s406917/workshops_recommender_systems
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity
8ad2469287
workshops_recommender_systems/P4. Matrix Factorization.ipynb

1404 lines
73 KiB
Plaintext
Raw Normal View History

Codes added
2020-05-21 13:42:50 +02:00
{
"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",
Slides added
2020-05-21 16:20:12 +02:00
"execution_count": 2,
Codes added
2020-05-21 13:42:50 +02:00
"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",
Slides added
2020-05-21 16:20:12 +02:00
"execution_count": 3,
Codes added
2020-05-21 13:42:50 +02:00
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
Slides added
2020-05-21 16:20:12 +02:00
"Epoch 39 RMSE: 0.7480082047970615. Training epoch 40...: 100%|██████████| 40/40 [01:21<00:00, 2.05s/it]\n"
Codes added
2020-05-21 13:42:50 +02:00
]
}
],
"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",
Slides added
2020-05-21 16:20:12 +02:00
"execution_count": 5,
Codes added
2020-05-21 13:42:50 +02:00
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
Slides added
2020-05-21 16:20:12 +02:00
"<matplotlib.legend.Legend at 0x7f77ab510e48>"
Codes added
2020-05-21 13:42:50 +02:00
]
},
Slides added
2020-05-21 16:20:12 +02:00
"execution_count": 5,
Codes added
2020-05-21 13:42:50 +02:00
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
Slides added
2020-05-21 16:20:12 +02:00
"image/png": "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
Codes added
2020-05-21 13:42:50 +02:00
"text/plain": [
Slides added
2020-05-21 16:20:12 +02:00
"<matplotlib.figure.Figure at 0x7f77a9afdba8>"
Codes added
2020-05-21 13:42:50 +02:00
]
},
"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",
Slides added
2020-05-21 16:20:12 +02:00
"execution_count": 6,
Codes added
2020-05-21 13:42:50 +02:00
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
Slides added
2020-05-21 16:20:12 +02:00
"<matplotlib.legend.Legend at 0x7f774c4e3fd0>"
Codes added
2020-05-21 13:42:50 +02:00
]
},
Slides added
2020-05-21 16:20:12 +02:00
"execution_count": 6,
Codes added
2020-05-21 13:42:50 +02:00
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
Slides added
2020-05-21 16:20:12 +02:00
"image/png": "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
Codes added
2020-05-21 13:42:50 +02:00
"text/plain": [
Slides added
2020-05-21 16:20:12 +02:00
"<matplotlib.figure.Figure at 0x7f77a08e7748>"
Codes added
2020-05-21 13:42:50 +02:00
]
},
"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",
Slides added
2020-05-21 16:20:12 +02:00
"execution_count": 7,
Codes added
2020-05-21 13:42:50 +02:00
"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",
Slides added
2020-05-21 16:20:12 +02:00
"execution_count": 8,
Codes added
2020-05-21 13:42:50 +02:00
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
Slides added
2020-05-21 16:20:12 +02:00
"943it [00:00, 8982.19it/s]\n"
Codes added
2020-05-21 13:42:50 +02:00
]
},
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>RMSE</th>\n",
" <th>MAE</th>\n",
" <th>precision</th>\n",
" <th>recall</th>\n",
" <th>F_1</th>\n",
" <th>F_05</th>\n",
" <th>precision_super</th>\n",
" <th>recall_super</th>\n",
" <th>NDCG</th>\n",
" <th>mAP</th>\n",
" <th>MRR</th>\n",
" <th>LAUC</th>\n",
" <th>HR</th>\n",
" <th>Reco in test</th>\n",
" <th>Test coverage</th>\n",
" <th>Shannon</th>\n",
" <th>Gini</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
Slides added
2020-05-21 16:20:12 +02:00
" <td>0.914856</td>\n",
" <td>0.718384</td>\n",
" <td>0.100424</td>\n",
" <td>0.040859</td>\n",
" <td>0.050523</td>\n",
" <td>0.067431</td>\n",
" <td>0.090665</td>\n",
" <td>0.068368</td>\n",
" <td>0.101328</td>\n",
" <td>0.047917</td>\n",
" <td>0.183792</td>\n",
" <td>0.517141</td>\n",
" <td>0.459173</td>\n",
" <td>0.860551</td>\n",
" <td>0.146465</td>\n",
" <td>3.853236</td>\n",
" <td>0.971798</td>\n",
Codes added
2020-05-21 13:42:50 +02:00
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
Slides added
2020-05-21 16:20:12 +02:00
" RMSE MAE precision recall F_1 F_05 \\\n",
"0 0.914856 0.718384 0.100424 0.040859 0.050523 0.067431 \n",
Codes added
2020-05-21 13:42:50 +02:00
"\n",
Slides added
2020-05-21 16:20:12 +02:00
" precision_super recall_super NDCG mAP MRR LAUC \\\n",
"0 0.090665 0.068368 0.101328 0.047917 0.183792 0.517141 \n",
Codes added
2020-05-21 13:42:50 +02:00
"\n",
Slides added
2020-05-21 16:20:12 +02:00
" HR Reco in test Test coverage Shannon Gini \n",
"0 0.459173 0.860551 0.146465 3.853236 0.971798 "
Codes added
2020-05-21 13:42:50 +02:00
]
},
Slides added
2020-05-21 16:20:12 +02:00
"execution_count": 8,
Codes added
2020-05-21 13:42:50 +02:00
"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",
Slides added
2020-05-21 16:20:12 +02:00
"execution_count": 11,
Codes added
2020-05-21 13:42:50 +02:00
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
Slides added
2020-05-21 16:20:12 +02:00
"943it [00:00, 9603.22it/s]\n",
"943it [00:00, 8786.72it/s]\n",
"943it [00:00, 8141.95it/s]\n",
"943it [00:00, 8884.14it/s]\n",
"943it [00:00, 10117.77it/s]\n",
"943it [00:00, 8687.46it/s]\n",
"943it [00:00, 10361.84it/s]\n",
"943it [00:00, 10162.64it/s]\n",
"943it [00:00, 8493.19it/s]\n",
"943it [00:00, 9153.50it/s]\n"
Codes added
2020-05-21 13:42:50 +02:00
]
},
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Model</th>\n",
" <th>RMSE</th>\n",
" <th>MAE</th>\n",
" <th>precision</th>\n",
" <th>recall</th>\n",
" <th>F_1</th>\n",
" <th>F_05</th>\n",
" <th>precision_super</th>\n",
" <th>recall_super</th>\n",
" <th>NDCG</th>\n",
" <th>mAP</th>\n",
" <th>MRR</th>\n",
" <th>LAUC</th>\n",
" <th>HR</th>\n",
" <th>Reco in test</th>\n",
" <th>Test coverage</th>\n",
" <th>Shannon</th>\n",
" <th>Gini</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Self_TopPop</td>\n",
" <td>2.508258</td>\n",
" <td>2.217909</td>\n",
" <td>0.188865</td>\n",
" <td>0.116919</td>\n",
" <td>0.118732</td>\n",
" <td>0.141584</td>\n",
" <td>0.130472</td>\n",
" <td>0.137473</td>\n",
" <td>0.214651</td>\n",
" <td>0.111707</td>\n",
" <td>0.400939</td>\n",
" <td>0.555546</td>\n",
" <td>0.765642</td>\n",
" <td>1.000000</td>\n",
" <td>0.038961</td>\n",
" <td>3.159079</td>\n",
" <td>0.987317</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Self_SVD</td>\n",
Slides added
2020-05-21 16:20:12 +02:00
" <td>0.914856</td>\n",
" <td>0.718384</td>\n",
" <td>0.100424</td>\n",
" <td>0.040859</td>\n",
" <td>0.050523</td>\n",
" <td>0.067431</td>\n",
" <td>0.090665</td>\n",
" <td>0.068368</td>\n",
" <td>0.101328</td>\n",
" <td>0.047917</td>\n",
" <td>0.183792</td>\n",
" <td>0.517141</td>\n",
" <td>0.459173</td>\n",
" <td>0.860551</td>\n",
" <td>0.146465</td>\n",
" <td>3.853236</td>\n",
" <td>0.971798</td>\n",
Codes added
2020-05-21 13:42:50 +02:00
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Ready_Baseline</td>\n",
" <td>0.949459</td>\n",
" <td>0.752487</td>\n",
" <td>0.091410</td>\n",
" <td>0.037652</td>\n",
" <td>0.046030</td>\n",
" <td>0.061286</td>\n",
" <td>0.079614</td>\n",
" <td>0.056463</td>\n",
" <td>0.095957</td>\n",
" <td>0.043178</td>\n",
" <td>0.198193</td>\n",
" <td>0.515501</td>\n",
" <td>0.437964</td>\n",
" <td>1.000000</td>\n",
" <td>0.033911</td>\n",
" <td>2.836513</td>\n",
" <td>0.991139</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Self_GlobalAvg</td>\n",
" <td>1.125760</td>\n",
" <td>0.943534</td>\n",
" <td>0.061188</td>\n",
" <td>0.025968</td>\n",
" <td>0.031383</td>\n",
" <td>0.041343</td>\n",
" <td>0.040558</td>\n",
" <td>0.032107</td>\n",
" <td>0.067695</td>\n",
" <td>0.027470</td>\n",
" <td>0.171187</td>\n",
" <td>0.509546</td>\n",
" <td>0.384942</td>\n",
" <td>1.000000</td>\n",
" <td>0.025974</td>\n",
" <td>2.711772</td>\n",
" <td>0.992003</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Ready_Random</td>\n",
Slides added
2020-05-21 16:20:12 +02:00
" <td>1.518964</td>\n",
" <td>1.222159</td>\n",
" <td>0.046554</td>\n",
" <td>0.020603</td>\n",
" <td>0.023679</td>\n",
" <td>0.031216</td>\n",
" <td>0.028970</td>\n",
" <td>0.021179</td>\n",
" <td>0.050489</td>\n",
" <td>0.019185</td>\n",
" <td>0.123856</td>\n",
" <td>0.506812</td>\n",
" <td>0.322375</td>\n",
" <td>0.987805</td>\n",
" <td>0.184704</td>\n",
" <td>5.103172</td>\n",
" <td>0.906873</td>\n",
Codes added
2020-05-21 13:42:50 +02:00
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Ready_I-KNN</td>\n",
" <td>1.030386</td>\n",
" <td>0.813067</td>\n",
" <td>0.026087</td>\n",
" <td>0.006908</td>\n",
" <td>0.010593</td>\n",
" <td>0.016046</td>\n",
" <td>0.021137</td>\n",
" <td>0.009522</td>\n",
" <td>0.024214</td>\n",
" <td>0.008958</td>\n",
" <td>0.048068</td>\n",
" <td>0.499885</td>\n",
" <td>0.154825</td>\n",
" <td>0.402333</td>\n",
" <td>0.434343</td>\n",
" <td>5.133650</td>\n",
" <td>0.877999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Ready_I-KNNBaseline</td>\n",
" <td>0.935327</td>\n",
" <td>0.737424</td>\n",
" <td>0.002545</td>\n",
" <td>0.000755</td>\n",
" <td>0.001105</td>\n",
" <td>0.001602</td>\n",
" <td>0.002253</td>\n",
" <td>0.000930</td>\n",
" <td>0.003444</td>\n",
" <td>0.001362</td>\n",
" <td>0.011760</td>\n",
" <td>0.496724</td>\n",
" <td>0.021209</td>\n",
" <td>0.482821</td>\n",
" <td>0.059885</td>\n",
" <td>2.232578</td>\n",
" <td>0.994487</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Ready_U-KNN</td>\n",
" <td>1.023495</td>\n",
" <td>0.807913</td>\n",
" <td>0.000742</td>\n",
" <td>0.000205</td>\n",
" <td>0.000305</td>\n",
" <td>0.000449</td>\n",
" <td>0.000536</td>\n",
" <td>0.000198</td>\n",
" <td>0.000845</td>\n",
" <td>0.000274</td>\n",
" <td>0.002744</td>\n",
" <td>0.496441</td>\n",
" <td>0.007423</td>\n",
" <td>0.602121</td>\n",
" <td>0.010823</td>\n",
" <td>2.089186</td>\n",
" <td>0.995706</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Self_BaselineUI</td>\n",
" <td>0.967585</td>\n",
" <td>0.762740</td>\n",
" <td>0.000954</td>\n",
" <td>0.000170</td>\n",
" <td>0.000278</td>\n",
" <td>0.000463</td>\n",
" <td>0.000644</td>\n",
" <td>0.000189</td>\n",
" <td>0.000752</td>\n",
" <td>0.000168</td>\n",
" <td>0.001677</td>\n",
" <td>0.496424</td>\n",
" <td>0.009544</td>\n",
" <td>0.600530</td>\n",
" <td>0.005051</td>\n",
" <td>1.803126</td>\n",
" <td>0.996380</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Self_IKNN</td>\n",
" <td>1.018363</td>\n",
" <td>0.808793</td>\n",
" <td>0.000318</td>\n",
" <td>0.000108</td>\n",
" <td>0.000140</td>\n",
" <td>0.000189</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000214</td>\n",
" <td>0.000037</td>\n",
" <td>0.000368</td>\n",
" <td>0.496391</td>\n",
" <td>0.003181</td>\n",
" <td>0.392153</td>\n",
" <td>0.115440</td>\n",
" <td>4.174741</td>\n",
" <td>0.965327</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Model RMSE MAE precision recall F_1 \\\n",
"0 Self_TopPop 2.508258 2.217909 0.188865 0.116919 0.118732 \n",
Slides added
2020-05-21 16:20:12 +02:00
"0 Self_SVD 0.914856 0.718384 0.100424 0.040859 0.050523 \n",
Codes added
2020-05-21 13:42:50 +02:00
"0 Ready_Baseline 0.949459 0.752487 0.091410 0.037652 0.046030 \n",
"0 Self_GlobalAvg 1.125760 0.943534 0.061188 0.025968 0.031383 \n",
Slides added
2020-05-21 16:20:12 +02:00
"0 Ready_Random 1.518964 1.222159 0.046554 0.020603 0.023679 \n",
Codes added
2020-05-21 13:42:50 +02:00
"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_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 0.141584 0.130472 0.137473 0.214651 0.111707 0.400939 \n",
Slides added
2020-05-21 16:20:12 +02:00
"0 0.067431 0.090665 0.068368 0.101328 0.047917 0.183792 \n",
Codes added
2020-05-21 13:42:50 +02:00
"0 0.061286 0.079614 0.056463 0.095957 0.043178 0.198193 \n",
"0 0.041343 0.040558 0.032107 0.067695 0.027470 0.171187 \n",
Slides added
2020-05-21 16:20:12 +02:00
"0 0.031216 0.028970 0.021179 0.050489 0.019185 0.123856 \n",
Codes added
2020-05-21 13:42:50 +02:00
"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 0.000463 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 Reco in test Test coverage Shannon Gini \n",
"0 0.555546 0.765642 1.000000 0.038961 3.159079 0.987317 \n",
Slides added
2020-05-21 16:20:12 +02:00
"0 0.517141 0.459173 0.860551 0.146465 3.853236 0.971798 \n",
Codes added
2020-05-21 13:42:50 +02:00
"0 0.515501 0.437964 1.000000 0.033911 2.836513 0.991139 \n",
"0 0.509546 0.384942 1.000000 0.025974 2.711772 0.992003 \n",
Slides added
2020-05-21 16:20:12 +02:00
"0 0.506812 0.322375 0.987805 0.184704 5.103172 0.906873 \n",
Codes added
2020-05-21 13:42:50 +02:00
"0 0.499885 0.154825 0.402333 0.434343 5.133650 0.877999 \n",
"0 0.496724 0.021209 0.482821 0.059885 2.232578 0.994487 \n",
"0 0.496441 0.007423 0.602121 0.010823 2.089186 0.995706 \n",
"0 0.496424 0.009544 0.600530 0.005051 1.803126 0.996380 \n",
"0 0.496391 0.003181 0.392153 0.115440 4.174741 0.965327 "
]
},
Slides added
2020-05-21 16:20:12 +02:00
"execution_count": 11,
Codes added
2020-05-21 13:42:50 +02:00
"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",
Slides added
2020-05-21 16:20:12 +02:00
"execution_count": 12,
Codes added
2020-05-21 13:42:50 +02:00
"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 ]])"
]
},
Slides added
2020-05-21 16:20:12 +02:00
"execution_count": 12,
Codes added
2020-05-21 13:42:50 +02:00
"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",
Slides added
2020-05-21 16:20:12 +02:00
"execution_count": 13,
Codes added
2020-05-21 13:42:50 +02:00
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>code</th>\n",
" <th>score</th>\n",
" <th>item_id</th>\n",
" <th>id</th>\n",
" <th>title</th>\n",
" <th>genres</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
Slides added
2020-05-21 16:20:12 +02:00
" <td>916</td>\n",
Codes added
2020-05-21 13:42:50 +02:00
" <td>1.000000</td>\n",
Slides added
2020-05-21 16:20:12 +02:00
" <td>917</td>\n",
" <td>917</td>\n",
" <td>Mercury Rising (1998)</td>\n",
" <td>Action, Drama, Thriller</td>\n",
Codes added
2020-05-21 13:42:50 +02:00
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
Slides added
2020-05-21 16:20:12 +02:00
" <td>914</td>\n",
" <td>0.991506</td>\n",
" <td>915</td>\n",
" <td>915</td>\n",
" <td>Primary Colors (1998)</td>\n",
" <td>Drama</td>\n",
Codes added
2020-05-21 13:42:50 +02:00
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
Slides added
2020-05-21 16:20:12 +02:00
" <td>908</td>\n",
" <td>0.990078</td>\n",
" <td>909</td>\n",
" <td>909</td>\n",
" <td>Dangerous Beauty (1998)</td>\n",
Codes added
2020-05-21 13:42:50 +02:00
" <td>Drama</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
Slides added
2020-05-21 16:20:12 +02:00
" <td>690</td>\n",
" <td>0.989487</td>\n",
" <td>691</td>\n",
" <td>691</td>\n",
" <td>Dark City (1998)</td>\n",
" <td>Film-Noir, Sci-Fi, Thriller</td>\n",
Codes added
2020-05-21 13:42:50 +02:00
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
Slides added
2020-05-21 16:20:12 +02:00
" <td>359</td>\n",
" <td>0.988384</td>\n",
" <td>360</td>\n",
" <td>360</td>\n",
" <td>Wonderland (1997)</td>\n",
" <td>Documentary</td>\n",
Codes added
2020-05-21 13:42:50 +02:00
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
Slides added
2020-05-21 16:20:12 +02:00
" <td>810</td>\n",
" <td>0.987781</td>\n",
" <td>811</td>\n",
" <td>811</td>\n",
" <td>Thirty-Two Short Films About Glenn Gould (1993)</td>\n",
" <td>Documentary</td>\n",
Codes added
2020-05-21 13:42:50 +02:00
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
Slides added
2020-05-21 16:20:12 +02:00
" <td>917</td>\n",
" <td>0.986770</td>\n",
" <td>918</td>\n",
" <td>918</td>\n",
" <td>City of Angels (1998)</td>\n",
" <td>Romance</td>\n",
Codes added
2020-05-21 13:42:50 +02:00
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
Slides added
2020-05-21 16:20:12 +02:00
" <td>869</td>\n",
" <td>0.986746</td>\n",
" <td>870</td>\n",
" <td>870</td>\n",
" <td>Touch (1997)</td>\n",
" <td>Romance</td>\n",
Codes added
2020-05-21 13:42:50 +02:00
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
Slides added
2020-05-21 16:20:12 +02:00
" <td>756</td>\n",
" <td>0.986005</td>\n",
" <td>757</td>\n",
" <td>757</td>\n",
" <td>Across the Sea of Time (1995)</td>\n",
" <td>Documentary</td>\n",
Codes added
2020-05-21 13:42:50 +02:00
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
Slides added
2020-05-21 16:20:12 +02:00
" <td>732</td>\n",
" <td>0.985919</td>\n",
" <td>733</td>\n",
" <td>733</td>\n",
" <td>Go Fish (1994)</td>\n",
" <td>Drama, Romance</td>\n",
Codes added
2020-05-21 13:42:50 +02:00
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
Slides added
2020-05-21 16:20:12 +02:00
" code score item_id id \\\n",
"0 916 1.000000 917 917 \n",
"1 914 0.991506 915 915 \n",
"2 908 0.990078 909 909 \n",
"3 690 0.989487 691 691 \n",
"4 359 0.988384 360 360 \n",
"5 810 0.987781 811 811 \n",
"6 917 0.986770 918 918 \n",
"7 869 0.986746 870 870 \n",
"8 756 0.986005 757 757 \n",
"9 732 0.985919 733 733 \n",
Codes added
2020-05-21 13:42:50 +02:00
"\n",
Slides added
2020-05-21 16:20:12 +02:00
" title \\\n",
"0 Mercury Rising (1998) \n",
"1 Primary Colors (1998) \n",
"2 Dangerous Beauty (1998) \n",
"3 Dark City (1998) \n",
"4 Wonderland (1997) \n",
"5 Thirty-Two Short Films About Glenn Gould (1993) \n",
"6 City of Angels (1998) \n",
"7 Touch (1997) \n",
"8 Across the Sea of Time (1995) \n",
"9 Go Fish (1994) \n",
"\n",
" genres \n",
"0 Action, Drama, Thriller \n",
"1 Drama \n",
"2 Drama \n",
"3 Film-Noir, Sci-Fi, Thriller \n",
"4 Documentary \n",
"5 Documentary \n",
"6 Romance \n",
"7 Romance \n",
"8 Documentary \n",
"9 Drama, Romance "
Codes added
2020-05-21 13:42:50 +02:00
]
},
Slides added
2020-05-21 16:20:12 +02:00
"execution_count": 13,
Codes added
2020-05-21 13:42:50 +02:00
"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": 34,
"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'"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Ready-made SVD - Surprise implementation"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### SVD"
]
},
{
"cell_type": "code",
Slides added
2020-05-21 16:20:12 +02:00
"execution_count": 14,
Codes added
2020-05-21 13:42:50 +02:00
"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",
Slides added
2020-05-21 16:20:12 +02:00
"execution_count": 15,
Codes added
2020-05-21 13:42:50 +02:00
"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",
Slides added
2020-05-21 16:20:12 +02:00
"execution_count": 16,
Codes added
2020-05-21 13:42:50 +02:00
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
Slides added
2020-05-21 16:20:12 +02:00
"943it [00:00, 8010.33it/s]\n",
"943it [00:00, 7939.12it/s]\n",
"943it [00:00, 8331.15it/s]\n",
"943it [00:00, 8696.10it/s]\n",
"943it [00:00, 8172.62it/s]\n",
"943it [00:00, 8807.34it/s]\n",
"943it [00:00, 8646.67it/s]\n",
"943it [00:00, 7192.36it/s]\n",
"943it [00:00, 8888.67it/s]\n",
"943it [00:00, 8736.94it/s]\n",
"943it [00:00, 8047.44it/s]\n",
"943it [00:00, 8326.85it/s]\n"
Codes added
2020-05-21 13:42:50 +02:00
]
},
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Model</th>\n",
" <th>RMSE</th>\n",
" <th>MAE</th>\n",
" <th>precision</th>\n",
" <th>recall</th>\n",
" <th>F_1</th>\n",
" <th>F_05</th>\n",
" <th>precision_super</th>\n",
" <th>recall_super</th>\n",
" <th>NDCG</th>\n",
" <th>mAP</th>\n",
" <th>MRR</th>\n",
" <th>LAUC</th>\n",
" <th>HR</th>\n",
" <th>Reco in test</th>\n",
" <th>Test coverage</th>\n",
" <th>Shannon</th>\n",
" <th>Gini</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Self_TopPop</td>\n",
" <td>2.508258</td>\n",
" <td>2.217909</td>\n",
" <td>0.188865</td>\n",
" <td>0.116919</td>\n",
" <td>0.118732</td>\n",
" <td>0.141584</td>\n",
" <td>0.130472</td>\n",
" <td>0.137473</td>\n",
" <td>0.214651</td>\n",
" <td>0.111707</td>\n",
" <td>0.400939</td>\n",
" <td>0.555546</td>\n",
" <td>0.765642</td>\n",
" <td>1.000000</td>\n",
" <td>0.038961</td>\n",
" <td>3.159079</td>\n",
" <td>0.987317</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Ready_SVD</td>\n",
Slides added
2020-05-21 16:20:12 +02:00
" <td>0.952889</td>\n",
" <td>0.750674</td>\n",
" <td>0.098834</td>\n",
" <td>0.047899</td>\n",
" <td>0.053663</td>\n",
" <td>0.068581</td>\n",
" <td>0.087876</td>\n",
" <td>0.076831</td>\n",
" <td>0.113446</td>\n",
" <td>0.054127</td>\n",
" <td>0.242918</td>\n",
" <td>0.520677</td>\n",
" <td>0.488865</td>\n",
" <td>0.998091</td>\n",
" <td>0.204906</td>\n",
" <td>4.440336</td>\n",
" <td>0.952374</td>\n",
Codes added
2020-05-21 13:42:50 +02:00
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Self_SVD</td>\n",
Slides added
2020-05-21 16:20:12 +02:00
" <td>0.914856</td>\n",
" <td>0.718384</td>\n",
" <td>0.100424</td>\n",
" <td>0.040859</td>\n",
" <td>0.050523</td>\n",
" <td>0.067431</td>\n",
" <td>0.090665</td>\n",
" <td>0.068368</td>\n",
" <td>0.101328</td>\n",
" <td>0.047917</td>\n",
" <td>0.183792</td>\n",
" <td>0.517141</td>\n",
" <td>0.459173</td>\n",
" <td>0.860551</td>\n",
" <td>0.146465</td>\n",
" <td>3.853236</td>\n",
" <td>0.971798</td>\n",
Codes added
2020-05-21 13:42:50 +02:00
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Ready_Baseline</td>\n",
" <td>0.949459</td>\n",
" <td>0.752487</td>\n",
" <td>0.091410</td>\n",
" <td>0.037652</td>\n",
" <td>0.046030</td>\n",
" <td>0.061286</td>\n",
" <td>0.079614</td>\n",
" <td>0.056463</td>\n",
" <td>0.095957</td>\n",
" <td>0.043178</td>\n",
" <td>0.198193</td>\n",
" <td>0.515501</td>\n",
" <td>0.437964</td>\n",
" <td>1.000000</td>\n",
" <td>0.033911</td>\n",
" <td>2.836513</td>\n",
" <td>0.991139</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
Slides added
2020-05-21 16:20:12 +02:00
" <td>Ready_SVDBiased</td>\n",
" <td>0.939807</td>\n",
" <td>0.741610</td>\n",
" <td>0.082078</td>\n",
" <td>0.032691</td>\n",
" <td>0.040611</td>\n",
" <td>0.054503</td>\n",
" <td>0.073391</td>\n",
" <td>0.051400</td>\n",
" <td>0.088531</td>\n",
" <td>0.039739</td>\n",
" <td>0.188187</td>\n",
" <td>0.512998</td>\n",
" <td>0.423118</td>\n",
" <td>0.995864</td>\n",
" <td>0.172439</td>\n",
" <td>4.176612</td>\n",
" <td>0.963967</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
Codes added
2020-05-21 13:42:50 +02:00
" <td>Self_GlobalAvg</td>\n",
" <td>1.125760</td>\n",
" <td>0.943534</td>\n",
" <td>0.061188</td>\n",
" <td>0.025968</td>\n",
" <td>0.031383</td>\n",
" <td>0.041343</td>\n",
" <td>0.040558</td>\n",
" <td>0.032107</td>\n",
" <td>0.067695</td>\n",
" <td>0.027470</td>\n",
" <td>0.171187</td>\n",
" <td>0.509546</td>\n",
" <td>0.384942</td>\n",
" <td>1.000000</td>\n",
" <td>0.025974</td>\n",
" <td>2.711772</td>\n",
" <td>0.992003</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Ready_Random</td>\n",
Slides added
2020-05-21 16:20:12 +02:00
" <td>1.518964</td>\n",
" <td>1.222159</td>\n",
" <td>0.046554</td>\n",
" <td>0.020603</td>\n",
" <td>0.023679</td>\n",
" <td>0.031216</td>\n",
" <td>0.028970</td>\n",
" <td>0.021179</td>\n",
" <td>0.050489</td>\n",
" <td>0.019185</td>\n",
" <td>0.123856</td>\n",
" <td>0.506812</td>\n",
" <td>0.322375</td>\n",
" <td>0.987805</td>\n",
" <td>0.184704</td>\n",
" <td>5.103172</td>\n",
" <td>0.906873</td>\n",
Codes added
2020-05-21 13:42:50 +02:00
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Ready_I-KNN</td>\n",
" <td>1.030386</td>\n",
" <td>0.813067</td>\n",
" <td>0.026087</td>\n",
" <td>0.006908</td>\n",
" <td>0.010593</td>\n",
" <td>0.016046</td>\n",
" <td>0.021137</td>\n",
" <td>0.009522</td>\n",
" <td>0.024214</td>\n",
" <td>0.008958</td>\n",
" <td>0.048068</td>\n",
" <td>0.499885</td>\n",
" <td>0.154825</td>\n",
" <td>0.402333</td>\n",
" <td>0.434343</td>\n",
" <td>5.133650</td>\n",
" <td>0.877999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Ready_I-KNNBaseline</td>\n",
" <td>0.935327</td>\n",
" <td>0.737424</td>\n",
" <td>0.002545</td>\n",
" <td>0.000755</td>\n",
" <td>0.001105</td>\n",
" <td>0.001602</td>\n",
" <td>0.002253</td>\n",
" <td>0.000930</td>\n",
" <td>0.003444</td>\n",
" <td>0.001362</td>\n",
" <td>0.011760</td>\n",
" <td>0.496724</td>\n",
" <td>0.021209</td>\n",
" <td>0.482821</td>\n",
" <td>0.059885</td>\n",
" <td>2.232578</td>\n",
" <td>0.994487</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Ready_U-KNN</td>\n",
" <td>1.023495</td>\n",
" <td>0.807913</td>\n",
" <td>0.000742</td>\n",
" <td>0.000205</td>\n",
" <td>0.000305</td>\n",
" <td>0.000449</td>\n",
" <td>0.000536</td>\n",
" <td>0.000198</td>\n",
" <td>0.000845</td>\n",
" <td>0.000274</td>\n",
" <td>0.002744</td>\n",
" <td>0.496441</td>\n",
" <td>0.007423</td>\n",
" <td>0.602121</td>\n",
" <td>0.010823</td>\n",
" <td>2.089186</td>\n",
" <td>0.995706</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Self_BaselineUI</td>\n",
" <td>0.967585</td>\n",
" <td>0.762740</td>\n",
" <td>0.000954</td>\n",
" <td>0.000170</td>\n",
" <td>0.000278</td>\n",
" <td>0.000463</td>\n",
" <td>0.000644</td>\n",
" <td>0.000189</td>\n",
" <td>0.000752</td>\n",
" <td>0.000168</td>\n",
" <td>0.001677</td>\n",
" <td>0.496424</td>\n",
" <td>0.009544</td>\n",
" <td>0.600530</td>\n",
" <td>0.005051</td>\n",
" <td>1.803126</td>\n",
" <td>0.996380</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Self_IKNN</td>\n",
" <td>1.018363</td>\n",
" <td>0.808793</td>\n",
" <td>0.000318</td>\n",
" <td>0.000108</td>\n",
" <td>0.000140</td>\n",
" <td>0.000189</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000214</td>\n",
" <td>0.000037</td>\n",
" <td>0.000368</td>\n",
" <td>0.496391</td>\n",
" <td>0.003181</td>\n",
" <td>0.392153</td>\n",
" <td>0.115440</td>\n",
" <td>4.174741</td>\n",
" <td>0.965327</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Model RMSE MAE precision recall F_1 \\\n",
"0 Self_TopPop 2.508258 2.217909 0.188865 0.116919 0.118732 \n",
Slides added
2020-05-21 16:20:12 +02:00
"0 Ready_SVD 0.952889 0.750674 0.098834 0.047899 0.053663 \n",
"0 Self_SVD 0.914856 0.718384 0.100424 0.040859 0.050523 \n",
Codes added
2020-05-21 13:42:50 +02:00
"0 Ready_Baseline 0.949459 0.752487 0.091410 0.037652 0.046030 \n",
Slides added
2020-05-21 16:20:12 +02:00
"0 Ready_SVDBiased 0.939807 0.741610 0.082078 0.032691 0.040611 \n",
Codes added
2020-05-21 13:42:50 +02:00
"0 Self_GlobalAvg 1.125760 0.943534 0.061188 0.025968 0.031383 \n",
Slides added
2020-05-21 16:20:12 +02:00
"0 Ready_Random 1.518964 1.222159 0.046554 0.020603 0.023679 \n",
Codes added
2020-05-21 13:42:50 +02:00
"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_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 0.141584 0.130472 0.137473 0.214651 0.111707 0.400939 \n",
Slides added
2020-05-21 16:20:12 +02:00
"0 0.068581 0.087876 0.076831 0.113446 0.054127 0.242918 \n",
"0 0.067431 0.090665 0.068368 0.101328 0.047917 0.183792 \n",
Codes added
2020-05-21 13:42:50 +02:00
"0 0.061286 0.079614 0.056463 0.095957 0.043178 0.198193 \n",
Slides added
2020-05-21 16:20:12 +02:00
"0 0.054503 0.073391 0.051400 0.088531 0.039739 0.188187 \n",
Codes added
2020-05-21 13:42:50 +02:00
"0 0.041343 0.040558 0.032107 0.067695 0.027470 0.171187 \n",
Slides added
2020-05-21 16:20:12 +02:00
"0 0.031216 0.028970 0.021179 0.050489 0.019185 0.123856 \n",
Codes added
2020-05-21 13:42:50 +02:00
"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 0.000463 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 Reco in test Test coverage Shannon Gini \n",
"0 0.555546 0.765642 1.000000 0.038961 3.159079 0.987317 \n",
Slides added
2020-05-21 16:20:12 +02:00
"0 0.520677 0.488865 0.998091 0.204906 4.440336 0.952374 \n",
"0 0.517141 0.459173 0.860551 0.146465 3.853236 0.971798 \n",
Codes added
2020-05-21 13:42:50 +02:00
"0 0.515501 0.437964 1.000000 0.033911 2.836513 0.991139 \n",
Slides added
2020-05-21 16:20:12 +02:00
"0 0.512998 0.423118 0.995864 0.172439 4.176612 0.963967 \n",
Codes added
2020-05-21 13:42:50 +02:00
"0 0.509546 0.384942 1.000000 0.025974 2.711772 0.992003 \n",
Slides added
2020-05-21 16:20:12 +02:00
"0 0.506812 0.322375 0.987805 0.184704 5.103172 0.906873 \n",
Codes added
2020-05-21 13:42:50 +02:00
"0 0.499885 0.154825 0.402333 0.434343 5.133650 0.877999 \n",
"0 0.496724 0.021209 0.482821 0.059885 2.232578 0.994487 \n",
"0 0.496441 0.007423 0.602121 0.010823 2.089186 0.995706 \n",
"0 0.496424 0.009544 0.600530 0.005051 1.803126 0.996380 \n",
"0 0.496391 0.003181 0.392153 0.115440 4.174741 0.965327 "
]
},
Slides added
2020-05-21 16:20:12 +02:00
"execution_count": 16,
Codes added
2020-05-21 13:42:50 +02:00
"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)"
]
}
],
"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
}
Reference in New Issue Copy Permalink