s416082/WSS-project
1
0
Fork 0
forked from robkw/introduction_to_recommender_systems
Code Issues Pull Requests Projects Releases Wiki Activity
bdf06c9c28
WSS-project/P5. Graph-based.ipynb

1865 lines
582 KiB
Plaintext
Raw Normal View History

3rd meeting
2021-05-07 22:16:28 +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",
"(\n",
" train_ui,\n",
" test_ui,\n",
" user_code_id,\n",
" user_id_code,\n",
" item_code_id,\n",
" item_id_code,\n",
") = 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)(\n",
" self.train_iu.sum(axis=1)\n",
" ) # 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",
Zadanie 6
2021-06-12 11:14:56 +02:00
" P3 = Pui * Piu * Pui \n",
3rd meeting
2021-05-07 22:16:28 +02:00
"\n",
" P3 /= np.power(\n",
" np.vectorize(lambda x: x if x > 0 else 1)(item_orders), self.beta\n",
" )\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[\n",
" self.train_ui.indptr[nb_user] : self.train_ui.indptr[nb_user + 1]\n",
" ]\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(\n",
" [\n",
" user_code_id[user],\n",
" item_code_id[item],\n",
" self.estimations[user, item]\n",
" if not np.isnan(self.estimations[user, item])\n",
" else 1,\n",
" ]\n",
" )\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(\n",
" \"Recommendations generated/ml-100k/Self_P3_reco.csv\", index=False, header=False\n",
")\n",
"\n",
"estimations = pd.DataFrame(model.estimate(user_code_id, item_code_id, test_ui))\n",
"estimations.to_csv(\n",
" \"Recommendations generated/ml-100k/Self_P3_estimations.csv\",\n",
" index=False,\n",
" header=False,\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
Zadanie 6
2021-06-12 11:14:56 +02:00
"943it [00:00, 12434.93it/s]\n"
3rd meeting
2021-05-07 22:16:28 +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",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <th>HitRate2</th>\n",
" <th>HitRate3</th>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" <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",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <td>0.685048</td>\n",
" <td>0.495228</td>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" <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",
Zadanie 6
2021-06-12 11:14:56 +02:00
" HR HitRate2 HitRate3 Reco in test Test coverage Shannon \\\n",
"0 0.875928 0.685048 0.495228 1.0 0.077201 3.875892 \n",
"\n",
" Gini \n",
"0 0.974947 "
3rd meeting
2021-05-07 22:16:28 +02:00
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import evaluation_measures as ev\n",
"\n",
"estimations_df = pd.read_csv(\n",
" \"Recommendations generated/ml-100k/Self_P3_estimations.csv\", header=None\n",
")\n",
"reco = np.loadtxt(\"Recommendations generated/ml-100k/Self_P3_reco.csv\", delimiter=\",\")\n",
"\n",
"ev.evaluate(\n",
" 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],\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Let's check hyperparameters"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"##### Alpha"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
Zadanie 6
2021-06-12 11:14:56 +02:00
" 0%| | 0/8 [00:00<?, ?it/s]\n",
"943it [00:00, 13897.79it/s]\n",
" 12%|██████████▌ | 1/8 [00:06<00:42, 6.02s/it]\n",
"943it [00:00, 13501.01it/s]\n",
" 25%|█████████████████████ | 2/8 [00:11<00:35, 5.97s/it]\n",
"943it [00:00, 12601.73it/s]\n",
" 38%|███████████████████████████████▌ | 3/8 [00:17<00:29, 5.99s/it]\n",
"943it [00:00, 12158.08it/s]\n",
" 50%|██████████████████████████████████████████ | 4/8 [00:24<00:24, 6.05s/it]\n",
"943it [00:00, 12607.07it/s]\n",
" 62%|████████████████████████████████████████████████████▌ | 5/8 [00:30<00:18, 6.12s/it]\n",
"943it [00:00, 13126.43it/s]\n",
" 75%|███████████████████████████████████████████████████████████████ | 6/8 [00:36<00:12, 6.11s/it]\n",
"943it [00:00, 12777.35it/s]\n",
" 88%|█████████████████████████████████████████████████████████████████████████▌ | 7/8 [00:42<00:06, 6.15s/it]\n",
"943it [00:00, 12441.39it/s]\n",
"100%|████████████████████████████████████████████████████████████████████████████████████| 8/8 [00:48<00:00, 6.10s/it]\n"
3rd meeting
2021-05-07 22:16:28 +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>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",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <th>HitRate2</th>\n",
" <th>HitRate3</th>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" <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",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <td>0.629905</td>\n",
" <td>0.451750</td>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" <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",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <td>0.644751</td>\n",
" <td>0.458112</td>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" <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",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <td>0.657476</td>\n",
" <td>0.470838</td>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" <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",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <td>0.685048</td>\n",
" <td>0.492047</td>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" <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",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <td>0.685048</td>\n",
" <td>0.495228</td>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" <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",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <td>0.681866</td>\n",
" <td>0.498409</td>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" <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",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <td>0.675504</td>\n",
" <td>0.489926</td>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" <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",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <td>0.669141</td>\n",
" <td>0.462354</td>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" <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",
Zadanie 6
2021-06-12 11:14:56 +02:00
" HR HitRate2 HitRate3 Reco in test Test coverage Shannon \\\n",
"0 0.850477 0.629905 0.451750 1.000000 0.060606 3.669627 \n",
"0 0.854719 0.644751 0.458112 1.000000 0.064214 3.726996 \n",
"0 0.870626 0.657476 0.470838 1.000000 0.065657 3.785282 \n",
"0 0.874867 0.685048 0.492047 1.000000 0.070707 3.832415 \n",
"0 0.875928 0.685048 0.495228 1.000000 0.077201 3.875892 \n",
"0 0.883351 0.681866 0.498409 1.000000 0.085859 3.910718 \n",
"0 0.871686 0.675504 0.489926 1.000000 0.107504 3.961915 \n",
"0 0.868505 0.669141 0.462354 0.999576 0.156566 4.060156 \n",
"\n",
" Gini \n",
"0 0.979636 \n",
"0 0.978426 \n",
"0 0.977090 \n",
"0 0.975998 \n",
"0 0.974947 \n",
"0 0.974073 \n",
"0 0.972674 \n",
"0 0.969203 "
3rd meeting
2021-05-07 22:16:28 +02:00
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from tqdm import tqdm\n",
"\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(\n",
" 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",
" )\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": [
Zadanie 6
2021-06-12 11:14:56 +02:00
{
"ename": "IndexError",
"evalue": "list index out of range",
"output_type": "error",
"traceback": [
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[1;31mIndexError\u001b[0m Traceback (most recent call last)",
"\u001b[1;32m<ipython-input-7-720c7bf8f8eb>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[0;32m 15\u001b[0m \u001b[1;32mfor\u001b[0m \u001b[0mi\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mrange\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mlen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mmetrics\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 16\u001b[0m \u001b[0mdf\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mresult\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m\"Alpha\"\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mmetrics\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mi\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 17\u001b[1;33m \u001b[0mdf\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mplot\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0max\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0maxes\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mto_iter\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mi\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mtitle\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mmetrics\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mi\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mx\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;36m0\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0my\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;36m1\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
"\u001b[1;31mIndexError\u001b[0m: list index out of range"
]
},
3rd meeting
2021-05-07 22:16:28 +02:00
{
"data": {
Zadanie 6
2021-06-12 11:14:56 +02:00
"image/png": "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
3rd meeting
2021-05-07 22:16:28 +02:00
"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(\n",
" nrows=charts_per_row, ncols=charts_per_column, figsize=(18, 7 * charts_per_row)\n",
")\n",
"import itertools\n",
"\n",
"to_iter = [\n",
" i for i in itertools.product(range(charts_per_row), range(charts_per_column))\n",
"]\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": [
Zadanie 6
2021-06-12 11:14:56 +02:00
" 0%| | 0/10 [00:00<?, ?it/s]\n",
"943it [00:00, 12120.56it/s]\n",
" 10%|████████▎ | 1/10 [00:06<00:54, 6.01s/it]\n",
"943it [00:00, 12283.97it/s]\n",
" 20%|████████████████▌ | 2/10 [00:12<00:48, 6.06s/it]\n",
"943it [00:00, 12771.78it/s]\n",
" 30%|████████████████████████▉ | 3/10 [00:18<00:42, 6.03s/it]\n",
"943it [00:00, 13126.91it/s]\n",
" 40%|█████████████████████████████████▏ | 4/10 [00:24<00:36, 6.05s/it]\n",
"943it [00:00, 12952.63it/s]\n",
" 50%|█████████████████████████████████████████▌ | 5/10 [00:30<00:30, 6.09s/it]\n",
"943it [00:00, 13132.62it/s]\n",
" 60%|█████████████████████████████████████████████████▊ | 6/10 [00:36<00:24, 6.12s/it]\n",
"943it [00:00, 12603.86it/s]\n",
" 70%|██████████████████████████████████████████████████████████ | 7/10 [00:42<00:18, 6.10s/it]\n",
"943it [00:00, 12273.98it/s]\n",
" 80%|██████████████████████████████████████████████████████████████████▍ | 8/10 [00:48<00:12, 6.08s/it]\n",
"943it [00:00, 13125.77it/s]\n",
" 90%|██████████████████████████████████████████████████████████████████████████▋ | 9/10 [00:54<00:06, 6.13s/it]\n",
"943it [00:00, 13697.33it/s]\n",
"100%|██████████████████████████████████████████████████████████████████████████████████| 10/10 [01:01<00:00, 6.12s/it]\n"
3rd meeting
2021-05-07 22:16:28 +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>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",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <th>HitRate2</th>\n",
" <th>HitRate3</th>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" <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",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <td>0.685048</td>\n",
" <td>0.495228</td>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" <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",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <td>0.695652</td>\n",
" <td>0.514316</td>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" <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",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <td>0.697773</td>\n",
" <td>0.515376</td>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" <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",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <td>0.707317</td>\n",
" <td>0.531283</td>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" <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",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <td>0.718982</td>\n",
" <td>0.537646</td>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" <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",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <td>0.724284</td>\n",
" <td>0.548250</td>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" <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",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <td>0.720042</td>\n",
" <td>0.542948</td>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" <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",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <td>0.693531</td>\n",
" <td>0.520679</td>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" <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",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <td>0.604454</td>\n",
" <td>0.428420</td>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" <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",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <td>0.400848</td>\n",
" <td>0.261930</td>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" <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",
Zadanie 6
2021-06-12 11:14:56 +02:00
" HR HitRate2 HitRate3 Reco in test Test coverage Shannon \\\n",
"0 0.875928 0.685048 0.495228 1.000000 0.077201 3.875892 \n",
"0 0.884411 0.695652 0.514316 1.000000 0.085137 3.957416 \n",
"0 0.886532 0.697773 0.515376 1.000000 0.094517 4.053212 \n",
"0 0.888653 0.707317 0.531283 1.000000 0.105339 4.147779 \n",
"0 0.895016 0.718982 0.537646 0.999894 0.132035 4.259682 \n",
"0 0.903499 0.724284 0.548250 0.999046 0.168831 4.411281 \n",
"0 0.897137 0.720042 0.542948 0.996394 0.212843 4.621938 \n",
"0 0.868505 0.693531 0.520679 0.983033 0.256854 4.898568 \n",
"0 0.803818 0.604454 0.428420 0.936373 0.341270 5.257397 \n",
"0 0.580064 0.400848 0.261930 0.800106 0.415584 5.563910 \n",
"\n",
" Gini \n",
"0 0.974947 \n",
"0 0.972784 \n",
"0 0.969980 \n",
"0 0.966948 \n",
"0 0.962989 \n",
"0 0.956648 \n",
"0 0.945932 \n",
"0 0.928065 \n",
"0 0.895882 \n",
"0 0.857396 "
3rd meeting
2021-05-07 22:16:28 +02:00
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from tqdm import tqdm\n",
"\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(\n",
" 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",
" )\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": [
"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(\n",
" nrows=charts_per_row, ncols=charts_per_column, figsize=(18, 7 * charts_per_row)\n",
")\n",
"import itertools\n",
"\n",
"to_iter = [\n",
" i for i in itertools.product(range(charts_per_row), range(charts_per_column))\n",
"]\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",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <th>29798</th>\n",
" <td>853</td>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" <td>5</td>\n",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <td>Soul Food (1997)</td>\n",
" <td>Drama</td>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" </tr>\n",
" <tr>\n",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <th>26282</th>\n",
" <td>853</td>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" <td>5</td>\n",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <td>Air Force One (1997)</td>\n",
" <td>Action, Thriller</td>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" </tr>\n",
" <tr>\n",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <th>73991</th>\n",
" <td>853</td>\n",
" <td>4</td>\n",
" <td>Fire Down Below (1997)</td>\n",
" <td>Action, Drama, Thriller</td>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" </tr>\n",
" <tr>\n",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <th>24846</th>\n",
" <td>853</td>\n",
" <td>4</td>\n",
" <td>Gattaca (1997)</td>\n",
" <td>Drama, Sci-Fi, Thriller</td>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" </tr>\n",
" <tr>\n",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <th>52746</th>\n",
" <td>853</td>\n",
" <td>4</td>\n",
" <td>Fly Away Home (1996)</td>\n",
" <td>Adventure, Children's</td>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" </tr>\n",
" <tr>\n",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <th>46026</th>\n",
" <td>853</td>\n",
" <td>4</td>\n",
" <td>L.A. Confidential (1997)</td>\n",
" <td>Crime, Film-Noir, Mystery, Thriller</td>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" </tr>\n",
" <tr>\n",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <th>33394</th>\n",
" <td>853</td>\n",
" <td>4</td>\n",
" <td>Game, The (1997)</td>\n",
" <td>Mystery, Thriller</td>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" </tr>\n",
" <tr>\n",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <th>58732</th>\n",
" <td>853</td>\n",
" <td>4</td>\n",
" <td>Volcano (1997)</td>\n",
" <td>Drama, Thriller</td>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" </tr>\n",
" <tr>\n",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <th>30970</th>\n",
" <td>853</td>\n",
" <td>4</td>\n",
" <td>Rosewood (1997)</td>\n",
" <td>Drama</td>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" </tr>\n",
" <tr>\n",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <th>55641</th>\n",
" <td>853</td>\n",
" <td>4</td>\n",
" <td>Hoodlum (1997)</td>\n",
" <td>Crime, Drama, Film-Noir</td>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" </tr>\n",
" <tr>\n",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <th>19322</th>\n",
" <td>853</td>\n",
" <td>4</td>\n",
" <td>Scream (1996)</td>\n",
" <td>Horror, Thriller</td>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" </tr>\n",
" <tr>\n",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <th>73653</th>\n",
" <td>853</td>\n",
" <td>4</td>\n",
" <td>Gang Related (1997)</td>\n",
" <td>Crime</td>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" </tr>\n",
" <tr>\n",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <th>20974</th>\n",
" <td>853</td>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" <td>4</td>\n",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <td>I Know What You Did Last Summer (1997)</td>\n",
" <td>Horror, Mystery, Thriller</td>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" </tr>\n",
" <tr>\n",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <th>62996</th>\n",
" <td>853</td>\n",
" <td>3</td>\n",
" <td>Kiss the Girls (1997)</td>\n",
" <td>Crime, Drama, Thriller</td>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" </tr>\n",
" <tr>\n",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <th>37091</th>\n",
" <td>853</td>\n",
" <td>3</td>\n",
" <td>Contact (1997)</td>\n",
" <td>Drama, Sci-Fi</td>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
Zadanie 6
2021-06-12 11:14:56 +02:00
" user rating title \\\n",
"29798 853 5 Soul Food (1997) \n",
"26282 853 5 Air Force One (1997) \n",
"73991 853 4 Fire Down Below (1997) \n",
"24846 853 4 Gattaca (1997) \n",
"52746 853 4 Fly Away Home (1996) \n",
"46026 853 4 L.A. Confidential (1997) \n",
"33394 853 4 Game, The (1997) \n",
"58732 853 4 Volcano (1997) \n",
"30970 853 4 Rosewood (1997) \n",
"55641 853 4 Hoodlum (1997) \n",
"19322 853 4 Scream (1996) \n",
"73653 853 4 Gang Related (1997) \n",
"20974 853 4 I Know What You Did Last Summer (1997) \n",
"62996 853 3 Kiss the Girls (1997) \n",
"37091 853 3 Contact (1997) \n",
3rd meeting
2021-05-07 22:16:28 +02:00
"\n",
Zadanie 6
2021-06-12 11:14:56 +02:00
" genres \n",
"29798 Drama \n",
"26282 Action, Thriller \n",
"73991 Action, Drama, Thriller \n",
"24846 Drama, Sci-Fi, Thriller \n",
"52746 Adventure, Children's \n",
"46026 Crime, Film-Noir, Mystery, Thriller \n",
"33394 Mystery, Thriller \n",
"58732 Drama, Thriller \n",
"30970 Drama \n",
"55641 Crime, Drama, Film-Noir \n",
"19322 Horror, Thriller \n",
"73653 Crime \n",
"20974 Horror, Mystery, Thriller \n",
"62996 Crime, Drama, Thriller \n",
"37091 Drama, Sci-Fi "
3rd meeting
2021-05-07 22:16:28 +02:00
]
},
"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",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <th>5009</th>\n",
" <td>853.0</td>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" <td>1</td>\n",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <td>Titanic (1997)</td>\n",
" <td>Action, Drama, Romance</td>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" </tr>\n",
" <tr>\n",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <th>5225</th>\n",
" <td>853.0</td>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" <td>2</td>\n",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <td>Full Monty, The (1997)</td>\n",
" <td>Comedy</td>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" </tr>\n",
" <tr>\n",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <th>8911</th>\n",
" <td>853.0</td>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" <td>3</td>\n",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <td>Murder at 1600 (1997)</td>\n",
" <td>Mystery, Thriller</td>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" </tr>\n",
" <tr>\n",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <th>3809</th>\n",
" <td>853.0</td>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" <td>4</td>\n",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <td>Chasing Amy (1997)</td>\n",
" <td>Drama, Romance</td>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" </tr>\n",
" <tr>\n",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <th>380</th>\n",
" <td>853.0</td>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" <td>5</td>\n",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <td>Star Wars (1977)</td>\n",
" <td>Action, Adventure, Romance, Sci-Fi, War</td>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" </tr>\n",
" <tr>\n",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <th>6337</th>\n",
" <td>853.0</td>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" <td>6</td>\n",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <td>Good Will Hunting (1997)</td>\n",
" <td>Drama</td>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" </tr>\n",
" <tr>\n",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <th>2979</th>\n",
" <td>853.0</td>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" <td>7</td>\n",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <td>Return of the Jedi (1983)</td>\n",
" <td>Action, Adventure, Romance, Sci-Fi, War</td>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" </tr>\n",
" <tr>\n",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <th>9039</th>\n",
" <td>853.0</td>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" <td>8</td>\n",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <td>Evita (1996)</td>\n",
" <td>Drama, Musical</td>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" </tr>\n",
" <tr>\n",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <th>9021</th>\n",
" <td>853.0</td>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" <td>9</td>\n",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <td>Seven Years in Tibet (1997)</td>\n",
" <td>Drama, War</td>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" </tr>\n",
" <tr>\n",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <th>7296</th>\n",
" <td>853.0</td>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" <td>10</td>\n",
Zadanie 6
2021-06-12 11:14:56 +02:00
" <td>Fargo (1996)</td>\n",
" <td>Crime, Drama, Thriller</td>\n",
3rd meeting
2021-05-07 22:16:28 +02:00
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
Zadanie 6
2021-06-12 11:14:56 +02:00
" user rec_nb title \\\n",
"5009 853.0 1 Titanic (1997) \n",
"5225 853.0 2 Full Monty, The (1997) \n",
"8911 853.0 3 Murder at 1600 (1997) \n",
"3809 853.0 4 Chasing Amy (1997) \n",
"380 853.0 5 Star Wars (1977) \n",
"6337 853.0 6 Good Will Hunting (1997) \n",
"2979 853.0 7 Return of the Jedi (1983) \n",
"9039 853.0 8 Evita (1996) \n",
"9021 853.0 9 Seven Years in Tibet (1997) \n",
"7296 853.0 10 Fargo (1996) \n",
3rd meeting
2021-05-07 22:16:28 +02:00
"\n",
" genres \n",
Zadanie 6
2021-06-12 11:14:56 +02:00
"5009 Action, Drama, Romance \n",
"5225 Comedy \n",
"8911 Mystery, Thriller \n",
"3809 Drama, Romance \n",
"380 Action, Adventure, Romance, Sci-Fi, War \n",
"6337 Drama \n",
"2979 Action, Adventure, Romance, Sci-Fi, War \n",
"9039 Drama, Musical \n",
"9021 Drama, War \n",
"7296 Crime, Drama, Thriller "
3rd meeting
2021-05-07 22:16:28 +02:00
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"train = pd.read_csv(\n",
" \"./Datasets/ml-100k/train.csv\",\n",
" sep=\"\\t\",\n",
" header=None,\n",
" names=[\"user\", \"item\", \"rating\", \"timestamp\"],\n",
")\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(\n",
" train_content[train_content[\"user\"] == user][\n",
" [\"user\", \"rating\", \"title\", \"genres\"]\n",
" ].sort_values(by=\"rating\", ascending=False)[:15]\n",
")\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][\n",
" [\"user\", \"rec_nb\", \"title\", \"genres\"]\n",
"].sort_values(by=\"rec_nb\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# project task 5: generate recommendations of RP3Beta for hyperparameters found to optimize recall"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [],
"source": [
"# We generated recommendations for P3, a special case of RP3Beta (with alpha=1, beta=0).\n",
"# We've observed that changing alpha and beta impacts the model performance.\n",
"\n",
task explanation
2021-05-08 11:46:21 +02:00
"# Your task is find values alpha and beta for which recall will be the highest \n",
"# (any solution with recall higher than P3 will be accepted)\n",
"# train the model and generate recommendations.\n",
3rd meeting
2021-05-07 22:16:28 +02:00
"\n",
"# save the outptut in 'Recommendations generated/ml-100k/Self_RP3Beta_estimations.csv'\n",
"# and 'Recommendations generated/ml-100k/Self_RP3Beta_reco.csv'"
]
},
Zadanie 6
2021-06-12 11:14:56 +02:00
{
"cell_type": "code",
"execution_count": 36,
"metadata": {},
"outputs": [],
"source": [
"model = RP3Beta()\n",
"model.fit(train_ui, alpha=0.6, beta=0.6)"
]
},
{
"cell_type": "code",
"execution_count": 37,
"metadata": {},
"outputs": [],
"source": [
"top_n = pd.DataFrame(model.recommend(user_code_id, item_code_id, topK=10))\n",
"\n",
"top_n.to_csv(\n",
" \"Recommendations generated/ml-100k/Self_RP3Beta_reco.csv\", index=False, header=False\n",
")\n",
"\n",
"estimations = pd.DataFrame(model.estimate(user_code_id, item_code_id, test_ui))\n",
"estimations.to_csv(\n",
" \"Recommendations generated/ml-100k/Self_RP3Beta_estimations.csv\",\n",
" index=False,\n",
" header=False,\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 38,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"943it [00:00, 12405.33it/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>HitRate2</th>\n",
" <th>HitRate3</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>3.675385</td>\n",
" <td>3.499644</td>\n",
" <td>0.321209</td>\n",
" <td>0.212728</td>\n",
" <td>0.210025</td>\n",
" <td>0.245804</td>\n",
" <td>0.240021</td>\n",
" <td>0.275765</td>\n",
" <td>0.39005</td>\n",
" <td>0.252127</td>\n",
" <td>0.641583</td>\n",
" <td>0.604033</td>\n",
" <td>0.898197</td>\n",
" <td>0.725345</td>\n",
" <td>0.552492</td>\n",
" <td>1.0</td>\n",
" <td>0.157287</td>\n",
" <td>4.524904</td>\n",
" <td>0.951442</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" RMSE MAE precision recall F_1 F_05 \\\n",
"0 3.675385 3.499644 0.321209 0.212728 0.210025 0.245804 \n",
"\n",
" precision_super recall_super NDCG mAP MRR LAUC \\\n",
"0 0.240021 0.275765 0.39005 0.252127 0.641583 0.604033 \n",
"\n",
" HR HitRate2 HitRate3 Reco in test Test coverage Shannon \\\n",
"0 0.898197 0.725345 0.552492 1.0 0.157287 4.524904 \n",
"\n",
" Gini \n",
"0 0.951442 "
]
},
"execution_count": 38,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import evaluation_measures as ev\n",
"\n",
"estimations_df = pd.read_csv(\n",
" \"Recommendations generated/ml-100k/Self_RP3Beta_estimations.csv\", header=None\n",
")\n",
"reco = np.loadtxt(\"Recommendations generated/ml-100k/Self_RP3Beta_reco.csv\", delimiter=\",\")\n",
"\n",
"ev.evaluate(\n",
" 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],\n",
")"
]
},
3rd meeting
2021-05-07 22:16:28 +02:00
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# project task 6 (optional): implement graph-based model of your choice "
]
},
{
"cell_type": "code",
Zadanie 6
2021-06-12 11:14:56 +02:00
"execution_count": 9,
3rd meeting
2021-05-07 22:16:28 +02:00
"metadata": {},
"outputs": [],
"source": [
"# for example change length of paths in RP3beta or make some other modification (but change more than input and hyperparameters)\n",
"# feel free to implement your idea or search for some ideas\n",
"\n",
"# save the outptut in 'Recommendations generated/ml-100k/Self_GraphTask_estimations.csv'\n",
"# and 'Recommendations generated/ml-100k/Self_GraphTask_reco.csv'"
]
Zadanie 6
2021-06-12 11:14:56 +02:00
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [],
"source": [
"class RP3Custom:\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)(\n",
" self.train_iu.sum(axis=1)\n",
" ) # 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",
" PuiAlfa = Pui.power(self.alpha)\n",
" PiuAlfa = Piu.power(self.alpha)\n",
" PuiBeta = Pui.power(self.beta)\n",
" PiuBeta = Piu.power(self.beta)\n",
"\n",
" P3 = PuiAlfa * PiuAlfa * PuiAlfa * PuiBeta * PiuBeta\n",
"\n",
" P3 /= np.power(\n",
" np.vectorize(lambda x: x if x > 0 else 1)(item_orders), self.beta\n",
" )\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[\n",
" self.train_ui.indptr[nb_user] : self.train_ui.indptr[nb_user + 1]\n",
" ]\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(\n",
" [\n",
" user_code_id[user],\n",
" item_code_id[item],\n",
" self.estimations[user, item]\n",
" if not np.isnan(self.estimations[user, item])\n",
" else 1,\n",
" ]\n",
" )\n",
" return result"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"943it [00:00, 13313.77it/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>HitRate2</th>\n",
" <th>HitRate3</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>3.702928</td>\n",
" <td>3.527713</td>\n",
" <td>0.322694</td>\n",
" <td>0.216069</td>\n",
" <td>0.212152</td>\n",
" <td>0.247538</td>\n",
" <td>0.245279</td>\n",
" <td>0.284983</td>\n",
" <td>0.388271</td>\n",
" <td>0.248239</td>\n",
" <td>0.636318</td>\n",
" <td>0.605683</td>\n",
" <td>0.910923</td>\n",
" <td>0.731707</td>\n",
" <td>0.554613</td>\n",
" <td>0.999788</td>\n",
" <td>0.178932</td>\n",
" <td>4.549663</td>\n",
" <td>0.950182</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" RMSE MAE precision recall F_1 F_05 \\\n",
"0 3.702928 3.527713 0.322694 0.216069 0.212152 0.247538 \n",
"\n",
" precision_super recall_super NDCG mAP MRR LAUC \\\n",
"0 0.245279 0.284983 0.388271 0.248239 0.636318 0.605683 \n",
"\n",
" HR HitRate2 HitRate3 Reco in test Test coverage Shannon \\\n",
"0 0.910923 0.731707 0.554613 0.999788 0.178932 4.549663 \n",
"\n",
" Gini \n",
"0 0.950182 "
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"myModel = RP3Custom()\n",
"model.fit(train_ui, alpha=0.8, beta=0.6)\n",
"\n",
"top_n = pd.DataFrame(model.recommend(user_code_id, item_code_id, topK=10))\n",
"\n",
"top_n.to_csv(\n",
" \"Recommendations generated/ml-100k/Self_GraphTask_reco.csv\", index=False, header=False\n",
")\n",
"\n",
"estimations = pd.DataFrame(model.estimate(user_code_id, item_code_id, test_ui))\n",
"estimations.to_csv(\n",
" \"Recommendations generated/ml-100k/Self_GraphTask_estimations.csv\",\n",
" index=False,\n",
" header=False,\n",
")\n",
"\n",
"estimations_df = pd.read_csv(\n",
" \"Recommendations generated/ml-100k/Self_GraphTask_estimations.csv\", header=None\n",
")\n",
"reco = np.loadtxt(\"Recommendations generated/ml-100k/Self_GraphTask_reco.csv\", delimiter=\",\")\n",
"\n",
"ev.evaluate(\n",
" 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],\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
3rd meeting
2021-05-07 22:16:28 +02:00
}
],
"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",
Zadanie 6
2021-06-12 11:14:56 +02:00
"version": "3.8.8"
3rd meeting
2021-05-07 22:16:28 +02:00
}
},
"nbformat": 4,
"nbformat_minor": 4
}
Reference in New Issue Copy Permalink