s416051/workshops_recommender_systems
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity
b7289d573a
workshops_recommender_systems/P3. k-nearest neighbours.ipynb

1709 lines
60 KiB
Plaintext
Raw Normal View History

all
2020-06-13 22:14:04 +02:00
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Self made simplified I-KNN"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import helpers\n",
"import pandas as pd\n",
"import numpy as np\n",
"import scipy.sparse as sparse\n",
"from collections import defaultdict\n",
"from itertools import chain\n",
"import random\n",
"\n",
"train_read=pd.read_csv('./Datasets/ml-100k/train.csv', sep='\\t', header=None)\n",
"test_read=pd.read_csv('./Datasets/ml-100k/test.csv', sep='\\t', header=None)\n",
"train_ui, test_ui, user_code_id, user_id_code, item_code_id, item_id_code = helpers.data_to_csr(train_read, test_read)"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"class IKNN():\n",
" \n",
" def fit(self, train_ui):\n",
" self.train_ui=train_ui\n",
" \n",
" train_iu=train_ui.transpose()\n",
" norms=np.linalg.norm(train_iu.A, axis=1) # here we compute lenth of each item ratings vector\n",
" norms=np.vectorize(lambda x: max(x,1))(norms[:,None]) # to avoid dividing by zero\n",
"\n",
" normalized_train_iu=sparse.csr_matrix(train_iu/norms)\n",
"\n",
" self.similarity_matrix_ii=normalized_train_iu*normalized_train_iu.transpose()\n",
" \n",
" self.estimations=np.array(train_ui*self.similarity_matrix_ii/((train_ui>0)*self.similarity_matrix_ii))\n",
" \n",
" def recommend(self, user_code_id, item_code_id, topK=10):\n",
" \n",
" top_k = defaultdict(list)\n",
" for nb_user, user in enumerate(self.estimations):\n",
" \n",
" user_rated=self.train_ui.indices[self.train_ui.indptr[nb_user]:self.train_ui.indptr[nb_user+1]]\n",
" for item, score in enumerate(user):\n",
" if item not in user_rated and not np.isnan(score):\n",
" top_k[user_code_id[nb_user]].append((item_code_id[item], score))\n",
" result=[]\n",
" # Let's choose k best items in the format: (user, item1, score1, item2, score2, ...)\n",
" for uid, item_scores in top_k.items():\n",
" item_scores.sort(key=lambda x: x[1], reverse=True)\n",
" result.append([uid]+list(chain(*item_scores[:topK])))\n",
" return result\n",
" \n",
" def estimate(self, user_code_id, item_code_id, test_ui):\n",
" result=[]\n",
" for user, item in zip(*test_ui.nonzero()):\n",
" result.append([user_code_id[user], item_code_id[item], \n",
" self.estimations[user,item] if not np.isnan(self.estimations[user,item]) else 1])\n",
" return result"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"toy train ui:\n"
]
},
{
"data": {
"text/plain": [
"array([[3, 4, 0, 0, 5, 0, 0, 4],\n",
" [0, 1, 2, 3, 0, 0, 0, 0],\n",
" [0, 0, 0, 5, 0, 3, 4, 0]], dtype=int64)"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"similarity matrix:\n"
]
},
{
"data": {
"text/plain": [
"array([[1. , 0.9701425 , 0. , 0. , 1. ,\n",
" 0. , 0. , 1. ],\n",
" [0.9701425 , 1. , 0.24253563, 0.12478355, 0.9701425 ,\n",
" 0. , 0. , 0.9701425 ],\n",
" [0. , 0.24253563, 1. , 0.51449576, 0. ,\n",
" 0. , 0. , 0. ],\n",
" [0. , 0.12478355, 0.51449576, 1. , 0. ,\n",
" 0.85749293, 0.85749293, 0. ],\n",
" [1. , 0.9701425 , 0. , 0. , 1. ,\n",
" 0. , 0. , 1. ],\n",
" [0. , 0. , 0. , 0.85749293, 0. ,\n",
" 1. , 1. , 0. ],\n",
" [0. , 0. , 0. , 0.85749293, 0. ,\n",
" 1. , 1. , 0. ],\n",
" [1. , 0.9701425 , 0. , 0. , 1. ,\n",
" 0. , 0. , 1. ]])"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"estimations matrix:\n"
]
},
{
"data": {
"text/plain": [
"array([[4. , 4. , 4. , 4. , 4. ,\n",
" nan, nan, 4. ],\n",
" [1. , 1.35990333, 2.15478388, 2.53390319, 1. ,\n",
" 3. , 3. , 1. ],\n",
" [ nan, 5. , 5. , 4.05248907, nan,\n",
" 3.95012863, 3.95012863, nan]])"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/plain": [
"[[0, 20, 4.0, 30, 4.0],\n",
" [10, 50, 3.0, 60, 3.0, 0, 1.0, 40, 1.0, 70, 1.0],\n",
" [20, 10, 5.0, 20, 5.0]]"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# toy example\n",
"toy_train_read=pd.read_csv('./Datasets/toy-example/train.csv', sep='\\t', header=None, names=['user', 'item', 'rating', 'timestamp'])\n",
"toy_test_read=pd.read_csv('./Datasets/toy-example/test.csv', sep='\\t', header=None, names=['user', 'item', 'rating', 'timestamp'])\n",
"\n",
"toy_train_ui, toy_test_ui, toy_user_code_id, toy_user_id_code, \\\n",
"toy_item_code_id, toy_item_id_code = helpers.data_to_csr(toy_train_read, toy_test_read)\n",
"\n",
"\n",
"model=IKNN()\n",
"model.fit(toy_train_ui)\n",
"\n",
"print('toy train ui:')\n",
"display(toy_train_ui.A)\n",
"\n",
"print('similarity matrix:')\n",
"display(model.similarity_matrix_ii.A)\n",
"\n",
"print('estimations matrix:')\n",
"display(model.estimations)\n",
"\n",
"model.recommend(toy_user_code_id, toy_item_code_id)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"model=IKNN()\n",
"model.fit(train_ui)\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_IKNN_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_IKNN_estimations.csv', index=False, header=False)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"943it [00:00, 7381.00it/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>HR2</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>1.018363</td>\n",
" <td>0.808793</td>\n",
" <td>0.000318</td>\n",
" <td>0.000108</td>\n",
" <td>0.00014</td>\n",
" <td>0.000189</td>\n",
" <td>0.0</td>\n",
" <td>0.0</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>0.0</td>\n",
" <td>0.392153</td>\n",
" <td>0.11544</td>\n",
" <td>4.174741</td>\n",
" <td>0.965327</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" RMSE MAE precision recall F_1 F_05 \\\n",
"0 1.018363 0.808793 0.000318 0.000108 0.00014 0.000189 \n",
"\n",
" precision_super recall_super NDCG mAP MRR LAUC \\\n",
"0 0.0 0.0 0.000214 0.000037 0.000368 0.496391 \n",
"\n",
" HR HR2 Reco in test Test coverage Shannon Gini \n",
"0 0.003181 0.0 0.392153 0.11544 4.174741 0.965327 "
]
},
"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_IKNN_estimations.csv', header=None)\n",
"reco=np.loadtxt('Recommendations generated/ml-100k/Self_IKNN_reco.csv', delimiter=',')\n",
"\n",
"ev.evaluate(test=pd.read_csv('./Datasets/ml-100k/test.csv', sep='\\t', header=None),\n",
" estimations_df=estimations_df, \n",
" reco=reco,\n",
" super_reactions=[4,5])"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"943it [00:00, 6244.78it/s]\n",
"943it [00:00, 6960.47it/s]\n",
"943it [00:00, 6090.17it/s]\n",
"943it [00:00, 6876.64it/s]\n",
"943it [00:00, 7185.17it/s]\n",
"943it [00:00, 6481.90it/s]\n",
"943it [00:00, 4245.42it/s]\n",
"943it [00:00, 6388.64it/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>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>HR2</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>0.492047</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_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>0.239661</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>0.142100</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",
" <td>1.517593</td>\n",
" <td>1.220181</td>\n",
" <td>0.046023</td>\n",
" <td>0.019038</td>\n",
" <td>0.023118</td>\n",
" <td>0.030734</td>\n",
" <td>0.029292</td>\n",
" <td>0.021639</td>\n",
" <td>0.050818</td>\n",
" <td>0.019958</td>\n",
" <td>0.126646</td>\n",
" <td>0.506031</td>\n",
" <td>0.305408</td>\n",
" <td>0.111347</td>\n",
" <td>0.988547</td>\n",
" <td>0.174603</td>\n",
" <td>5.082383</td>\n",
" <td>0.908434</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Self_TopRated</td>\n",
" <td>2.508258</td>\n",
" <td>2.217909</td>\n",
" <td>0.000954</td>\n",
" <td>0.000188</td>\n",
" <td>0.000298</td>\n",
" <td>0.000481</td>\n",
" <td>0.000644</td>\n",
" <td>0.000223</td>\n",
" <td>0.001043</td>\n",
" <td>0.000335</td>\n",
" <td>0.003348</td>\n",
" <td>0.496433</td>\n",
" <td>0.009544</td>\n",
" <td>0.000000</td>\n",
" <td>0.699046</td>\n",
" <td>0.005051</td>\n",
" <td>1.945910</td>\n",
" <td>0.995669</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Self_BaselineIU</td>\n",
" <td>0.958136</td>\n",
" <td>0.754051</td>\n",
" <td>0.000954</td>\n",
" <td>0.000188</td>\n",
" <td>0.000298</td>\n",
" <td>0.000481</td>\n",
" <td>0.000644</td>\n",
" <td>0.000223</td>\n",
" <td>0.001043</td>\n",
" <td>0.000335</td>\n",
" <td>0.003348</td>\n",
" <td>0.496433</td>\n",
" <td>0.009544</td>\n",
" <td>0.000000</td>\n",
" <td>0.699046</td>\n",
" <td>0.005051</td>\n",
" <td>1.945910</td>\n",
" <td>0.995669</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>0.000000</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>0.000000</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",
"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",
"0 Ready_Random 1.517593 1.220181 0.046023 0.019038 0.023118 \n",
"0 Self_TopRated 2.508258 2.217909 0.000954 0.000188 0.000298 \n",
"0 Self_BaselineIU 0.958136 0.754051 0.000954 0.000188 0.000298 \n",
"0 Self_BaselineUI 0.967585 0.762740 0.000954 0.000170 0.000278 \n",
"0 Self_IKNN 1.018363 0.808793 0.000318 0.000108 0.000140 \n",
"\n",
" F_05 precision_super recall_super NDCG mAP MRR \\\n",
"0 0.141584 0.130472 0.137473 0.214651 0.111707 0.400939 \n",
"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",
"0 0.030734 0.029292 0.021639 0.050818 0.019958 0.126646 \n",
"0 0.000481 0.000644 0.000223 0.001043 0.000335 0.003348 \n",
"0 0.000481 0.000644 0.000223 0.001043 0.000335 0.003348 \n",
"0 0.000463 0.000644 0.000189 0.000752 0.000168 0.001677 \n",
"0 0.000189 0.000000 0.000000 0.000214 0.000037 0.000368 \n",
"\n",
" LAUC HR HR2 Reco in test Test coverage Shannon \\\n",
"0 0.555546 0.765642 0.492047 1.000000 0.038961 3.159079 \n",
"0 0.515501 0.437964 0.239661 1.000000 0.033911 2.836513 \n",
"0 0.509546 0.384942 0.142100 1.000000 0.025974 2.711772 \n",
"0 0.506031 0.305408 0.111347 0.988547 0.174603 5.082383 \n",
"0 0.496433 0.009544 0.000000 0.699046 0.005051 1.945910 \n",
"0 0.496433 0.009544 0.000000 0.699046 0.005051 1.945910 \n",
"0 0.496424 0.009544 0.000000 0.600530 0.005051 1.803126 \n",
"0 0.496391 0.003181 0.000000 0.392153 0.115440 4.174741 \n",
"\n",
" Gini \n",
"0 0.987317 \n",
"0 0.991139 \n",
"0 0.992003 \n",
"0 0.908434 \n",
"0 0.995669 \n",
"0 0.995669 \n",
"0 0.996380 \n",
"0 0.965327 "
]
},
"execution_count": 6,
"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": [
"# Ready-made KNNs - Surprise implementation"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### I-KNN - basic"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Computing the cosine similarity matrix...\n",
"Done computing similarity matrix.\n",
"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",
"sim_options = {'name': 'cosine',\n",
" 'user_based': False} # compute similarities between items\n",
"algo = sp.KNNBasic(sim_options=sim_options)\n",
"\n",
"helpers.ready_made(algo, reco_path='Recommendations generated/ml-100k/Ready_I-KNN_reco.csv',\n",
" estimations_path='Recommendations generated/ml-100k/Ready_I-KNN_estimations.csv')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### U-KNN - basic"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Computing the cosine similarity matrix...\n",
"Done computing similarity matrix.\n",
"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",
"sim_options = {'name': 'cosine',\n",
" 'user_based': True} # compute similarities between users\n",
"algo = sp.KNNBasic(sim_options=sim_options)\n",
"\n",
"helpers.ready_made(algo, reco_path='Recommendations generated/ml-100k/Ready_U-KNN_reco.csv',\n",
" estimations_path='Recommendations generated/ml-100k/Ready_U-KNN_estimations.csv')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### I-KNN - on top baseline"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import helpers\n",
"import surprise as sp\n",
"import imp\n",
"imp.reload(helpers)\n",
"\n",
"sim_options = {'name': 'cosine',\n",
" 'user_based': False} # compute similarities between items\n",
"algo = sp.KNNBaseline()\n",
"\n",
"helpers.ready_made(algo, reco_path='Recommendations generated/ml-100k/Ready_I-KNNBaseline_reco.csv',\n",
" estimations_path='Recommendations generated/ml-100k/Ready_I-KNNBaseline_estimations.csv')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# project task 4: use a version of your choice of Surprise KNNalgorithm"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [],
"source": [
"# read the docs and try to find best parameter configuration (let say in terms of RMSE)\n",
"# https://surprise.readthedocs.io/en/stable/knn_inspired.html##surprise.prediction_algorithms.knns.KNNBaseline\n",
"# the solution here can be similar to examples above\n",
"# please save the output in 'Recommendations generated/ml-100k/Self_KNNSurprisetask_reco.csv' and\n",
"# 'Recommendations generated/ml-100k/Self_KNNSurprisetask_estimations.csv'"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Computing the msd similarity matrix...\n",
"Done computing similarity matrix.\n",
"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",
"sim_options = {'name': 'cosine',\n",
" 'user_based': False} # compute similarities between items\n",
"algo = sp.KNNWithMeans()\n",
"\n",
"helpers.ready_made(algo, reco_path='Recommendations generated/ml-100k/Ready_I-KNNWithMeans_reco.csv',\n",
" estimations_path='Recommendations generated/ml-100k/Ready_I-KNNWithMeans_estimations.csv')"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Computing the msd similarity matrix...\n",
"Done computing similarity matrix.\n",
"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",
"sim_options = {'name': 'cosine',\n",
" 'user_based': False} # compute similarities between items\n",
"algo = sp.KNNWithZScore()\n",
"\n",
"helpers.ready_made(algo, reco_path='Recommendations generated/ml-100k/Ready_I-KNNWithZScore_reco.csv',\n",
" estimations_path='Recommendations generated/ml-100k/Ready_I-KNNWithZScore_estimations.csv')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import helpers\n",
"import surprise as sp\n",
"import imp\n",
"imp.reload(helpers)\n",
"\n",
"sim_options = {'name': 'cosine',\n",
" 'user_based': False} # compute similarities between items\n",
"k = 38\n",
"\n",
"for i in range(10):\n",
" path1 = \"Recommendations generated/ml-100k/Self_I-KNNBaseline%d_reco.csv\" % (k)\n",
" path2 = \"Recommendations generated/ml-100k/Self_I-KNNBaseline%d_estimations.csv\" % (k)\n",
" algo = sp.KNNBaseline(k=k)\n",
" helpers.ready_made(algo, reco_path=path1,\n",
" estimations_path=path2)\n",
" k+=1\n"
]
},
{
"cell_type": "code",
"execution_count": 35,
"metadata": {
"scrolled": true
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"943it [00:00, 6566.70it/s]\n",
"943it [00:00, 6053.18it/s]\n",
"943it [00:00, 6753.76it/s]\n",
"943it [00:00, 6451.06it/s]\n",
"943it [00:00, 3763.62it/s]\n",
"943it [00:00, 4634.14it/s]\n",
"943it [00:00, 6520.99it/s]\n",
"943it [00:00, 6061.07it/s]\n",
"943it [00:00, 5946.69it/s]\n",
"943it [00:00, 6520.59it/s]\n",
"943it [00:00, 4047.05it/s]\n",
"943it [00:00, 6061.15it/s]\n",
"943it [00:00, 6430.82it/s]\n",
"943it [00:00, 6519.56it/s]\n",
"943it [00:00, 6127.91it/s]\n",
"943it [00:00, 6220.07it/s]\n",
"943it [00:00, 6731.95it/s]\n",
"943it [00:00, 5617.04it/s]\n",
"943it [00:00, 5984.37it/s]\n",
"943it [00:00, 3923.26it/s]\n",
"943it [00:00, 4799.65it/s]\n",
"943it [00:00, 6678.60it/s]\n",
"943it [00:00, 5984.12it/s]\n",
"943it [00:00, 7217.79it/s]\n",
"943it [00:00, 4799.62it/s]\n",
"943it [00:00, 4799.67it/s]\n",
"943it [00:00, 6566.16it/s]\n"
]
}
],
"source": [
"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",
"result = ev.evaluate_all(test, dir_path, super_reactions)"
]
},
{
"cell_type": "code",
"execution_count": 36,
"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>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>HR2</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_SVDBaseline</td>\n",
" <td>0.913253</td>\n",
" <td>0.719475</td>\n",
" <td>0.105090</td>\n",
" <td>0.043952</td>\n",
" <td>0.053454</td>\n",
" <td>0.070803</td>\n",
" <td>0.095279</td>\n",
" <td>0.073469</td>\n",
" <td>0.118152</td>\n",
" <td>0.058739</td>\n",
" <td>0.244096</td>\n",
" <td>0.518714</td>\n",
" <td>0.471898</td>\n",
" <td>0.279958</td>\n",
" <td>0.999682</td>\n",
" <td>0.111111</td>\n",
" <td>3.572421</td>\n",
" <td>0.980655</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Self_SVD</td>\n",
" <td>0.914521</td>\n",
" <td>0.717680</td>\n",
" <td>0.102757</td>\n",
" <td>0.043043</td>\n",
" <td>0.052432</td>\n",
" <td>0.069515</td>\n",
" <td>0.094528</td>\n",
" <td>0.075122</td>\n",
" <td>0.106751</td>\n",
" <td>0.051431</td>\n",
" <td>0.198701</td>\n",
" <td>0.518248</td>\n",
" <td>0.462354</td>\n",
" <td>0.255567</td>\n",
" <td>0.854931</td>\n",
" <td>0.147186</td>\n",
" <td>3.888926</td>\n",
" <td>0.972044</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Self_I-KNNBaseline42</td>\n",
" <td>0.935028</td>\n",
" <td>0.737210</td>\n",
" <td>0.002969</td>\n",
" <td>0.000980</td>\n",
" <td>0.001374</td>\n",
" <td>0.001929</td>\n",
" <td>0.002682</td>\n",
" <td>0.001217</td>\n",
" <td>0.004069</td>\n",
" <td>0.001677</td>\n",
" <td>0.013349</td>\n",
" <td>0.496838</td>\n",
" <td>0.023330</td>\n",
" <td>0.006363</td>\n",
" <td>0.481972</td>\n",
" <td>0.059163</td>\n",
" <td>2.227849</td>\n",
" <td>0.994531</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Self_KNNSurprisetask</td>\n",
" <td>0.935028</td>\n",
" <td>0.737210</td>\n",
" <td>0.002969</td>\n",
" <td>0.000980</td>\n",
" <td>0.001374</td>\n",
" <td>0.001929</td>\n",
" <td>0.002682</td>\n",
" <td>0.001217</td>\n",
" <td>0.004069</td>\n",
" <td>0.001677</td>\n",
" <td>0.013349</td>\n",
" <td>0.496838</td>\n",
" <td>0.023330</td>\n",
" <td>0.006363</td>\n",
" <td>0.481972</td>\n",
" <td>0.059163</td>\n",
" <td>2.227849</td>\n",
" <td>0.994531</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Self_I-KNNBaseline41</td>\n",
" <td>0.935205</td>\n",
" <td>0.737439</td>\n",
" <td>0.002651</td>\n",
" <td>0.000774</td>\n",
" <td>0.001138</td>\n",
" <td>0.001658</td>\n",
" <td>0.002361</td>\n",
" <td>0.000959</td>\n",
" <td>0.003537</td>\n",
" <td>0.001435</td>\n",
" <td>0.011494</td>\n",
" <td>0.496734</td>\n",
" <td>0.021209</td>\n",
" <td>0.005302</td>\n",
" <td>0.482503</td>\n",
" <td>0.057720</td>\n",
" <td>2.228123</td>\n",
" <td>0.994555</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Self_I-KNNBaseline43</td>\n",
" <td>0.935241</td>\n",
" <td>0.737463</td>\n",
" <td>0.002863</td>\n",
" <td>0.000952</td>\n",
" <td>0.001331</td>\n",
" <td>0.001862</td>\n",
" <td>0.002575</td>\n",
" <td>0.001186</td>\n",
" <td>0.004014</td>\n",
" <td>0.001663</td>\n",
" <td>0.013467</td>\n",
" <td>0.496824</td>\n",
" <td>0.023330</td>\n",
" <td>0.005302</td>\n",
" <td>0.482609</td>\n",
" <td>0.055556</td>\n",
" <td>2.225996</td>\n",
" <td>0.994623</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Self_I-KNNBaseline46</td>\n",
" <td>0.935244</td>\n",
" <td>0.737512</td>\n",
" <td>0.003287</td>\n",
" <td>0.001096</td>\n",
" <td>0.001534</td>\n",
" <td>0.002148</td>\n",
" <td>0.003004</td>\n",
" <td>0.001376</td>\n",
" <td>0.004398</td>\n",
" <td>0.001856</td>\n",
" <td>0.013719</td>\n",
" <td>0.496898</td>\n",
" <td>0.024390</td>\n",
" <td>0.007423</td>\n",
" <td>0.482397</td>\n",
" <td>0.057720</td>\n",
" <td>2.225807</td>\n",
" <td>0.994607</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Self_I-KNNBaseline44</td>\n",
" <td>0.935259</td>\n",
" <td>0.737530</td>\n",
" <td>0.002969</td>\n",
" <td>0.000902</td>\n",
" <td>0.001305</td>\n",
" <td>0.001880</td>\n",
" <td>0.002682</td>\n",
" <td>0.001129</td>\n",
" <td>0.004215</td>\n",
" <td>0.001823</td>\n",
" <td>0.013977</td>\n",
" <td>0.496799</td>\n",
" <td>0.023330</td>\n",
" <td>0.005302</td>\n",
" <td>0.482397</td>\n",
" <td>0.057720</td>\n",
" <td>2.225495</td>\n",
" <td>0.994598</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Self_I-KNNBaseline45</td>\n",
" <td>0.935268</td>\n",
" <td>0.737543</td>\n",
" <td>0.003075</td>\n",
" <td>0.001044</td>\n",
" <td>0.001450</td>\n",
" <td>0.002016</td>\n",
" <td>0.002790</td>\n",
" <td>0.001317</td>\n",
" <td>0.004287</td>\n",
" <td>0.001812</td>\n",
" <td>0.014189</td>\n",
" <td>0.496871</td>\n",
" <td>0.024390</td>\n",
" <td>0.005302</td>\n",
" <td>0.482609</td>\n",
" <td>0.058442</td>\n",
" <td>2.225340</td>\n",
" <td>0.994599</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Self_I-KNNBaseline47</td>\n",
" <td>0.935295</td>\n",
" <td>0.737563</td>\n",
" <td>0.003075</td>\n",
" <td>0.001044</td>\n",
" <td>0.001450</td>\n",
" <td>0.002016</td>\n",
" <td>0.002790</td>\n",
" <td>0.001317</td>\n",
" <td>0.004199</td>\n",
" <td>0.001735</td>\n",
" <td>0.013888</td>\n",
" <td>0.496871</td>\n",
" <td>0.024390</td>\n",
" <td>0.005302</td>\n",
" <td>0.482397</td>\n",
" <td>0.055556</td>\n",
" <td>2.221942</td>\n",
" <td>0.994676</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Self_I-KNNBaseline40</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>0.004242</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_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>0.004242</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>Self_I-KNNBaseline39</td>\n",
" <td>0.935520</td>\n",
" <td>0.737631</td>\n",
" <td>0.002757</td>\n",
" <td>0.000856</td>\n",
" <td>0.001230</td>\n",
" <td>0.001758</td>\n",
" <td>0.002468</td>\n",
" <td>0.001048</td>\n",
" <td>0.003899</td>\n",
" <td>0.001620</td>\n",
" <td>0.013296</td>\n",
" <td>0.496775</td>\n",
" <td>0.022269</td>\n",
" <td>0.005302</td>\n",
" <td>0.483351</td>\n",
" <td>0.059885</td>\n",
" <td>2.235102</td>\n",
" <td>0.994479</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Self_I-KNNBaseline38</td>\n",
" <td>0.935685</td>\n",
" <td>0.737828</td>\n",
" <td>0.002651</td>\n",
" <td>0.000837</td>\n",
" <td>0.001197</td>\n",
" <td>0.001702</td>\n",
" <td>0.002361</td>\n",
" <td>0.001020</td>\n",
" <td>0.003635</td>\n",
" <td>0.001443</td>\n",
" <td>0.012589</td>\n",
" <td>0.496765</td>\n",
" <td>0.022269</td>\n",
" <td>0.004242</td>\n",
" <td>0.483245</td>\n",
" <td>0.059163</td>\n",
" <td>2.235851</td>\n",
" <td>0.994507</td>\n",
" </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>0.239661</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>Ready_I-KNNWithMeans</td>\n",
" <td>0.955921</td>\n",
" <td>0.754037</td>\n",
" <td>0.004984</td>\n",
" <td>0.003225</td>\n",
" <td>0.003406</td>\n",
" <td>0.003956</td>\n",
" <td>0.004506</td>\n",
" <td>0.003861</td>\n",
" <td>0.006815</td>\n",
" <td>0.002906</td>\n",
" <td>0.020332</td>\n",
" <td>0.497969</td>\n",
" <td>0.039236</td>\n",
" <td>0.007423</td>\n",
" <td>0.587699</td>\n",
" <td>0.071429</td>\n",
" <td>2.699278</td>\n",
" <td>0.991353</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Ready_I-KNNWithZScore</td>\n",
" <td>0.957701</td>\n",
" <td>0.752387</td>\n",
" <td>0.003712</td>\n",
" <td>0.001994</td>\n",
" <td>0.002380</td>\n",
" <td>0.002919</td>\n",
" <td>0.003433</td>\n",
" <td>0.002401</td>\n",
" <td>0.005137</td>\n",
" <td>0.002158</td>\n",
" <td>0.016458</td>\n",
" <td>0.497349</td>\n",
" <td>0.027572</td>\n",
" <td>0.007423</td>\n",
" <td>0.389926</td>\n",
" <td>0.067821</td>\n",
" <td>2.475747</td>\n",
" <td>0.992793</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Self_BaselineIU</td>\n",
" <td>0.958136</td>\n",
" <td>0.754051</td>\n",
" <td>0.000954</td>\n",
" <td>0.000188</td>\n",
" <td>0.000298</td>\n",
" <td>0.000481</td>\n",
" <td>0.000644</td>\n",
" <td>0.000223</td>\n",
" <td>0.001043</td>\n",
" <td>0.000335</td>\n",
" <td>0.003348</td>\n",
" <td>0.496433</td>\n",
" <td>0.009544</td>\n",
" <td>0.000000</td>\n",
" <td>0.699046</td>\n",
" <td>0.005051</td>\n",
" <td>1.945910</td>\n",
" <td>0.995669</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>0.000000</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>0.000000</td>\n",
" <td>0.392153</td>\n",
" <td>0.115440</td>\n",
" <td>4.174741</td>\n",
" <td>0.965327</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>0.000000</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>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>0.072110</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>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>0.142100</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",
" <td>1.517593</td>\n",
" <td>1.220181</td>\n",
" <td>0.046023</td>\n",
" <td>0.019038</td>\n",
" <td>0.023118</td>\n",
" <td>0.030734</td>\n",
" <td>0.029292</td>\n",
" <td>0.021639</td>\n",
" <td>0.050818</td>\n",
" <td>0.019958</td>\n",
" <td>0.126646</td>\n",
" <td>0.506031</td>\n",
" <td>0.305408</td>\n",
" <td>0.111347</td>\n",
" <td>0.988547</td>\n",
" <td>0.174603</td>\n",
" <td>5.082383</td>\n",
" <td>0.908434</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Self_TopRated</td>\n",
" <td>2.508258</td>\n",
" <td>2.217909</td>\n",
" <td>0.000954</td>\n",
" <td>0.000188</td>\n",
" <td>0.000298</td>\n",
" <td>0.000481</td>\n",
" <td>0.000644</td>\n",
" <td>0.000223</td>\n",
" <td>0.001043</td>\n",
" <td>0.000335</td>\n",
" <td>0.003348</td>\n",
" <td>0.496433</td>\n",
" <td>0.009544</td>\n",
" <td>0.000000</td>\n",
" <td>0.699046</td>\n",
" <td>0.005051</td>\n",
" <td>1.945910</td>\n",
" <td>0.995669</td>\n",
" </tr>\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>0.492047</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_P3</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>0.685048</td>\n",
" <td>1.000000</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": [
" Model RMSE MAE precision recall F_1 \\\n",
"0 Self_SVDBaseline 0.913253 0.719475 0.105090 0.043952 0.053454 \n",
"0 Self_SVD 0.914521 0.717680 0.102757 0.043043 0.052432 \n",
"0 Self_I-KNNBaseline42 0.935028 0.737210 0.002969 0.000980 0.001374 \n",
"0 Self_KNNSurprisetask 0.935028 0.737210 0.002969 0.000980 0.001374 \n",
"0 Self_I-KNNBaseline41 0.935205 0.737439 0.002651 0.000774 0.001138 \n",
"0 Self_I-KNNBaseline43 0.935241 0.737463 0.002863 0.000952 0.001331 \n",
"0 Self_I-KNNBaseline46 0.935244 0.737512 0.003287 0.001096 0.001534 \n",
"0 Self_I-KNNBaseline44 0.935259 0.737530 0.002969 0.000902 0.001305 \n",
"0 Self_I-KNNBaseline45 0.935268 0.737543 0.003075 0.001044 0.001450 \n",
"0 Self_I-KNNBaseline47 0.935295 0.737563 0.003075 0.001044 0.001450 \n",
"0 Self_I-KNNBaseline40 0.935327 0.737424 0.002545 0.000755 0.001105 \n",
"0 Ready_I-KNNBaseline 0.935327 0.737424 0.002545 0.000755 0.001105 \n",
"0 Self_I-KNNBaseline39 0.935520 0.737631 0.002757 0.000856 0.001230 \n",
"0 Self_I-KNNBaseline38 0.935685 0.737828 0.002651 0.000837 0.001197 \n",
"0 Ready_Baseline 0.949459 0.752487 0.091410 0.037652 0.046030 \n",
"0 Ready_I-KNNWithMeans 0.955921 0.754037 0.004984 0.003225 0.003406 \n",
"0 Ready_I-KNNWithZScore 0.957701 0.752387 0.003712 0.001994 0.002380 \n",
"0 Self_BaselineIU 0.958136 0.754051 0.000954 0.000188 0.000298 \n",
"0 Self_BaselineUI 0.967585 0.762740 0.000954 0.000170 0.000278 \n",
"0 Self_IKNN 1.018363 0.808793 0.000318 0.000108 0.000140 \n",
"0 Ready_U-KNN 1.023495 0.807913 0.000742 0.000205 0.000305 \n",
"0 Ready_I-KNN 1.030386 0.813067 0.026087 0.006908 0.010593 \n",
"0 Self_GlobalAvg 1.125760 0.943534 0.061188 0.025968 0.031383 \n",
"0 Ready_Random 1.517593 1.220181 0.046023 0.019038 0.023118 \n",
"0 Self_TopRated 2.508258 2.217909 0.000954 0.000188 0.000298 \n",
"0 Self_TopPop 2.508258 2.217909 0.188865 0.116919 0.118732 \n",
"0 Self_P3 3.702446 3.527273 0.282185 0.192092 0.186749 \n",
"\n",
" F_05 precision_super recall_super NDCG mAP MRR \\\n",
"0 0.070803 0.095279 0.073469 0.118152 0.058739 0.244096 \n",
"0 0.069515 0.094528 0.075122 0.106751 0.051431 0.198701 \n",
"0 0.001929 0.002682 0.001217 0.004069 0.001677 0.013349 \n",
"0 0.001929 0.002682 0.001217 0.004069 0.001677 0.013349 \n",
"0 0.001658 0.002361 0.000959 0.003537 0.001435 0.011494 \n",
"0 0.001862 0.002575 0.001186 0.004014 0.001663 0.013467 \n",
"0 0.002148 0.003004 0.001376 0.004398 0.001856 0.013719 \n",
"0 0.001880 0.002682 0.001129 0.004215 0.001823 0.013977 \n",
"0 0.002016 0.002790 0.001317 0.004287 0.001812 0.014189 \n",
"0 0.002016 0.002790 0.001317 0.004199 0.001735 0.013888 \n",
"0 0.001602 0.002253 0.000930 0.003444 0.001362 0.011760 \n",
"0 0.001602 0.002253 0.000930 0.003444 0.001362 0.011760 \n",
"0 0.001758 0.002468 0.001048 0.003899 0.001620 0.013296 \n",
"0 0.001702 0.002361 0.001020 0.003635 0.001443 0.012589 \n",
"0 0.061286 0.079614 0.056463 0.095957 0.043178 0.198193 \n",
"0 0.003956 0.004506 0.003861 0.006815 0.002906 0.020332 \n",
"0 0.002919 0.003433 0.002401 0.005137 0.002158 0.016458 \n",
"0 0.000481 0.000644 0.000223 0.001043 0.000335 0.003348 \n",
"0 0.000463 0.000644 0.000189 0.000752 0.000168 0.001677 \n",
"0 0.000189 0.000000 0.000000 0.000214 0.000037 0.000368 \n",
"0 0.000449 0.000536 0.000198 0.000845 0.000274 0.002744 \n",
"0 0.016046 0.021137 0.009522 0.024214 0.008958 0.048068 \n",
"0 0.041343 0.040558 0.032107 0.067695 0.027470 0.171187 \n",
"0 0.030734 0.029292 0.021639 0.050818 0.019958 0.126646 \n",
"0 0.000481 0.000644 0.000223 0.001043 0.000335 0.003348 \n",
"0 0.141584 0.130472 0.137473 0.214651 0.111707 0.400939 \n",
"0 0.216980 0.204185 0.240096 0.339114 0.204905 0.572157 \n",
"\n",
" LAUC HR HR2 Reco in test Test coverage Shannon \\\n",
"0 0.518714 0.471898 0.279958 0.999682 0.111111 3.572421 \n",
"0 0.518248 0.462354 0.255567 0.854931 0.147186 3.888926 \n",
"0 0.496838 0.023330 0.006363 0.481972 0.059163 2.227849 \n",
"0 0.496838 0.023330 0.006363 0.481972 0.059163 2.227849 \n",
"0 0.496734 0.021209 0.005302 0.482503 0.057720 2.228123 \n",
"0 0.496824 0.023330 0.005302 0.482609 0.055556 2.225996 \n",
"0 0.496898 0.024390 0.007423 0.482397 0.057720 2.225807 \n",
"0 0.496799 0.023330 0.005302 0.482397 0.057720 2.225495 \n",
"0 0.496871 0.024390 0.005302 0.482609 0.058442 2.225340 \n",
"0 0.496871 0.024390 0.005302 0.482397 0.055556 2.221942 \n",
"0 0.496724 0.021209 0.004242 0.482821 0.059885 2.232578 \n",
"0 0.496724 0.021209 0.004242 0.482821 0.059885 2.232578 \n",
"0 0.496775 0.022269 0.005302 0.483351 0.059885 2.235102 \n",
"0 0.496765 0.022269 0.004242 0.483245 0.059163 2.235851 \n",
"0 0.515501 0.437964 0.239661 1.000000 0.033911 2.836513 \n",
"0 0.497969 0.039236 0.007423 0.587699 0.071429 2.699278 \n",
"0 0.497349 0.027572 0.007423 0.389926 0.067821 2.475747 \n",
"0 0.496433 0.009544 0.000000 0.699046 0.005051 1.945910 \n",
"0 0.496424 0.009544 0.000000 0.600530 0.005051 1.803126 \n",
"0 0.496391 0.003181 0.000000 0.392153 0.115440 4.174741 \n",
"0 0.496441 0.007423 0.000000 0.602121 0.010823 2.089186 \n",
"0 0.499885 0.154825 0.072110 0.402333 0.434343 5.133650 \n",
"0 0.509546 0.384942 0.142100 1.000000 0.025974 2.711772 \n",
"0 0.506031 0.305408 0.111347 0.988547 0.174603 5.082383 \n",
"0 0.496433 0.009544 0.000000 0.699046 0.005051 1.945910 \n",
"0 0.555546 0.765642 0.492047 1.000000 0.038961 3.159079 \n",
"0 0.593544 0.875928 0.685048 1.000000 0.077201 3.875892 \n",
"\n",
" Gini \n",
"0 0.980655 \n",
"0 0.972044 \n",
"0 0.994531 \n",
"0 0.994531 \n",
"0 0.994555 \n",
"0 0.994623 \n",
"0 0.994607 \n",
"0 0.994598 \n",
"0 0.994599 \n",
"0 0.994676 \n",
"0 0.994487 \n",
"0 0.994487 \n",
"0 0.994479 \n",
"0 0.994507 \n",
"0 0.991139 \n",
"0 0.991353 \n",
"0 0.992793 \n",
"0 0.995669 \n",
"0 0.996380 \n",
"0 0.965327 \n",
"0 0.995706 \n",
"0 0.877999 \n",
"0 0.992003 \n",
"0 0.908434 \n",
"0 0.995669 \n",
"0 0.987317 \n",
"0 0.974947 "
]
},
"execution_count": 36,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"result.sort_values(by='RMSE')"
]
},
{
"cell_type": "code",
"execution_count": 34,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Estimating biases using als...\n",
"Computing the msd similarity matrix...\n",
"Done computing similarity matrix.\n",
"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",
"sim_options = {'name': 'cosine',\n",
" 'user_based': False}\n",
"algo = sp.KNNBaseline(k=42)\n",
"\n",
"helpers.ready_made(algo, reco_path='Recommendations generated/ml-100k/Self_KNNSurprisetask_reco.csv',\n",
" estimations_path='Recommendations generated/ml-100k/Self_KNNSurprisetask_estimations.csv')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.5"
}
},
"nbformat": 4,
"nbformat_minor": 4
}
Reference in New Issue Copy Permalink