s406917/workshops_recommender_systems
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Changes in slides

Browse Source
This commit is contained in:
Robert 2020-05-21 22:53:34 +02:00
parent 8ad2469287
commit 45e88a01aa
15 changed files with 102481 additions and 102950 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

528
P0. Data preparation.ipynb
View File

File diff suppressed because one or more lines are too long

70
P1. Baseline.ipynb
View File

@ -195,7 +195,7 @@
{ {
"data": { "data": {
"text/plain": [ "text/plain": [
"<3x4 sparse matrix of type '<class 'numpy.int64'>'\n", "<3x4 sparse matrix of type '<class 'numpy.longlong'>'\n",
"\twith 8 stored elements in Compressed Sparse Row format>" "\twith 8 stored elements in Compressed Sparse Row format>"
] ]
}, },
@ -307,7 +307,7 @@
"name": "stdout", "name": "stdout",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"472 ns ± 7.02 ns per loop (mean ± std. dev. of 7 runs, 1000000 loops each)\n", "1.03 µs ± 114 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 +325,7 @@
"name": "stdout", "name": "stdout",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"57.3 µs ± 6.26 µs per loop (mean ± std. dev. of 7 runs, 10000 loops each)\n" "132 µs ± 5.13 µs per loop (mean ± std. dev. of 7 runs, 10000 loops each)\n"
] ]
} }
], ],
@ -411,7 +411,7 @@
{ {
"data": { "data": {
"text/plain": [ "text/plain": [
"array([ 2.66666667, 1.5 , 3.66666667])" "array([2.66666667, 1.5 , 3.66666667])"
] ]
}, },
"metadata": {}, "metadata": {},
@ -427,9 +427,9 @@
{ {
"data": { "data": {
"text/plain": [ "text/plain": [
"matrix([[ 2.66666667, 0. , 0. ],\n", "matrix([[2.66666667, 0. , 0. ],\n",
" [ 0. , 1.5 , 0. ],\n", " [0. , 1.5 , 0. ],\n",
" [ 0. , 0. , 3.66666667]])" " [0. , 0. , 3.66666667]])"
] ]
}, },
"metadata": {}, "metadata": {},
@ -445,9 +445,9 @@
{ {
"data": { "data": {
"text/plain": [ "text/plain": [
"matrix([[ 2.66666667, 2.66666667, 2.66666667, 0. ],\n", "matrix([[2.66666667, 2.66666667, 2.66666667, 0. ],\n",
" [ 0. , 1.5 , 0. , 1.5 ],\n", " [0. , 1.5 , 0. , 1.5 ],\n",
" [ 3.66666667, 0. , 3.66666667, 3.66666667]])" " [3.66666667, 0. , 3.66666667, 3.66666667]])"
] ]
}, },
"metadata": {}, "metadata": {},
@ -556,7 +556,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 21, "execution_count": 14,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -569,7 +569,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 22, "execution_count": 15,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -618,7 +618,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 23, "execution_count": 16,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -655,7 +655,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 24, "execution_count": 17,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -757,18 +757,18 @@
"</div>" "</div>"
], ],
"text/plain": [ "text/plain": [
" 0 1 2 3 4 5 6 7 8 9 ... \\\n", " 0 1 2 3 4 5 6 7 8 9 ... 11 \\\n",
"0 1 5 3.529975 10 3.529975 25 3.529975 32 3.529975 33 ... \n", "0 1 5 3.529975 10 3.529975 25 3.529975 32 3.529975 33 ... 44 \n",
"1 2 1 3.529975 2 3.529975 3 3.529975 4 3.529975 5 ... \n", "1 2 1 3.529975 2 3.529975 3 3.529975 4 3.529975 5 ... 6 \n",
"\n", "\n",
" 11 12 13 14 15 16 17 18 19 20 \n", " 12 13 14 15 16 17 18 19 20 \n",
"0 44 3.529975 46 3.529975 50 3.529975 52 3.529975 55 3.529975 \n", "0 3.529975 46 3.529975 50 3.529975 52 3.529975 55 3.529975 \n",
"1 6 3.529975 7 3.529975 8 3.529975 9 3.529975 11 3.529975 \n", "1 3.529975 7 3.529975 8 3.529975 9 3.529975 11 3.529975 \n",
"\n", "\n",
"[2 rows x 21 columns]" "[2 rows x 21 columns]"
] ]
}, },
"execution_count": 24, "execution_count": 17,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -786,7 +786,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 25, "execution_count": 18,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -805,7 +805,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 26, "execution_count": 19,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -878,7 +878,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 27, "execution_count": 20,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -1046,7 +1046,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 28, "execution_count": 21,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1070,7 +1070,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 29, "execution_count": 22,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1089,7 +1089,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 30, "execution_count": 23,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -1146,7 +1146,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 31, "execution_count": 24,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -1160,10 +1160,10 @@
{ {
"data": { "data": {
"text/plain": [ "text/plain": [
"0.75248710128207985" "0.7524871012820799"
] ]
}, },
"execution_count": 31, "execution_count": 24,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -1193,24 +1193,24 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 32, "execution_count": 25,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
"name": "stdout", "name": "stdout",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"RMSE: 1.5190\n", "RMSE: 1.5070\n",
"MAE: 1.2222\n" "MAE: 1.2072\n"
] ]
}, },
{ {
"data": { "data": {
"text/plain": [ "text/plain": [
"1.222159317007133" "1.2071684732991073"
] ]
}, },
"execution_count": 32, "execution_count": 25,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }

BIN
P1. Introduction and baseline.pdf
View File

Binary file not shown.

410
P2. Evaluation.ipynb
View File

@ -273,7 +273,7 @@
"name": "stderr", "name": "stderr",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"943it [00:00, 9409.37it/s]\n" "943it [00:00, 6311.05it/s]\n"
] ]
}, },
{ {
@ -398,7 +398,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 14, "execution_count": 9,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -445,7 +445,7 @@
"0 1.0 0.033911 2.836513 0.991139" "0 1.0 0.033911 2.836513 0.991139"
] ]
}, },
"execution_count": 14, "execution_count": 9,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -470,14 +470,14 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 15, "execution_count": 10,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
"name": "stderr", "name": "stderr",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"943it [00:00, 8290.29it/s]\n" "943it [00:00, 7479.62it/s]\n"
] ]
}, },
{ {
@ -556,7 +556,7 @@
"0 0.437964 1.0 0.033911 2.836513 0.991139 " "0 0.437964 1.0 0.033911 2.836513 0.991139 "
] ]
}, },
"execution_count": 15, "execution_count": 10,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -578,18 +578,18 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 16, "execution_count": 11,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
"name": "stderr", "name": "stderr",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"943it [00:00, 9608.49it/s]\n", "943it [00:00, 7637.21it/s]\n",
"943it [00:00, 9837.12it/s]\n", "943it [00:00, 6445.83it/s]\n",
"943it [00:00, 10292.46it/s]\n", "943it [00:00, 7342.27it/s]\n",
"943it [00:00, 9906.94it/s]\n", "943it [00:00, 7577.08it/s]\n",
"943it [00:00, 9162.09it/s]\n" "943it [00:00, 7295.64it/s]\n"
] ]
} }
], ],
@ -608,7 +608,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 17, "execution_count": 12,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -683,14 +683,14 @@
" <tr>\n", " <tr>\n",
" <th>0</th>\n", " <th>0</th>\n",
" <td>Ready_Random</td>\n", " <td>Ready_Random</td>\n",
" <td>1.518964</td>\n", " <td>1.517787</td>\n",
" <td>1.222159</td>\n", " <td>1.217953</td>\n",
" <td>0.046554</td>\n", " <td>0.047826</td>\n",
" <td>0.020603</td>\n", " <td>0.017861</td>\n",
" <td>0.023679</td>\n", " <td>0.022711</td>\n",
" <td>0.031216</td>\n", " <td>0.031080</td>\n",
" <td>0.028970</td>\n", " <td>0.028219</td>\n",
" <td>0.021179</td>\n", " <td>0.016982</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>0</th>\n", " <th>0</th>\n",
@ -713,18 +713,18 @@
"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 Self_GlobalAvg 1.125760 0.943534 0.061188 0.025968 0.031383 \n",
"0 Ready_Random 1.518964 1.222159 0.046554 0.020603 0.023679 \n", "0 Ready_Random 1.517787 1.217953 0.047826 0.017861 0.022711 \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 0.041343 0.040558 0.032107 \n",
"0 0.031216 0.028970 0.021179 \n", "0 0.031080 0.028219 0.016982 \n",
"0 0.000463 0.000644 0.000189 " "0 0.000463 0.000644 0.000189 "
] ]
}, },
"execution_count": 17, "execution_count": 12,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -735,7 +735,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 18, "execution_count": 13,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -814,15 +814,15 @@
" <tr>\n", " <tr>\n",
" <th>0</th>\n", " <th>0</th>\n",
" <td>Ready_Random</td>\n", " <td>Ready_Random</td>\n",
" <td>0.050489</td>\n", " <td>0.051154</td>\n",
" <td>0.019185</td>\n", " <td>0.019551</td>\n",
" <td>0.123856</td>\n", " <td>0.125693</td>\n",
" <td>0.506812</td>\n", " <td>0.505448</td>\n",
" <td>0.322375</td>\n", " <td>0.318134</td>\n",
" <td>0.987805</td>\n", " <td>0.986426</td>\n",
" <td>0.184704</td>\n", " <td>0.186869</td>\n",
" <td>5.103172</td>\n", " <td>5.091730</td>\n",
" <td>0.906873</td>\n", " <td>0.908288</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>0</th>\n", " <th>0</th>\n",
@ -846,18 +846,18 @@
"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 Self_GlobalAvg 0.067695 0.027470 0.171187 0.509546 0.384942 \n",
"0 Ready_Random 0.050489 0.019185 0.123856 0.506812 0.322375 \n", "0 Ready_Random 0.051154 0.019551 0.125693 0.505448 0.318134 \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 1.000000 0.025974 2.711772 0.992003 \n",
"0 0.987805 0.184704 5.103172 0.906873 \n", "0 0.986426 0.186869 5.091730 0.908288 \n",
"0 0.600530 0.005051 1.803126 0.996380 " "0 0.600530 0.005051 1.803126 0.996380 "
] ]
}, },
"execution_count": 18, "execution_count": 13,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -875,14 +875,14 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 19, "execution_count": 14,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
"name": "stderr", "name": "stderr",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"3it [00:00, 1651.52it/s]\n" "3it [00:00, 2446.61it/s]\n"
] ]
}, },
{ {
@ -1207,7 +1207,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 20, "execution_count": 15,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -1246,148 +1246,148 @@
" </thead>\n", " </thead>\n",
" <tbody>\n", " <tbody>\n",
" <tr>\n", " <tr>\n",
" <th>24754</th>\n", " <th>7917</th>\n",
" <td>105</td>\n", " <td>100</td>\n",
" <td>5</td>\n", " <td>5</td>\n",
" <td>Gattaca (1997)</td>\n", " <td>As Good As It Gets (1997)</td>\n",
" <td>Drama, Sci-Fi, Thriller</td>\n", " <td>Comedy, Drama</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>37073</th>\n", " <th>40494</th>\n",
" <td>105</td>\n", " <td>100</td>\n",
" <td>5</td>\n",
" <td>Contact (1997)</td>\n",
" <td>Drama, Sci-Fi</td>\n",
" </tr>\n",
" <tr>\n",
" <th>40592</th>\n",
" <td>105</td>\n",
" <td>5</td>\n", " <td>5</td>\n",
" <td>Titanic (1997)</td>\n", " <td>Titanic (1997)</td>\n",
" <td>Action, Drama, Romance</td>\n", " <td>Action, Drama, Romance</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>46032</th>\n", " <th>23127</th>\n",
" <td>105</td>\n", " <td>100</td>\n",
" <td>5</td>\n", " <td>5</td>\n",
" <td>Apt Pupil (1998)</td>\n",
" <td>Drama, Thriller</td>\n",
" </tr>\n",
" <tr>\n",
" <th>45163</th>\n",
" <td>100</td>\n",
" <td>4</td>\n",
" <td>Tomorrow Never Dies (1997)</td>\n",
" <td>Action, Romance, Thriller</td>\n",
" </tr>\n",
" <tr>\n",
" <th>28194</th>\n",
" <td>100</td>\n",
" <td>4</td>\n",
" <td>Conspiracy Theory (1997)</td>\n",
" <td>Action, Mystery, Romance, Thriller</td>\n",
" </tr>\n",
" <tr>\n",
" <th>46108</th>\n",
" <td>100</td>\n",
" <td>4</td>\n",
" <td>L.A. Confidential (1997)</td>\n", " <td>L.A. Confidential (1997)</td>\n",
" <td>Crime, Film-Noir, Mystery, Thriller</td>\n", " <td>Crime, Film-Noir, Mystery, Thriller</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>17916</th>\n", " <th>43730</th>\n",
" <td>105</td>\n", " <td>100</td>\n",
" <td>4</td>\n", " <td>4</td>\n",
" <td>English Patient, The (1996)</td>\n", " <td>Amistad (1997)</td>\n",
" <td>Drama, Romance, War</td>\n", " <td>Drama</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>23767</th>\n", " <th>42366</th>\n",
" <td>105</td>\n", " <td>100</td>\n",
" <td>4</td>\n", " <td>4</td>\n",
" <td>Chasing Amy (1997)</td>\n", " <td>Postman, The (1997)</td>\n",
" <td>Drama, Romance</td>\n", " <td>Drama</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>47003</th>\n", " <th>37000</th>\n",
" <td>105</td>\n", " <td>100</td>\n",
" <td>4</td>\n", " <td>4</td>\n",
" <td>Cop Land (1997)</td>\n", " <td>Contact (1997)</td>\n",
" <td>Crime, Drama, Mystery</td>\n", " <td>Drama, Sci-Fi</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>48891</th>\n", " <th>66556</th>\n",
" <td>105</td>\n", " <td>100</td>\n",
" <td>4</td>\n", " <td>4</td>\n",
" <td>Lost Highway (1997)</td>\n", " <td>Apostle, The (1997)</td>\n",
" <td>Mystery</td>\n", " <td>Drama</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>67355</th>\n", " <th>67009</th>\n",
" <td>105</td>\n", " <td>100</td>\n",
" <td>4</td>\n",
" <td>Big Bang Theory, The (1994)</td>\n",
" <td>Crime</td>\n",
" </tr>\n",
" <tr>\n",
" <th>67332</th>\n",
" <td>100</td>\n",
" <td>4</td>\n", " <td>4</td>\n",
" <td>Good Will Hunting (1997)</td>\n", " <td>Good Will Hunting (1997)</td>\n",
" <td>Drama</td>\n", " <td>Drama</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>54121</th>\n", " <th>29564</th>\n",
" <td>105</td>\n", " <td>100</td>\n",
" <td>3</td>\n", " <td>4</td>\n",
" <td>Boogie Nights (1997)</td>\n", " <td>Kundun (1997)</td>\n",
" <td>Drama</td>\n", " <td>Drama</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>55439</th>\n", " <th>26441</th>\n",
" <td>105</td>\n", " <td>100</td>\n",
" <td>3</td>\n", " <td>4</td>\n",
" <td>Seven Years in Tibet (1997)</td>\n", " <td>Air Force One (1997)</td>\n",
" <td>Drama, War</td>\n", " <td>Action, Thriller</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>69687</th>\n", " <th>69735</th>\n",
" <td>105</td>\n", " <td>100</td>\n",
" <td>3</td>\n", " <td>4</td>\n",
" <td>Wag the Dog (1997)</td>\n", " <td>Wag the Dog (1997)</td>\n",
" <td>Comedy, Drama</td>\n", " <td>Comedy, Drama</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n",
" <th>7321</th>\n",
" <td>105</td>\n",
" <td>2</td>\n",
" <td>Saint, The (1997)</td>\n",
" <td>Action, Romance, Thriller</td>\n",
" </tr>\n",
" <tr>\n",
" <th>45056</th>\n",
" <td>105</td>\n",
" <td>2</td>\n",
" <td>Tomorrow Never Dies (1997)</td>\n",
" <td>Action, Romance, Thriller</td>\n",
" </tr>\n",
" <tr>\n",
" <th>64052</th>\n",
" <td>105</td>\n",
" <td>2</td>\n",
" <td>Alien: Resurrection (1997)</td>\n",
" <td>Action, Horror, Sci-Fi</td>\n",
" </tr>\n",
" </tbody>\n", " </tbody>\n",
"</table>\n", "</table>\n",
"</div>" "</div>"
], ],
"text/plain": [ "text/plain": [
" user rating title \\\n", " user rating title \\\n",
"24754 105 5 Gattaca (1997) \n", "7917 100 5 As Good As It Gets (1997) \n",
"37073 105 5 Contact (1997) \n", "40494 100 5 Titanic (1997) \n",
"40592 105 5 Titanic (1997) \n", "23127 100 5 Apt Pupil (1998) \n",
"46032 105 5 L.A. Confidential (1997) \n", "45163 100 4 Tomorrow Never Dies (1997) \n",
"17916 105 4 English Patient, The (1996) \n", "28194 100 4 Conspiracy Theory (1997) \n",
"23767 105 4 Chasing Amy (1997) \n", "46108 100 4 L.A. Confidential (1997) \n",
"47003 105 4 Cop Land (1997) \n", "43730 100 4 Amistad (1997) \n",
"48891 105 4 Lost Highway (1997) \n", "42366 100 4 Postman, The (1997) \n",
"67355 105 4 Good Will Hunting (1997) \n", "37000 100 4 Contact (1997) \n",
"54121 105 3 Boogie Nights (1997) \n", "66556 100 4 Apostle, The (1997) \n",
"55439 105 3 Seven Years in Tibet (1997) \n", "67009 100 4 Big Bang Theory, The (1994) \n",
"69687 105 3 Wag the Dog (1997) \n", "67332 100 4 Good Will Hunting (1997) \n",
"7321 105 2 Saint, The (1997) \n", "29564 100 4 Kundun (1997) \n",
"45056 105 2 Tomorrow Never Dies (1997) \n", "26441 100 4 Air Force One (1997) \n",
"64052 105 2 Alien: Resurrection (1997) \n", "69735 100 4 Wag the Dog (1997) \n",
"\n", "\n",
" genres \n", " genres \n",
"24754 Drama, Sci-Fi, Thriller \n", "7917 Comedy, Drama \n",
"37073 Drama, Sci-Fi \n", "40494 Action, Drama, Romance \n",
"40592 Action, Drama, Romance \n", "23127 Drama, Thriller \n",
"46032 Crime, Film-Noir, Mystery, Thriller \n", "45163 Action, Romance, Thriller \n",
"17916 Drama, Romance, War \n", "28194 Action, Mystery, Romance, Thriller \n",
"23767 Drama, Romance \n", "46108 Crime, Film-Noir, Mystery, Thriller \n",
"47003 Crime, Drama, Mystery \n", "43730 Drama \n",
"48891 Mystery \n", "42366 Drama \n",
"67355 Drama \n", "37000 Drama, Sci-Fi \n",
"54121 Drama \n", "66556 Drama \n",
"55439 Drama, War \n", "67009 Crime \n",
"69687 Comedy, Drama \n", "67332 Drama \n",
"7321 Action, Romance, Thriller \n", "29564 Drama \n",
"45056 Action, Romance, Thriller \n", "26441 Action, Thriller \n",
"64052 Action, Horror, Sci-Fi " "69735 Comedy, Drama "
] ]
}, },
"metadata": {}, "metadata": {},
@ -1429,71 +1429,71 @@
" </thead>\n", " </thead>\n",
" <tbody>\n", " <tbody>\n",
" <tr>\n", " <tr>\n",
" <th>103</th>\n", " <th>98</th>\n",
" <td>105.0</td>\n", " <td>100.0</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>1046</th>\n", " <th>1041</th>\n",
" <td>105.0</td>\n", " <td>100.0</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>1988</th>\n", " <th>1983</th>\n",
" <td>105.0</td>\n", " <td>100.0</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>2930</th>\n", " <th>2925</th>\n",
" <td>105.0</td>\n", " <td>100.0</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>3872</th>\n", " <th>3867</th>\n",
" <td>105.0</td>\n", " <td>100.0</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>4814</th>\n", " <th>4809</th>\n",
" <td>105.0</td>\n", " <td>100.0</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>5755</th>\n", " <th>5750</th>\n",
" <td>105.0</td>\n", " <td>100.0</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>6698</th>\n", " <th>6693</th>\n",
" <td>105.0</td>\n", " <td>100.0</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>8592</th>\n", " <th>8587</th>\n",
" <td>105.0</td>\n", " <td>100.0</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>7638</th>\n", " <th>7633</th>\n",
" <td>105.0</td>\n", " <td>100.0</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",
@ -1504,31 +1504,31 @@
], ],
"text/plain": [ "text/plain": [
" user rec_nb title \\\n", " user rec_nb title \\\n",
"103 105.0 1 Great Day in Harlem, A (1994) \n", "98 100.0 1 Great Day in Harlem, A (1994) \n",
"1046 105.0 2 Tough and Deadly (1995) \n", "1041 100.0 2 Tough and Deadly (1995) \n",
"1988 105.0 3 Aiqing wansui (1994) \n", "1983 100.0 3 Aiqing wansui (1994) \n",
"2930 105.0 4 Delta of Venus (1994) \n", "2925 100.0 4 Delta of Venus (1994) \n",
"3872 105.0 5 Someone Else's America (1995) \n", "3867 100.0 5 Someone Else's America (1995) \n",
"4814 105.0 6 Saint of Fort Washington, The (1993) \n", "4809 100.0 6 Saint of Fort Washington, The (1993) \n",
"5755 105.0 7 Celestial Clockwork (1994) \n", "5750 100.0 7 Celestial Clockwork (1994) \n",
"6698 105.0 8 Some Mother's Son (1996) \n", "6693 100.0 8 Some Mother's Son (1996) \n",
"8592 105.0 9 Maya Lin: A Strong Clear Vision (1994) \n", "8587 100.0 9 Maya Lin: A Strong Clear Vision (1994) \n",
"7638 105.0 10 Prefontaine (1997) \n", "7633 100.0 10 Prefontaine (1997) \n",
"\n", "\n",
" genres \n", " genres \n",
"103 Documentary \n", "98 Documentary \n",
"1046 Action, Drama, Thriller \n", "1041 Action, Drama, Thriller \n",
"1988 Drama \n", "1983 Drama \n",
"2930 Drama \n", "2925 Drama \n",
"3872 Drama \n", "3867 Drama \n",
"4814 Drama \n", "4809 Drama \n",
"5755 Comedy \n", "5750 Comedy \n",
"6698 Drama \n", "6693 Drama \n",
"8592 Documentary \n", "8587 Documentary \n",
"7638 Drama " "7633 Drama "
] ]
}, },
"execution_count": 20, "execution_count": 15,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -1576,7 +1576,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 71, "execution_count": 16,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1588,18 +1588,18 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 21, "execution_count": 17,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
"name": "stderr", "name": "stderr",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"943it [00:00, 9023.32it/s]\n", "943it [00:00, 6211.85it/s]\n",
"943it [00:00, 9004.98it/s]\n", "943it [00:00, 7728.29it/s]\n",
"943it [00:00, 8532.40it/s]\n", "943it [00:00, 7446.93it/s]\n",
"943it [00:00, 8974.06it/s]\n", "943it [00:00, 6379.07it/s]\n",
"943it [00:00, 8818.01it/s]\n" "943it [00:00, 6994.80it/s]\n"
] ]
}, },
{ {
@ -1710,23 +1710,23 @@
" <tr>\n", " <tr>\n",
" <th>0</th>\n", " <th>0</th>\n",
" <td>Ready_Random</td>\n", " <td>Ready_Random</td>\n",
" <td>1.518964</td>\n", " <td>1.517787</td>\n",
" <td>1.222159</td>\n", " <td>1.217953</td>\n",
" <td>0.046554</td>\n", " <td>0.047826</td>\n",
" <td>0.020603</td>\n", " <td>0.017861</td>\n",
" <td>0.023679</td>\n", " <td>0.022711</td>\n",
" <td>0.031216</td>\n", " <td>0.031080</td>\n",
" <td>0.028970</td>\n", " <td>0.028219</td>\n",
" <td>0.021179</td>\n", " <td>0.016982</td>\n",
" <td>0.050489</td>\n", " <td>0.051154</td>\n",
" <td>0.019185</td>\n", " <td>0.019551</td>\n",
" <td>0.123856</td>\n", " <td>0.125693</td>\n",
" <td>0.506812</td>\n", " <td>0.505448</td>\n",
" <td>0.322375</td>\n", " <td>0.318134</td>\n",
" <td>0.987805</td>\n", " <td>0.986426</td>\n",
" <td>0.184704</td>\n", " <td>0.186869</td>\n",
" <td>5.103172</td>\n", " <td>5.091730</td>\n",
" <td>0.906873</td>\n", " <td>0.908288</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>0</th>\n", " <th>0</th>\n",
@ -1758,25 +1758,25 @@
"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 Self_GlobalAvg 1.125760 0.943534 0.061188 0.025968 0.031383 \n",
"0 Ready_Random 1.518964 1.222159 0.046554 0.020603 0.023679 \n", "0 Ready_Random 1.517787 1.217953 0.047826 0.017861 0.022711 \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 0.041343 0.040558 0.032107 0.067695 0.027470 0.171187 \n",
"0 0.031216 0.028970 0.021179 0.050489 0.019185 0.123856 \n", "0 0.031080 0.028219 0.016982 0.051154 0.019551 0.125693 \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 0.509546 0.384942 1.000000 0.025974 2.711772 0.992003 \n",
"0 0.506812 0.322375 0.987805 0.184704 5.103172 0.906873 \n", "0 0.505448 0.318134 0.986426 0.186869 5.091730 0.908288 \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 "
] ]
}, },
"execution_count": 21, "execution_count": 17,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }

BIN
P2. Evaluation.pdf
View File

Binary file not shown.

60
P3. k-nearest neighbours.ipynb
View File

@ -209,7 +209,7 @@
"name": "stderr", "name": "stderr",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"943it [00:00, 10667.92it/s]\n" "943it [00:00, 8068.73it/s]\n"
] ]
}, },
{ {
@ -313,12 +313,12 @@
"name": "stderr", "name": "stderr",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"943it [00:00, 8975.00it/s]\n", "943it [00:00, 8130.43it/s]\n",
"943it [00:00, 10288.02it/s]\n", "943it [00:00, 7928.93it/s]\n",
"943it [00:00, 9740.46it/s]\n", "943it [00:00, 7309.27it/s]\n",
"943it [00:00, 10104.74it/s]\n", "943it [00:00, 7687.73it/s]\n",
"943it [00:00, 10418.45it/s]\n", "943it [00:00, 8153.31it/s]\n",
"943it [00:00, 10339.85it/s]\n" "943it [00:00, 7785.12it/s]\n"
] ]
}, },
{ {
@ -429,23 +429,23 @@
" <tr>\n", " <tr>\n",
" <th>0</th>\n", " <th>0</th>\n",
" <td>Ready_Random</td>\n", " <td>Ready_Random</td>\n",
" <td>1.518964</td>\n", " <td>1.517787</td>\n",
" <td>1.222159</td>\n", " <td>1.217953</td>\n",
" <td>0.046554</td>\n", " <td>0.047826</td>\n",
" <td>0.020603</td>\n", " <td>0.017861</td>\n",
" <td>0.023679</td>\n", " <td>0.022711</td>\n",
" <td>0.031216</td>\n", " <td>0.031080</td>\n",
" <td>0.028970</td>\n", " <td>0.028219</td>\n",
" <td>0.021179</td>\n", " <td>0.016982</td>\n",
" <td>0.050489</td>\n", " <td>0.051154</td>\n",
" <td>0.019185</td>\n", " <td>0.019551</td>\n",
" <td>0.123856</td>\n", " <td>0.125693</td>\n",
" <td>0.506812</td>\n", " <td>0.505448</td>\n",
" <td>0.322375</td>\n", " <td>0.318134</td>\n",
" <td>0.987805</td>\n", " <td>0.986426</td>\n",
" <td>0.184704</td>\n", " <td>0.186869</td>\n",
" <td>5.103172</td>\n", " <td>5.091730</td>\n",
" <td>0.906873</td>\n", " <td>0.908288</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>0</th>\n", " <th>0</th>\n",
@ -498,7 +498,7 @@
"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 Self_GlobalAvg 1.125760 0.943534 0.061188 0.025968 0.031383 \n",
"0 Ready_Random 1.518964 1.222159 0.046554 0.020603 0.023679 \n", "0 Ready_Random 1.517787 1.217953 0.047826 0.017861 0.022711 \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",
"0 Self_IKNN 1.018363 0.808793 0.000318 0.000108 0.000140 \n", "0 Self_IKNN 1.018363 0.808793 0.000318 0.000108 0.000140 \n",
"\n", "\n",
@ -506,7 +506,7 @@
"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 0.041343 0.040558 0.032107 0.067695 0.027470 0.171187 \n",
"0 0.031216 0.028970 0.021179 0.050489 0.019185 0.123856 \n", "0 0.031080 0.028219 0.016982 0.051154 0.019551 0.125693 \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",
"0 0.000189 0.000000 0.000000 0.000214 0.000037 0.000368 \n", "0 0.000189 0.000000 0.000000 0.000214 0.000037 0.000368 \n",
"\n", "\n",
@ -514,7 +514,7 @@
"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 0.509546 0.384942 1.000000 0.025974 2.711772 0.992003 \n",
"0 0.506812 0.322375 0.987805 0.184704 5.103172 0.906873 \n", "0 0.505448 0.318134 0.986426 0.186869 5.091730 0.908288 \n",
"0 0.496424 0.009544 0.600530 0.005051 1.803126 0.996380 \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 " "0 0.496391 0.003181 0.392153 0.115440 4.174741 0.965327 "
] ]
@ -552,7 +552,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 10, "execution_count": 7,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -590,7 +590,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 11, "execution_count": 8,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -667,7 +667,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 12, "execution_count": 10,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [

BIN
P3. k-nearest neighbours.pdf
View File

Binary file not shown.

8
P4. Appendix - embeddings in high demensional spaces.ipynb
View File

@ -11,10 +11,10 @@
"['dimensions: 1, cases when observation is the nearest: 0.0%',\n", "['dimensions: 1, cases when observation is the nearest: 0.0%',\n",
" 'dimensions: 2, cases when observation is the nearest: 0.0%',\n", " 'dimensions: 2, cases when observation is the nearest: 0.0%',\n",
" 'dimensions: 3, cases when observation is the nearest: 0.0%',\n", " 'dimensions: 3, cases when observation is the nearest: 0.0%',\n",
" 'dimensions: 10, cases when observation is the nearest: 14.000000000000002%',\n", " 'dimensions: 10, cases when observation is the nearest: 7.000000000000001%',\n",
" 'dimensions: 20, cases when observation is the nearest: 65.0%',\n", " 'dimensions: 20, cases when observation is the nearest: 57.99999999999999%',\n",
" 'dimensions: 30, cases when observation is the nearest: 100.0%',\n", " 'dimensions: 30, cases when observation is the nearest: 92.0%',\n",
" 'dimensions: 40, cases when observation is the nearest: 100.0%',\n", " 'dimensions: 40, cases when observation is the nearest: 99.0%',\n",
" 'dimensions: 50, cases when observation is the nearest: 100.0%',\n", " 'dimensions: 50, cases when observation is the nearest: 100.0%',\n",
" 'dimensions: 60, cases when observation is the nearest: 100.0%',\n", " 'dimensions: 60, cases when observation is the nearest: 100.0%',\n",
" 'dimensions: 70, cases when observation is the nearest: 100.0%',\n", " 'dimensions: 70, cases when observation is the nearest: 100.0%',\n",

542
P4. Matrix Factorization.ipynb
View File

File diff suppressed because one or more lines are too long

BIN
P4. Matrix Factorization.pdf
View File

Binary file not shown.

BIN
P5. Graph-based models.pdf
View File

Binary file not shown.

447
P5. Graph-based.ipynb
View File

File diff suppressed because one or more lines are too long