0.86109435\n", " 0.86110294 0.86109839 0.86109597 0.86109998 0.86109735 0.86110324\n", " 0.86109536 0.86110052 0.86109861 0.86109987 0.86110357 0.86109208\n", " 0.86109876 0.86110217 0.86109577 0.86109338 0.8610957 0.861098\n", " 0.86109327 0.86109804 0.86110613 0.86109114 0.86110013 0.86109695\n", " 0.86109409 0.86109602 0.86109743 0.86110196 0.8610996 0.8610997\n", " 0.86109523 0.86110151 0.86109746 0.86109567 0.86109655 0.86109468\n", "Epoch 31 RMSE: [0.85366208 0.8536512 0.85365154 0.85365852 0.85366058 0.8536614█▊ | 31/40 [02:47<00:48, 5.42s/it]\n", " 0.85366187 0.85366186 0.85365826 0.85365968 0.85366043 0.85366452\n", " 0.85366223 0.85366873 0.85365907 0.85365719 0.85365917 0.85367156\n", " 0.85366291 0.85366622 0.8536611 0.85365924 0.85365342 0.85366465\n", " 0.85365595 0.85366222 0.8536604 0.85366154 0.85366359 0.85365899\n", " 0.85366042 0.85366158 0.85365923 0.85365632 0.85366 0.85365967\n", " 0.85365697 0.85366057 0.85366668 0.85366008 0.85366332 0.85366834\n", " 0.853659 0.85366475 0.85365754 0.85366053 0.85366156 0.85365771\n", " 0.85365493 0.85366241 0.85366556 0.85366125 0.8536572 0.85366224\n", " 0.85365745 0.85365869 0.85365873 0.85365359 0.85366411 0.85365637\n", " 0.85366465 0.85366055 0.8536579 0.85366198 0.85365927 0.85366529\n", " 0.85365757 0.85366231 0.85366066 0.85366172 0.85366532 0.85365414\n", " 0.85366065 0.85366374 0.85365783 0.85365547 0.85365796 0.85365986\n", " 0.85365538 0.85366 0.85366759 0.85365347 0.85366188 0.85365909\n", " 0.85365633 0.85365804 0.85365941 0.85366392 0.85366158 0.85366157\n", " 0.85365694 0.85366323 0.85365949 0.85365771 0.85365851 0.85365664\n", "Epoch 31 RMSE: [0.85366208 0.8536512 0.85365154 0.85365852 0.85366058 0.8536614█▊ | 31/40 [02:47<00:48, 5.42s/it]\n", " 0.85366187 0.85366186 0.85365826 0.85365968 0.85366043 0.85366452\n", " 0.85366223 0.85366873 0.85365907 0.85365719 0.85365917 0.85367156\n", " 0.85366291 0.85366622 0.8536611 0.85365924 0.85365342 0.85366465\n", " 0.85365595 0.85366222 0.8536604 0.85366154 0.85366359 0.85365899\n", " 0.85366042 0.85366158 0.85365923 0.85365632 0.85366 0.85365967\n", " 0.85365697 0.85366057 0.85366668 0.85366008 0.85366332 0.85366834\n", " 0.853659 0.85366475 0.85365754 0.85366053 0.85366156 0.85365771\n", " 0.85365493 0.85366241 0.85366556 0.85366125 0.8536572 0.85366224\n", " 0.85365745 0.85365869 0.85365873 0.85365359 0.85366411 0.85365637\n", " 0.85366465 0.85366055 0.8536579 0.85366198 0.85365927 0.85366529\n", " 0.85365757 0.85366231 0.85366066 0.85366172 0.85366532 0.85365414\n", " 0.85366065 0.85366374 0.85365783 0.85365547 0.85365796 0.85365986\n", " 0.85365538 0.85366 0.85366759 0.85365347 0.85366188 0.85365909\n", " 0.85365633 0.85365804 0.85365941 0.85366392 0.85366158 0.85366157\n", " 0.85365694 0.85366323 0.85365949 0.85365771 0.85365851 0.85365664\n", "Epoch 32 RMSE: [0.84594586 0.84593507 0.84593559 0.84594237 0.84594421 0.84594509█ | 32/40 [02:53<00:43, 5.40s/it]\n", " 0.84594566 0.84594534 0.84594213 0.84594322 0.84594434 0.84594795\n", " 0.84594583 0.84595223 0.84594263 0.84594109 0.84594312 0.84595501\n", " 0.8459465 0.84594959 0.84594501 0.84594311 0.84593757 0.8459482\n", " 0.84594013 0.84594583 0.84594402 0.84594522 0.84594734 0.84594291\n", " 0.84594443 0.84594526 0.84594318 0.84594011 0.84594379 0.84594359\n", " 0.84594102 0.84594446 0.84595027 0.84594398 0.84594684 0.84595155\n", " 0.84594297 0.84594827 0.84594161 0.84594428 0.84594511 0.84594163\n", " 0.84593905 0.84594617 0.84594921 0.84594511 0.84594133 0.8459459\n", " 0.84594134 0.84594266 0.84594281 0.84593768 0.84594772 0.84594009\n", " 0.84594836 0.84594434 0.84594163 0.84594589 0.8459431 0.84594906\n", " 0.84594166 0.84594595 0.84594445 0.84594517 0.84594899 0.84593818\n", " 0.8459444 0.84594727 0.84594165 0.84593954 0.8459419 0.8459437\n", " 0.8459393 0.84594389 0.84595098 0.84593773 0.84594554 0.8459431\n", " 0.84594023 0.84594188 0.84594329 0.84594764 0.84594544 0.84594538\n", " 0.84594058 0.84594678 0.84594343 0.84594165 0.84594246 0.84594058\n", "Epoch 32 RMSE: [0.84594586 0.84593507 0.84593559 0.84594237 0.84594421 0.84594509█ | 32/40 [02:53<00:43, 5.40s/it] \n", " 0.84594566 0.84594534 0.84594213 0.84594322 0.84594434 0.84594795\n", " 0.84594583 0.84595223 0.84594263 0.84594109 0.84594312 0.84595501\n", " 0.8459465 0.84594959 0.84594501 0.84594311 0.84593757 0.8459482\n", " 0.84594013 0.84594583 0.84594402 0.84594522 0.84594734 0.84594291\n", " 0.84594443 0.84594526 0.84594318 0.84594011 0.84594379 0.84594359\n", " 0.84594102 0.84594446 0.84595027 0.84594398 0.84594684 0.84595155\n", " 0.84594297 0.84594827 0.84594161 0.84594428 0.84594511 0.84594163\n", " 0.84593905 0.84594617 0.84594921 0.84594511 0.84594133 0.8459459\n", " 0.84594134 0.84594266 0.84594281 0.84593768 0.84594772 0.84594009\n", " 0.84594836 0.84594434 0.84594163 0.84594589 0.8459431 0.84594906\n", " 0.84594166 0.84594595 0.84594445 0.84594517 0.84594899 0.84593818\n", " 0.8459444 0.84594727 0.84594165 0.84593954 0.8459419 0.8459437\n", " 0.8459393 0.84594389 0.84595098 0.84593773 0.84594554 0.8459431\n", " 0.84594023 0.84594188 0.84594329 0.84594764 0.84594544 0.84594538\n", " 0.84594058 0.84594678 0.84594343 0.84594165 0.84594246 0.84594058\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Epoch 33 RMSE: [0.83771943 0.8377086 0.8377095 0.83771574 0.83771762 0.8377185██▎ | 33/40 [02:58<00:37, 5.39s/it]\n", " 0.83771903 0.83771866 0.8377158 0.83771667 0.83771793 0.83772127\n", " 0.83771922 0.83772547 0.83771622 0.83771474 0.83771651 0.83772803\n", " 0.83771996 0.8377228 0.83771847 0.83771653 0.83771155 0.83772148\n", " 0.83771396 0.83771926 0.83771747 0.83771852 0.83772094 0.8377167\n", " 0.83771801 0.83771879 0.83771667 0.83771389 0.83771749 0.83771721\n", " 0.83771471 0.83771805 0.83772337 0.83771744 0.83772014 0.8377247\n", " 0.8377164 0.83772154 0.83771525 0.8377175 0.83771824 0.83771513\n", " 0.83771271 0.83771956 0.83772238 0.83771823 0.83771512 0.83771929\n", " 0.83771487 0.83771656 0.83771647 0.83771152 0.83772088 0.83771364\n", " 0.83772171 0.83771793 0.83771514 0.83771959 0.83771663 0.83772244\n", " 0.83771531 0.8377194 0.83771789 0.83771869 0.83772234 0.83771167\n", " 0.83771806 0.8377206 0.83771532 0.83771307 0.83771561 0.83771703\n", " 0.83771292 0.83771733 0.83772404 0.83771162 0.83771882 0.83771671\n", " 0.83771385 0.83771542 0.83771674 0.83772092 0.83771887 0.83771878\n", " 0.83771398 0.83772002 0.83771701 0.83771509 0.83771609 0.83771392\n", "Epoch 33 RMSE: [0.83771943 0.8377086 0.8377095 0.83771574 0.83771762 0.8377185██▎ | 33/40 [02:58<00:37, 5.39s/it]\n", " 0.83771903 0.83771866 0.8377158 0.83771667 0.83771793 0.83772127\n", " 0.83771922 0.83772547 0.83771622 0.83771474 0.83771651 0.83772803\n", " 0.83771996 0.8377228 0.83771847 0.83771653 0.83771155 0.83772148\n", " 0.83771396 0.83771926 0.83771747 0.83771852 0.83772094 0.8377167\n", " 0.83771801 0.83771879 0.83771667 0.83771389 0.83771749 0.83771721\n", " 0.83771471 0.83771805 0.83772337 0.83771744 0.83772014 0.8377247\n", " 0.8377164 0.83772154 0.83771525 0.8377175 0.83771824 0.83771513\n", " 0.83771271 0.83771956 0.83772238 0.83771823 0.83771512 0.83771929\n", " 0.83771487 0.83771656 0.83771647 0.83771152 0.83772088 0.83771364\n", " 0.83772171 0.83771793 0.83771514 0.83771959 0.83771663 0.83772244\n", " 0.83771531 0.8377194 0.83771789 0.83771869 0.83772234 0.83771167\n", " 0.83771806 0.8377206 0.83771532 0.83771307 0.83771561 0.83771703\n", " 0.83771292 0.83771733 0.83772404 0.83771162 0.83771882 0.83771671\n", " 0.83771385 0.83771542 0.83771674 0.83772092 0.83771887 0.83771878\n", " 0.83771398 0.83772002 0.83771701 0.83771509 0.83771609 0.83771392\n", "Epoch 34 RMSE: [0.82906242 0.82905181 0.82905282 0.82905877 0.82906061 0.82906153█▌ | 34/40 [03:03<00:32, 5.39s/it]\n", " 0.82906211 0.82906154 0.82905886 0.82905972 0.82906121 0.82906405\n", " 0.82906215 0.82906818 0.82905918 0.82905794 0.82905951 0.82907069\n", " 0.82906285 0.82906559 0.8290616 0.82905964 0.82905486 0.8290643\n", " 0.82905723 0.82906212 0.82906052 0.82906143 0.82906404 0.82905989\n", " 0.82906124 0.82906175 0.82905977 0.82905697 0.82906059 0.82906034\n", " 0.82905816 0.82906122 0.8290661 0.82906042 0.82906303 0.82906726\n", " 0.82905952 0.82906441 0.8290585 0.82906046 0.82906095 0.82905824\n", " 0.829056 0.82906252 0.82906519 0.82906123 0.82905849 0.82906223\n", " 0.82905789 0.82905976 0.82905974 0.82905496 0.82906382 0.82905679\n", " 0.8290647 0.8290611 0.8290581 0.82906269 0.82905983 0.82906548\n", " 0.8290586 0.82906236 0.82906112 0.82906161 0.82906524 0.82905494\n", " 0.82906106 0.82906344 0.8290585 0.82905637 0.82905886 0.8290601\n", " 0.82905615 0.82906054 0.8290667 0.82905507 0.82906173 0.82905983\n", " 0.82905715 0.82905861 0.82905985 0.82906393 0.82906203 0.82906179\n", " 0.82905677 0.82906296 0.82906009 0.82905844 0.82905931 0.82905696\n", "Epoch 34 RMSE: [0.82906242 0.82905181 0.82905282 0.82905877 0.82906061 0.82906153█▌ | 34/40 [03:03<00:32, 5.39s/it]\n", " 0.82906211 0.82906154 0.82905886 0.82905972 0.82906121 0.82906405\n", " 0.82906215 0.82906818 0.82905918 0.82905794 0.82905951 0.82907069\n", " 0.82906285 0.82906559 0.8290616 0.82905964 0.82905486 0.8290643\n", " 0.82905723 0.82906212 0.82906052 0.82906143 0.82906404 0.82905989\n", " 0.82906124 0.82906175 0.82905977 0.82905697 0.82906059 0.82906034\n", " 0.82905816 0.82906122 0.8290661 0.82906042 0.82906303 0.82906726\n", " 0.82905952 0.82906441 0.8290585 0.82906046 0.82906095 0.82905824\n", " 0.829056 0.82906252 0.82906519 0.82906123 0.82905849 0.82906223\n", " 0.82905789 0.82905976 0.82905974 0.82905496 0.82906382 0.82905679\n", " 0.8290647 0.8290611 0.8290581 0.82906269 0.82905983 0.82906548\n", " 0.8290586 0.82906236 0.82906112 0.82906161 0.82906524 0.82905494\n", " 0.82906106 0.82906344 0.8290585 0.82905637 0.82905886 0.8290601\n", " 0.82905615 0.82906054 0.8290667 0.82905507 0.82906173 0.82905983\n", " 0.82905715 0.82905861 0.82905985 0.82906393 0.82906203 0.82906179\n", " 0.82905677 0.82906296 0.82906009 0.82905844 0.82905931 0.82905696\n", "Epoch 35 RMSE: [0.82017231 0.82016204 0.82016311 0.82016864 0.82017055 0.82017148█▊ | 35/40 [03:09<00:26, 5.39s/it]\n", " 0.8201721 0.8201715 0.8201689 0.82016971 0.82017122 0.82017384\n", " 0.82017215 0.82017791 0.82016916 0.82016807 0.82016953 0.82018029\n", " 0.82017272 0.8201754 0.82017164 0.82016967 0.82016518 0.82017405\n", " 0.82016754 0.82017205 0.82017061 0.82017142 0.82017416 0.82016997\n", " 0.82017132 0.82017164 0.82016973 0.82016705 0.82017054 0.82017051\n", " 0.82016827 0.82017127 0.82017577 0.82017032 0.8201729 0.82017693\n", " 0.82016949 0.82017423 0.82016872 0.82017031 0.82017079 0.82016828\n", " 0.82016614 0.82017246 0.82017497 0.82017105 0.82016867 0.82017223\n", " 0.82016795 0.82016992 0.8201699 0.82016526 0.82017363 0.82016676\n", " 0.82017456 0.82017114 0.82016809 0.82017271 0.82016995 0.82017544\n", " 0.82016878 0.82017224 0.82017109 0.82017154 0.82017509 0.82016506\n", " 0.82017096 0.82017317 0.82016858 0.82016643 0.8201689 0.82017012\n", " 0.82016626 0.82017046 0.82017632 0.82016548 0.82017168 0.82016991\n", " 0.8201673 0.82016864 0.82016995 0.82017382 0.82017194 0.82017173\n", " 0.82016677 0.82017283 0.82017015 0.82016854 0.82016944 0.82016701\n", "Epoch 35 RMSE: [0.82017231 0.82016204 0.82016311 0.82016864 0.82017055 0.82017148█▊ | 35/40 [03:09<00:26, 5.39s/it]\n", " 0.8201721 0.8201715 0.8201689 0.82016971 0.82017122 0.82017384\n", " 0.82017215 0.82017791 0.82016916 0.82016807 0.82016953 0.82018029\n", " 0.82017272 0.8201754 0.82017164 0.82016967 0.82016518 0.82017405\n", " 0.82016754 0.82017205 0.82017061 0.82017142 0.82017416 0.82016997\n", " 0.82017132 0.82017164 0.82016973 0.82016705 0.82017054 0.82017051\n", " 0.82016827 0.82017127 0.82017577 0.82017032 0.8201729 0.82017693\n", " 0.82016949 0.82017423 0.82016872 0.82017031 0.82017079 0.82016828\n", " 0.82016614 0.82017246 0.82017497 0.82017105 0.82016867 0.82017223\n", " 0.82016795 0.82016992 0.8201699 0.82016526 0.82017363 0.82016676\n", " 0.82017456 0.82017114 0.82016809 0.82017271 0.82016995 0.82017544\n", " 0.82016878 0.82017224 0.82017109 0.82017154 0.82017509 0.82016506\n", " 0.82017096 0.82017317 0.82016858 0.82016643 0.8201689 0.82017012\n", " 0.82016626 0.82017046 0.82017632 0.82016548 0.82017168 0.82016991\n", " 0.8201673 0.82016864 0.82016995 0.82017382 0.82017194 0.82017173\n", " 0.82016677 0.82017283 0.82017015 0.82016854 0.82016944 0.82016701\n", "Epoch 36 RMSE: [0.81081981 0.81080947 0.81081085 0.81081603 0.81081794 0.81081889██ | 36/40 [03:14<00:21, 5.39s/it]\n", " 0.81081953 0.81081878 0.81081649 0.81081708 0.81081868 0.81082123\n", " 0.81081943 0.81082507 0.81081654 0.81081556 0.81081706 0.81082727\n", " 0.81082016 0.81082261 0.8108191 0.81081713 0.81081282 0.81082138\n", " 0.81081519 0.81081928 0.81081798 0.81081867 0.81082166 0.81081759\n", " 0.81081887 0.81081909 0.81081722 0.81081455 0.81081805 0.81081795\n", " 0.81081603 0.81081881 0.81082297 0.81081775 0.81082016 0.81082404\n", " 0.810817 0.81082146 0.81081635 0.81081773 0.81081798 0.81081577\n", " 0.81081395 0.81081978 0.81082226 0.81081839 0.81081635 0.81081948\n", " 0.81081547 0.81081756 0.81081765 0.81081293 0.81082084 0.81081429\n", " 0.81082202 0.81081866 0.81081565 0.81082023 0.81081741 0.810823\n", " 0.81081641 0.8108196 0.8108186 0.81081898 0.81082245 0.81081256\n", " 0.81081846 0.81082055 0.8108161 0.81081414 0.81081652 0.81081752\n", " 0.81081399 0.81081803 0.81082343 0.81081312 0.810819 0.81081753\n", " 0.81081492 0.81081624 0.81081739 0.81082118 0.81081948 0.81081908\n", " 0.81081411 0.81082014 0.81081767 0.81081611 0.810817 0.81081452\n", "Epoch 36 RMSE: [0.81081981 0.81080947 0.81081085 0.81081603 0.81081794 0.81081889██ | 36/40 [03:14<00:21, 5.39s/it] \n", " 0.81081953 0.81081878 0.81081649 0.81081708 0.81081868 0.81082123\n", " 0.81081943 0.81082507 0.81081654 0.81081556 0.81081706 0.81082727\n", " 0.81082016 0.81082261 0.8108191 0.81081713 0.81081282 0.81082138\n", " 0.81081519 0.81081928 0.81081798 0.81081867 0.81082166 0.81081759\n", " 0.81081887 0.81081909 0.81081722 0.81081455 0.81081805 0.81081795\n", " 0.81081603 0.81081881 0.81082297 0.81081775 0.81082016 0.81082404\n", " 0.810817 0.81082146 0.81081635 0.81081773 0.81081798 0.81081577\n", " 0.81081395 0.81081978 0.81082226 0.81081839 0.81081635 0.81081948\n", " 0.81081547 0.81081756 0.81081765 0.81081293 0.81082084 0.81081429\n", " 0.81082202 0.81081866 0.81081565 0.81082023 0.81081741 0.810823\n", " 0.81081641 0.8108196 0.8108186 0.81081898 0.81082245 0.81081256\n", " 0.81081846 0.81082055 0.8108161 0.81081414 0.81081652 0.81081752\n", " 0.81081399 0.81081803 0.81082343 0.81081312 0.810819 0.81081753\n", " 0.81081492 0.81081624 0.81081739 0.81082118 0.81081948 0.81081908\n", " 0.81081411 0.81082014 0.81081767 0.81081611 0.810817 0.81081452\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Epoch 37 RMSE: [0.80113799 0.80112786 0.80112946 0.8011344 0.80113625 0.80113716██▎| 37/40 [03:20<00:16, 5.38s/it]\n", " 0.80113779 0.80113699 0.80113489 0.80113526 0.80113717 0.80113932\n", " 0.80113751 0.80114324 0.80113487 0.80113398 0.80113541 0.80114532\n", " 0.80113833 0.80114074 0.80113741 0.8011355 0.80113144 0.80113951\n", " 0.8011337 0.80113761 0.80113614 0.80113682 0.8011399 0.80113607\n", " 0.80113731 0.80113738 0.80113565 0.8011329 0.80113646 0.8011364\n", " 0.80113447 0.80113722 0.80114115 0.80113603 0.80113829 0.80114203\n", " 0.80113527 0.80113972 0.80113468 0.80113594 0.8011362 0.80113419\n", " 0.80113248 0.80113809 0.80114036 0.80113674 0.80113486 0.80113773\n", " 0.80113387 0.80113608 0.80113613 0.80113155 0.80113904 0.80113272\n", " 0.80114025 0.80113697 0.80113399 0.80113849 0.80113575 0.80114118\n", " 0.80113488 0.80113782 0.80113708 0.80113718 0.80114051 0.80113103\n", " 0.8011367 0.80113878 0.80113463 0.80113255 0.80113509 0.80113586\n", " 0.80113244 0.80113643 0.80114146 0.80113171 0.80113712 0.80113596\n", " 0.80113338 0.80113463 0.80113561 0.80113943 0.80113786 0.80113742\n", " 0.80113239 0.80113832 0.80113601 0.80113463 0.80113538 0.80113285\n", "Epoch 37 RMSE: [0.80113799 0.80112786 0.80112946 0.8011344 0.80113625 0.80113716██▎| 37/40 [03:20<00:16, 5.38s/it]\n", " 0.80113779 0.80113699 0.80113489 0.80113526 0.80113717 0.80113932\n", " 0.80113751 0.80114324 0.80113487 0.80113398 0.80113541 0.80114532\n", " 0.80113833 0.80114074 0.80113741 0.8011355 0.80113144 0.80113951\n", " 0.8011337 0.80113761 0.80113614 0.80113682 0.8011399 0.80113607\n", " 0.80113731 0.80113738 0.80113565 0.8011329 0.80113646 0.8011364\n", " 0.80113447 0.80113722 0.80114115 0.80113603 0.80113829 0.80114203\n", " 0.80113527 0.80113972 0.80113468 0.80113594 0.8011362 0.80113419\n", " 0.80113248 0.80113809 0.80114036 0.80113674 0.80113486 0.80113773\n", " 0.80113387 0.80113608 0.80113613 0.80113155 0.80113904 0.80113272\n", " 0.80114025 0.80113697 0.80113399 0.80113849 0.80113575 0.80114118\n", " 0.80113488 0.80113782 0.80113708 0.80113718 0.80114051 0.80113103\n", " 0.8011367 0.80113878 0.80113463 0.80113255 0.80113509 0.80113586\n", " 0.80113244 0.80113643 0.80114146 0.80113171 0.80113712 0.80113596\n", " 0.80113338 0.80113463 0.80113561 0.80113943 0.80113786 0.80113742\n", " 0.80113239 0.80113832 0.80113601 0.80113463 0.80113538 0.80113285\n", "Epoch 38 RMSE: [0.79122696 0.79121708 0.79121867 0.79122332 0.79122516 0.79122614██▌| 38/40 [03:25<00:10, 5.38s/it]\n", " 0.7912267 0.79122588 0.79122388 0.79122431 0.79122614 0.79122807\n", " 0.79122642 0.79123206 0.79122377 0.79122318 0.79122444 0.79123391\n", " 0.79122715 0.79122941 0.79122645 0.79122432 0.79122066 0.79122825\n", " 0.791223 0.79122635 0.79122512 0.79122584 0.79122889 0.79122501\n", " 0.79122638 0.79122623 0.79122459 0.79122185 0.79122537 0.79122531\n", " 0.79122357 0.79122622 0.79122981 0.79122496 0.79122719 0.79123058\n", " 0.79122432 0.79122854 0.79122391 0.79122483 0.79122503 0.79122319\n", " 0.79122159 0.79122685 0.79122907 0.79122558 0.79122394 0.79122661\n", " 0.79122288 0.79122503 0.79122514 0.79122075 0.79122793 0.79122165\n", " 0.79122909 0.79122607 0.79122303 0.79122756 0.79122472 0.79123009\n", " 0.79122403 0.79122682 0.79122615 0.79122614 0.79122933 0.79122012\n", " 0.79122565 0.79122763 0.79122357 0.79122168 0.79122415 0.79122482\n", " 0.79122153 0.79122531 0.79123012 0.79122104 0.791226 0.79122498\n", " 0.79122254 0.79122362 0.7912245 0.79122833 0.79122682 0.7912263\n", " 0.79122115 0.79122715 0.79122493 0.79122377 0.79122452 0.7912218\n", "Epoch 38 RMSE: [0.79122696 0.79121708 0.79121867 0.79122332 0.79122516 0.79122614██▌| 38/40 [03:25<00:10, 5.38s/it] \n", " 0.7912267 0.79122588 0.79122388 0.79122431 0.79122614 0.79122807\n", " 0.79122642 0.79123206 0.79122377 0.79122318 0.79122444 0.79123391\n", " 0.79122715 0.79122941 0.79122645 0.79122432 0.79122066 0.79122825\n", " 0.791223 0.79122635 0.79122512 0.79122584 0.79122889 0.79122501\n", " 0.79122638 0.79122623 0.79122459 0.79122185 0.79122537 0.79122531\n", " 0.79122357 0.79122622 0.79122981 0.79122496 0.79122719 0.79123058\n", " 0.79122432 0.79122854 0.79122391 0.79122483 0.79122503 0.79122319\n", " 0.79122159 0.79122685 0.79122907 0.79122558 0.79122394 0.79122661\n", " 0.79122288 0.79122503 0.79122514 0.79122075 0.79122793 0.79122165\n", " 0.79122909 0.79122607 0.79122303 0.79122756 0.79122472 0.79123009\n", " 0.79122403 0.79122682 0.79122615 0.79122614 0.79122933 0.79122012\n", " 0.79122565 0.79122763 0.79122357 0.79122168 0.79122415 0.79122482\n", " 0.79122153 0.79122531 0.79123012 0.79122104 0.791226 0.79122498\n", " 0.79122254 0.79122362 0.7912245 0.79122833 0.79122682 0.7912263\n", " 0.79122115 0.79122715 0.79122493 0.79122377 0.79122452 0.7912218\n", "Epoch 39 RMSE: [0.78078513 0.78077536 0.78077706 0.78078141 0.78078339 0.78078432██▊| 39/40 [03:30<00:05, 5.38s/it]\n", " 0.78078488 0.78078405 0.78078212 0.78078244 0.78078443 0.78078615\n", " 0.78078445 0.78078999 0.78078183 0.78078142 0.78078265 0.78079179\n", " 0.78078528 0.78078739 0.78078456 0.7807825 0.78077907 0.7807863\n", " 0.7807814 0.78078436 0.78078328 0.78078399 0.78078715 0.78078328\n", " 0.78078464 0.78078443 0.78078289 0.78078008 0.78078361 0.7807835\n", " 0.78078188 0.78078444 0.78078781 0.78078311 0.78078521 0.78078856\n", " 0.78078253 0.78078657 0.7807823 0.78078296 0.78078306 0.78078138\n", " 0.78078 0.78078495 0.78078713 0.78078365 0.78078236 0.78078467\n", " 0.78078112 0.7807834 0.78078347 0.78077925 0.78078592 0.78077975\n", " 0.7807872 0.78078425 0.78078123 0.78078582 0.780783 0.78078834\n", " 0.78078244 0.78078492 0.78078433 0.78078429 0.78078745 0.78077847\n", " 0.78078381 0.78078568 0.78078189 0.78078002 0.78078253 0.78078302\n", " 0.78077985 0.78078347 0.78078803 0.78077943 0.78078407 0.78078319\n", " 0.78078081 0.78078185 0.78078269 0.78078646 0.78078506 0.78078443\n", " 0.78077923 0.78078527 0.7807832 0.78078205 0.78078281 0.78078012\n", "Epoch 39 RMSE: [0.78078513 0.78077536 0.78077706 0.78078141 0.78078339 0.78078432██▊| 39/40 [03:30<00:05, 5.38s/it]\n", " 0.78078488 0.78078405 0.78078212 0.78078244 0.78078443 0.78078615\n", " 0.78078445 0.78078999 0.78078183 0.78078142 0.78078265 0.78079179\n", " 0.78078528 0.78078739 0.78078456 0.7807825 0.78077907 0.7807863\n", " 0.7807814 0.78078436 0.78078328 0.78078399 0.78078715 0.78078328\n", " 0.78078464 0.78078443 0.78078289 0.78078008 0.78078361 0.7807835\n", " 0.78078188 0.78078444 0.78078781 0.78078311 0.78078521 0.78078856\n", " 0.78078253 0.78078657 0.7807823 0.78078296 0.78078306 0.78078138\n", " 0.78078 0.78078495 0.78078713 0.78078365 0.78078236 0.78078467\n", " 0.78078112 0.7807834 0.78078347 0.78077925 0.78078592 0.78077975\n", " 0.7807872 0.78078425 0.78078123 0.78078582 0.780783 0.78078834\n", " 0.78078244 0.78078492 0.78078433 0.78078429 0.78078745 0.78077847\n", " 0.78078381 0.78078568 0.78078189 0.78078002 0.78078253 0.78078302\n", " 0.78077985 0.78078347 0.78078803 0.78077943 0.78078407 0.78078319\n", " 0.78078081 0.78078185 0.78078269 0.78078646 0.78078506 0.78078443\n", " 0.78077923 0.78078527 0.7807832 0.78078205 0.78078281 0.78078012\n", "Epoch 39 RMSE: [0.78078513 0.78077536 0.78077706 0.78078141 0.78078339 0.78078432███| 40/40 [03:36<00:00, 5.36s/it]\n", " 0.78078488 0.78078405 0.78078212 0.78078244 0.78078443 0.78078615\n", " 0.78078445 0.78078999 0.78078183 0.78078142 0.78078265 0.78079179\n", " 0.78078528 0.78078739 0.78078456 0.7807825 0.78077907 0.7807863\n", " 0.7807814 0.78078436 0.78078328 0.78078399 0.78078715 0.78078328\n", " 0.78078464 0.78078443 0.78078289 0.78078008 0.78078361 0.7807835\n", " 0.78078188 0.78078444 0.78078781 0.78078311 0.78078521 0.78078856\n", " 0.78078253 0.78078657 0.7807823 0.78078296 0.78078306 0.78078138\n", " 0.78078 0.78078495 0.78078713 0.78078365 0.78078236 0.78078467\n", " 0.78078112 0.7807834 0.78078347 0.78077925 0.78078592 0.78077975\n", " 0.7807872 0.78078425 0.78078123 0.78078582 0.780783 0.78078834\n", " 0.78078244 0.78078492 0.78078433 0.78078429 0.78078745 0.78077847\n", " 0.78078381 0.78078568 0.78078189 0.78078002 0.78078253 0.78078302\n", " 0.78077985 0.78078347 0.78078803 0.78077943 0.78078407 0.78078319\n", " 0.78078081 0.78078185 0.78078269 0.78078646 0.78078506 0.78078443\n", " 0.78077923 0.78078527 0.7807832 0.78078205 0.78078281 0.78078012\n", " 0.78078184 0.78078461 0.78078518 0.7807888 ]. Training epoch 40...: 100%|██████████| 40/40 [03:36<00:00, 5.40s/it]\n" ] } ], "source": [ "model = SVDbaseline(train_ui, learning_rate = 0.005, regularization = 0.02, nb_factors = 100, iterations = 40)\n", "model.train(test_ui)" ] }, { "cell_type": "code", "execution_count": 13, "metadata": {}, "outputs": [], "source": [ "model.estimations()\n", "\n", "top_n = pd.DataFrame(model.recommend(user_code_id, item_code_id, topK = 10))\n", "top_n.to_csv('Recommendations generated/ml-100k/Self_SVDBaseline_reco.csv', index = False, header = False)\n", "\n", "estimations = pd.DataFrame(model.estimate(user_code_id, item_code_id, test_ui))\n", "estimations.to_csv('Recommendations generated/ml-100k/Self_SVDBaseline_estimations.csv', index = False, header = False)" ] }, { "cell_type": "code", "execution_count": 14, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "943it [00:00, 5269.39it/s]\n" ] }, { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
RMSEMAEprecisionrecallF_1F_05precision_superrecall_superNDCGmAPMRRLAUCHRF_2Whole_averageReco in testTest coverageShannonGini
03.6423593.4769560.1359490.0797510.0824230.0996730.1065450.1041640.16010.0793130.3287980.5367640.6299050.0776170.201751.00.2828285.1300080.90976
\n", "
" ], "text/plain": [ " RMSE MAE precision recall F_1 F_05 \\\n", "0 3.642359 3.476956 0.135949 0.079751 0.082423 0.099673 \n", "\n", " precision_super recall_super NDCG mAP MRR LAUC \\\n", "0 0.106545 0.104164 0.1601 0.079313 0.328798 0.536764 \n", "\n", " HR F_2 Whole_average Reco in test Test coverage Shannon \\\n", "0 0.629905 0.077617 0.20175 1.0 0.282828 5.130008 \n", "\n", " Gini \n", "0 0.90976 " ] }, "execution_count": 14, "metadata": {}, "output_type": "execute_result" } ], "source": [ "import evaluation_measures as ev\n", "\n", "estimations_df = pd.read_csv('Recommendations generated/ml-100k/Self_SVDBaseline_estimations.csv', header = None)\n", "reco = np.loadtxt('Recommendations generated/ml-100k/Self_SVDBaseline_reco.csv', delimiter = ',')\n", "\n", "ev.evaluate(test = pd.read_csv('./Datasets/ml-100k/test.csv', sep = '\\t', header = None),\n", " estimations_df = estimations_df, \n", " reco = reco,\n", " super_reactions = [4, 5])" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Ready-made SVD - Surprise implementation" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### SVD" ] }, { "cell_type": "code", "execution_count": 15, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Generating predictions...\n", "Generating top N recommendations...\n", "Generating predictions...\n" ] } ], "source": [ "import helpers\n", "import surprise as sp\n", "import imp\n", "imp.reload(helpers)\n", "\n", "algo = sp.SVD(biased=False) # to use unbiased version\n", "\n", "helpers.ready_made(algo, reco_path='Recommendations generated/ml-100k/Ready_SVD_reco.csv',\n", " estimations_path='Recommendations generated/ml-100k/Ready_SVD_estimations.csv')" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### SVD biased - on top baseline" ] }, { "cell_type": "code", "execution_count": 16, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Generating predictions...\n", "Generating top N recommendations...\n", "Generating predictions...\n" ] } ], "source": [ "import helpers\n", "import surprise as sp\n", "import imp\n", "imp.reload(helpers)\n", "\n", "algo = sp.SVD() # default is biased=True\n", "\n", "helpers.ready_made(algo, reco_path='Recommendations generated/ml-100k/Ready_SVDBiased_reco.csv',\n", " estimations_path='Recommendations generated/ml-100k/Ready_SVDBiased_estimations.csv')" ] }, { "cell_type": "code", "execution_count": 17, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "943it [00:00, 5574.85it/s]\n", "943it [00:00, 5577.21it/s]\n", "943it [00:00, 5713.84it/s]\n", "943it [00:00, 5581.92it/s]\n", "943it [00:00, 3580.16it/s]\n", "943it [00:00, 4836.58it/s]\n", "943it [00:00, 5756.69it/s]\n", "943it [00:00, 5399.56it/s]\n", "943it [00:00, 5308.13it/s]\n", "943it [00:00, 5658.53it/s]\n", "943it [00:00, 5425.27it/s]\n", "943it [00:00, 5078.50it/s]\n", "943it [00:00, 5840.70it/s]\n", "943it [00:00, 5851.85it/s]\n", "943it [00:00, 5100.40it/s]\n", "943it [00:00, 5096.28it/s]\n", "943it [00:00, 5309.65it/s]\n", "943it [00:00, 5903.76it/s]\n" ] }, { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
ModelRMSEMAEprecisionrecallF_1F_05precision_superrecall_superNDCGmAPMRRLAUCHRF_2Whole_averageReco in testTest coverageShannonGini
0Self_RP3Beta3.7029283.5277130.3226940.2160690.2121520.2475380.2452790.2849830.3882710.2482390.6363180.6056830.9109230.2054500.3769670.9997880.1789324.5496630.950182
0Self_P33.7024463.5272730.2821850.1920920.1867490.2169800.2041850.2400960.3391140.2049050.5721570.5935440.8759280.1817020.3408031.0000000.0772013.8758920.974947
0Self_TopPop2.5082582.2179090.1888650.1169190.1187320.1415840.1304720.1374730.2146510.1117070.4009390.5555460.7656420.1127500.2496071.0000000.0389613.1590790.987317
0Self_SVDBaseline3.6423593.4769560.1359490.0797510.0824230.0996730.1065450.1041640.1601000.0793130.3287980.5367640.6299050.0776170.2017501.0000000.2828285.1300080.909760
0Ready_SVD0.9511860.7505530.0949100.0445640.0511820.0656390.0845490.0744100.1061640.0492630.2283260.5189880.4772000.0456010.1534000.9969250.2193364.4948000.949844
0Self_SVD0.9140240.7171810.1044540.0438360.0533310.0707160.0945280.0767510.1067110.0505320.1943660.5186470.4793210.0459410.1532610.8537650.1486293.8363340.973007
0Ready_Baseline0.9494590.7524870.0914100.0376520.0460300.0612860.0796140.0564630.0959570.0431780.1981930.5155010.4379640.0395490.1419001.0000000.0339112.8365130.991139
0Ready_SVDBiased0.9393590.7405640.0868500.0363590.0439330.0581230.0763950.0569130.0945280.0438300.2032040.5148460.4432660.0380360.1413570.9948040.1796544.1996990.962848
0Self_KNNSurprisetask0.9462550.7452090.0834570.0328480.0412270.0554930.0747850.0488900.0895770.0409020.1890570.5130760.4178150.0349960.1351770.8885470.1305923.6118060.978659
0Self_TopRated2.5082582.2179090.0793210.0326670.0399830.0531700.0688840.0485820.0707660.0276020.1147900.5129430.4114530.0343850.1245461.0000000.0245312.7612380.991660
0Self_GlobalAvg1.1257600.9435340.0611880.0259680.0313830.0413430.0405580.0321070.0676950.0274700.1711870.5095460.3849420.0272130.1183831.0000000.0259742.7117720.992003
0Ready_Random1.5256331.2257140.0477200.0220490.0254940.0328450.0290770.0250150.0517570.0192420.1281810.5075430.3276780.0226280.1032690.9872750.1847045.1051220.906561
0Ready_I-KNN1.0303860.8130670.0260870.0069080.0105930.0160460.0211370.0095220.0242140.0089580.0480680.4998850.1548250.0080070.0695210.4023330.4343435.1336500.877999
0Ready_I-KNNBaseline0.9353270.7374240.0025450.0007550.0011050.0016020.0022530.0009300.0034440.0013620.0117600.4967240.0212090.0008620.0453790.4828210.0598852.2325780.994487
0Ready_U-KNN1.0234950.8079130.0007420.0002050.0003050.0004490.0005360.0001980.0008450.0002740.0027440.4964410.0074230.0002350.0425330.6021210.0108232.0891860.995706
0Self_BaselineIU0.9581360.7540510.0009540.0001880.0002980.0004810.0006440.0002230.0010430.0003350.0033480.4964330.0095440.0002200.0428090.6990460.0050511.9459100.995669
0Self_BaselineUI0.9675850.7627400.0009540.0001700.0002780.0004630.0006440.0001890.0007520.0001680.0016770.4964240.0095440.0002010.0426220.6005300.0050511.8031260.996380
0Self_IKNN1.0183630.8087930.0003180.0001080.0001400.0001890.0000000.0000000.0002140.0000370.0003680.4963910.0031810.0001180.0417550.3921530.1154404.1747410.965327
\n", "
" ], "text/plain": [ " Model RMSE MAE precision recall F_1 \\\n", "0 Self_RP3Beta 3.702928 3.527713 0.322694 0.216069 0.212152 \n", "0 Self_P3 3.702446 3.527273 0.282185 0.192092 0.186749 \n", "0 Self_TopPop 2.508258 2.217909 0.188865 0.116919 0.118732 \n", "0 Self_SVDBaseline 3.642359 3.476956 0.135949 0.079751 0.082423 \n", "0 Ready_SVD 0.951186 0.750553 0.094910 0.044564 0.051182 \n", "0 Self_SVD 0.914024 0.717181 0.104454 0.043836 0.053331 \n", "0 Ready_Baseline 0.949459 0.752487 0.091410 0.037652 0.046030 \n", "0 Ready_SVDBiased 0.939359 0.740564 0.086850 0.036359 0.043933 \n", "0 Self_KNNSurprisetask 0.946255 0.745209 0.083457 0.032848 0.041227 \n", "0 Self_TopRated 2.508258 2.217909 0.079321 0.032667 0.039983 \n", "0 Self_GlobalAvg 1.125760 0.943534 0.061188 0.025968 0.031383 \n", "0 Ready_Random 1.525633 1.225714 0.047720 0.022049 0.025494 \n", "0 Ready_I-KNN 1.030386 0.813067 0.026087 0.006908 0.010593 \n", "0 Ready_I-KNNBaseline 0.935327 0.737424 0.002545 0.000755 0.001105 \n", "0 Ready_U-KNN 1.023495 0.807913 0.000742 0.000205 0.000305 \n", "0 Self_BaselineIU 0.958136 0.754051 0.000954 0.000188 0.000298 \n", "0 Self_BaselineUI 0.967585 0.762740 0.000954 0.000170 0.000278 \n", "0 Self_IKNN 1.018363 0.808793 0.000318 0.000108 0.000140 \n", "\n", " F_05 precision_super recall_super NDCG mAP MRR \\\n", "0 0.247538 0.245279 0.284983 0.388271 0.248239 0.636318 \n", "0 0.216980 0.204185 0.240096 0.339114 0.204905 0.572157 \n", "0 0.141584 0.130472 0.137473 0.214651 0.111707 0.400939 \n", "0 0.099673 0.106545 0.104164 0.160100 0.079313 0.328798 \n", "0 0.065639 0.084549 0.074410 0.106164 0.049263 0.228326 \n", "0 0.070716 0.094528 0.076751 0.106711 0.050532 0.194366 \n", "0 0.061286 0.079614 0.056463 0.095957 0.043178 0.198193 \n", "0 0.058123 0.076395 0.056913 0.094528 0.043830 0.203204 \n", "0 0.055493 0.074785 0.048890 0.089577 0.040902 0.189057 \n", "0 0.053170 0.068884 0.048582 0.070766 0.027602 0.114790 \n", "0 0.041343 0.040558 0.032107 0.067695 0.027470 0.171187 \n", "0 0.032845 0.029077 0.025015 0.051757 0.019242 0.128181 \n", "0 0.016046 0.021137 0.009522 0.024214 0.008958 0.048068 \n", "0 0.001602 0.002253 0.000930 0.003444 0.001362 0.011760 \n", "0 0.000449 0.000536 0.000198 0.000845 0.000274 0.002744 \n", "0 0.000481 0.000644 0.000223 0.001043 0.000335 0.003348 \n", "0 0.000463 0.000644 0.000189 0.000752 0.000168 0.001677 \n", "0 0.000189 0.000000 0.000000 0.000214 0.000037 0.000368 \n", "\n", " LAUC HR F_2 Whole_average Reco in test Test coverage \\\n", "0 0.605683 0.910923 0.205450 0.376967 0.999788 0.178932 \n", "0 0.593544 0.875928 0.181702 0.340803 1.000000 0.077201 \n", "0 0.555546 0.765642 0.112750 0.249607 1.000000 0.038961 \n", "0 0.536764 0.629905 0.077617 0.201750 1.000000 0.282828 \n", "0 0.518988 0.477200 0.045601 0.153400 0.996925 0.219336 \n", "0 0.518647 0.479321 0.045941 0.153261 0.853765 0.148629 \n", "0 0.515501 0.437964 0.039549 0.141900 1.000000 0.033911 \n", "0 0.514846 0.443266 0.038036 0.141357 0.994804 0.179654 \n", "0 0.513076 0.417815 0.034996 0.135177 0.888547 0.130592 \n", "0 0.512943 0.411453 0.034385 0.124546 1.000000 0.024531 \n", "0 0.509546 0.384942 0.027213 0.118383 1.000000 0.025974 \n", "0 0.507543 0.327678 0.022628 0.103269 0.987275 0.184704 \n", "0 0.499885 0.154825 0.008007 0.069521 0.402333 0.434343 \n", "0 0.496724 0.021209 0.000862 0.045379 0.482821 0.059885 \n", "0 0.496441 0.007423 0.000235 0.042533 0.602121 0.010823 \n", "0 0.496433 0.009544 0.000220 0.042809 0.699046 0.005051 \n", "0 0.496424 0.009544 0.000201 0.042622 0.600530 0.005051 \n", "0 0.496391 0.003181 0.000118 0.041755 0.392153 0.115440 \n", "\n", " Shannon Gini \n", "0 4.549663 0.950182 \n", "0 3.875892 0.974947 \n", "0 3.159079 0.987317 \n", "0 5.130008 0.909760 \n", "0 4.494800 0.949844 \n", "0 3.836334 0.973007 \n", "0 2.836513 0.991139 \n", "0 4.199699 0.962848 \n", "0 3.611806 0.978659 \n", "0 2.761238 0.991660 \n", "0 2.711772 0.992003 \n", "0 5.105122 0.906561 \n", "0 5.133650 0.877999 \n", "0 2.232578 0.994487 \n", "0 2.089186 0.995706 \n", "0 1.945910 0.995669 \n", "0 1.803126 0.996380 \n", "0 4.174741 0.965327 " ] }, "execution_count": 17, "metadata": {}, "output_type": "execute_result" } ], "source": [ "import imp\n", "imp.reload(ev)\n", "\n", "import evaluation_measures as ev\n", "dir_path=\"Recommendations generated/ml-100k/\"\n", "super_reactions=[4,5]\n", "test=pd.read_csv('./Datasets/ml-100k/test.csv', sep='\\t', header=None)\n", "\n", "ev.evaluate_all(test, dir_path, super_reactions)" ] }, { "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": "3.6.9" } }, "nbformat": 4, "nbformat_minor": 4 }