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

finished first 2 lectures

Browse Source
This commit is contained in:
Robert 2021-03-23 21:52:46 +01:00
parent 18d5c09409
commit e36414e7ce
5 changed files with 360 additions and 374 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
P0. Data preparation.ipynb
View File

@ -13,12 +13,15 @@
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"# if you don't have some library installed try using pip (or pip3) to install it - you can do it from the notebook\n",
"# example: !pip install tqdm\n",
"# also on labs it's better to use python3 kernel - ipython3 notebook\n",
"\n",
"import pandas as pd\n", "import pandas as pd\n",
"import numpy as np\n", "import numpy as np\n",
"import scipy.sparse as sparse\n", "import scipy.sparse as sparse\n",
"import time\n", "import time\n",
"import random\n", "import random\n",
"import evaluation_measures as ev\n",
"import matplotlib\n", "import matplotlib\n",
"import matplotlib.pyplot as plt\n", "import matplotlib.pyplot as plt\n",
"import os\n", "import os\n",
@ -161,7 +164,7 @@
"text": [ "text": [
"We have 943 users, 1682 items and 100000 ratings.\n", "We have 943 users, 1682 items and 100000 ratings.\n",
"\n", "\n",
"Average number of ratings per user is 106.04. \n", "Average number of ratings per user is 106.0445. \n",
"\n", "\n",
"Average number of ratings per item is 59.453.\n", "Average number of ratings per item is 59.453.\n",
"\n", "\n",
@ -170,13 +173,13 @@
} }
], ],
"source": [ "source": [
"users, items, ratings=len(set(df['user'])), len(set(df['item'])), len(df)\n", "users, items, ratings=df['user'].nunique(), df['item'].nunique(), len(df)\n",
"\n", "\n",
"print('We have {} users, {} items and {} ratings.\\n'.format(users, items, ratings))\n", "print(f'We have {users} users, {items} items and {ratings} ratings.\\n')\n",
"\n", "\n",
"print('Average number of ratings per user is {}. \\n'.format(round(ratings/users,2)))\n", "print(f'Average number of ratings per user is {round(ratings/users,4)}. \\n')\n",
"print('Average number of ratings per item is {}.\\n'.format(round(ratings/items,4)))\n", "print(f'Average number of ratings per item is {round(ratings/items,4)}.\\n')\n",
"print('Data sparsity (% of missing entries) is {}%.'.format(round(100*ratings/(users*items),4)))" "print(f'Data sparsity (% of missing entries) is {round(100*ratings/(users*items),4)}%.')"
] ]
}, },
{ {
@ -636,7 +639,6 @@
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"import os\n",
"os.makedirs('./Datasets/toy-example/', exist_ok = True)" "os.makedirs('./Datasets/toy-example/', exist_ok = True)"
] ]
}, },

190
P1. Baseline.ipynb
View File

@ -239,11 +239,9 @@
"name": "stdout", "name": "stdout",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"\n",
"Number of ratings: 8\n", "Number of ratings: 8\n",
"Number of users: 3\n", "Number of users: 3\n",
"Number of items: 4 \n", "Number of items: 4\n"
"\n"
] ]
} }
], ],
@ -251,8 +249,9 @@
"print('Ratings matrix with missing entries replaced by zeros:')\n", "print('Ratings matrix with missing entries replaced by zeros:')\n",
"display(sample_csr.todense())\n", "display(sample_csr.todense())\n",
"\n", "\n",
"print('\\nNumber of ratings: {} \\nNumber of users: {} \\nNumber of items: {} \\n'\n", "print(f'Number of ratings: {sample_csr.nnz}')\n",
" .format(sample_csr.nnz, sample_csr.shape[0], sample_csr.shape[1]))" "print(f'Number of users: {sample_csr.shape[0]}')\n",
"print(f'Number of items: {sample_csr.shape[1]}')"
] ]
}, },
{ {
@ -278,7 +277,7 @@
"print('Regarding items:', sample_csr.indices)\n", "print('Regarding items:', sample_csr.indices)\n",
"\n", "\n",
"for i in range(sample_csr.shape[0]):\n", "for i in range(sample_csr.shape[0]):\n",
" print('Where ratings from {} to {} belongs to user {}.'.format(sample_csr.indptr[i], sample_csr.indptr[i+1]-1, i))" " print(f'Where ratings from {sample_csr.indptr[i]} to {sample_csr.indptr[i+1]-1} belongs to user {i}.')"
] ]
}, },
{ {
@ -307,7 +306,7 @@
"name": "stdout", "name": "stdout",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"885 ns ± 165 ns per loop (mean ± std. dev. of 7 runs, 1000000 loops each)\n", "1.44 µs ± 184 ns per loop (mean ± std. dev. of 7 runs, 1000000 loops each)\n",
"Inefficient way to access items rated by user:\n" "Inefficient way to access items rated by user:\n"
] ]
}, },
@ -325,7 +324,7 @@
"name": "stdout", "name": "stdout",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"153 µs ± 9.4 µs per loop (mean ± std. dev. of 7 runs, 10000 loops each)\n" "172 µs ± 14.4 µs per loop (mean ± std. dev. of 7 runs, 10000 loops each)\n"
] ]
} }
], ],
@ -482,7 +481,7 @@
"display(sparse.diags(row_means).todense())\n", "display(sparse.diags(row_means).todense())\n",
"\n", "\n",
"print(\"\"\"Let's apply them in nonzero entries:\"\"\")\n", "print(\"\"\"Let's apply them in nonzero entries:\"\"\")\n",
"to_subtract=sparse.diags(row_means)*sample_csr.power(0)\n", "to_subtract=sparse.diags(row_means)*(sample_csr>0)\n",
"display(to_subtract.todense())\n", "display(to_subtract.todense())\n",
"\n", "\n",
"print(\"Finally after subtraction:\")\n", "print(\"Finally after subtraction:\")\n",
@ -573,15 +572,15 @@
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"TopPop=[]\n", "top_pop = []\n",
"train_iu = train_ui.transpose().tocsr()\n", "train_iu = train_ui.transpose().tocsr()\n",
"scaling_factor = train_ui.max()/max(np.diff(train_iu.indptr))\n", "scaling_factor = train_ui.max()/max(np.diff(train_iu.indptr))\n",
"\n", "\n",
"for i in range(train_iu.shape[0]):\n", "for i in range(train_iu.shape[0]):\n",
" TopPop.append((i, (train_iu.indptr[i+1]-train_iu.indptr[i])*scaling_factor))\n", " top_pop.append((i, (train_iu.indptr[i+1]-train_iu.indptr[i])*scaling_factor))\n",
" \n", " \n",
"TopPop.sort(key=lambda x: x[1], reverse=True)\n", "top_pop.sort(key=lambda x: x[1], reverse=True)\n",
"#TopPop is an array of pairs (item, rescaled_popularity) sorted descending from the most popular\n", "#top_pop is an array of pairs (item, rescaled_popularity) sorted descending from the most popular\n",
"\n", "\n",
"k = 10\n", "k = 10\n",
"result = []\n", "result = []\n",
@ -591,8 +590,8 @@
" rec_user = []\n", " rec_user = []\n",
" item_pos = 0\n", " item_pos = 0\n",
" while len(rec_user)<10:\n", " while len(rec_user)<10:\n",
" if TopPop[item_pos][0] not in user_rated:\n", " if top_pop[item_pos][0] not in user_rated:\n",
" rec_user.append((item_code_id[TopPop[item_pos][0]], TopPop[item_pos][1]))\n", " rec_user.append((item_code_id[top_pop[item_pos][0]], top_pop[item_pos][1]))\n",
" item_pos+=1\n", " item_pos+=1\n",
" result.append([user_code_id[u]]+list(chain(*rec_user)))\n", " result.append([user_code_id[u]]+list(chain(*rec_user)))\n",
"\n", "\n",
@ -613,7 +612,7 @@
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"# Self made global average" "# Self made top rated"
] ]
}, },
{ {
@ -622,11 +621,15 @@
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"GlobalAvg=[]\n", "top_rated = []\n",
"avg=np.sum(train_ui)/train_ui.nnz\n", "global_avg = sum(train_iu.data)/train_ui.nnz\n",
"\n", "\n",
"for i in range(train_iu.shape[0]):\n", "for i in range(train_iu.shape[0]):\n",
" GlobalAvg.append((i, avg))\n", " ratings = train_iu.data[train_iu.indptr[i]: train_iu.indptr[i+1]]\n",
" avg = np.mean(ratings) if len(ratings)>0 else global_avg\n",
" top_rated.append((i, avg))\n",
" \n",
"top_rated.sort(key=lambda x: x[1], reverse=True)\n",
" \n", " \n",
"k=10\n", "k=10\n",
"result=[]\n", "result=[]\n",
@ -636,21 +639,21 @@
" rec_user=[]\n", " rec_user=[]\n",
" item_pos=0\n", " item_pos=0\n",
" while len(rec_user)<10:\n", " while len(rec_user)<10:\n",
" if GlobalAvg[item_pos][0] not in user_rated:\n", " if top_rated[item_pos][0] not in user_rated:\n",
" rec_user.append((item_code_id[GlobalAvg[item_pos][0]], GlobalAvg[item_pos][1]))\n", " rec_user.append((item_code_id[top_rated[item_pos][0]], top_rated[item_pos][1]))\n",
" item_pos+=1\n", " item_pos+=1\n",
" result.append([user_code_id[u]]+list(chain(*rec_user)))\n", " result.append([user_code_id[u]]+list(chain(*rec_user)))\n",
"\n", "\n",
"(pd.DataFrame(result)).to_csv('Recommendations generated/ml-100k/Self_GlobalAvg_reco.csv', index=False, header=False)\n", "(pd.DataFrame(result)).to_csv('Recommendations generated/ml-100k/Self_TopRated_reco.csv', index=False, header=False)\n",
"\n", "\n",
"\n", "\n",
"# estimations - score is a bit artificial since that method is not designed for scoring, but for ranking\n",
"\n", "\n",
"estimations=[]\n", "estimations=[]\n",
"d = dict(top_rated)\n",
"\n", "\n",
"for user, item in zip(*test_ui.nonzero()):\n", "for user, item in zip(*test_ui.nonzero()):\n",
" estimations.append([user_code_id[user], item_code_id[item], avg])\n", " estimations.append([user_code_id[user], item_code_id[item], d[item]])\n",
"(pd.DataFrame(estimations)).to_csv('Recommendations generated/ml-100k/Self_GlobalAvg_estimations.csv', index=False, header=False)" "(pd.DataFrame(estimations)).to_csv('Recommendations generated/ml-100k/Self_TopRated_estimations.csv', index=False, header=False)"
] ]
}, },
{ {
@ -706,50 +709,50 @@
" <tr>\n", " <tr>\n",
" <th>0</th>\n", " <th>0</th>\n",
" <td>1</td>\n", " <td>1</td>\n",
" <td>5</td>\n", " <td>814</td>\n",
" <td>3.529975</td>\n", " <td>5.0</td>\n",
" <td>10</td>\n", " <td>1122</td>\n",
" <td>3.529975</td>\n", " <td>5.0</td>\n",
" <td>25</td>\n", " <td>1189</td>\n",
" <td>3.529975</td>\n", " <td>5.0</td>\n",
" <td>32</td>\n", " <td>1201</td>\n",
" <td>3.529975</td>\n", " <td>5.0</td>\n",
" <td>33</td>\n", " <td>1293</td>\n",
" <td>...</td>\n", " <td>...</td>\n",
" <td>44</td>\n", " <td>1306</td>\n",
" <td>3.529975</td>\n", " <td>5.0</td>\n",
" <td>46</td>\n", " <td>1467</td>\n",
" <td>3.529975</td>\n", " <td>5.0</td>\n",
" <td>50</td>\n", " <td>1491</td>\n",
" <td>3.529975</td>\n", " <td>5.0</td>\n",
" <td>52</td>\n", " <td>1500</td>\n",
" <td>3.529975</td>\n", " <td>5.0</td>\n",
" <td>55</td>\n", " <td>1536</td>\n",
" <td>3.529975</td>\n", " <td>5.0</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>1</th>\n", " <th>1</th>\n",
" <td>2</td>\n", " <td>2</td>\n",
" <td>1</td>\n", " <td>119</td>\n",
" <td>3.529975</td>\n", " <td>5.0</td>\n",
" <td>2</td>\n", " <td>814</td>\n",
" <td>3.529975</td>\n", " <td>5.0</td>\n",
" <td>3</td>\n", " <td>1122</td>\n",
" <td>3.529975</td>\n", " <td>5.0</td>\n",
" <td>4</td>\n", " <td>1189</td>\n",
" <td>3.529975</td>\n", " <td>5.0</td>\n",
" <td>5</td>\n", " <td>1201</td>\n",
" <td>...</td>\n", " <td>...</td>\n",
" <td>6</td>\n", " <td>1293</td>\n",
" <td>3.529975</td>\n", " <td>5.0</td>\n",
" <td>7</td>\n", " <td>1306</td>\n",
" <td>3.529975</td>\n", " <td>5.0</td>\n",
" <td>8</td>\n", " <td>1467</td>\n",
" <td>3.529975</td>\n", " <td>5.0</td>\n",
" <td>9</td>\n", " <td>1491</td>\n",
" <td>3.529975</td>\n", " <td>5.0</td>\n",
" <td>11</td>\n", " <td>1500</td>\n",
" <td>3.529975</td>\n", " <td>5.0</td>\n",
" </tr>\n", " </tr>\n",
" </tbody>\n", " </tbody>\n",
"</table>\n", "</table>\n",
@ -757,13 +760,13 @@
"</div>" "</div>"
], ],
"text/plain": [ "text/plain": [
" 0 1 2 3 4 5 6 7 8 9 ... 11 \\\n", " 0 1 2 3 4 5 6 7 8 9 ... 11 12 13 \\\n",
"0 1 5 3.529975 10 3.529975 25 3.529975 32 3.529975 33 ... 44 \n", "0 1 814 5.0 1122 5.0 1189 5.0 1201 5.0 1293 ... 1306 5.0 1467 \n",
"1 2 1 3.529975 2 3.529975 3 3.529975 4 3.529975 5 ... 6 \n", "1 2 119 5.0 814 5.0 1122 5.0 1189 5.0 1201 ... 1293 5.0 1306 \n",
"\n", "\n",
" 12 13 14 15 16 17 18 19 20 \n", " 14 15 16 17 18 19 20 \n",
"0 3.529975 46 3.529975 50 3.529975 52 3.529975 55 3.529975 \n", "0 5.0 1491 5.0 1500 5.0 1536 5.0 \n",
"1 3.529975 7 3.529975 8 3.529975 9 3.529975 11 3.529975 \n", "1 5.0 1467 5.0 1491 5.0 1500 5.0 \n",
"\n", "\n",
"[2 rows x 21 columns]" "[2 rows x 21 columns]"
] ]
@ -777,25 +780,6 @@
"pd.DataFrame(result)[:2]" "pd.DataFrame(result)[:2]"
] ]
}, },
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Project task 1 - self made top rated"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {},
"outputs": [],
"source": [
"# project task 1: implement TopRated\n",
"# Implement recommender system which will recommend movies (which user hasn't seen) with the highest average rating\n",
"# The output should be saved in 'Recommendations generated/ml-100k/Self_TopRated_reco.csv'\n",
"# and 'Recommendations generated/ml-100k/Self_TopRated_estimations.csv'"
]
},
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
@ -805,7 +789,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 19, "execution_count": 18,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -825,7 +809,7 @@
" \n", " \n",
" max_row_mean=np.max(row_means)\n", " max_row_mean=np.max(row_means)\n",
" row_means[row_means==0]=max_row_mean+1\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=sparse.diags(row_means)*(result>0)\n",
" to_subtract_rows.sort_indices() # needed to have valid .data\n", " to_subtract_rows.sort_indices() # needed to have valid .data\n",
" \n", " \n",
" subtract=to_subtract_rows.data\n", " subtract=to_subtract_rows.data\n",
@ -878,7 +862,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 20, "execution_count": 19,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -1046,7 +1030,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 21, "execution_count": 20,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1065,17 +1049,17 @@
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"# project task 2: implement self-made BaselineIU" "# project task 1: implement self-made BaselineIU"
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 22, "execution_count": 21,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"# Implement recommender system which will recommend movies (which user hasn't seen) which is similar to BaselineUI\n", "# Implement recommender system which will recommend movies (which user hasn't seen) which is similar to BaselineUI\n",
"# but first subtract col means then row means\n", "# but first subtract column means then row means\n",
"# The output should be saved in 'Recommendations generated/ml-100k/Self_BaselineIU_reco.csv'\n", "# The output should be saved in 'Recommendations generated/ml-100k/Self_BaselineIU_reco.csv'\n",
"# and 'Recommendations generated/ml-100k/Self_BaselineIU_estimations.csv'" "# and 'Recommendations generated/ml-100k/Self_BaselineIU_estimations.csv'"
] ]
@ -1089,7 +1073,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 23, "execution_count": 22,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -1146,7 +1130,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 24, "execution_count": 23,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -1163,7 +1147,7 @@
"0.7524871012820799" "0.7524871012820799"
] ]
}, },
"execution_count": 24, "execution_count": 23,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -1193,24 +1177,24 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 25, "execution_count": 24,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
"name": "stdout", "name": "stdout",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"RMSE: 1.5317\n", "RMSE: 1.5147\n",
"MAE: 1.2304\n" "MAE: 1.2155\n"
] ]
}, },
{ {
"data": { "data": {
"text/plain": [ "text/plain": [
"1.2303840461147084" "1.2154990549993152"
] ]
}, },
"execution_count": 25, "execution_count": 24,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }

BIN
P1. Introduction and baseline.pdf
View File

Binary file not shown.

504
P2. Evaluation.ipynb
View File

@ -273,7 +273,7 @@
"name": "stderr", "name": "stderr",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"943it [00:00, 7666.87it/s]\n" "943it [00:00, 6497.15it/s]\n"
] ]
}, },
{ {
@ -477,7 +477,7 @@
"name": "stderr", "name": "stderr",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"943it [00:00, 7370.69it/s]\n" "943it [00:00, 5143.71it/s]\n"
] ]
}, },
{ {
@ -585,11 +585,11 @@
"name": "stderr", "name": "stderr",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"943it [00:00, 7772.74it/s]\n", "943it [00:00, 3573.64it/s]\n",
"943it [00:00, 5607.69it/s]\n", "943it [00:00, 5141.54it/s]\n",
"943it [00:00, 4737.64it/s]\n", "943it [00:00, 2827.19it/s]\n",
"943it [00:00, 4986.41it/s]\n", "943it [00:00, 2513.13it/s]\n",
"943it [00:00, 3513.77it/s]\n" "943it [00:00, 3555.67it/s]\n"
] ]
} }
], ],
@ -670,27 +670,27 @@
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>0</th>\n", " <th>0</th>\n",
" <td>Self_GlobalAvg</td>\n", " <td>Ready_Random</td>\n",
" <td>1.125760</td>\n", " <td>1.525959</td>\n",
" <td>0.943534</td>\n", " <td>1.225122</td>\n",
" <td>0.061188</td>\n", " <td>0.047402</td>\n",
" <td>0.025968</td>\n", " <td>0.020629</td>\n",
" <td>0.031383</td>\n", " <td>0.024471</td>\n",
" <td>0.041343</td>\n", " <td>0.032042</td>\n",
" <td>0.040558</td>\n", " <td>0.027682</td>\n",
" <td>0.032107</td>\n", " <td>0.019353</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>0</th>\n", " <th>0</th>\n",
" <td>Ready_Random</td>\n", " <td>Self_TopRated</td>\n",
" <td>1.531724</td>\n", " <td>1.030712</td>\n",
" <td>1.230384</td>\n", " <td>0.820904</td>\n",
" <td>0.049417</td>\n", " <td>0.000954</td>\n",
" <td>0.022558</td>\n", " <td>0.000188</td>\n",
" <td>0.025490</td>\n", " <td>0.000298</td>\n",
" <td>0.033242</td>\n", " <td>0.000481</td>\n",
" <td>0.030365</td>\n", " <td>0.000644</td>\n",
" <td>0.022626</td>\n", " <td>0.000223</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>0</th>\n", " <th>0</th>\n",
@ -712,15 +712,15 @@
" Model RMSE MAE precision recall F_1 \\\n", " Model RMSE MAE precision recall F_1 \\\n",
"0 Self_TopPop 2.508258 2.217909 0.188865 0.116919 0.118732 \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_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 1.525959 1.225122 0.047402 0.020629 0.024471 \n",
"0 Ready_Random 1.531724 1.230384 0.049417 0.022558 0.025490 \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_BaselineUI 0.967585 0.762740 0.000954 0.000170 0.000278 \n",
"\n", "\n",
" F_05 precision_super recall_super \n", " F_05 precision_super recall_super \n",
"0 0.141584 0.130472 0.137473 \n", "0 0.141584 0.130472 0.137473 \n",
"0 0.061286 0.079614 0.056463 \n", "0 0.061286 0.079614 0.056463 \n",
"0 0.041343 0.040558 0.032107 \n", "0 0.032042 0.027682 0.019353 \n",
"0 0.033242 0.030365 0.022626 \n", "0 0.000481 0.000644 0.000223 \n",
"0 0.000463 0.000644 0.000189 " "0 0.000463 0.000644 0.000189 "
] ]
}, },
@ -800,29 +800,29 @@
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>0</th>\n", " <th>0</th>\n",
" <td>Self_GlobalAvg</td>\n", " <td>Ready_Random</td>\n",
" <td>0.067695</td>\n", " <td>0.051593</td>\n",
" <td>0.027470</td>\n", " <td>0.019428</td>\n",
" <td>0.171187</td>\n", " <td>0.129062</td>\n",
" <td>0.509546</td>\n", " <td>0.506826</td>\n",
" <td>0.384942</td>\n", " <td>0.336161</td>\n",
" <td>1.000000</td>\n", " <td>0.987593</td>\n",
" <td>0.025974</td>\n", " <td>0.175325</td>\n",
" <td>2.711772</td>\n", " <td>5.087656</td>\n",
" <td>0.992003</td>\n", " <td>0.908118</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>0</th>\n", " <th>0</th>\n",
" <td>Ready_Random</td>\n", " <td>Self_TopRated</td>\n",
" <td>0.054166</td>\n", " <td>0.001043</td>\n",
" <td>0.021656</td>\n", " <td>0.000335</td>\n",
" <td>0.128378</td>\n", " <td>0.003348</td>\n",
" <td>0.507802</td>\n", " <td>0.496433</td>\n",
" <td>0.325557</td>\n", " <td>0.009544</td>\n",
" <td>0.988865</td>\n", " <td>0.699046</td>\n",
" <td>0.190476</td>\n", " <td>0.005051</td>\n",
" <td>5.100033</td>\n", " <td>1.945910</td>\n",
" <td>0.907724</td>\n", " <td>0.995669</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>0</th>\n", " <th>0</th>\n",
@ -845,15 +845,15 @@
" Model NDCG mAP MRR LAUC HR \\\n", " Model NDCG mAP MRR LAUC HR \\\n",
"0 Self_TopPop 0.214651 0.111707 0.400939 0.555546 0.765642 \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_Baseline 0.095957 0.043178 0.198193 0.515501 0.437964 \n",
"0 Self_GlobalAvg 0.067695 0.027470 0.171187 0.509546 0.384942 \n", "0 Ready_Random 0.051593 0.019428 0.129062 0.506826 0.336161 \n",
"0 Ready_Random 0.054166 0.021656 0.128378 0.507802 0.325557 \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_BaselineUI 0.000752 0.000168 0.001677 0.496424 0.009544 \n",
"\n", "\n",
" Reco in test Test coverage Shannon Gini \n", " Reco in test Test coverage Shannon Gini \n",
"0 1.000000 0.038961 3.159079 0.987317 \n", "0 1.000000 0.038961 3.159079 0.987317 \n",
"0 1.000000 0.033911 2.836513 0.991139 \n", "0 1.000000 0.033911 2.836513 0.991139 \n",
"0 1.000000 0.025974 2.711772 0.992003 \n", "0 0.987593 0.175325 5.087656 0.908118 \n",
"0 0.988865 0.190476 5.100033 0.907724 \n", "0 0.699046 0.005051 1.945910 0.995669 \n",
"0 0.600530 0.005051 1.803126 0.996380 " "0 0.600530 0.005051 1.803126 0.996380 "
] ]
}, },
@ -882,7 +882,7 @@
"name": "stderr", "name": "stderr",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"3it [00:00, 1941.81it/s]\n" "3it [00:00, 1191.68it/s]\n"
] ]
}, },
{ {
@ -1246,109 +1246,109 @@
" </thead>\n", " </thead>\n",
" <tbody>\n", " <tbody>\n",
" <tr>\n", " <tr>\n",
" <th>2985</th>\n", " <th>50941</th>\n",
" <td>789</td>\n", " <td>661</td>\n",
" <td>5</td>\n", " <td>5</td>\n",
" <td>Star Wars (1977)</td>\n", " <td>It's a Wonderful Life (1946)</td>\n",
" <td>Action, Adventure, Romance, Sci-Fi, War</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25980</th>\n",
" <td>789</td>\n",
" <td>5</td>\n",
" <td>Dead Man Walking (1995)</td>\n",
" <td>Drama</td>\n", " <td>Drama</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>9357</th>\n", " <th>9531</th>\n",
" <td>789</td>\n", " <td>661</td>\n",
" <td>5</td>\n", " <td>5</td>\n",
" <td>Last Supper, The (1995)</td>\n", " <td>Wizard of Oz, The (1939)</td>\n",
" <td>Drama, Thriller</td>\n", " <td>Adventure, Children's, Drama, Musical</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>17306</th>\n", " <th>27182</th>\n",
" <td>789</td>\n", " <td>661</td>\n",
" <td>5</td>\n", " <td>5</td>\n",
" <td>Leaving Las Vegas (1995)</td>\n", " <td>Empire Strikes Back, The (1980)</td>\n",
" <td>Drama, Romance</td>\n", " <td>Action, Adventure, Drama, Romance, Sci-Fi, War</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>36474</th>\n", " <th>23944</th>\n",
" <td>789</td>\n", " <td>661</td>\n",
" <td>5</td>\n", " <td>5</td>\n",
" <td>Swingers (1996)</td>\n", " <td>Apocalypse Now (1979)</td>\n",
" <td>Comedy, Drama</td>\n", " <td>Drama, War</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>65139</th>\n", " <th>20285</th>\n",
" <td>789</td>\n", " <td>661</td>\n",
" <td>4</td>\n", " <td>5</td>\n",
" <td>Welcome to the Dollhouse (1995)</td>\n",
" <td>Comedy, Drama</td>\n",
" </tr>\n",
" <tr>\n",
" <th>61975</th>\n",
" <td>789</td>\n",
" <td>4</td>\n",
" <td>Private Parts (1997)</td>\n",
" <td>Comedy, Drama</td>\n",
" </tr>\n",
" <tr>\n",
" <th>56522</th>\n",
" <td>789</td>\n",
" <td>4</td>\n",
" <td>Waiting for Guffman (1996)</td>\n",
" <td>Comedy</td>\n",
" </tr>\n",
" <tr>\n",
" <th>41414</th>\n",
" <td>789</td>\n",
" <td>4</td>\n",
" <td>Donnie Brasco (1997)</td>\n",
" <td>Crime, Drama</td>\n",
" </tr>\n",
" <tr>\n",
" <th>36617</th>\n",
" <td>789</td>\n",
" <td>4</td>\n",
" <td>Lone Star (1996)</td>\n",
" <td>Drama, Mystery</td>\n",
" </tr>\n",
" <tr>\n",
" <th>24501</th>\n",
" <td>789</td>\n",
" <td>4</td>\n",
" <td>People vs. Larry Flynt, The (1996)</td>\n",
" <td>Drama</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20210</th>\n",
" <td>789</td>\n",
" <td>4</td>\n",
" <td>Return of the Jedi (1983)</td>\n", " <td>Return of the Jedi (1983)</td>\n",
" <td>Action, Adventure, Romance, Sci-Fi, War</td>\n", " <td>Action, Adventure, Romance, Sci-Fi, War</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>8230</th>\n", " <th>37504</th>\n",
" <td>789</td>\n", " <td>661</td>\n",
" <td>3</td>\n", " <td>5</td>\n",
" <td>Beautiful Girls (1996)</td>\n", " <td>Aladdin (1992)</td>\n",
" <td>Animation, Children's, Comedy, Musical</td>\n",
" </tr>\n",
" <tr>\n",
" <th>68312</th>\n",
" <td>661</td>\n",
" <td>5</td>\n",
" <td>Babe (1995)</td>\n",
" <td>Children's, Comedy, Drama</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16362</th>\n",
" <td>661</td>\n",
" <td>5</td>\n",
" <td>Apollo 13 (1995)</td>\n",
" <td>Action, Drama, Thriller</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15168</th>\n",
" <td>661</td>\n",
" <td>5</td>\n",
" <td>Indiana Jones and the Last Crusade (1989)</td>\n",
" <td>Action, Adventure</td>\n",
" </tr>\n",
" <tr>\n",
" <th>29402</th>\n",
" <td>661</td>\n",
" <td>5</td>\n",
" <td>Psycho (1960)</td>\n",
" <td>Horror, Romance, Thriller</td>\n",
" </tr>\n",
" <tr>\n",
" <th>40755</th>\n",
" <td>661</td>\n",
" <td>5</td>\n",
" <td>Jean de Florette (1986)</td>\n",
" <td>Drama</td>\n", " <td>Drama</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>19781</th>\n", " <th>41950</th>\n",
" <td>789</td>\n", " <td>661</td>\n",
" <td>3</td>\n", " <td>5</td>\n",
" <td>Liar Liar (1997)</td>\n", " <td>Die Hard (1988)</td>\n",
" <td>Comedy</td>\n", " <td>Action, Thriller</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>39387</th>\n", " <th>58932</th>\n",
" <td>789</td>\n", " <td>661</td>\n",
" <td>3</td>\n", " <td>5</td>\n",
" <td>Sleepers (1996)</td>\n", " <td>Enchanted April (1991)</td>\n",
" <td>Crime, Drama</td>\n", " <td>Drama</td>\n",
" </tr>\n",
" <tr>\n",
" <th>43013</th>\n",
" <td>661</td>\n",
" <td>5</td>\n",
" <td>2001: A Space Odyssey (1968)</td>\n",
" <td>Drama, Mystery, Sci-Fi, Thriller</td>\n",
" </tr>\n",
" <tr>\n",
" <th>65664</th>\n",
" <td>661</td>\n",
" <td>5</td>\n",
" <td>Star Trek: The Wrath of Khan (1982)</td>\n",
" <td>Action, Adventure, Sci-Fi</td>\n",
" </tr>\n", " </tr>\n",
" </tbody>\n", " </tbody>\n",
"</table>\n", "</table>\n",
@ -1356,38 +1356,38 @@
], ],
"text/plain": [ "text/plain": [
" user rating title \\\n", " user rating title \\\n",
"2985 789 5 Star Wars (1977) \n", "50941 661 5 It's a Wonderful Life (1946) \n",
"25980 789 5 Dead Man Walking (1995) \n", "9531 661 5 Wizard of Oz, The (1939) \n",
"9357 789 5 Last Supper, The (1995) \n", "27182 661 5 Empire Strikes Back, The (1980) \n",
"17306 789 5 Leaving Las Vegas (1995) \n", "23944 661 5 Apocalypse Now (1979) \n",
"36474 789 5 Swingers (1996) \n", "20285 661 5 Return of the Jedi (1983) \n",
"65139 789 4 Welcome to the Dollhouse (1995) \n", "37504 661 5 Aladdin (1992) \n",
"61975 789 4 Private Parts (1997) \n", "68312 661 5 Babe (1995) \n",
"56522 789 4 Waiting for Guffman (1996) \n", "16362 661 5 Apollo 13 (1995) \n",
"41414 789 4 Donnie Brasco (1997) \n", "15168 661 5 Indiana Jones and the Last Crusade (1989) \n",
"36617 789 4 Lone Star (1996) \n", "29402 661 5 Psycho (1960) \n",
"24501 789 4 People vs. Larry Flynt, The (1996) \n", "40755 661 5 Jean de Florette (1986) \n",
"20210 789 4 Return of the Jedi (1983) \n", "41950 661 5 Die Hard (1988) \n",
"8230 789 3 Beautiful Girls (1996) \n", "58932 661 5 Enchanted April (1991) \n",
"19781 789 3 Liar Liar (1997) \n", "43013 661 5 2001: A Space Odyssey (1968) \n",
"39387 789 3 Sleepers (1996) \n", "65664 661 5 Star Trek: The Wrath of Khan (1982) \n",
"\n", "\n",
" genres \n", " genres \n",
"2985 Action, Adventure, Romance, Sci-Fi, War \n", "50941 Drama \n",
"25980 Drama \n", "9531 Adventure, Children's, Drama, Musical \n",
"9357 Drama, Thriller \n", "27182 Action, Adventure, Drama, Romance, Sci-Fi, War \n",
"17306 Drama, Romance \n", "23944 Drama, War \n",
"36474 Comedy, Drama \n", "20285 Action, Adventure, Romance, Sci-Fi, War \n",
"65139 Comedy, Drama \n", "37504 Animation, Children's, Comedy, Musical \n",
"61975 Comedy, Drama \n", "68312 Children's, Comedy, Drama \n",
"56522 Comedy \n", "16362 Action, Drama, Thriller \n",
"41414 Crime, Drama \n", "15168 Action, Adventure \n",
"36617 Drama, Mystery \n", "29402 Horror, Romance, Thriller \n",
"24501 Drama \n", "40755 Drama \n",
"20210 Action, Adventure, Romance, Sci-Fi, War \n", "41950 Action, Thriller \n",
"8230 Drama \n", "58932 Drama \n",
"19781 Comedy \n", "43013 Drama, Mystery, Sci-Fi, Thriller \n",
"39387 Crime, Drama " "65664 Action, Adventure, Sci-Fi "
] ]
}, },
"metadata": {}, "metadata": {},
@ -1429,71 +1429,71 @@
" </thead>\n", " </thead>\n",
" <tbody>\n", " <tbody>\n",
" <tr>\n", " <tr>\n",
" <th>787</th>\n", " <th>659</th>\n",
" <td>789.0</td>\n", " <td>661.0</td>\n",
" <td>1</td>\n", " <td>1</td>\n",
" <td>Great Day in Harlem, A (1994)</td>\n", " <td>Great Day in Harlem, A (1994)</td>\n",
" <td>Documentary</td>\n", " <td>Documentary</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>1729</th>\n", " <th>1601</th>\n",
" <td>789.0</td>\n", " <td>661.0</td>\n",
" <td>2</td>\n", " <td>2</td>\n",
" <td>Tough and Deadly (1995)</td>\n", " <td>Tough and Deadly (1995)</td>\n",
" <td>Action, Drama, Thriller</td>\n", " <td>Action, Drama, Thriller</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>2671</th>\n", " <th>2543</th>\n",
" <td>789.0</td>\n", " <td>661.0</td>\n",
" <td>3</td>\n", " <td>3</td>\n",
" <td>Aiqing wansui (1994)</td>\n", " <td>Aiqing wansui (1994)</td>\n",
" <td>Drama</td>\n", " <td>Drama</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>3613</th>\n", " <th>3485</th>\n",
" <td>789.0</td>\n", " <td>661.0</td>\n",
" <td>4</td>\n", " <td>4</td>\n",
" <td>Delta of Venus (1994)</td>\n", " <td>Delta of Venus (1994)</td>\n",
" <td>Drama</td>\n", " <td>Drama</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>4555</th>\n", " <th>4427</th>\n",
" <td>789.0</td>\n", " <td>661.0</td>\n",
" <td>5</td>\n", " <td>5</td>\n",
" <td>Someone Else's America (1995)</td>\n", " <td>Someone Else's America (1995)</td>\n",
" <td>Drama</td>\n", " <td>Drama</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>5497</th>\n", " <th>5369</th>\n",
" <td>789.0</td>\n", " <td>661.0</td>\n",
" <td>6</td>\n", " <td>6</td>\n",
" <td>Saint of Fort Washington, The (1993)</td>\n", " <td>Saint of Fort Washington, The (1993)</td>\n",
" <td>Drama</td>\n", " <td>Drama</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>6439</th>\n", " <th>6311</th>\n",
" <td>789.0</td>\n", " <td>661.0</td>\n",
" <td>7</td>\n", " <td>7</td>\n",
" <td>Celestial Clockwork (1994)</td>\n", " <td>Celestial Clockwork (1994)</td>\n",
" <td>Comedy</td>\n", " <td>Comedy</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>7380</th>\n", " <th>7253</th>\n",
" <td>789.0</td>\n", " <td>661.0</td>\n",
" <td>8</td>\n", " <td>8</td>\n",
" <td>Some Mother's Son (1996)</td>\n", " <td>Some Mother's Son (1996)</td>\n",
" <td>Drama</td>\n", " <td>Drama</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>9276</th>\n", " <th>9148</th>\n",
" <td>789.0</td>\n", " <td>661.0</td>\n",
" <td>9</td>\n", " <td>9</td>\n",
" <td>Maya Lin: A Strong Clear Vision (1994)</td>\n", " <td>Maya Lin: A Strong Clear Vision (1994)</td>\n",
" <td>Documentary</td>\n", " <td>Documentary</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>8322</th>\n", " <th>8194</th>\n",
" <td>789.0</td>\n", " <td>661.0</td>\n",
" <td>10</td>\n", " <td>10</td>\n",
" <td>Prefontaine (1997)</td>\n", " <td>Prefontaine (1997)</td>\n",
" <td>Drama</td>\n", " <td>Drama</td>\n",
@ -1504,28 +1504,28 @@
], ],
"text/plain": [ "text/plain": [
" user rec_nb title \\\n", " user rec_nb title \\\n",
"787 789.0 1 Great Day in Harlem, A (1994) \n", "659 661.0 1 Great Day in Harlem, A (1994) \n",
"1729 789.0 2 Tough and Deadly (1995) \n", "1601 661.0 2 Tough and Deadly (1995) \n",
"2671 789.0 3 Aiqing wansui (1994) \n", "2543 661.0 3 Aiqing wansui (1994) \n",
"3613 789.0 4 Delta of Venus (1994) \n", "3485 661.0 4 Delta of Venus (1994) \n",
"4555 789.0 5 Someone Else's America (1995) \n", "4427 661.0 5 Someone Else's America (1995) \n",
"5497 789.0 6 Saint of Fort Washington, The (1993) \n", "5369 661.0 6 Saint of Fort Washington, The (1993) \n",
"6439 789.0 7 Celestial Clockwork (1994) \n", "6311 661.0 7 Celestial Clockwork (1994) \n",
"7380 789.0 8 Some Mother's Son (1996) \n", "7253 661.0 8 Some Mother's Son (1996) \n",
"9276 789.0 9 Maya Lin: A Strong Clear Vision (1994) \n", "9148 661.0 9 Maya Lin: A Strong Clear Vision (1994) \n",
"8322 789.0 10 Prefontaine (1997) \n", "8194 661.0 10 Prefontaine (1997) \n",
"\n", "\n",
" genres \n", " genres \n",
"787 Documentary \n", "659 Documentary \n",
"1729 Action, Drama, Thriller \n", "1601 Action, Drama, Thriller \n",
"2671 Drama \n", "2543 Drama \n",
"3613 Drama \n", "3485 Drama \n",
"4555 Drama \n", "4427 Drama \n",
"5497 Drama \n", "5369 Drama \n",
"6439 Comedy \n", "6311 Comedy \n",
"7380 Drama \n", "7253 Drama \n",
"9276 Documentary \n", "9148 Documentary \n",
"8322 Drama " "8194 Drama "
] ]
}, },
"execution_count": 15, "execution_count": 15,
@ -1595,11 +1595,11 @@
"name": "stderr", "name": "stderr",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"943it [00:00, 4479.94it/s]\n", "943it [00:00, 4220.01it/s]\n",
"943it [00:00, 4036.40it/s]\n", "943it [00:00, 3015.35it/s]\n",
"943it [00:00, 4598.99it/s]\n", "943it [00:00, 2308.31it/s]\n",
"943it [00:00, 5170.18it/s]\n", "943it [00:00, 3461.11it/s]\n",
"943it [00:00, 4778.23it/s]\n" "943it [00:00, 3442.41it/s]\n"
] ]
}, },
{ {
@ -1688,45 +1688,45 @@
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>0</th>\n", " <th>0</th>\n",
" <td>Self_GlobalAvg</td>\n", " <td>Ready_Random</td>\n",
" <td>1.125760</td>\n", " <td>1.525959</td>\n",
" <td>0.943534</td>\n", " <td>1.225122</td>\n",
" <td>0.061188</td>\n", " <td>0.047402</td>\n",
" <td>0.025968</td>\n", " <td>0.020629</td>\n",
" <td>0.031383</td>\n", " <td>0.024471</td>\n",
" <td>0.041343</td>\n", " <td>0.032042</td>\n",
" <td>0.040558</td>\n", " <td>0.027682</td>\n",
" <td>0.032107</td>\n", " <td>0.019353</td>\n",
" <td>0.067695</td>\n", " <td>0.051593</td>\n",
" <td>0.027470</td>\n", " <td>0.019428</td>\n",
" <td>0.171187</td>\n", " <td>0.129062</td>\n",
" <td>0.509546</td>\n", " <td>0.506826</td>\n",
" <td>0.384942</td>\n", " <td>0.336161</td>\n",
" <td>1.000000</td>\n", " <td>0.987593</td>\n",
" <td>0.025974</td>\n", " <td>0.175325</td>\n",
" <td>2.711772</td>\n", " <td>5.087656</td>\n",
" <td>0.992003</td>\n", " <td>0.908118</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>0</th>\n", " <th>0</th>\n",
" <td>Ready_Random</td>\n", " <td>Self_TopRated</td>\n",
" <td>1.531724</td>\n", " <td>1.030712</td>\n",
" <td>1.230384</td>\n", " <td>0.820904</td>\n",
" <td>0.049417</td>\n", " <td>0.000954</td>\n",
" <td>0.022558</td>\n", " <td>0.000188</td>\n",
" <td>0.025490</td>\n", " <td>0.000298</td>\n",
" <td>0.033242</td>\n", " <td>0.000481</td>\n",
" <td>0.030365</td>\n", " <td>0.000644</td>\n",
" <td>0.022626</td>\n", " <td>0.000223</td>\n",
" <td>0.054166</td>\n", " <td>0.001043</td>\n",
" <td>0.021656</td>\n", " <td>0.000335</td>\n",
" <td>0.128378</td>\n", " <td>0.003348</td>\n",
" <td>0.507802</td>\n", " <td>0.496433</td>\n",
" <td>0.325557</td>\n", " <td>0.009544</td>\n",
" <td>0.988865</td>\n", " <td>0.699046</td>\n",
" <td>0.190476</td>\n", " <td>0.005051</td>\n",
" <td>5.100033</td>\n", " <td>1.945910</td>\n",
" <td>0.907724</td>\n", " <td>0.995669</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>0</th>\n", " <th>0</th>\n",
@ -1757,22 +1757,22 @@
" Model RMSE MAE precision recall F_1 \\\n", " Model RMSE MAE precision recall F_1 \\\n",
"0 Self_TopPop 2.508258 2.217909 0.188865 0.116919 0.118732 \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_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 1.525959 1.225122 0.047402 0.020629 0.024471 \n",
"0 Ready_Random 1.531724 1.230384 0.049417 0.022558 0.025490 \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_BaselineUI 0.967585 0.762740 0.000954 0.000170 0.000278 \n",
"\n", "\n",
" F_05 precision_super recall_super NDCG mAP MRR \\\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 0.141584 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 0.061286 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 0.032042 0.027682 0.019353 0.051593 0.019428 0.129062 \n",
"0 0.033242 0.030365 0.022626 0.054166 0.021656 0.128378 \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 0.000463 0.000644 0.000189 0.000752 0.000168 0.001677 \n",
"\n", "\n",
" LAUC HR Reco in test Test coverage Shannon Gini \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 0.555546 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 0.515501 0.437964 1.000000 0.033911 2.836513 0.991139 \n",
"0 0.509546 0.384942 1.000000 0.025974 2.711772 0.992003 \n", "0 0.506826 0.336161 0.987593 0.175325 5.087656 0.908118 \n",
"0 0.507802 0.325557 0.988865 0.190476 5.100033 0.907724 \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 " "0 0.496424 0.009544 0.600530 0.005051 1.803126 0.996380 "
] ]
}, },

BIN
P2. Evaluation.pdf
View File

Binary file not shown.