s452101/workshops_recommender_systems
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity
master
workshops_recommender_systems/P5. Graph-based.ipynb

1386 lines
554 KiB
Plaintext
Raw Permalink Normal View History

Project task 1 - self made top rated
2020-09-29 20:23:22 +02:00
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Self made RP3-beta"
]
},
{
"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",
"import time\n",
"import matplotlib.pyplot as plt\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": [
"class RP3Beta():\n",
" def fit(self, train_ui, alpha, beta):\n",
" \"\"\"We weight our edges by user's explicit ratings so if user rated movie high we'll follow that path\n",
" with higher probability.\"\"\"\n",
" self.train_ui=train_ui\n",
" self.train_iu=train_ui.transpose()\n",
" \n",
" self.alpha = alpha\n",
" self.beta = beta\n",
" \n",
" # Define Pui \n",
" Pui=sparse.csr_matrix(self.train_ui/self.train_ui.sum(axis=1))\n",
" \n",
" # Define Piu\n",
" to_divide=np.vectorize(lambda x: x if x>0 else 1)(self.train_iu.sum(axis=1)) # to avoid dividing by zero\n",
" Piu=sparse.csr_matrix(self.train_iu/to_divide)\n",
" item_orders=(self.train_ui>0).sum(axis=0)\n",
" \n",
" Pui = Pui.power(self.alpha)\n",
" Piu = Piu.power(self.alpha)\n",
"\n",
" P3=Pui*Piu*Pui\n",
" \n",
" P3/=np.power(np.vectorize(lambda x: x if x>0 else 1)(item_orders), self.beta)\n",
" \n",
" self.estimations=np.array(P3)\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": [],
"source": [
"model=RP3Beta()\n",
"model.fit(train_ui, alpha=1, beta=0)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"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_P3_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_P3_estimations.csv', index=False, header=False)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"943it [00:00, 7214.50it/s]\n"
]
},
{
"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",
" <td>3.702446</td>\n",
" <td>3.527273</td>\n",
" <td>0.282185</td>\n",
" <td>0.192092</td>\n",
" <td>0.186749</td>\n",
" <td>0.21698</td>\n",
" <td>0.204185</td>\n",
" <td>0.240096</td>\n",
" <td>0.339114</td>\n",
" <td>0.204905</td>\n",
" <td>0.572157</td>\n",
" <td>0.593544</td>\n",
" <td>0.875928</td>\n",
" <td>1.0</td>\n",
" <td>0.077201</td>\n",
" <td>3.875892</td>\n",
" <td>0.974947</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" RMSE MAE precision recall F_1 F_05 \\\n",
"0 3.702446 3.527273 0.282185 0.192092 0.186749 0.21698 \n",
"\n",
" precision_super recall_super NDCG mAP MRR LAUC \\\n",
"0 0.204185 0.240096 0.339114 0.204905 0.572157 0.593544 \n",
"\n",
" HR Reco in test Test coverage Shannon Gini \n",
"0 0.875928 1.0 0.077201 3.875892 0.974947 "
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import evaluation_measures as ev\n",
"estimations_df=pd.read_csv('Recommendations generated/ml-100k/Self_P3_estimations.csv', header=None)\n",
"reco=np.loadtxt('Recommendations generated/ml-100k/Self_P3_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": [
"# Let's check hiperparameters"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"##### Alpha"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
" 0%| | 0/8 [00:00<?, ?it/s]\n",
"0it [00:00, ?it/s]\u001b[A\n",
"943it [00:00, 6952.21it/s]\u001b[A\n",
" 12%|█▎ | 1/8 [00:09<01:06, 9.56s/it]\n",
"0it [00:00, ?it/s]\u001b[A\n",
"943it [00:00, 6822.51it/s]\u001b[A\n",
" 25%|██▌ | 2/8 [00:19<00:57, 9.53s/it]\n",
"0it [00:00, ?it/s]\u001b[A\n",
"943it [00:00, 6841.03it/s]\u001b[A\n",
" 38%|███▊ | 3/8 [00:28<00:48, 9.63s/it]\n",
"0it [00:00, ?it/s]\u001b[A\n",
"943it [00:00, 7086.32it/s]\u001b[A\n",
" 50%|█████ | 4/8 [00:38<00:38, 9.68s/it]\n",
"0it [00:00, ?it/s]\u001b[A\n",
"943it [00:00, 7470.38it/s]\u001b[A\n",
" 62%|██████▎ | 5/8 [00:48<00:29, 9.72s/it]\n",
"0it [00:00, ?it/s]\u001b[A\n",
"943it [00:00, 7429.22it/s]\u001b[A\n",
" 75%|███████▌ | 6/8 [00:58<00:19, 9.73s/it]\n",
"0it [00:00, ?it/s]\u001b[A\n",
"943it [00:00, 7042.01it/s]\u001b[A\n",
" 88%|████████▊ | 7/8 [01:07<00:09, 9.67s/it]\n",
"0it [00:00, ?it/s]\u001b[A\n",
"943it [00:00, 7035.02it/s]\u001b[A\n",
"100%|██████████| 8/8 [01:17<00:00, 9.67s/it]\n"
]
},
{
"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>Alpha</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>0.2</td>\n",
" <td>268.177832</td>\n",
" <td>211.732649</td>\n",
" <td>0.262672</td>\n",
" <td>0.166858</td>\n",
" <td>0.166277</td>\n",
" <td>0.197184</td>\n",
" <td>0.187661</td>\n",
" <td>0.203252</td>\n",
" <td>0.320910</td>\n",
" <td>0.196132</td>\n",
" <td>0.563378</td>\n",
" <td>0.580866</td>\n",
" <td>0.850477</td>\n",
" <td>1.000000</td>\n",
" <td>0.060606</td>\n",
" <td>3.669627</td>\n",
" <td>0.979636</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0.4</td>\n",
" <td>10.546689</td>\n",
" <td>7.792373</td>\n",
" <td>0.268505</td>\n",
" <td>0.172669</td>\n",
" <td>0.171569</td>\n",
" <td>0.202643</td>\n",
" <td>0.192489</td>\n",
" <td>0.212653</td>\n",
" <td>0.326760</td>\n",
" <td>0.200172</td>\n",
" <td>0.565148</td>\n",
" <td>0.583801</td>\n",
" <td>0.854719</td>\n",
" <td>1.000000</td>\n",
" <td>0.064214</td>\n",
" <td>3.726996</td>\n",
" <td>0.978426</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0.6</td>\n",
" <td>3.143988</td>\n",
" <td>2.948790</td>\n",
" <td>0.274655</td>\n",
" <td>0.180502</td>\n",
" <td>0.177820</td>\n",
" <td>0.208730</td>\n",
" <td>0.198176</td>\n",
" <td>0.222746</td>\n",
" <td>0.332872</td>\n",
" <td>0.203290</td>\n",
" <td>0.568872</td>\n",
" <td>0.587738</td>\n",
" <td>0.870626</td>\n",
" <td>1.000000</td>\n",
" <td>0.065657</td>\n",
" <td>3.785282</td>\n",
" <td>0.977090</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0.8</td>\n",
" <td>3.670728</td>\n",
" <td>3.495735</td>\n",
" <td>0.281972</td>\n",
" <td>0.189868</td>\n",
" <td>0.185300</td>\n",
" <td>0.216071</td>\n",
" <td>0.203541</td>\n",
" <td>0.236751</td>\n",
" <td>0.339867</td>\n",
" <td>0.206688</td>\n",
" <td>0.573729</td>\n",
" <td>0.592432</td>\n",
" <td>0.874867</td>\n",
" <td>1.000000</td>\n",
" <td>0.070707</td>\n",
" <td>3.832415</td>\n",
" <td>0.975998</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1.0</td>\n",
" <td>3.702446</td>\n",
" <td>3.527273</td>\n",
" <td>0.282185</td>\n",
" <td>0.192092</td>\n",
" <td>0.186749</td>\n",
" <td>0.216980</td>\n",
" <td>0.204185</td>\n",
" <td>0.240096</td>\n",
" <td>0.339114</td>\n",
" <td>0.204905</td>\n",
" <td>0.572157</td>\n",
" <td>0.593544</td>\n",
" <td>0.875928</td>\n",
" <td>1.000000</td>\n",
" <td>0.077201</td>\n",
" <td>3.875892</td>\n",
" <td>0.974947</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1.2</td>\n",
" <td>3.704441</td>\n",
" <td>3.529251</td>\n",
" <td>0.280912</td>\n",
" <td>0.193633</td>\n",
" <td>0.187311</td>\n",
" <td>0.216872</td>\n",
" <td>0.203004</td>\n",
" <td>0.240588</td>\n",
" <td>0.338049</td>\n",
" <td>0.203453</td>\n",
" <td>0.571830</td>\n",
" <td>0.594313</td>\n",
" <td>0.883351</td>\n",
" <td>1.000000</td>\n",
" <td>0.085859</td>\n",
" <td>3.910718</td>\n",
" <td>0.974073</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1.4</td>\n",
" <td>3.704580</td>\n",
" <td>3.529388</td>\n",
" <td>0.273595</td>\n",
" <td>0.190651</td>\n",
" <td>0.183874</td>\n",
" <td>0.212183</td>\n",
" <td>0.199464</td>\n",
" <td>0.239118</td>\n",
" <td>0.329550</td>\n",
" <td>0.195433</td>\n",
" <td>0.566171</td>\n",
" <td>0.592793</td>\n",
" <td>0.871686</td>\n",
" <td>1.000000</td>\n",
" <td>0.107504</td>\n",
" <td>3.961915</td>\n",
" <td>0.972674</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1.6</td>\n",
" <td>3.704591</td>\n",
" <td>3.529399</td>\n",
" <td>0.263097</td>\n",
" <td>0.186255</td>\n",
" <td>0.178709</td>\n",
" <td>0.205170</td>\n",
" <td>0.191094</td>\n",
" <td>0.232920</td>\n",
" <td>0.317439</td>\n",
" <td>0.184917</td>\n",
" <td>0.552349</td>\n",
" <td>0.590545</td>\n",
" <td>0.868505</td>\n",
" <td>0.999576</td>\n",
" <td>0.156566</td>\n",
" <td>4.060156</td>\n",
" <td>0.969203</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Alpha RMSE MAE precision recall F_1 F_05 \\\n",
"0 0.2 268.177832 211.732649 0.262672 0.166858 0.166277 0.197184 \n",
"0 0.4 10.546689 7.792373 0.268505 0.172669 0.171569 0.202643 \n",
"0 0.6 3.143988 2.948790 0.274655 0.180502 0.177820 0.208730 \n",
"0 0.8 3.670728 3.495735 0.281972 0.189868 0.185300 0.216071 \n",
"0 1.0 3.702446 3.527273 0.282185 0.192092 0.186749 0.216980 \n",
"0 1.2 3.704441 3.529251 0.280912 0.193633 0.187311 0.216872 \n",
"0 1.4 3.704580 3.529388 0.273595 0.190651 0.183874 0.212183 \n",
"0 1.6 3.704591 3.529399 0.263097 0.186255 0.178709 0.205170 \n",
"\n",
" precision_super recall_super NDCG mAP MRR LAUC \\\n",
"0 0.187661 0.203252 0.320910 0.196132 0.563378 0.580866 \n",
"0 0.192489 0.212653 0.326760 0.200172 0.565148 0.583801 \n",
"0 0.198176 0.222746 0.332872 0.203290 0.568872 0.587738 \n",
"0 0.203541 0.236751 0.339867 0.206688 0.573729 0.592432 \n",
"0 0.204185 0.240096 0.339114 0.204905 0.572157 0.593544 \n",
"0 0.203004 0.240588 0.338049 0.203453 0.571830 0.594313 \n",
"0 0.199464 0.239118 0.329550 0.195433 0.566171 0.592793 \n",
"0 0.191094 0.232920 0.317439 0.184917 0.552349 0.590545 \n",
"\n",
" HR Reco in test Test coverage Shannon Gini \n",
"0 0.850477 1.000000 0.060606 3.669627 0.979636 \n",
"0 0.854719 1.000000 0.064214 3.726996 0.978426 \n",
"0 0.870626 1.000000 0.065657 3.785282 0.977090 \n",
"0 0.874867 1.000000 0.070707 3.832415 0.975998 \n",
"0 0.875928 1.000000 0.077201 3.875892 0.974947 \n",
"0 0.883351 1.000000 0.085859 3.910718 0.974073 \n",
"0 0.871686 1.000000 0.107504 3.961915 0.972674 \n",
"0 0.868505 0.999576 0.156566 4.060156 0.969203 "
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from tqdm import tqdm\n",
"result=[]\n",
"for alpha in tqdm([round(i,1) for i in np.arange(0.2,1.6001,0.2)]):\n",
" model=RP3Beta()\n",
" model.fit(train_ui, alpha=alpha, beta=0)\n",
" reco=pd.DataFrame(model.recommend(user_code_id, item_code_id, topK=10))\n",
" estimations_df=pd.DataFrame(model.estimate(user_code_id, item_code_id, test_ui))\n",
" to_append=ev.evaluate(test=pd.read_csv('./Datasets/ml-100k/test.csv', sep='\\t', header=None),\n",
" estimations_df=estimations_df, \n",
" reco=np.array(reco),\n",
" super_reactions=[4,5])\n",
" to_append.insert(0, \"Alpha\", alpha)\n",
" result.append(to_append)\n",
" \n",
"result=pd.concat(result)\n",
"result"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {
"scrolled": false
},
"outputs": [
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 1296x3024 with 18 Axes>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
}
],
"source": [
"metrics=list(result.columns[[i not in ['Alpha'] for i in result.columns]])\n",
"\n",
"charts_per_row=6\n",
"charts_per_column=3\n",
"\n",
"fig, axes = plt.subplots(nrows=charts_per_row, ncols=charts_per_column,figsize=(18, 7*charts_per_row ))\n",
"import itertools\n",
"to_iter=[i for i in itertools.product(range(charts_per_row), range(charts_per_column))]\n",
"\n",
"for i in range(len(metrics)):\n",
" df=result[['Alpha', metrics[i]]]\n",
" df.plot(ax=axes[to_iter[i]], title=metrics[i], x=0, y=1)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"##### Beta"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
" 0%| | 0/10 [00:00<?, ?it/s]\n",
"0it [00:00, ?it/s]\u001b[A\n",
"943it [00:00, 7111.67it/s]\u001b[A\n",
" 10%|█ | 1/10 [00:10<01:36, 10.70s/it]\n",
"0it [00:00, ?it/s]\u001b[A\n",
"943it [00:00, 7130.50it/s]\u001b[A\n",
" 20%|██ | 2/10 [00:21<01:26, 10.87s/it]\n",
"0it [00:00, ?it/s]\u001b[A\n",
"943it [00:00, 6952.85it/s]\u001b[A\n",
" 30%|███ | 3/10 [00:32<01:16, 10.90s/it]\n",
"0it [00:00, ?it/s]\u001b[A\n",
"943it [00:00, 7108.39it/s]\u001b[A\n",
" 40%|████ | 4/10 [00:43<01:05, 10.87s/it]\n",
"0it [00:00, ?it/s]\u001b[A\n",
"943it [00:00, 6175.82it/s]\u001b[A\n",
" 50%|█████ | 5/10 [00:54<00:54, 10.89s/it]\n",
"0it [00:00, ?it/s]\u001b[A\n",
"943it [00:00, 6668.87it/s]\u001b[A\n",
" 60%|██████ | 6/10 [01:05<00:43, 10.87s/it]\n",
"0it [00:00, ?it/s]\u001b[A\n",
"943it [00:00, 7369.27it/s]\u001b[A\n",
" 70%|███████ | 7/10 [01:16<00:33, 11.01s/it]\n",
"0it [00:00, ?it/s]\u001b[A\n",
"943it [00:00, 7014.52it/s]\u001b[A\n",
" 80%|████████ | 8/10 [01:27<00:21, 10.95s/it]\n",
"0it [00:00, ?it/s]\u001b[A\n",
"943it [00:00, 6965.11it/s]\u001b[A\n",
" 90%|█████████ | 9/10 [01:38<00:10, 10.91s/it]\n",
"0it [00:00, ?it/s]\u001b[A\n",
"943it [00:00, 7744.74it/s]\u001b[A\n",
"100%|██████████| 10/10 [01:49<00:00, 10.94s/it]\n"
]
},
{
"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>Beta</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>0.0</td>\n",
" <td>3.702446</td>\n",
" <td>3.527273</td>\n",
" <td>0.282185</td>\n",
" <td>0.192092</td>\n",
" <td>0.186749</td>\n",
" <td>0.216980</td>\n",
" <td>0.204185</td>\n",
" <td>0.240096</td>\n",
" <td>0.339114</td>\n",
" <td>0.204905</td>\n",
" <td>0.572157</td>\n",
" <td>0.593544</td>\n",
" <td>0.875928</td>\n",
" <td>1.000000</td>\n",
" <td>0.077201</td>\n",
" <td>3.875892</td>\n",
" <td>0.974947</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0.1</td>\n",
" <td>3.703312</td>\n",
" <td>3.528128</td>\n",
" <td>0.290138</td>\n",
" <td>0.197597</td>\n",
" <td>0.192259</td>\n",
" <td>0.223336</td>\n",
" <td>0.210944</td>\n",
" <td>0.246153</td>\n",
" <td>0.347768</td>\n",
" <td>0.212034</td>\n",
" <td>0.581038</td>\n",
" <td>0.596328</td>\n",
" <td>0.884411</td>\n",
" <td>1.000000</td>\n",
" <td>0.085137</td>\n",
" <td>3.957416</td>\n",
" <td>0.972784</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0.2</td>\n",
" <td>3.703825</td>\n",
" <td>3.528636</td>\n",
" <td>0.297137</td>\n",
" <td>0.201202</td>\n",
" <td>0.196067</td>\n",
" <td>0.228169</td>\n",
" <td>0.218026</td>\n",
" <td>0.252767</td>\n",
" <td>0.355655</td>\n",
" <td>0.219909</td>\n",
" <td>0.588904</td>\n",
" <td>0.598160</td>\n",
" <td>0.886532</td>\n",
" <td>1.000000</td>\n",
" <td>0.094517</td>\n",
" <td>4.053212</td>\n",
" <td>0.969980</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0.3</td>\n",
" <td>3.704130</td>\n",
" <td>3.528939</td>\n",
" <td>0.303499</td>\n",
" <td>0.204749</td>\n",
" <td>0.199901</td>\n",
" <td>0.232829</td>\n",
" <td>0.225107</td>\n",
" <td>0.260797</td>\n",
" <td>0.363757</td>\n",
" <td>0.226825</td>\n",
" <td>0.599969</td>\n",
" <td>0.599964</td>\n",
" <td>0.888653</td>\n",
" <td>1.000000</td>\n",
" <td>0.105339</td>\n",
" <td>4.147779</td>\n",
" <td>0.966948</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0.4</td>\n",
" <td>3.704313</td>\n",
" <td>3.529120</td>\n",
" <td>0.308908</td>\n",
" <td>0.208811</td>\n",
" <td>0.203854</td>\n",
" <td>0.237241</td>\n",
" <td>0.229614</td>\n",
" <td>0.266918</td>\n",
" <td>0.370758</td>\n",
" <td>0.232673</td>\n",
" <td>0.609385</td>\n",
" <td>0.602014</td>\n",
" <td>0.895016</td>\n",
" <td>0.999894</td>\n",
" <td>0.132035</td>\n",
" <td>4.259682</td>\n",
" <td>0.962989</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0.5</td>\n",
" <td>3.704422</td>\n",
" <td>3.529229</td>\n",
" <td>0.314316</td>\n",
" <td>0.211411</td>\n",
" <td>0.206768</td>\n",
" <td>0.240986</td>\n",
" <td>0.237124</td>\n",
" <td>0.273416</td>\n",
" <td>0.378307</td>\n",
" <td>0.239297</td>\n",
" <td>0.622792</td>\n",
" <td>0.603327</td>\n",
" <td>0.903499</td>\n",
" <td>0.999046</td>\n",
" <td>0.168831</td>\n",
" <td>4.411281</td>\n",
" <td>0.956648</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0.6</td>\n",
" <td>3.704488</td>\n",
" <td>3.529295</td>\n",
" <td>0.314634</td>\n",
" <td>0.206209</td>\n",
" <td>0.204818</td>\n",
" <td>0.240159</td>\n",
" <td>0.242489</td>\n",
" <td>0.273850</td>\n",
" <td>0.376438</td>\n",
" <td>0.238428</td>\n",
" <td>0.622042</td>\n",
" <td>0.600721</td>\n",
" <td>0.897137</td>\n",
" <td>0.996394</td>\n",
" <td>0.212843</td>\n",
" <td>4.621938</td>\n",
" <td>0.945932</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0.7</td>\n",
" <td>3.704528</td>\n",
" <td>3.529335</td>\n",
" <td>0.304136</td>\n",
" <td>0.187298</td>\n",
" <td>0.191990</td>\n",
" <td>0.228749</td>\n",
" <td>0.238305</td>\n",
" <td>0.256201</td>\n",
" <td>0.358807</td>\n",
" <td>0.226808</td>\n",
" <td>0.593897</td>\n",
" <td>0.591207</td>\n",
" <td>0.868505</td>\n",
" <td>0.983033</td>\n",
" <td>0.256854</td>\n",
" <td>4.898568</td>\n",
" <td>0.928065</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0.8</td>\n",
" <td>3.704552</td>\n",
" <td>3.529360</td>\n",
" <td>0.266384</td>\n",
" <td>0.147571</td>\n",
" <td>0.158660</td>\n",
" <td>0.194838</td>\n",
" <td>0.214485</td>\n",
" <td>0.209336</td>\n",
" <td>0.299850</td>\n",
" <td>0.184356</td>\n",
" <td>0.492852</td>\n",
" <td>0.571152</td>\n",
" <td>0.803818</td>\n",
" <td>0.936373</td>\n",
" <td>0.341270</td>\n",
" <td>5.257397</td>\n",
" <td>0.895882</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0.9</td>\n",
" <td>3.704567</td>\n",
" <td>3.529375</td>\n",
" <td>0.162354</td>\n",
" <td>0.076967</td>\n",
" <td>0.089233</td>\n",
" <td>0.114583</td>\n",
" <td>0.134657</td>\n",
" <td>0.113253</td>\n",
" <td>0.160868</td>\n",
" <td>0.085486</td>\n",
" <td>0.243590</td>\n",
" <td>0.535405</td>\n",
" <td>0.580064</td>\n",
" <td>0.800106</td>\n",
" <td>0.415584</td>\n",
" <td>5.563910</td>\n",
" <td>0.857396</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Beta RMSE MAE precision recall F_1 F_05 \\\n",
"0 0.0 3.702446 3.527273 0.282185 0.192092 0.186749 0.216980 \n",
"0 0.1 3.703312 3.528128 0.290138 0.197597 0.192259 0.223336 \n",
"0 0.2 3.703825 3.528636 0.297137 0.201202 0.196067 0.228169 \n",
"0 0.3 3.704130 3.528939 0.303499 0.204749 0.199901 0.232829 \n",
"0 0.4 3.704313 3.529120 0.308908 0.208811 0.203854 0.237241 \n",
"0 0.5 3.704422 3.529229 0.314316 0.211411 0.206768 0.240986 \n",
"0 0.6 3.704488 3.529295 0.314634 0.206209 0.204818 0.240159 \n",
"0 0.7 3.704528 3.529335 0.304136 0.187298 0.191990 0.228749 \n",
"0 0.8 3.704552 3.529360 0.266384 0.147571 0.158660 0.194838 \n",
"0 0.9 3.704567 3.529375 0.162354 0.076967 0.089233 0.114583 \n",
"\n",
" precision_super recall_super NDCG mAP MRR LAUC \\\n",
"0 0.204185 0.240096 0.339114 0.204905 0.572157 0.593544 \n",
"0 0.210944 0.246153 0.347768 0.212034 0.581038 0.596328 \n",
"0 0.218026 0.252767 0.355655 0.219909 0.588904 0.598160 \n",
"0 0.225107 0.260797 0.363757 0.226825 0.599969 0.599964 \n",
"0 0.229614 0.266918 0.370758 0.232673 0.609385 0.602014 \n",
"0 0.237124 0.273416 0.378307 0.239297 0.622792 0.603327 \n",
"0 0.242489 0.273850 0.376438 0.238428 0.622042 0.600721 \n",
"0 0.238305 0.256201 0.358807 0.226808 0.593897 0.591207 \n",
"0 0.214485 0.209336 0.299850 0.184356 0.492852 0.571152 \n",
"0 0.134657 0.113253 0.160868 0.085486 0.243590 0.535405 \n",
"\n",
" HR Reco in test Test coverage Shannon Gini \n",
"0 0.875928 1.000000 0.077201 3.875892 0.974947 \n",
"0 0.884411 1.000000 0.085137 3.957416 0.972784 \n",
"0 0.886532 1.000000 0.094517 4.053212 0.969980 \n",
"0 0.888653 1.000000 0.105339 4.147779 0.966948 \n",
"0 0.895016 0.999894 0.132035 4.259682 0.962989 \n",
"0 0.903499 0.999046 0.168831 4.411281 0.956648 \n",
"0 0.897137 0.996394 0.212843 4.621938 0.945932 \n",
"0 0.868505 0.983033 0.256854 4.898568 0.928065 \n",
"0 0.803818 0.936373 0.341270 5.257397 0.895882 \n",
"0 0.580064 0.800106 0.415584 5.563910 0.857396 "
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from tqdm import tqdm\n",
"result=[]\n",
"for beta in tqdm([round(i,1) for i in np.arange(0,1,0.1)]):\n",
" model=RP3Beta()\n",
" model.fit(train_ui, alpha=1, beta=beta)\n",
" reco=pd.DataFrame(model.recommend(user_code_id, item_code_id, topK=10))\n",
" estimations_df=pd.DataFrame(model.estimate(user_code_id, item_code_id, test_ui))\n",
" to_append=ev.evaluate(test=pd.read_csv('./Datasets/ml-100k/test.csv', sep='\\t', header=None),\n",
" estimations_df=estimations_df, \n",
" reco=np.array(reco),\n",
" super_reactions=[4,5])\n",
" to_append.insert(0, \"Beta\", beta)\n",
" result.append(to_append)\n",
" \n",
"result=pd.concat(result)\n",
"result"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {
"scrolled": false
},
"outputs": [
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 1296x3024 with 18 Axes>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
}
],
"source": [
"### import matplotlib.pyplot as plt\n",
"\n",
"metrics=list(result.columns[[i not in ['Beta'] for i in result.columns]])\n",
"\n",
"charts_per_row=6\n",
"charts_per_column=3\n",
"\n",
"fig, axes = plt.subplots(nrows=charts_per_row, ncols=charts_per_column,figsize=(18, 7*charts_per_row ))\n",
"import itertools\n",
"to_iter=[i for i in itertools.product(range(charts_per_row), range(charts_per_column))]\n",
"\n",
"for i in range(len(metrics)):\n",
" df=result[['Beta', metrics[i]]]\n",
" df.plot(ax=axes[to_iter[i]], title=metrics[i], x=0, y=1)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Check sample recommendations"
]
},
{
"cell_type": "code",
"execution_count": 10,
"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>user</th>\n",
" <th>rating</th>\n",
" <th>title</th>\n",
" <th>genres</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>47381</th>\n",
" <td>504</td>\n",
" <td>5</td>\n",
" <td>Crow, The (1994)</td>\n",
" <td>Action, Romance, Thriller</td>\n",
" </tr>\n",
" <tr>\n",
" <th>38682</th>\n",
" <td>504</td>\n",
" <td>5</td>\n",
" <td>First Wives Club, The (1996)</td>\n",
" <td>Comedy</td>\n",
" </tr>\n",
" <tr>\n",
" <th>49310</th>\n",
" <td>504</td>\n",
" <td>5</td>\n",
" <td>Schindler's List (1993)</td>\n",
" <td>Drama, War</td>\n",
" </tr>\n",
" <tr>\n",
" <th>47893</th>\n",
" <td>504</td>\n",
" <td>5</td>\n",
" <td>Nell (1994)</td>\n",
" <td>Drama</td>\n",
" </tr>\n",
" <tr>\n",
" <th>22082</th>\n",
" <td>504</td>\n",
" <td>5</td>\n",
" <td>Men in Black (1997)</td>\n",
" <td>Action, Adventure, Comedy, Sci-Fi</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15938</th>\n",
" <td>504</td>\n",
" <td>5</td>\n",
" <td>Godfather, The (1972)</td>\n",
" <td>Action, Crime, Drama</td>\n",
" </tr>\n",
" <tr>\n",
" <th>51421</th>\n",
" <td>504</td>\n",
" <td>5</td>\n",
" <td>Interview with the Vampire (1994)</td>\n",
" <td>Drama, Horror</td>\n",
" </tr>\n",
" <tr>\n",
" <th>47837</th>\n",
" <td>504</td>\n",
" <td>5</td>\n",
" <td>Omen, The (1976)</td>\n",
" <td>Horror</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14267</th>\n",
" <td>504</td>\n",
" <td>5</td>\n",
" <td>Fargo (1996)</td>\n",
" <td>Crime, Drama, Thriller</td>\n",
" </tr>\n",
" <tr>\n",
" <th>51759</th>\n",
" <td>504</td>\n",
" <td>5</td>\n",
" <td>Man Without a Face, The (1993)</td>\n",
" <td>Drama</td>\n",
" </tr>\n",
" <tr>\n",
" <th>45355</th>\n",
" <td>504</td>\n",
" <td>5</td>\n",
" <td>Lion King, The (1994)</td>\n",
" <td>Animation, Children's, Musical</td>\n",
" </tr>\n",
" <tr>\n",
" <th>77192</th>\n",
" <td>504</td>\n",
" <td>5</td>\n",
" <td>Ghosts of Mississippi (1996)</td>\n",
" <td>Drama</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19123</th>\n",
" <td>504</td>\n",
" <td>5</td>\n",
" <td>Scream (1996)</td>\n",
" <td>Horror, Thriller</td>\n",
" </tr>\n",
" <tr>\n",
" <th>56591</th>\n",
" <td>504</td>\n",
" <td>5</td>\n",
" <td>My Favorite Year (1982)</td>\n",
" <td>Comedy</td>\n",
" </tr>\n",
" <tr>\n",
" <th>41312</th>\n",
" <td>504</td>\n",
" <td>5</td>\n",
" <td>Gone with the Wind (1939)</td>\n",
" <td>Drama, Romance, War</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" user rating title \\\n",
"47381 504 5 Crow, The (1994) \n",
"38682 504 5 First Wives Club, The (1996) \n",
"49310 504 5 Schindler's List (1993) \n",
"47893 504 5 Nell (1994) \n",
"22082 504 5 Men in Black (1997) \n",
"15938 504 5 Godfather, The (1972) \n",
"51421 504 5 Interview with the Vampire (1994) \n",
"47837 504 5 Omen, The (1976) \n",
"14267 504 5 Fargo (1996) \n",
"51759 504 5 Man Without a Face, The (1993) \n",
"45355 504 5 Lion King, The (1994) \n",
"77192 504 5 Ghosts of Mississippi (1996) \n",
"19123 504 5 Scream (1996) \n",
"56591 504 5 My Favorite Year (1982) \n",
"41312 504 5 Gone with the Wind (1939) \n",
"\n",
" genres \n",
"47381 Action, Romance, Thriller \n",
"38682 Comedy \n",
"49310 Drama, War \n",
"47893 Drama \n",
"22082 Action, Adventure, Comedy, Sci-Fi \n",
"15938 Action, Crime, Drama \n",
"51421 Drama, Horror \n",
"47837 Horror \n",
"14267 Crime, Drama, Thriller \n",
"51759 Drama \n",
"45355 Animation, Children's, Musical \n",
"77192 Drama \n",
"19123 Horror, Thriller \n",
"56591 Comedy \n",
"41312 Drama, Romance, War "
]
},
"metadata": {},
"output_type": "display_data"
},
{
"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>user</th>\n",
" <th>rec_nb</th>\n",
" <th>title</th>\n",
" <th>genres</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>3231</th>\n",
" <td>504.0</td>\n",
" <td>1</td>\n",
" <td>Toy Story (1995)</td>\n",
" <td>Animation, Children's, Comedy</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6474</th>\n",
" <td>504.0</td>\n",
" <td>2</td>\n",
" <td>Pulp Fiction (1994)</td>\n",
" <td>Crime, Drama</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5823</th>\n",
" <td>504.0</td>\n",
" <td>3</td>\n",
" <td>Contact (1997)</td>\n",
" <td>Drama, Sci-Fi</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6689</th>\n",
" <td>504.0</td>\n",
" <td>4</td>\n",
" <td>Empire Strikes Back, The (1980)</td>\n",
" <td>Action, Adventure, Drama, Romance, Sci-Fi, War</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7779</th>\n",
" <td>504.0</td>\n",
" <td>5</td>\n",
" <td>Princess Bride, The (1987)</td>\n",
" <td>Action, Adventure, Comedy, Romance</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4212</th>\n",
" <td>504.0</td>\n",
" <td>6</td>\n",
" <td>Twelve Monkeys (1995)</td>\n",
" <td>Drama, Sci-Fi</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1420</th>\n",
" <td>504.0</td>\n",
" <td>7</td>\n",
" <td>Fugitive, The (1993)</td>\n",
" <td>Action, Thriller</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6847</th>\n",
" <td>504.0</td>\n",
" <td>8</td>\n",
" <td>Braveheart (1995)</td>\n",
" <td>Action, Drama, War</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7615</th>\n",
" <td>504.0</td>\n",
" <td>9</td>\n",
" <td>Rock, The (1996)</td>\n",
" <td>Action, Adventure, Thriller</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7914</th>\n",
" <td>504.0</td>\n",
" <td>10</td>\n",
" <td>Amadeus (1984)</td>\n",
" <td>Drama, Mystery</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" user rec_nb title \\\n",
"3231 504.0 1 Toy Story (1995) \n",
"6474 504.0 2 Pulp Fiction (1994) \n",
"5823 504.0 3 Contact (1997) \n",
"6689 504.0 4 Empire Strikes Back, The (1980) \n",
"7779 504.0 5 Princess Bride, The (1987) \n",
"4212 504.0 6 Twelve Monkeys (1995) \n",
"1420 504.0 7 Fugitive, The (1993) \n",
"6847 504.0 8 Braveheart (1995) \n",
"7615 504.0 9 Rock, The (1996) \n",
"7914 504.0 10 Amadeus (1984) \n",
"\n",
" genres \n",
"3231 Animation, Children's, Comedy \n",
"6474 Crime, Drama \n",
"5823 Drama, Sci-Fi \n",
"6689 Action, Adventure, Drama, Romance, Sci-Fi, War \n",
"7779 Action, Adventure, Comedy, Romance \n",
"4212 Drama, Sci-Fi \n",
"1420 Action, Thriller \n",
"6847 Action, Drama, War \n",
"7615 Action, Adventure, Thriller \n",
"7914 Drama, Mystery "
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"train=pd.read_csv('./Datasets/ml-100k/train.csv', sep='\\t', header=None, names=['user', 'item', 'rating', 'timestamp'])\n",
"items=pd.read_csv('./Datasets/ml-100k/movies.csv')\n",
"\n",
"user=random.choice(list(set(train['user'])))\n",
"\n",
"train_content=pd.merge(train, items, left_on='item', right_on='id')\n",
"display(train_content[train_content['user']==user][['user', 'rating', 'title', 'genres']]\\\n",
" .sort_values(by='rating', ascending=False)[:15])\n",
"\n",
"reco = np.loadtxt('Recommendations generated/ml-100k/Self_P3_reco.csv', delimiter=',')\n",
"items=pd.read_csv('./Datasets/ml-100k/movies.csv')\n",
"\n",
"# Let's ignore scores - they are not used in evaluation: \n",
"reco_users=reco[:,:1]\n",
"reco_items=reco[:,1::2]\n",
"# Let's put them into one array\n",
"reco=np.concatenate((reco_users, reco_items), axis=1)\n",
"\n",
"# Let's rebuild it user-item dataframe\n",
"recommended=[]\n",
"for row in reco:\n",
" for rec_nb, entry in enumerate(row[1:]):\n",
" recommended.append((row[0], rec_nb+1, entry))\n",
"recommended=pd.DataFrame(recommended, columns=['user','rec_nb', 'item'])\n",
"\n",
"recommended_content=pd.merge(recommended, items, left_on='item', right_on='id')\n",
"recommended_content[recommended_content['user']==user][['user', 'rec_nb', 'title', 'genres']].sort_values(by='rec_nb')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# project task 6: generate recommendations of RP3Beta for hiperparameters found to optimize recall"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [],
"source": [
"# use better values than (1,0) for alpha and beta\n",
"# if you want you can also modify the model to consider different weights (we took as weights user ratings, maybe take ones or squares of ratings instead)\n",
"# save the outptut in 'Recommendations generated/ml-100k/Self_RP3Beta_estimations.csv'\n",
"# and 'Recommendations generated/ml-100k/Self_RP3Beta_reco.csv'"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# project task 7 (optional): implement graph-based model of your choice "
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [],
"source": [
"# for example change length of paths in RP3beta\n",
"# save the outptut in 'Recommendations generated/ml-100k/Self_GraphTask_estimations.csv'\n",
"# and 'Recommendations generated/ml-100k/Self_GraphTask_reco.csv'"
]
}
],
"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