robkw/introduction_to_recommender_systems
1
0
Fork 1
Code Issues Pull Requests Releases Wiki Activity

Compare commits

merge into: robkw:master
Branches Tags
robkw:master
robkw:last_meeting
s416082:master
s416082:last_meeting
...
pull from: s416082:master
Branches Tags
s416082:master
s416082:last_meeting
robkw:master
robkw:last_meeting

6 Commits
master ... master

Author SHA1 Message Date
unknown
bdf06c9c28 Zadanie 6 2021-06-12 11:14:56 +02:00
unknown
587f3d3661 Zadanie 3 2021-06-12 10:56:22 +02:00
unknown
60194de853 Zadanie 5 2021-06-10 22:10:42 +02:00
unknown
5bd0649ffa Add another files Project 2 2021-06-09 22:16:22 +02:00
unknown
fa6ba669c8 Project 2 2021-06-09 22:12:22 +02:00
unknown
4499231c79 Zadanie-1 2021-06-07 19:19:39 +02:00
10 changed files with 6929 additions and 567 deletions
Show Stats Expand all files Collapse all files

698
.ipynb_checkpoints/P0. Data preparation-checkpoint.ipynb Normal file
View File

File diff suppressed because one or more lines are too long

1527
.ipynb_checkpoints/P1. Baseline-checkpoint.ipynb Normal file
View File

File diff suppressed because it is too large Load Diff

1678
.ipynb_checkpoints/P2. Evaluation-checkpoint.ipynb Normal file
View File

File diff suppressed because it is too large Load Diff

1057
.ipynb_checkpoints/P3. k-nearest neighbours-checkpoint.ipynb Normal file
View File

File diff suppressed because it is too large Load Diff

20
P0. Data preparation.ipynb
View File

File diff suppressed because one or more lines are too long

296
P1. Baseline.ipynb
View File

@ -195,7 +195,7 @@
{
"data": {
"text/plain": [
"<3x4 sparse matrix of type '<class 'numpy.int64'>'\n",
"<3x4 sparse matrix of type '<class 'numpy.intc'>'\n",
"\twith 8 stored elements in Compressed Sparse Row format>"
]
},
@ -229,7 +229,7 @@
"text/plain": [
"matrix([[4, 1, 3, 0],\n",
" [0, 2, 0, 1],\n",
" [2, 0, 5, 4]])"
" [2, 0, 5, 4]], dtype=int32)"
]
},
"metadata": {},
@ -306,7 +306,7 @@
"name": "stdout",
"output_type": "stream",
"text": [
"1.13 µs ± 79.9 ns per loop (mean ± std. dev. of 7 runs, 1000000 loops each)\n",
"471 ns ± 15.3 ns per loop (mean ± std. dev. of 7 runs, 1000000 loops each)\n",
"Inefficient way to access items rated by user:\n"
]
},
@ -314,7 +314,7 @@
"data": {
"text/plain": [
"array([ 0, 6, 10, 27, 49, 78, 95, 97, 116, 143, 153, 156, 167,\n",
" 171, 172, 173, 194, 208, 225, 473, 495, 549, 615], dtype=int32)"
" 171, 172, 173, 194, 208, 225, 473, 495, 549, 615])"
]
},
"metadata": {},
@ -324,7 +324,7 @@
"name": "stdout",
"output_type": "stream",
"text": [
"149 µs ± 11.5 µs per loop (mean ± std. dev. of 7 runs, 10000 loops each)\n"
"48.3 µs ± 1.51 µs per loop (mean ± std. dev. of 7 runs, 10000 loops each)\n"
]
}
],
@ -364,7 +364,7 @@
"text/plain": [
"matrix([[4, 1, 3, 0],\n",
" [0, 2, 0, 1],\n",
" [2, 0, 5, 4]])"
" [2, 0, 5, 4]], dtype=int32)"
]
},
"metadata": {},
@ -877,7 +877,7 @@
"text/plain": [
"matrix([[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]])"
" [0, 0, 0, 5, 0, 3, 4, 0]], dtype=int64)"
]
},
"metadata": {},
@ -1070,6 +1070,269 @@
"- For each row of matrix M' representing the user u, we compute the mean of ratings and denote by b_u."
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {},
"outputs": [],
"source": [
"class selfBaselineIU():\n",
" \n",
" def fit(self, train_ui):\n",
" self.train_ui=train_ui.copy()\n",
" self.train_iu=train_ui.transpose().tocsr()\n",
" \n",
" result=self.train_ui.copy()\n",
" \n",
" #we can't do result=train_ui-to_subtract_rows since then 0 entries will \"disappear\" in csr format\n",
" self.col_means=np.divide(np.asarray(result.sum(axis=0).ravel())[0], np.diff(self.train_iu.indptr),\\\n",
" out=np.zeros(self.train_iu.shape[0]), where=np.diff(self.train_iu.indptr)!=0) # handling items without ratings\n",
" \n",
" # again - it is possible that some mean will be zero, so let's use the same workaround\n",
" col_means=self.col_means.copy()\n",
" \n",
" max_col_mean=np.max(col_means)\n",
" col_means[col_means==0]=max_col_mean+1\n",
" to_subtract_cols=result.power(0)*sparse.diags(col_means)\n",
" to_subtract_cols.sort_indices() # needed to have valid .data\n",
" \n",
" subtract=to_subtract_cols.data\n",
" subtract[subtract==max_col_mean+1]=0\n",
" \n",
" result.data=result.data-subtract\n",
"\n",
"\n",
" self.row_means=np.asarray(result.sum(axis=1).ravel())[0]/np.diff(result.indptr)\n",
" \n",
" # in csr format after addition or multiplication 0 entries \"disappear\" - so some workaraunds are needed \n",
" # (other option is to define addition/multiplication in a desired way)\n",
" row_means=self.row_means.copy()\n",
" \n",
" max_row_mean=np.max(row_means)\n",
" row_means[row_means==0]=max_row_mean+1\n",
" to_subtract_rows=sparse.diags(row_means)*(result.power(0))\n",
" to_subtract_rows.sort_indices() # needed to have valid .data\n",
" \n",
" subtract=to_subtract_rows.data\n",
" subtract[subtract==max_row_mean+1]=0\n",
" \n",
" result.data=result.data-subtract\n",
"\n",
" return result\n",
" \n",
" \n",
" def recommend(self, user_code_id, item_code_id, topK=10):\n",
" estimations=np.tile(self.row_means[:,None], [1, self.train_ui.shape[1]]) +np.tile(self.col_means, [self.train_ui.shape[0], 1])\n",
" \n",
" top_k = defaultdict(list)\n",
" for nb_user, user in enumerate(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:\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], self.row_means[user]+self.col_means[item]])\n",
" return result"
]
},
{
"cell_type": "code",
"execution_count": 26,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Training data:\n"
]
},
{
"data": {
"text/plain": [
"matrix([[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": [
"After subtracting columns and rows:\n"
]
},
{
"data": {
"text/plain": [
"matrix([[-0.375 , 1.125 , 0. , 0. , -0.375 ,\n",
" 0. , 0. , -0.375 ],\n",
" [ 0. , -0.66666667, 0.83333333, -0.16666667, 0. ,\n",
" 0. , 0. , 0. ],\n",
" [ 0. , 0. , 0. , 0.66666667, 0. ,\n",
" -0.33333333, -0.33333333, 0. ]])"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Recommend best unseen item:\n"
]
},
{
"data": {
"text/plain": [
"[[0, 30, 4.375], [10, 40, 4.166666666666667], [20, 40, 5.333333333333333]]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Print estimations on unseen items:\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>user</th>\n",
" <th>item</th>\n",
" <th>est_score</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0</td>\n",
" <td>60</td>\n",
" <td>4.375000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>10</td>\n",
" <td>40</td>\n",
" <td>4.166667</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>20</td>\n",
" <td>0</td>\n",
" <td>3.333333</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>20</td>\n",
" <td>20</td>\n",
" <td>2.333333</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>20</td>\n",
" <td>70</td>\n",
" <td>4.333333</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" user item est_score\n",
"0 0 60 4.375000\n",
"1 10 40 4.166667\n",
"2 20 0 3.333333\n",
"3 20 20 2.333333\n",
"4 20 70 4.333333"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"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_iu, toy_test_iu, 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",
"print('Training data:')\n",
"display(toy_train_iu.todense())\n",
"\n",
"model=selfBaselineIU()\n",
"print('After subtracting columns and rows:')\n",
"display(model.fit(toy_train_iu).todense())\n",
"\n",
"print('Recommend best unseen item:')\n",
"display(model.recommend(toy_user_code_id, toy_item_code_id, topK=1))\n",
"\n",
"print('Print estimations on unseen items:')\n",
"estimations=pd.DataFrame(model.estimate(toy_user_code_id, toy_item_code_id, toy_test_iu))\n",
"estimations.columns=['user', 'item', 'est_score']\n",
"display(estimations)\n",
"\n",
"top_n=pd.DataFrame(model.recommend(toy_user_code_id, toy_item_code_id, topK=3))\n",
"\n",
"top_n.to_csv('Recommendations generated/toy-example/Self_BaselineIU_reco.csv', index=False, header=False)\n",
"\n",
"estimations=pd.DataFrame(model.estimate(toy_user_code_id, toy_item_code_id, toy_test_iu))\n",
"estimations.to_csv('Recommendations generated/toy-example/Self_BaselineIU_estimations.csv', index=False, header=False)"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {},
"outputs": [],
"source": [
"model=selfBaselineIU()\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/Projects/Project1_Self_BaselineIU_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/Projects/Project1_Self_BaselineIU_estimations.csv', index=False, header=False)"
]
},
{
"cell_type": "markdown",
"metadata": {},
@ -1079,7 +1342,7 @@
},
{
"cell_type": "code",
"execution_count": 22,
"execution_count": 23,
"metadata": {},
"outputs": [
{
@ -1136,7 +1399,7 @@
},
{
"cell_type": "code",
"execution_count": 23,
"execution_count": 29,
"metadata": {},
"outputs": [
{
@ -1153,7 +1416,7 @@
"0.7524871012820799"
]
},
"execution_count": 23,
"execution_count": 29,
"metadata": {},
"output_type": "execute_result"
}
@ -1190,14 +1453,14 @@
"name": "stdout",
"output_type": "stream",
"text": [
"RMSE: 1.5239\n",
"MAE: 1.2268\n"
"RMSE: 1.5165\n",
"MAE: 1.2172\n"
]
},
{
"data": {
"text/plain": [
"1.2267993503843746"
"1.2172144988785374"
]
},
"execution_count": 24,
@ -1251,7 +1514,12 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.8.5"
"version": "3.8.8"
},
"metadata": {
"interpreter": {
"hash": "2a3a95f8b675c5b7dd6a35e1675edaf697539b1f0a71c4603e9520a8bbd07d82"
}
}
},
"nbformat": 4,

504
P2. Evaluation.ipynb
View File

@ -397,7 +397,7 @@
},
{
"cell_type": "code",
"execution_count": 8,
"execution_count": 7,
"metadata": {},
"outputs": [],
"source": [
@ -453,7 +453,7 @@
},
{
"cell_type": "code",
"execution_count": 9,
"execution_count": 8,
"metadata": {},
"outputs": [
{
@ -500,7 +500,7 @@
"0 1.0 0.033911 2.836513 0.991139"
]
},
"execution_count": 9,
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
@ -521,14 +521,14 @@
},
{
"cell_type": "code",
"execution_count": 10,
"execution_count": 9,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"943it [00:00, 11012.47it/s]\n"
"943it [00:00, 12952.59it/s]\n"
]
},
{
@ -565,6 +565,8 @@
" <th>MRR</th>\n",
" <th>LAUC</th>\n",
" <th>HR</th>\n",
" <th>HitRate2</th>\n",
" <th>HitRate3</th>\n",
" <th>Reco in test</th>\n",
" <th>Test coverage</th>\n",
" <th>Shannon</th>\n",
@ -587,6 +589,8 @@
" <td>0.198193</td>\n",
" <td>0.515501</td>\n",
" <td>0.437964</td>\n",
" <td>0.239661</td>\n",
" <td>0.126193</td>\n",
" <td>1.0</td>\n",
" <td>0.033911</td>\n",
" <td>2.836513</td>\n",
@ -603,11 +607,14 @@
" precision_super recall_super NDCG mAP MRR LAUC \\\n",
"0 0.079614 0.056463 0.095957 0.043178 0.198193 0.515501 \n",
"\n",
" HR Reco in test Test coverage Shannon Gini \n",
"0 0.437964 1.0 0.033911 2.836513 0.991139 "
" HR HitRate2 HitRate3 Reco in test Test coverage Shannon \\\n",
"0 0.437964 0.239661 0.126193 1.0 0.033911 2.836513 \n",
"\n",
" Gini \n",
"0 0.991139 "
]
},
"execution_count": 10,
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
@ -633,18 +640,19 @@
},
{
"cell_type": "code",
"execution_count": 11,
"execution_count": 10,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"943it [00:00, 10346.82it/s]\n",
"943it [00:00, 11772.32it/s]\n",
"943it [00:00, 10636.62it/s]\n",
"943it [00:00, 10767.92it/s]\n",
"943it [00:00, 12019.93it/s]\n"
"943it [00:00, 13130.52it/s]\n",
"943it [00:00, 12777.31it/s]\n",
"943it [00:00, 13513.65it/s]\n",
"943it [00:00, 13323.06it/s]\n",
"943it [00:00, 13507.69it/s]\n",
"943it [00:00, 13697.48it/s]\n"
]
}
],
@ -659,7 +667,7 @@
},
{
"cell_type": "code",
"execution_count": 12,
"execution_count": 11,
"metadata": {},
"outputs": [
{
@ -722,14 +730,14 @@
" <tr>\n",
" <th>0</th>\n",
" <td>Ready_Random</td>\n",
" <td>1.521845</td>\n",
" <td>1.225949</td>\n",
" <td>0.047190</td>\n",
" <td>0.020753</td>\n",
" <td>0.024810</td>\n",
" <td>0.032269</td>\n",
" <td>0.029506</td>\n",
" <td>0.023707</td>\n",
" <td>1.516512</td>\n",
" <td>1.217214</td>\n",
" <td>0.045599</td>\n",
" <td>0.021001</td>\n",
" <td>0.024136</td>\n",
" <td>0.031226</td>\n",
" <td>0.028541</td>\n",
" <td>0.022057</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
@ -755,6 +763,18 @@
" <td>0.000644</td>\n",
" <td>0.000189</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",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
@ -763,19 +783,21 @@
" 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 Ready_Random 1.521845 1.225949 0.047190 0.020753 0.024810 \n",
"0 Ready_Random 1.516512 1.217214 0.045599 0.021001 0.024136 \n",
"0 Self_TopRated 1.030712 0.820904 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 \n",
"0 0.141584 0.130472 0.137473 \n",
"0 0.061286 0.079614 0.056463 \n",
"0 0.032269 0.029506 0.023707 \n",
"0 0.031226 0.028541 0.022057 \n",
"0 0.000481 0.000644 0.000223 \n",
"0 0.000463 0.000644 0.000189 "
"0 0.000463 0.000644 0.000189 \n",
"0 0.000189 0.000000 0.000000 "
]
},
"execution_count": 12,
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
@ -786,7 +808,7 @@
},
{
"cell_type": "code",
"execution_count": 13,
"execution_count": 12,
"metadata": {},
"outputs": [
{
@ -816,6 +838,8 @@
" <th>MRR</th>\n",
" <th>LAUC</th>\n",
" <th>HR</th>\n",
" <th>HitRate2</th>\n",
" <th>HitRate3</th>\n",
" <th>Reco in test</th>\n",
" <th>Test coverage</th>\n",
" <th>Shannon</th>\n",
@ -831,6 +855,8 @@
" <td>0.400939</td>\n",
" <td>0.555546</td>\n",
" <td>0.765642</td>\n",
" <td>0.492047</td>\n",
" <td>0.290562</td>\n",
" <td>1.000000</td>\n",
" <td>0.038961</td>\n",
" <td>3.159079</td>\n",
@ -844,6 +870,8 @@
" <td>0.198193</td>\n",
" <td>0.515501</td>\n",
" <td>0.437964</td>\n",
" <td>0.239661</td>\n",
" <td>0.126193</td>\n",
" <td>1.000000</td>\n",
" <td>0.033911</td>\n",
" <td>2.836513</td>\n",
@ -852,15 +880,17 @@
" <tr>\n",
" <th>0</th>\n",
" <td>Ready_Random</td>\n",
" <td>0.050075</td>\n",
" <td>0.018728</td>\n",
" <td>0.121957</td>\n",
" <td>0.506893</td>\n",
" <td>0.329799</td>\n",
" <td>0.986532</td>\n",
" <td>0.184704</td>\n",
" <td>5.099706</td>\n",
" <td>0.907217</td>\n",
" <td>0.050154</td>\n",
" <td>0.019000</td>\n",
" <td>0.125089</td>\n",
" <td>0.507013</td>\n",
" <td>0.327678</td>\n",
" <td>0.093319</td>\n",
" <td>0.026511</td>\n",
" <td>0.988017</td>\n",
" <td>0.192641</td>\n",
" <td>5.141246</td>\n",
" <td>0.903763</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
@ -870,6 +900,8 @@
" <td>0.003348</td>\n",
" <td>0.496433</td>\n",
" <td>0.009544</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.699046</td>\n",
" <td>0.005051</td>\n",
" <td>1.945910</td>\n",
@ -883,11 +915,28 @@
" <td>0.001677</td>\n",
" <td>0.496424</td>\n",
" <td>0.009544</td>\n",
" <td>0.000000</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>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>0.000000</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>"
@ -896,19 +945,21 @@
" Model NDCG mAP MRR LAUC HR \\\n",
"0 Self_TopPop 0.214651 0.111707 0.400939 0.555546 0.765642 \n",
"0 Ready_Baseline 0.095957 0.043178 0.198193 0.515501 0.437964 \n",
"0 Ready_Random 0.050075 0.018728 0.121957 0.506893 0.329799 \n",
"0 Ready_Random 0.050154 0.019000 0.125089 0.507013 0.327678 \n",
"0 Self_TopRated 0.001043 0.000335 0.003348 0.496433 0.009544 \n",
"0 Self_BaselineUI 0.000752 0.000168 0.001677 0.496424 0.009544 \n",
"0 Self_IKNN 0.000214 0.000037 0.000368 0.496391 0.003181 \n",
"\n",
" Reco in test Test coverage Shannon Gini \n",
"0 1.000000 0.038961 3.159079 0.987317 \n",
"0 1.000000 0.033911 2.836513 0.991139 \n",
"0 0.986532 0.184704 5.099706 0.907217 \n",
"0 0.699046 0.005051 1.945910 0.995669 \n",
"0 0.600530 0.005051 1.803126 0.996380 "
" HitRate2 HitRate3 Reco in test Test coverage Shannon Gini \n",
"0 0.492047 0.290562 1.000000 0.038961 3.159079 0.987317 \n",
"0 0.239661 0.126193 1.000000 0.033911 2.836513 0.991139 \n",
"0 0.093319 0.026511 0.988017 0.192641 5.141246 0.903763 \n",
"0 0.000000 0.000000 0.699046 0.005051 1.945910 0.995669 \n",
"0 0.000000 0.000000 0.600530 0.005051 1.803126 0.996380 \n",
"0 0.000000 0.000000 0.392153 0.115440 4.174741 0.965327 "
]
},
"execution_count": 13,
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
@ -926,14 +977,15 @@
},
{
"cell_type": "code",
"execution_count": 14,
"execution_count": 13,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"3it [00:00, 5771.98it/s]\n"
"3it [00:00, ?it/s]\n",
"3it [00:00, ?it/s]\n"
]
},
{
@ -971,6 +1023,8 @@
" <th>MRR</th>\n",
" <th>LAUC</th>\n",
" <th>HR</th>\n",
" <th>HitRate2</th>\n",
" <th>HitRate3</th>\n",
" <th>Reco in test</th>\n",
" <th>Test coverage</th>\n",
" <th>Shannon</th>\n",
@ -982,7 +1036,7 @@
" <th>0</th>\n",
" <td>Self_BaselineUI</td>\n",
" <td>1.612452</td>\n",
" <td>1.4</td>\n",
" <td>1.400</td>\n",
" <td>0.444444</td>\n",
" <td>0.888889</td>\n",
" <td>0.555556</td>\n",
@ -994,24 +1048,52 @@
" <td>0.611111</td>\n",
" <td>0.638889</td>\n",
" <td>1.0</td>\n",
" <td>0.333333</td>\n",
" <td>0.0</td>\n",
" <td>0.888889</td>\n",
" <td>0.8</td>\n",
" <td>1.386294</td>\n",
" <td>0.25</td>\n",
" <td>0.250000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Self_BaselineIU</td>\n",
" <td>1.648337</td>\n",
" <td>1.575</td>\n",
" <td>0.444444</td>\n",
" <td>0.888889</td>\n",
" <td>0.555556</td>\n",
" <td>0.478632</td>\n",
" <td>0.333333</td>\n",
" <td>0.75</td>\n",
" <td>0.720550</td>\n",
" <td>0.629630</td>\n",
" <td>0.666667</td>\n",
" <td>0.722222</td>\n",
" <td>1.0</td>\n",
" <td>0.333333</td>\n",
" <td>0.0</td>\n",
" <td>0.777778</td>\n",
" <td>0.8</td>\n",
" <td>1.351784</td>\n",
" <td>0.357143</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Model RMSE MAE precision recall F_1 F_05 \\\n",
"0 Self_BaselineUI 1.612452 1.4 0.444444 0.888889 0.555556 0.478632 \n",
" Model RMSE MAE precision recall F_1 F_05 \\\n",
"0 Self_BaselineUI 1.612452 1.400 0.444444 0.888889 0.555556 0.478632 \n",
"0 Self_BaselineIU 1.648337 1.575 0.444444 0.888889 0.555556 0.478632 \n",
"\n",
" precision_super recall_super NDCG mAP MRR LAUC HR \\\n",
"0 0.333333 0.75 0.676907 0.574074 0.611111 0.638889 1.0 \n",
"0 0.333333 0.75 0.720550 0.629630 0.666667 0.722222 1.0 \n",
"\n",
" Reco in test Test coverage Shannon Gini \n",
"0 0.888889 0.8 1.386294 0.25 "
" HitRate2 HitRate3 Reco in test Test coverage Shannon Gini \n",
"0 0.333333 0.0 0.888889 0.8 1.386294 0.250000 \n",
"0 0.333333 0.0 0.777778 0.8 1.351784 0.357143 "
]
},
"metadata": {},
@ -1029,7 +1111,7 @@
"text/plain": [
"matrix([[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]])"
" [0, 0, 0, 5, 0, 3, 4, 0]], dtype=int64)"
]
},
"metadata": {},
@ -1047,7 +1129,7 @@
"text/plain": [
"matrix([[0, 0, 0, 0, 0, 0, 3, 0],\n",
" [0, 0, 0, 0, 5, 0, 0, 0],\n",
" [5, 0, 4, 0, 0, 0, 0, 2]])"
" [5, 0, 4, 0, 0, 0, 0, 2]], dtype=int64)"
]
},
"metadata": {},
@ -1276,7 +1358,7 @@
},
{
"cell_type": "code",
"execution_count": 15,
"execution_count": 14,
"metadata": {},
"outputs": [
{
@ -1315,148 +1397,148 @@
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>57482</th>\n",
" <td>2</td>\n",
" <th>36652</th>\n",
" <td>735</td>\n",
" <td>5</td>\n",
" <td>Emma (1996)</td>\n",
" <td>Drama, Romance</td>\n",
" <td>Lone Star (1996)</td>\n",
" <td>Drama, Mystery</td>\n",
" </tr>\n",
" <tr>\n",
" <th>54506</th>\n",
" <td>2</td>\n",
" <td>5</td>\n",
" <td>Sense and Sensibility (1995)</td>\n",
" <td>Drama, Romance</td>\n",
" </tr>\n",
" <tr>\n",
" <th>40581</th>\n",
" <td>2</td>\n",
" <td>5</td>\n",
" <td>Titanic (1997)</td>\n",
" <td>Action, Drama, Romance</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2949</th>\n",
" <td>2</td>\n",
" <th>3143</th>\n",
" <td>735</td>\n",
" <td>5</td>\n",
" <td>Star Wars (1977)</td>\n",
" <td>Action, Adventure, Romance, Sci-Fi, War</td>\n",
" </tr>\n",
" <tr>\n",
" <th>69653</th>\n",
" <td>2</td>\n",
" <td>5</td>\n",
" <td>Wings of the Dove, The (1997)</td>\n",
" <td>Drama, Romance, Thriller</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7906</th>\n",
" <td>2</td>\n",
" <td>5</td>\n",
" <td>As Good As It Gets (1997)</td>\n",
" <td>Comedy, Drama</td>\n",
" </tr>\n",
" <tr>\n",
" <th>69400</th>\n",
" <td>2</td>\n",
" <td>5</td>\n",
" <td>Shall We Dance? (1996)</td>\n",
" <td>Comedy</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14469</th>\n",
" <td>2</td>\n",
" <td>5</td>\n",
" <td>Fargo (1996)</td>\n",
" <td>Crime, Drama, Thriller</td>\n",
" </tr>\n",
" <tr>\n",
" <th>46151</th>\n",
" <td>2</td>\n",
" <td>5</td>\n",
" <td>L.A. Confidential (1997)</td>\n",
" <td>Crime, Film-Noir, Mystery, Thriller</td>\n",
" </tr>\n",
" <tr>\n",
" <th>67293</th>\n",
" <td>2</td>\n",
" <td>5</td>\n",
" <td>Good Will Hunting (1997)</td>\n",
" <td>Drama</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20923</th>\n",
" <td>2</td>\n",
" <td>5</td>\n",
" <td>Secrets &amp; Lies (1996)</td>\n",
" <td>Drama</td>\n",
" </tr>\n",
" <tr>\n",
" <th>52921</th>\n",
" <td>2</td>\n",
" <th>52919</th>\n",
" <td>735</td>\n",
" <td>5</td>\n",
" <td>Kolya (1996)</td>\n",
" <td>Comedy</td>\n",
" </tr>\n",
" <tr>\n",
" <th>50103</th>\n",
" <td>2</td>\n",
" <th>275</th>\n",
" <td>735</td>\n",
" <td>4</td>\n",
" <td>Mrs. Brown (Her Majesty, Mrs. Brown) (1997)</td>\n",
" <td>Drama, Romance</td>\n",
" <td>Toy Story (1995)</td>\n",
" <td>Animation, Children's, Comedy</td>\n",
" </tr>\n",
" <tr>\n",
" <th>51972</th>\n",
" <td>2</td>\n",
" <th>41134</th>\n",
" <td>735</td>\n",
" <td>4</td>\n",
" <td>Trainspotting (1996)</td>\n",
" <td>Drama</td>\n",
" </tr>\n",
" <tr>\n",
" <th>28094</th>\n",
" <td>735</td>\n",
" <td>4</td>\n",
" <td>Face/Off (1997)</td>\n",
" <td>Action, Sci-Fi, Thriller</td>\n",
" </tr>\n",
" <tr>\n",
" <th>26548</th>\n",
" <td>735</td>\n",
" <td>4</td>\n",
" <td>Everyone Says I Love You (1996)</td>\n",
" <td>Comedy, Musical, Romance</td>\n",
" </tr>\n",
" <tr>\n",
" <th>26186</th>\n",
" <td>735</td>\n",
" <td>4</td>\n",
" <td>Air Force One (1997)</td>\n",
" <td>Action, Thriller</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25791</th>\n",
" <td>735</td>\n",
" <td>4</td>\n",
" <td>Dead Man Walking (1995)</td>\n",
" <td>Drama</td>\n",
" </tr>\n",
" <tr>\n",
" <th>51948</th>\n",
" <td>735</td>\n",
" <td>4</td>\n",
" <td>Mighty Aphrodite (1995)</td>\n",
" <td>Comedy</td>\n",
" </tr>\n",
" <tr>\n",
" <th>515</th>\n",
" <td>2</td>\n",
" <th>52778</th>\n",
" <td>735</td>\n",
" <td>4</td>\n",
" <td>Heat (1995)</td>\n",
" <td>Action, Crime, Thriller</td>\n",
" <td>Fly Away Home (1996)</td>\n",
" <td>Adventure, Children's</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20966</th>\n",
" <td>735</td>\n",
" <td>4</td>\n",
" <td>Secrets &amp; Lies (1996)</td>\n",
" <td>Drama</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19301</th>\n",
" <td>735</td>\n",
" <td>4</td>\n",
" <td>Scream (1996)</td>\n",
" <td>Horror, Thriller</td>\n",
" </tr>\n",
" <tr>\n",
" <th>54450</th>\n",
" <td>735</td>\n",
" <td>4</td>\n",
" <td>Sense and Sensibility (1995)</td>\n",
" <td>Drama, Romance</td>\n",
" </tr>\n",
" <tr>\n",
" <th>17177</th>\n",
" <td>735</td>\n",
" <td>4</td>\n",
" <td>Leaving Las Vegas (1995)</td>\n",
" <td>Drama, Romance</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" user rating title \\\n",
"57482 2 5 Emma (1996) \n",
"54506 2 5 Sense and Sensibility (1995) \n",
"40581 2 5 Titanic (1997) \n",
"2949 2 5 Star Wars (1977) \n",
"69653 2 5 Wings of the Dove, The (1997) \n",
"7906 2 5 As Good As It Gets (1997) \n",
"69400 2 5 Shall We Dance? (1996) \n",
"14469 2 5 Fargo (1996) \n",
"46151 2 5 L.A. Confidential (1997) \n",
"67293 2 5 Good Will Hunting (1997) \n",
"20923 2 5 Secrets & Lies (1996) \n",
"52921 2 5 Kolya (1996) \n",
"50103 2 4 Mrs. Brown (Her Majesty, Mrs. Brown) (1997) \n",
"51972 2 4 Mighty Aphrodite (1995) \n",
"515 2 4 Heat (1995) \n",
" user rating title \\\n",
"36652 735 5 Lone Star (1996) \n",
"3143 735 5 Star Wars (1977) \n",
"52919 735 5 Kolya (1996) \n",
"275 735 4 Toy Story (1995) \n",
"41134 735 4 Trainspotting (1996) \n",
"28094 735 4 Face/Off (1997) \n",
"26548 735 4 Everyone Says I Love You (1996) \n",
"26186 735 4 Air Force One (1997) \n",
"25791 735 4 Dead Man Walking (1995) \n",
"51948 735 4 Mighty Aphrodite (1995) \n",
"52778 735 4 Fly Away Home (1996) \n",
"20966 735 4 Secrets & Lies (1996) \n",
"19301 735 4 Scream (1996) \n",
"54450 735 4 Sense and Sensibility (1995) \n",
"17177 735 4 Leaving Las Vegas (1995) \n",
"\n",
" genres \n",
"57482 Drama, Romance \n",
"54506 Drama, Romance \n",
"40581 Action, Drama, Romance \n",
"2949 Action, Adventure, Romance, Sci-Fi, War \n",
"69653 Drama, Romance, Thriller \n",
"7906 Comedy, Drama \n",
"69400 Comedy \n",
"14469 Crime, Drama, Thriller \n",
"46151 Crime, Film-Noir, Mystery, Thriller \n",
"67293 Drama \n",
"20923 Drama \n",
"52921 Comedy \n",
"50103 Drama, Romance \n",
"51972 Comedy \n",
"515 Action, Crime, Thriller "
"36652 Drama, Mystery \n",
"3143 Action, Adventure, Romance, Sci-Fi, War \n",
"52919 Comedy \n",
"275 Animation, Children's, Comedy \n",
"41134 Drama \n",
"28094 Action, Sci-Fi, Thriller \n",
"26548 Comedy, Musical, Romance \n",
"26186 Action, Thriller \n",
"25791 Drama \n",
"51948 Comedy \n",
"52778 Adventure, Children's \n",
"20966 Drama \n",
"19301 Horror, Thriller \n",
"54450 Drama, Romance \n",
"17177 Drama, Romance "
]
},
"metadata": {},
@ -1498,71 +1580,71 @@
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2.0</td>\n",
" <th>733</th>\n",
" <td>735.0</td>\n",
" <td>1</td>\n",
" <td>Great Day in Harlem, A (1994)</td>\n",
" <td>Documentary</td>\n",
" </tr>\n",
" <tr>\n",
" <th>943</th>\n",
" <td>2.0</td>\n",
" <th>1675</th>\n",
" <td>735.0</td>\n",
" <td>2</td>\n",
" <td>Tough and Deadly (1995)</td>\n",
" <td>Action, Drama, Thriller</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1885</th>\n",
" <td>2.0</td>\n",
" <th>2617</th>\n",
" <td>735.0</td>\n",
" <td>3</td>\n",
" <td>Aiqing wansui (1994)</td>\n",
" <td>Drama</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2827</th>\n",
" <td>2.0</td>\n",
" <th>3559</th>\n",
" <td>735.0</td>\n",
" <td>4</td>\n",
" <td>Delta of Venus (1994)</td>\n",
" <td>Drama</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3769</th>\n",
" <td>2.0</td>\n",
" <th>4501</th>\n",
" <td>735.0</td>\n",
" <td>5</td>\n",
" <td>Someone Else's America (1995)</td>\n",
" <td>Drama</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4711</th>\n",
" <td>2.0</td>\n",
" <th>5443</th>\n",
" <td>735.0</td>\n",
" <td>6</td>\n",
" <td>Saint of Fort Washington, The (1993)</td>\n",
" <td>Drama</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5653</th>\n",
" <td>2.0</td>\n",
" <th>6385</th>\n",
" <td>735.0</td>\n",
" <td>7</td>\n",
" <td>Celestial Clockwork (1994)</td>\n",
" <td>Comedy</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6595</th>\n",
" <td>2.0</td>\n",
" <th>7326</th>\n",
" <td>735.0</td>\n",
" <td>8</td>\n",
" <td>Some Mother's Son (1996)</td>\n",
" <td>Drama</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8489</th>\n",
" <td>2.0</td>\n",
" <th>9222</th>\n",
" <td>735.0</td>\n",
" <td>9</td>\n",
" <td>Maya Lin: A Strong Clear Vision (1994)</td>\n",
" <td>Documentary</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7536</th>\n",
" <td>2.0</td>\n",
" <th>8268</th>\n",
" <td>735.0</td>\n",
" <td>10</td>\n",
" <td>Prefontaine (1997)</td>\n",
" <td>Drama</td>\n",
@ -1572,32 +1654,32 @@
"</div>"
],
"text/plain": [
" user rec_nb title \\\n",
"1 2.0 1 Great Day in Harlem, A (1994) \n",
"943 2.0 2 Tough and Deadly (1995) \n",
"1885 2.0 3 Aiqing wansui (1994) \n",
"2827 2.0 4 Delta of Venus (1994) \n",
"3769 2.0 5 Someone Else's America (1995) \n",
"4711 2.0 6 Saint of Fort Washington, The (1993) \n",
"5653 2.0 7 Celestial Clockwork (1994) \n",
"6595 2.0 8 Some Mother's Son (1996) \n",
"8489 2.0 9 Maya Lin: A Strong Clear Vision (1994) \n",
"7536 2.0 10 Prefontaine (1997) \n",
" user rec_nb title \\\n",
"733 735.0 1 Great Day in Harlem, A (1994) \n",
"1675 735.0 2 Tough and Deadly (1995) \n",
"2617 735.0 3 Aiqing wansui (1994) \n",
"3559 735.0 4 Delta of Venus (1994) \n",
"4501 735.0 5 Someone Else's America (1995) \n",
"5443 735.0 6 Saint of Fort Washington, The (1993) \n",
"6385 735.0 7 Celestial Clockwork (1994) \n",
"7326 735.0 8 Some Mother's Son (1996) \n",
"9222 735.0 9 Maya Lin: A Strong Clear Vision (1994) \n",
"8268 735.0 10 Prefontaine (1997) \n",
"\n",
" genres \n",
"1 Documentary \n",
"943 Action, Drama, Thriller \n",
"1885 Drama \n",
"2827 Drama \n",
"3769 Drama \n",
"4711 Drama \n",
"5653 Comedy \n",
"6595 Drama \n",
"8489 Documentary \n",
"7536 Drama "
"733 Documentary \n",
"1675 Action, Drama, Thriller \n",
"2617 Drama \n",
"3559 Drama \n",
"4501 Drama \n",
"5443 Drama \n",
"6385 Comedy \n",
"7326 Drama \n",
"9222 Documentary \n",
"8268 Drama "
]
},
"execution_count": 15,
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
@ -1684,7 +1766,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.8.5"
"version": "3.8.8"
}
},
"nbformat": 4,

765
P3. k-nearest neighbours.ipynb
View File

@ -113,7 +113,7 @@
"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]])"
" [0, 0, 0, 5, 0, 3, 4, 0]], dtype=int64)"
]
},
"metadata": {},
@ -256,7 +256,7 @@
"name": "stderr",
"output_type": "stream",
"text": [
"943it [00:00, 9004.71it/s]\n"
"943it [00:00, 9914.99it/s]\n"
]
},
{
@ -293,6 +293,8 @@
" <th>MRR</th>\n",
" <th>LAUC</th>\n",
" <th>HR</th>\n",
" <th>HitRate2</th>\n",
" <th>HitRate3</th>\n",
" <th>Reco in test</th>\n",
" <th>Test coverage</th>\n",
" <th>Shannon</th>\n",
@ -315,6 +317,8 @@
" <td>0.000368</td>\n",
" <td>0.496391</td>\n",
" <td>0.003181</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.392153</td>\n",
" <td>0.11544</td>\n",
" <td>4.174741</td>\n",
@ -331,8 +335,11 @@
" 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 Reco in test Test coverage Shannon Gini \n",
"0 0.003181 0.392153 0.11544 4.174741 0.965327 "
" HR HitRate2 HitRate3 Reco in test Test coverage Shannon \\\n",
"0 0.003181 0.0 0.0 0.392153 0.11544 4.174741 \n",
"\n",
" Gini \n",
"0 0.965327 "
]
},
"execution_count": 5,
@ -365,12 +372,15 @@
"name": "stderr",
"output_type": "stream",
"text": [
"943it [00:00, 8517.83it/s]\n",
"943it [00:00, 11438.64it/s]\n",
"943it [00:00, 11933.36it/s]\n",
"943it [00:00, 10307.81it/s]\n",
"943it [00:00, 12250.41it/s]\n",
"943it [00:00, 12064.07it/s]\n"
"943it [00:00, 9928.75it/s]\n",
"943it [00:00, 10480.56it/s]\n",
"943it [00:00, 8591.71it/s]\n",
"943it [00:00, 9949.81it/s]\n",
"943it [00:00, 9925.57it/s]\n",
"943it [00:00, 9911.02it/s]\n",
"943it [00:00, 9196.77it/s]\n",
"943it [00:00, 9443.97it/s]\n",
"943it [00:00, 8577.83it/s]\n"
]
},
{
@ -408,6 +418,8 @@
" <th>MRR</th>\n",
" <th>LAUC</th>\n",
" <th>HR</th>\n",
" <th>HitRate2</th>\n",
" <th>HitRate3</th>\n",
" <th>Reco in test</th>\n",
" <th>Test coverage</th>\n",
" <th>Shannon</th>\n",
@ -431,6 +443,8 @@
" <td>0.400939</td>\n",
" <td>0.555546</td>\n",
" <td>0.765642</td>\n",
" <td>0.492047</td>\n",
" <td>0.290562</td>\n",
" <td>1.000000</td>\n",
" <td>0.038961</td>\n",
" <td>3.159079</td>\n",
@ -452,6 +466,8 @@
" <td>0.198193</td>\n",
" <td>0.515501</td>\n",
" <td>0.437964</td>\n",
" <td>0.239661</td>\n",
" <td>0.126193</td>\n",
" <td>1.000000</td>\n",
" <td>0.033911</td>\n",
" <td>2.836513</td>\n",
@ -460,23 +476,94 @@
" <tr>\n",
" <th>0</th>\n",
" <td>Ready_Random</td>\n",
" <td>1.521845</td>\n",
" <td>1.225949</td>\n",
" <td>0.047190</td>\n",
" <td>0.020753</td>\n",
" <td>0.024810</td>\n",
" <td>0.032269</td>\n",
" <td>0.029506</td>\n",
" <td>0.023707</td>\n",
" <td>0.050075</td>\n",
" <td>0.018728</td>\n",
" <td>0.121957</td>\n",
" <td>0.506893</td>\n",
" <td>0.329799</td>\n",
" <td>0.986532</td>\n",
" <td>0.184704</td>\n",
" <td>5.099706</td>\n",
" <td>0.907217</td>\n",
" <td>1.516512</td>\n",
" <td>1.217214</td>\n",
" <td>0.045599</td>\n",
" <td>0.021001</td>\n",
" <td>0.024136</td>\n",
" <td>0.031226</td>\n",
" <td>0.028541</td>\n",
" <td>0.022057</td>\n",
" <td>0.050154</td>\n",
" <td>0.019000</td>\n",
" <td>0.125089</td>\n",
" <td>0.507013</td>\n",
" <td>0.327678</td>\n",
" <td>0.093319</td>\n",
" <td>0.026511</td>\n",
" <td>0.988017</td>\n",
" <td>0.192641</td>\n",
" <td>5.141246</td>\n",
" <td>0.903763</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>0.024390</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>0.000000</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>0.000000</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",
@ -494,6 +581,8 @@
" <td>0.003348</td>\n",
" <td>0.496433</td>\n",
" <td>0.009544</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.699046</td>\n",
" <td>0.005051</td>\n",
" <td>1.945910</td>\n",
@ -515,6 +604,8 @@
" <td>0.001677</td>\n",
" <td>0.496424</td>\n",
" <td>0.009544</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.600530</td>\n",
" <td>0.005051</td>\n",
" <td>1.803126</td>\n",
@ -536,6 +627,8 @@
" <td>0.000368</td>\n",
" <td>0.496391</td>\n",
" <td>0.003181</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.392153</td>\n",
" <td>0.115440</td>\n",
" <td>4.174741</td>\n",
@ -546,29 +639,49 @@
"</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 Ready_Random 1.521845 1.225949 0.047190 0.020753 0.024810 \n",
"0 Self_TopRated 1.030712 0.820904 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",
" 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 Ready_Random 1.516512 1.217214 0.045599 0.021001 0.024136 \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 1.030712 0.820904 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 0.032269 0.029506 0.023707 0.050075 0.018728 0.121957 \n",
"0 0.031226 0.028541 0.022057 0.050154 0.019000 0.125089 \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 0.000463 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 Reco in test Test coverage Shannon Gini \n",
"0 0.555546 0.765642 1.000000 0.038961 3.159079 0.987317 \n",
"0 0.515501 0.437964 1.000000 0.033911 2.836513 0.991139 \n",
"0 0.506893 0.329799 0.986532 0.184704 5.099706 0.907217 \n",
"0 0.496433 0.009544 0.699046 0.005051 1.945910 0.995669 \n",
"0 0.496424 0.009544 0.600530 0.005051 1.803126 0.996380 \n",
"0 0.496391 0.003181 0.392153 0.115440 4.174741 0.965327 "
" LAUC HR HitRate2 HitRate3 Reco in test Test coverage \\\n",
"0 0.555546 0.765642 0.492047 0.290562 1.000000 0.038961 \n",
"0 0.515501 0.437964 0.239661 0.126193 1.000000 0.033911 \n",
"0 0.507013 0.327678 0.093319 0.026511 0.988017 0.192641 \n",
"0 0.499885 0.154825 0.072110 0.024390 0.402333 0.434343 \n",
"0 0.496724 0.021209 0.004242 0.000000 0.482821 0.059885 \n",
"0 0.496441 0.007423 0.000000 0.000000 0.602121 0.010823 \n",
"0 0.496433 0.009544 0.000000 0.000000 0.699046 0.005051 \n",
"0 0.496424 0.009544 0.000000 0.000000 0.600530 0.005051 \n",
"0 0.496391 0.003181 0.000000 0.000000 0.392153 0.115440 \n",
"\n",
" Shannon Gini \n",
"0 3.159079 0.987317 \n",
"0 2.836513 0.991139 \n",
"0 5.141246 0.903763 \n",
"0 5.133650 0.877999 \n",
"0 2.232578 0.994487 \n",
"0 2.089186 0.995706 \n",
"0 1.945910 0.995669 \n",
"0 1.803126 0.996380 \n",
"0 4.174741 0.965327 "
]
},
"execution_count": 6,
@ -718,15 +831,15 @@
"name": "stderr",
"output_type": "stream",
"text": [
"943it [00:00, 11286.27it/s]\n",
"943it [00:00, 10874.86it/s]\n",
"943it [00:00, 11509.97it/s]\n",
"943it [00:00, 11855.81it/s]\n",
"943it [00:00, 11574.00it/s]\n",
"943it [00:00, 11080.19it/s]\n",
"943it [00:00, 11550.84it/s]\n",
"943it [00:00, 12148.14it/s]\n",
"943it [00:00, 10779.39it/s]\n"
"943it [00:00, 8051.57it/s]\n",
"943it [00:00, 9790.90it/s]\n",
"943it [00:00, 9404.38it/s]\n",
"943it [00:00, 9429.83it/s]\n",
"943it [00:00, 9915.86it/s]\n",
"943it [00:00, 8625.66it/s]\n",
"943it [00:00, 9687.63it/s]\n",
"943it [00:00, 10469.91it/s]\n",
"943it [00:00, 8577.63it/s]\n"
]
},
{
@ -764,6 +877,8 @@
" <th>MRR</th>\n",
" <th>LAUC</th>\n",
" <th>HR</th>\n",
" <th>HitRate2</th>\n",
" <th>HitRate3</th>\n",
" <th>Reco in test</th>\n",
" <th>Test coverage</th>\n",
" <th>Shannon</th>\n",
@ -787,6 +902,8 @@
" <td>0.400939</td>\n",
" <td>0.555546</td>\n",
" <td>0.765642</td>\n",
" <td>0.492047</td>\n",
" <td>0.290562</td>\n",
" <td>1.000000</td>\n",
" <td>0.038961</td>\n",
" <td>3.159079</td>\n",
@ -808,6 +925,8 @@
" <td>0.198193</td>\n",
" <td>0.515501</td>\n",
" <td>0.437964</td>\n",
" <td>0.239661</td>\n",
" <td>0.126193</td>\n",
" <td>1.000000</td>\n",
" <td>0.033911</td>\n",
" <td>2.836513</td>\n",
@ -816,23 +935,25 @@
" <tr>\n",
" <th>0</th>\n",
" <td>Ready_Random</td>\n",
" <td>1.521845</td>\n",
" <td>1.225949</td>\n",
" <td>0.047190</td>\n",
" <td>0.020753</td>\n",
" <td>0.024810</td>\n",
" <td>0.032269</td>\n",
" <td>0.029506</td>\n",
" <td>0.023707</td>\n",
" <td>0.050075</td>\n",
" <td>0.018728</td>\n",
" <td>0.121957</td>\n",
" <td>0.506893</td>\n",
" <td>0.329799</td>\n",
" <td>0.986532</td>\n",
" <td>0.184704</td>\n",
" <td>5.099706</td>\n",
" <td>0.907217</td>\n",
" <td>1.516512</td>\n",
" <td>1.217214</td>\n",
" <td>0.045599</td>\n",
" <td>0.021001</td>\n",
" <td>0.024136</td>\n",
" <td>0.031226</td>\n",
" <td>0.028541</td>\n",
" <td>0.022057</td>\n",
" <td>0.050154</td>\n",
" <td>0.019000</td>\n",
" <td>0.125089</td>\n",
" <td>0.507013</td>\n",
" <td>0.327678</td>\n",
" <td>0.093319</td>\n",
" <td>0.026511</td>\n",
" <td>0.988017</td>\n",
" <td>0.192641</td>\n",
" <td>5.141246</td>\n",
" <td>0.903763</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
@ -850,6 +971,8 @@
" <td>0.048068</td>\n",
" <td>0.499885</td>\n",
" <td>0.154825</td>\n",
" <td>0.072110</td>\n",
" <td>0.024390</td>\n",
" <td>0.402333</td>\n",
" <td>0.434343</td>\n",
" <td>5.133650</td>\n",
@ -871,6 +994,8 @@
" <td>0.011760</td>\n",
" <td>0.496724</td>\n",
" <td>0.021209</td>\n",
" <td>0.004242</td>\n",
" <td>0.000000</td>\n",
" <td>0.482821</td>\n",
" <td>0.059885</td>\n",
" <td>2.232578</td>\n",
@ -892,6 +1017,8 @@
" <td>0.002744</td>\n",
" <td>0.496441</td>\n",
" <td>0.007423</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.602121</td>\n",
" <td>0.010823</td>\n",
" <td>2.089186</td>\n",
@ -913,6 +1040,8 @@
" <td>0.003348</td>\n",
" <td>0.496433</td>\n",
" <td>0.009544</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.699046</td>\n",
" <td>0.005051</td>\n",
" <td>1.945910</td>\n",
@ -934,6 +1063,8 @@
" <td>0.001677</td>\n",
" <td>0.496424</td>\n",
" <td>0.009544</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.600530</td>\n",
" <td>0.005051</td>\n",
" <td>1.803126</td>\n",
@ -955,6 +1086,8 @@
" <td>0.000368</td>\n",
" <td>0.496391</td>\n",
" <td>0.003181</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.392153</td>\n",
" <td>0.115440</td>\n",
" <td>4.174741</td>\n",
@ -968,7 +1101,7 @@
" 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 Ready_Random 1.521845 1.225949 0.047190 0.020753 0.024810 \n",
"0 Ready_Random 1.516512 1.217214 0.045599 0.021001 0.024136 \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",
@ -979,7 +1112,7 @@
" 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 0.032269 0.029506 0.023707 0.050075 0.018728 0.121957 \n",
"0 0.031226 0.028541 0.022057 0.050154 0.019000 0.125089 \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",
@ -987,16 +1120,27 @@
"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 Reco in test Test coverage Shannon Gini \n",
"0 0.555546 0.765642 1.000000 0.038961 3.159079 0.987317 \n",
"0 0.515501 0.437964 1.000000 0.033911 2.836513 0.991139 \n",
"0 0.506893 0.329799 0.986532 0.184704 5.099706 0.907217 \n",
"0 0.499885 0.154825 0.402333 0.434343 5.133650 0.877999 \n",
"0 0.496724 0.021209 0.482821 0.059885 2.232578 0.994487 \n",
"0 0.496441 0.007423 0.602121 0.010823 2.089186 0.995706 \n",
"0 0.496433 0.009544 0.699046 0.005051 1.945910 0.995669 \n",
"0 0.496424 0.009544 0.600530 0.005051 1.803126 0.996380 \n",
"0 0.496391 0.003181 0.392153 0.115440 4.174741 0.965327 "
" LAUC HR HitRate2 HitRate3 Reco in test Test coverage \\\n",
"0 0.555546 0.765642 0.492047 0.290562 1.000000 0.038961 \n",
"0 0.515501 0.437964 0.239661 0.126193 1.000000 0.033911 \n",
"0 0.507013 0.327678 0.093319 0.026511 0.988017 0.192641 \n",
"0 0.499885 0.154825 0.072110 0.024390 0.402333 0.434343 \n",
"0 0.496724 0.021209 0.004242 0.000000 0.482821 0.059885 \n",
"0 0.496441 0.007423 0.000000 0.000000 0.602121 0.010823 \n",
"0 0.496433 0.009544 0.000000 0.000000 0.699046 0.005051 \n",
"0 0.496424 0.009544 0.000000 0.000000 0.600530 0.005051 \n",
"0 0.496391 0.003181 0.000000 0.000000 0.392153 0.115440 \n",
"\n",
" Shannon Gini \n",
"0 3.159079 0.987317 \n",
"0 2.836513 0.991139 \n",
"0 5.141246 0.903763 \n",
"0 5.133650 0.877999 \n",
"0 2.232578 0.994487 \n",
"0 2.089186 0.995706 \n",
"0 1.945910 0.995669 \n",
"0 1.803126 0.996380 \n",
"0 4.174741 0.965327 "
]
},
"execution_count": 10,
@ -1021,7 +1165,7 @@
},
{
"cell_type": "code",
"execution_count": 11,
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
@ -1031,6 +1175,463 @@
"# 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": 43,
"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": [
"sim_options = {\n",
" \"name\": \"cosine\",\n",
" \"user_based\": True,\n",
"} # compute similarities between items\n",
"algorytm = sp.KNNBaseline(min_k=55, k=155)\n",
"\n",
"helpers.ready_made(\n",
" algorytm,\n",
" reco_path=\"Recommendations generated/ml-100k/Self_KNNSurprisetask_reco.csv\",\n",
" estimations_path=\"Recommendations generated/ml-100k/Self_KNNSurprisetask_estimations.csv\",\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 44,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"943it [00:00, 12777.10it/s]\n",
"943it [00:00, 13902.58it/s]\n",
"943it [00:00, 13703.41it/s]\n",
"943it [00:00, 12363.57it/s]\n",
"943it [00:00, 14321.56it/s]\n",
"943it [00:00, 13132.35it/s]\n",
"943it [00:00, 14318.76it/s]\n",
"943it [00:00, 11530.04it/s]\n",
"943it [00:00, 11255.60it/s]\n",
"943it [00:00, 12605.02it/s]\n",
"943it [00:00, 12946.27it/s]\n",
"943it [00:00, 12127.73it/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>HitRate2</th>\n",
" <th>HitRate3</th>\n",
" <th>Reco in test</th>\n",
" <th>Test coverage</th>\n",
" <th>Shannon</th>\n",
" <th>Gini</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Self_RP3Beta</td>\n",
" <td>3.501158</td>\n",
" <td>3.321368</td>\n",
" <td>0.315907</td>\n",
" <td>0.213088</td>\n",
" <td>0.208492</td>\n",
" <td>0.242756</td>\n",
" <td>0.233476</td>\n",
" <td>0.270002</td>\n",
" <td>0.382946</td>\n",
" <td>0.245988</td>\n",
" <td>0.626241</td>\n",
" <td>0.604180</td>\n",
" <td>0.896076</td>\n",
" <td>0.727466</td>\n",
" <td>0.538706</td>\n",
" <td>1.000000</td>\n",
" <td>0.122655</td>\n",
" <td>4.342930</td>\n",
" <td>0.959561</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>0.495228</td>\n",
" <td>1.000000</td>\n",
" <td>0.077201</td>\n",
" <td>3.875892</td>\n",
" <td>0.974947</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>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>0.290562</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_KNNSurprisetask</td>\n",
" <td>0.942531</td>\n",
" <td>0.744851</td>\n",
" <td>0.090562</td>\n",
" <td>0.038031</td>\n",
" <td>0.045951</td>\n",
" <td>0.060863</td>\n",
" <td>0.080258</td>\n",
" <td>0.058681</td>\n",
" <td>0.090174</td>\n",
" <td>0.038552</td>\n",
" <td>0.178715</td>\n",
" <td>0.515679</td>\n",
" <td>0.448568</td>\n",
" <td>0.232238</td>\n",
" <td>0.123012</td>\n",
" <td>1.000000</td>\n",
" <td>0.042569</td>\n",
" <td>3.015508</td>\n",
" <td>0.989612</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>0.126193</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_Random</td>\n",
" <td>1.516512</td>\n",
" <td>1.217214</td>\n",
" <td>0.045599</td>\n",
" <td>0.021001</td>\n",
" <td>0.024136</td>\n",
" <td>0.031226</td>\n",
" <td>0.028541</td>\n",
" <td>0.022057</td>\n",
" <td>0.050154</td>\n",
" <td>0.019000</td>\n",
" <td>0.125089</td>\n",
" <td>0.507013</td>\n",
" <td>0.327678</td>\n",
" <td>0.093319</td>\n",
" <td>0.026511</td>\n",
" <td>0.988017</td>\n",
" <td>0.192641</td>\n",
" <td>5.141246</td>\n",
" <td>0.903763</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>0.024390</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>0.000000</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>0.000000</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>1.030712</td>\n",
" <td>0.820904</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>0.000000</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>0.000000</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>0.000000</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_RP3Beta 3.501158 3.321368 0.315907 0.213088 0.208492 \n",
"0 Self_P3 3.702446 3.527273 0.282185 0.192092 0.186749 \n",
"0 Self_TopPop 2.508258 2.217909 0.188865 0.116919 0.118732 \n",
"0 Self_KNNSurprisetask 0.942531 0.744851 0.090562 0.038031 0.045951 \n",
"0 Ready_Baseline 0.949459 0.752487 0.091410 0.037652 0.046030 \n",
"0 Ready_Random 1.516512 1.217214 0.045599 0.021001 0.024136 \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 1.030712 0.820904 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 0.242756 0.233476 0.270002 0.382946 0.245988 0.626241 \n",
"0 0.216980 0.204185 0.240096 0.339114 0.204905 0.572157 \n",
"0 0.141584 0.130472 0.137473 0.214651 0.111707 0.400939 \n",
"0 0.060863 0.080258 0.058681 0.090174 0.038552 0.178715 \n",
"0 0.061286 0.079614 0.056463 0.095957 0.043178 0.198193 \n",
"0 0.031226 0.028541 0.022057 0.050154 0.019000 0.125089 \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 0.000463 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 HitRate2 HitRate3 Reco in test Test coverage \\\n",
"0 0.604180 0.896076 0.727466 0.538706 1.000000 0.122655 \n",
"0 0.593544 0.875928 0.685048 0.495228 1.000000 0.077201 \n",
"0 0.555546 0.765642 0.492047 0.290562 1.000000 0.038961 \n",
"0 0.515679 0.448568 0.232238 0.123012 1.000000 0.042569 \n",
"0 0.515501 0.437964 0.239661 0.126193 1.000000 0.033911 \n",
"0 0.507013 0.327678 0.093319 0.026511 0.988017 0.192641 \n",
"0 0.499885 0.154825 0.072110 0.024390 0.402333 0.434343 \n",
"0 0.496724 0.021209 0.004242 0.000000 0.482821 0.059885 \n",
"0 0.496441 0.007423 0.000000 0.000000 0.602121 0.010823 \n",
"0 0.496433 0.009544 0.000000 0.000000 0.699046 0.005051 \n",
"0 0.496424 0.009544 0.000000 0.000000 0.600530 0.005051 \n",
"0 0.496391 0.003181 0.000000 0.000000 0.392153 0.115440 \n",
"\n",
" Shannon Gini \n",
"0 4.342930 0.959561 \n",
"0 3.875892 0.974947 \n",
"0 3.159079 0.987317 \n",
"0 3.015508 0.989612 \n",
"0 2.836513 0.991139 \n",
"0 5.141246 0.903763 \n",
"0 5.133650 0.877999 \n",
"0 2.232578 0.994487 \n",
"0 2.089186 0.995706 \n",
"0 1.945910 0.995669 \n",
"0 1.803126 0.996380 \n",
"0 4.174741 0.965327 "
]
},
"execution_count": 44,
"metadata": {},
"output_type": "execute_result"
}
],
"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",
"ev.evaluate_all(test, dir_path, super_reactions)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
@ -1049,7 +1650,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.8.5"
"version": "3.8.8"
}
},
"nbformat": 4,

939
P5. Graph-based.ipynb
View File

File diff suppressed because one or more lines are too long

12
evaluation_measures.py
View File

@ -67,8 +67,8 @@ def evaluate(test,
def ranking_metrics(test_ui, reco, super_reactions=[], topK=10):
nb_items=test_ui.shape[1]
relevant_users, super_relevant_users, prec, rec, F_1, F_05, prec_super, rec_super, ndcg, mAP, MRR, LAUC, HR=\
0,0,0,0,0,0,0,0,0,0,0,0,0
relevant_users, super_relevant_users, prec, rec, F_1, F_05, prec_super, rec_super, ndcg, mAP, MRR, LAUC, HR, HitRate2, HitRate3=\
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0
cg = (1.0 / np.log2(np.arange(2, topK + 2)))
cg_sum = np.cumsum(cg)
@ -121,7 +121,10 @@ def ranking_metrics(test_ui, reco, super_reactions=[], topK=10):
((nb_items-nb_u_rated_items)*nb_u_rated_items)
HR+=nb_user_successes>0
HitRate2+=nb_user_successes>1
HitRate3+=nb_user_successes>2
result=[]
result.append(('precision', prec/relevant_users))
@ -135,6 +138,9 @@ def ranking_metrics(test_ui, reco, super_reactions=[], topK=10):
result.append(('MRR', MRR/relevant_users))
result.append(('LAUC', LAUC/relevant_users))
result.append(('HR', HR/relevant_users))
result.append(('HitRate2', HitRate2/relevant_users))
result.append(('HitRate3', HitRate3/relevant_users))
df_result=pd.DataFrame()
if len(result)>0: