s460932/workshops_recommender_systems
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity
afa9655186
workshops_recommender_systems/P3. k-nearest neighbours.ipynb

1227 lines
42 KiB
Plaintext
Raw Normal View History

Solutions
2020-06-15 00:15:17 +02:00
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Self made simplified I-KNN"
]
},
{
"cell_type": "code",
"execution_count": 5,
"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": 6,
"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": 7,
"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": 7,
"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": 8,
"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": 9,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"943it [00:00, 7867.08it/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": 9,
"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": 10,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"943it [00:00, 8630.78it/s]\n",
"943it [00:00, 9234.18it/s]\n",
"943it [00:00, 9860.04it/s]\n",
"943it [00:00, 9890.74it/s]\n",
"943it [00:00, 9782.25it/s]\n",
"943it [00:00, 8807.11it/s]\n",
"943it [00:00, 8925.24it/s]\n",
"943it [00:00, 8808.87it/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>1.522798</td>\n",
" <td>1.222501</td>\n",
" <td>0.049841</td>\n",
" <td>0.020656</td>\n",
" <td>0.025232</td>\n",
" <td>0.033446</td>\n",
" <td>0.030579</td>\n",
" <td>0.022927</td>\n",
" <td>0.051680</td>\n",
" <td>0.019110</td>\n",
" <td>0.123085</td>\n",
" <td>0.506849</td>\n",
" <td>0.331919</td>\n",
" <td>0.119830</td>\n",
" <td>0.985048</td>\n",
" <td>0.183983</td>\n",
" <td>5.097973</td>\n",
" <td>0.907483</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 1.522798 1.222501 0.049841 0.020656 0.025232 \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 0.033446 0.030579 0.022927 0.051680 0.019110 0.123085 \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 0.506849 0.331919 0.119830 0.985048 0.183983 5.097973 \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 0.907483 \n",
"0 0.995669 \n",
"0 0.995669 \n",
"0 0.996380 \n",
"0 0.965327 "
]
},
"execution_count": 10,
"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": 11,
"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": 12,
"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": 13,
"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} # 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": 14,
"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": 15,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Estimating biases using als...\n",
"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",
"\n",
"imp.reload(helpers)\n",
"\n",
"sim_options = {'name': 'cosine',\n",
" 'user_based': False}\n",
"\n",
"algo = sp.KNNBaseline(sim_options = sim_options)\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": 16,
"metadata": {
"scrolled": true
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"943it [00:00, 9238.34it/s]\n",
"943it [00:00, 9588.43it/s]\n",
"943it [00:00, 9569.67it/s]\n",
"943it [00:00, 9293.69it/s]\n",
"943it [00:00, 9863.41it/s]\n",
"943it [00:00, 8672.47it/s]\n",
"943it [00:00, 9321.91it/s]\n",
"943it [00:00, 9440.66it/s]\n",
"943it [00:00, 9619.66it/s]\n",
"943it [00:00, 9841.64it/s]\n",
"943it [00:00, 9634.00it/s]\n",
"943it [00:00, 8838.72it/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_KNNSurprisetask</td>\n",
" <td>0.946255</td>\n",
" <td>0.745209</td>\n",
" <td>0.083457</td>\n",
" <td>0.032848</td>\n",
" <td>0.041227</td>\n",
" <td>0.055493</td>\n",
" <td>0.074785</td>\n",
" <td>0.048890</td>\n",
" <td>0.089577</td>\n",
" <td>0.040902</td>\n",
" <td>0.189057</td>\n",
" <td>0.513076</td>\n",
" <td>0.417815</td>\n",
" <td>0.217391</td>\n",
" <td>0.888547</td>\n",
" <td>0.130592</td>\n",
" <td>3.611806</td>\n",
" <td>0.978659</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>1.522798</td>\n",
" <td>1.222501</td>\n",
" <td>0.049841</td>\n",
" <td>0.020656</td>\n",
" <td>0.025232</td>\n",
" <td>0.033446</td>\n",
" <td>0.030579</td>\n",
" <td>0.022927</td>\n",
" <td>0.051680</td>\n",
" <td>0.019110</td>\n",
" <td>0.123085</td>\n",
" <td>0.506849</td>\n",
" <td>0.331919</td>\n",
" <td>0.119830</td>\n",
" <td>0.985048</td>\n",
" <td>0.183983</td>\n",
" <td>5.097973</td>\n",
" <td>0.907483</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>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>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>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_KNNSurprisetask 0.946255 0.745209 0.083457 0.032848 0.041227 \n",
"0 Self_GlobalAvg 1.125760 0.943534 0.061188 0.025968 0.031383 \n",
"0 Ready_Random 1.522798 1.222501 0.049841 0.020656 0.025232 \n",
"0 Ready_I-KNN 1.030386 0.813067 0.026087 0.006908 0.010593 \n",
"0 Ready_I-KNNBaseline 0.935327 0.737424 0.002545 0.000755 0.001105 \n",
"0 Ready_U-KNN 1.023495 0.807913 0.000742 0.000205 0.000305 \n",
"0 Self_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 0.055493 0.074785 0.048890 0.089577 0.040902 0.189057 \n",
"0 0.041343 0.040558 0.032107 0.067695 0.027470 0.171187 \n",
"0 0.033446 0.030579 0.022927 0.051680 0.019110 0.123085 \n",
"0 0.016046 0.021137 0.009522 0.024214 0.008958 0.048068 \n",
"0 0.001602 0.002253 0.000930 0.003444 0.001362 0.011760 \n",
"0 0.000449 0.000536 0.000198 0.000845 0.000274 0.002744 \n",
"0 0.000481 0.000644 0.000223 0.001043 0.000335 0.003348 \n",
"0 0.000481 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 0.513076 0.417815 0.217391 0.888547 0.130592 3.611806 \n",
"0 0.509546 0.384942 0.142100 1.000000 0.025974 2.711772 \n",
"0 0.506849 0.331919 0.119830 0.985048 0.183983 5.097973 \n",
"0 0.499885 0.154825 0.072110 0.402333 0.434343 5.133650 \n",
"0 0.496724 0.021209 0.004242 0.482821 0.059885 2.232578 \n",
"0 0.496441 0.007423 0.000000 0.602121 0.010823 2.089186 \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 0.978659 \n",
"0 0.992003 \n",
"0 0.907483 \n",
"0 0.877999 \n",
"0 0.994487 \n",
"0 0.995706 \n",
"0 0.995669 \n",
"0 0.995669 \n",
"0 0.996380 \n",
"0 0.965327 "
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import imp\n",
"imp.reload(ev)\n",
"\n",
"import evaluation_measures as ev\n",
"dir_path = \"Recommendations generated/ml-100k/\"\n",
"super_reactions = [4, 5]\n",
"test = pd.read_csv('./Datasets/ml-100k/test.csv', sep = '\\t', header = None)\n",
"\n",
"ev.evaluate_all(test, dir_path, super_reactions)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.6.9"
}
},
"nbformat": 4,
"nbformat_minor": 4
}
Reference in New Issue Copy Permalink