Prześlij pliki do ''
This commit is contained in:
parent
f93096afff
commit
769d9aa62f
757
P3. k-nearest neighbours.ipynb
Normal file
757
P3. k-nearest neighbours.ipynb
Normal file
@ -0,0 +1,757 @@
|
||||
{
|
||||
"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, 6719.05it/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>H2R</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 H2R 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, 7023.03it/s]\n",
|
||||
"943it [00:00, 6323.02it/s]\n",
|
||||
"943it [00:00, 6003.69it/s]\n",
|
||||
"943it [00:00, 6582.48it/s]\n",
|
||||
"943it [00:00, 5623.69it/s]\n",
|
||||
"943it [00:00, 6775.77it/s]\n",
|
||||
"943it [00:00, 6119.28it/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>H2R</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>1.524954</td>\n",
|
||||
" <td>1.223352</td>\n",
|
||||
" <td>0.045599</td>\n",
|
||||
" <td>0.021181</td>\n",
|
||||
" <td>0.024585</td>\n",
|
||||
" <td>0.031518</td>\n",
|
||||
" <td>0.027897</td>\n",
|
||||
" <td>0.021931</td>\n",
|
||||
" <td>0.048111</td>\n",
|
||||
" <td>0.017381</td>\n",
|
||||
" <td>0.119005</td>\n",
|
||||
" <td>0.507096</td>\n",
|
||||
" <td>0.330859</td>\n",
|
||||
" <td>0.091198</td>\n",
|
||||
" <td>0.988123</td>\n",
|
||||
" <td>0.181818</td>\n",
|
||||
" <td>5.100792</td>\n",
|
||||
" <td>0.906866</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>0</th>\n",
|
||||
" <td>Self_TopRated</td>\n",
|
||||
" <td>NaN</td>\n",
|
||||
" <td>NaN</td>\n",
|
||||
" <td>0.032025</td>\n",
|
||||
" <td>0.012674</td>\n",
|
||||
" <td>0.015714</td>\n",
|
||||
" <td>0.021183</td>\n",
|
||||
" <td>0.028433</td>\n",
|
||||
" <td>0.018573</td>\n",
|
||||
" <td>0.022741</td>\n",
|
||||
" <td>0.005328</td>\n",
|
||||
" <td>0.031602</td>\n",
|
||||
" <td>0.502764</td>\n",
|
||||
" <td>0.237540</td>\n",
|
||||
" <td>0.065748</td>\n",
|
||||
" <td>0.697031</td>\n",
|
||||
" <td>0.014430</td>\n",
|
||||
" <td>2.220811</td>\n",
|
||||
" <td>0.995173</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 1.524954 1.223352 0.045599 0.021181 0.024585 \n",
|
||||
"0 Self_TopRated NaN NaN 0.032025 0.012674 0.015714 \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 0.031518 0.027897 0.021931 0.048111 0.017381 0.119005 \n",
|
||||
"0 0.021183 0.028433 0.018573 0.022741 0.005328 0.031602 \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 H2R 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 0.507096 0.330859 0.091198 0.988123 0.181818 5.100792 \n",
|
||||
"0 0.502764 0.237540 0.065748 0.697031 0.014430 2.220811 \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 0.906866 \n",
|
||||
"0 0.995173 \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": 8,
|
||||
"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.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": 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': 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": null,
|
||||
"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": 9,
|
||||
"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": [
|
||||
"#I chose KNN With Means because I thought it would be interesting if the algorithm take into account\n",
|
||||
"#the mean ratings of each user\n",
|
||||
"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.KNNWithZScore(k=10,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": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
},
|
||||
{
|
||||
"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": "3.6.5"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 4
|
||||
}
|
||||
80
P4. Appendix - embeddings in high demensional spaces.ipynb
Normal file
80
P4. Appendix - embeddings in high demensional spaces.ipynb
Normal file
@ -0,0 +1,80 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"['dimensions: 1, cases when observation is the nearest: 0.0%',\n",
|
||||
" 'dimensions: 2, cases when observation is the nearest: 0.0%',\n",
|
||||
" 'dimensions: 3, cases when observation is the nearest: 0.0%',\n",
|
||||
" 'dimensions: 10, cases when observation is the nearest: 7.000000000000001%',\n",
|
||||
" 'dimensions: 20, cases when observation is the nearest: 57.99999999999999%',\n",
|
||||
" 'dimensions: 30, cases when observation is the nearest: 92.0%',\n",
|
||||
" 'dimensions: 40, cases when observation is the nearest: 99.0%',\n",
|
||||
" 'dimensions: 50, cases when observation is the nearest: 100.0%',\n",
|
||||
" 'dimensions: 60, cases when observation is the nearest: 100.0%',\n",
|
||||
" 'dimensions: 70, cases when observation is the nearest: 100.0%',\n",
|
||||
" 'dimensions: 80, cases when observation is the nearest: 100.0%',\n",
|
||||
" 'dimensions: 90, cases when observation is the nearest: 100.0%']"
|
||||
]
|
||||
},
|
||||
"execution_count": 1,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"import numpy as np\n",
|
||||
"import pandas as pd\n",
|
||||
"import random\n",
|
||||
"from numpy.linalg import norm\n",
|
||||
"\n",
|
||||
"dimensions=[1,2,3]+[10*i for i in range(1,10)]\n",
|
||||
"nb_vectors=10000\n",
|
||||
"trials=100\n",
|
||||
"k=1 # by setting k=1 we want to check how often the closest vector to the avarage of 2 random vectors is one of these 2 vectors\n",
|
||||
"\n",
|
||||
"result=[]\n",
|
||||
"for dimension in dimensions:\n",
|
||||
" vectors=np.random.normal(0,1,size=(nb_vectors, dimension))\n",
|
||||
" successes=0\n",
|
||||
" for i in range(trials):\n",
|
||||
" i1,i2=random.sample(range(nb_vectors),2)\n",
|
||||
" target=(vectors[i1]+vectors[i2])/2\n",
|
||||
"\n",
|
||||
" distances=pd.DataFrame(enumerate(np.dot(target, vectors.transpose())/norm(target)/norm(vectors.transpose(), axis=0)))\n",
|
||||
" distances=distances.sort_values(by=[1], ascending=False)\n",
|
||||
" if (i1 in (list(distances[0][:k]))) | (i2 in (list(distances[0][:k]))):\n",
|
||||
" successes+=1\n",
|
||||
" result.append(successes/trials)\n",
|
||||
" \n",
|
||||
"[f'dimensions: {i}, cases when observation is the nearest: {100*round(j,3)}%' for i,j in zip(dimensions, result)]"
|
||||
]
|
||||
}
|
||||
],
|
||||
"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": 2
|
||||
}
|
||||
1490
P4. Matrix Factorization.ipynb
Normal file
1490
P4. Matrix Factorization.ipynb
Normal file
File diff suppressed because one or more lines are too long
Loading…
Reference in New Issue
Block a user