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

Slides added

Browse Source
This commit is contained in:
Robert Kwieciński 2020-05-21 16:20:12 +02:00
parent 67d6328405
commit 8ad2469287
12 changed files with 1390 additions and 2061 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

491
P0. Data preparation.ipynb
View File

File diff suppressed because one or more lines are too long

115
P1. Baseline.ipynb
View File

@ -9,7 +9,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 2, "execution_count": 1,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -26,7 +26,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 3, "execution_count": 2,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -43,7 +43,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 4, "execution_count": 3,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -134,7 +134,7 @@
"4 560 24 2 879976772 559 23" "4 560 24 2 879976772 559 23"
] ]
}, },
"execution_count": 4, "execution_count": 3,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -145,7 +145,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 5, "execution_count": 4,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -155,7 +155,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 6, "execution_count": 5,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -169,7 +169,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 7, "execution_count": 6,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -189,17 +189,17 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 9, "execution_count": 7,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
"data": { "data": {
"text/plain": [ "text/plain": [
"<3x4 sparse matrix of type '<class 'numpy.longlong'>'\n", "<3x4 sparse matrix of type '<class 'numpy.int64'>'\n",
"\twith 8 stored elements in Compressed Sparse Row format>" "\twith 8 stored elements in Compressed Sparse Row format>"
] ]
}, },
"execution_count": 9, "execution_count": 7,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -214,7 +214,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 10, "execution_count": 8,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -257,7 +257,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 11, "execution_count": 9,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -283,7 +283,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 12, "execution_count": 10,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -307,7 +307,7 @@
"name": "stdout", "name": "stdout",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"563 ns ± 16.7 ns per loop (mean ± std. dev. of 7 runs, 1000000 loops each)\n", "472 ns ± 7.02 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": [
"70.8 µs ± 2.93 µs per loop (mean ± std. dev. of 7 runs, 10000 loops each)\n" "57.3 µs ± 6.26 µs per loop (mean ± std. dev. of 7 runs, 10000 loops each)\n"
] ]
} }
], ],
@ -350,7 +350,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 17, "execution_count": 11,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -384,7 +384,7 @@
"matrix([[ 8, 3, 11]])" "matrix([[ 8, 3, 11]])"
] ]
}, },
"execution_count": 17, "execution_count": 11,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -398,7 +398,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 19, "execution_count": 12,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -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": {},
@ -468,7 +468,7 @@
" [-1.66666667, 0. , 1.33333333, 0.33333333]])" " [-1.66666667, 0. , 1.33333333, 0.33333333]])"
] ]
}, },
"execution_count": 19, "execution_count": 12,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -498,7 +498,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 20, "execution_count": 13,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -556,7 +556,20 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 19, "execution_count": 21,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"if not os.path.exists('./Recommendations generated/'):\n",
" os.mkdir('./Recommendations generated/')\n",
" os.mkdir('./Recommendations generated/ml-100k/')\n",
" os.mkdir('./Recommendations generated/toy-example/')"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -605,7 +618,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 30, "execution_count": 23,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -642,7 +655,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 31, "execution_count": 24,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -744,18 +757,18 @@
"</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 ... \\\n",
"0 1 5 3.529975 10 3.529975 25 3.529975 32 3.529975 33 ... 44 \n", "0 1 5 3.529975 10 3.529975 25 3.529975 32 3.529975 33 ... \n",
"1 2 1 3.529975 2 3.529975 3 3.529975 4 3.529975 5 ... 6 \n", "1 2 1 3.529975 2 3.529975 3 3.529975 4 3.529975 5 ... \n",
"\n", "\n",
" 12 13 14 15 16 17 18 19 20 \n", " 11 12 13 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 44 3.529975 46 3.529975 50 3.529975 52 3.529975 55 3.529975 \n",
"1 3.529975 7 3.529975 8 3.529975 9 3.529975 11 3.529975 \n", "1 6 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": 31, "execution_count": 24,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -773,7 +786,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 32, "execution_count": 25,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -792,7 +805,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 33, "execution_count": 26,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -865,7 +878,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 41, "execution_count": 27,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -1033,7 +1046,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 36, "execution_count": 28,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1057,7 +1070,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 37, "execution_count": 29,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1076,7 +1089,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 46, "execution_count": 30,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -1133,7 +1146,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 47, "execution_count": 31,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -1147,10 +1160,10 @@
{ {
"data": { "data": {
"text/plain": [ "text/plain": [
"0.7524871012820799" "0.75248710128207985"
] ]
}, },
"execution_count": 47, "execution_count": 31,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -1180,24 +1193,24 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 48, "execution_count": 32,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
"name": "stdout", "name": "stdout",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"RMSE: 1.5186\n", "RMSE: 1.5190\n",
"MAE: 1.2188\n" "MAE: 1.2222\n"
] ]
}, },
{ {
"data": { "data": {
"text/plain": [ "text/plain": [
"1.2187837474576546" "1.222159317007133"
] ]
}, },
"execution_count": 48, "execution_count": 32,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }

BIN
P1. Introduction and baseline.pdf Normal file
View File

Binary file not shown.

1186
P2. Evaluation.ipynb
View File

File diff suppressed because it is too large Load Diff

BIN
P2. Evaluation.pdf Normal file
View File

Binary file not shown.

380
P3. k-nearest neighbours.ipynb
View File

@ -9,7 +9,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 3, "execution_count": 1,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -28,7 +28,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 4, "execution_count": 2,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -73,7 +73,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 5, "execution_count": 3,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -154,7 +154,7 @@
" [20, 10, 5.0, 20, 5.0]]" " [20, 10, 5.0, 20, 5.0]]"
] ]
}, },
"execution_count": 5, "execution_count": 3,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -185,7 +185,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 6, "execution_count": 4,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -202,14 +202,14 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 7, "execution_count": 5,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
"name": "stderr", "name": "stderr",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"943it [00:00, 8845.73it/s]\n" "943it [00:00, 10667.92it/s]\n"
] ]
}, },
{ {
@ -288,7 +288,7 @@
"0 0.003181 0.392153 0.11544 4.174741 0.965327 " "0 0.003181 0.392153 0.11544 4.174741 0.965327 "
] ]
}, },
"execution_count": 7, "execution_count": 5,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -306,29 +306,19 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 8, "execution_count": 6,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
"name": "stderr", "name": "stderr",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"943it [00:00, 7423.18it/s]\n", "943it [00:00, 8975.00it/s]\n",
"943it [00:00, 7890.87it/s]\n", "943it [00:00, 10288.02it/s]\n",
"943it [00:00, 7370.82it/s]\n", "943it [00:00, 9740.46it/s]\n",
"943it [00:00, 8035.93it/s]\n", "943it [00:00, 10104.74it/s]\n",
"943it [00:00, 8071.70it/s]\n", "943it [00:00, 10418.45it/s]\n",
"943it [00:00, 7893.80it/s]\n", "943it [00:00, 10339.85it/s]\n"
"943it [00:00, 8159.55it/s]\n",
"943it [00:00, 7982.77it/s]\n",
"943it [00:00, 7514.53it/s]\n",
"943it [00:00, 8047.34it/s]\n",
"943it [00:00, 7874.80it/s]\n",
"943it [00:00, 7657.62it/s]\n",
"943it [00:00, 8281.73it/s]\n",
"943it [00:00, 8253.33it/s]\n",
"943it [00:00, 8332.31it/s]\n",
"943it [00:00, 8348.73it/s]\n"
] ]
}, },
{ {
@ -375,27 +365,6 @@
" <tbody>\n", " <tbody>\n",
" <tr>\n", " <tr>\n",
" <th>0</th>\n", " <th>0</th>\n",
" <td>Self_RP3Beta</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>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>Self_TopPop</td>\n",
" <td>2.508258</td>\n", " <td>2.508258</td>\n",
" <td>2.217909</td>\n", " <td>2.217909</td>\n",
@ -417,69 +386,6 @@
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>0</th>\n", " <th>0</th>\n",
" <td>Ready_SVD</td>\n",
" <td>0.952784</td>\n",
" <td>0.750597</td>\n",
" <td>0.095228</td>\n",
" <td>0.047497</td>\n",
" <td>0.053142</td>\n",
" <td>0.067082</td>\n",
" <td>0.084871</td>\n",
" <td>0.076457</td>\n",
" <td>0.109075</td>\n",
" <td>0.050124</td>\n",
" <td>0.241366</td>\n",
" <td>0.520459</td>\n",
" <td>0.499470</td>\n",
" <td>0.992047</td>\n",
" <td>0.217893</td>\n",
" <td>4.405246</td>\n",
" <td>0.953484</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Self_SVDBaseline</td>\n",
" <td>0.930321</td>\n",
" <td>0.734643</td>\n",
" <td>0.092683</td>\n",
" <td>0.042046</td>\n",
" <td>0.048568</td>\n",
" <td>0.063218</td>\n",
" <td>0.082940</td>\n",
" <td>0.068730</td>\n",
" <td>0.098937</td>\n",
" <td>0.044405</td>\n",
" <td>0.203936</td>\n",
" <td>0.517696</td>\n",
" <td>0.469777</td>\n",
" <td>1.000000</td>\n",
" <td>0.058442</td>\n",
" <td>3.085857</td>\n",
" <td>0.988824</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Ready_SVDBiased</td>\n",
" <td>0.940375</td>\n",
" <td>0.742264</td>\n",
" <td>0.092153</td>\n",
" <td>0.039645</td>\n",
" <td>0.046804</td>\n",
" <td>0.061886</td>\n",
" <td>0.079399</td>\n",
" <td>0.055967</td>\n",
" <td>0.102017</td>\n",
" <td>0.047972</td>\n",
" <td>0.216876</td>\n",
" <td>0.516515</td>\n",
" <td>0.441145</td>\n",
" <td>0.997455</td>\n",
" <td>0.167388</td>\n",
" <td>4.235348</td>\n",
" <td>0.962085</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Ready_Baseline</td>\n", " <td>Ready_Baseline</td>\n",
" <td>0.949459</td>\n", " <td>0.949459</td>\n",
" <td>0.752487</td>\n", " <td>0.752487</td>\n",
@ -501,27 +407,6 @@
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>0</th>\n", " <th>0</th>\n",
" <td>Self_SVD</td>\n",
" <td>0.939326</td>\n",
" <td>0.740022</td>\n",
" <td>0.074549</td>\n",
" <td>0.031755</td>\n",
" <td>0.038425</td>\n",
" <td>0.050562</td>\n",
" <td>0.065665</td>\n",
" <td>0.050602</td>\n",
" <td>0.077117</td>\n",
" <td>0.031574</td>\n",
" <td>0.165509</td>\n",
" <td>0.512485</td>\n",
" <td>0.414634</td>\n",
" <td>0.981866</td>\n",
" <td>0.080087</td>\n",
" <td>3.858982</td>\n",
" <td>0.975271</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Self_GlobalAvg</td>\n", " <td>Self_GlobalAvg</td>\n",
" <td>1.125760</td>\n", " <td>1.125760</td>\n",
" <td>0.943534</td>\n", " <td>0.943534</td>\n",
@ -544,128 +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>1.518551</td>\n", " <td>1.518964</td>\n",
" <td>1.218784</td>\n", " <td>1.222159</td>\n",
" <td>0.050583</td>\n", " <td>0.046554</td>\n",
" <td>0.024085</td>\n", " <td>0.020603</td>\n",
" <td>0.027323</td>\n", " <td>0.023679</td>\n",
" <td>0.034826</td>\n", " <td>0.031216</td>\n",
" <td>0.031223</td>\n", " <td>0.028970</td>\n",
" <td>0.026436</td>\n", " <td>0.021179</td>\n",
" <td>0.054902</td>\n", " <td>0.050489</td>\n",
" <td>0.020652</td>\n", " <td>0.019185</td>\n",
" <td>0.137928</td>\n", " <td>0.123856</td>\n",
" <td>0.508570</td>\n", " <td>0.506812</td>\n",
" <td>0.353128</td>\n", " <td>0.322375</td>\n",
" <td>0.987699</td>\n", " <td>0.987805</td>\n",
" <td>0.183261</td>\n", " <td>0.184704</td>\n",
" <td>5.093805</td>\n", " <td>5.103172</td>\n",
" <td>0.908215</td>\n", " <td>0.906873</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>0.402333</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_U-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>0.482821</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_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>0.482821</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>0.602121</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>1.033085</td>\n",
" <td>0.822057</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>0.699046</td>\n",
" <td>0.005051</td>\n",
" <td>1.945910</td>\n",
" <td>0.995669</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>0</th>\n", " <th>0</th>\n",
@ -714,62 +494,32 @@
"</div>" "</div>"
], ],
"text/plain": [ "text/plain": [
" Model RMSE MAE precision recall F_1 \\\n", " Model RMSE MAE precision recall F_1 \\\n",
"0 Self_RP3Beta 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_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_SVD 0.952784 0.750597 0.095228 0.047497 0.053142 \n", "0 Self_GlobalAvg 1.125760 0.943534 0.061188 0.025968 0.031383 \n",
"0 Self_SVDBaseline 0.930321 0.734643 0.092683 0.042046 0.048568 \n", "0 Ready_Random 1.518964 1.222159 0.046554 0.020603 0.023679 \n",
"0 Ready_SVDBiased 0.940375 0.742264 0.092153 0.039645 0.046804 \n", "0 Self_BaselineUI 0.967585 0.762740 0.000954 0.000170 0.000278 \n",
"0 Ready_Baseline 0.949459 0.752487 0.091410 0.037652 0.046030 \n", "0 Self_IKNN 1.018363 0.808793 0.000318 0.000108 0.000140 \n",
"0 Self_SVD 0.939326 0.740022 0.074549 0.031755 0.038425 \n",
"0 Self_GlobalAvg 1.125760 0.943534 0.061188 0.025968 0.031383 \n",
"0 Ready_Random 1.518551 1.218784 0.050583 0.024085 0.027323 \n",
"0 Ready_I-KNN 1.030386 0.813067 0.026087 0.006908 0.010593 \n",
"0 Ready_U-KNNBaseline 0.935327 0.737424 0.002545 0.000755 0.001105 \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 1.033085 0.822057 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", "\n",
" F_05 precision_super recall_super NDCG mAP MRR \\\n", " F_05 precision_super recall_super NDCG mAP MRR \\\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 0.141584 0.130472 0.137473 0.214651 0.111707 0.400939 \n",
"0 0.067082 0.084871 0.076457 0.109075 0.050124 0.241366 \n",
"0 0.063218 0.082940 0.068730 0.098937 0.044405 0.203936 \n",
"0 0.061886 0.079399 0.055967 0.102017 0.047972 0.216876 \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 0.050562 0.065665 0.050602 0.077117 0.031574 0.165509 \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 0.034826 0.031223 0.026436 0.054902 0.020652 0.137928 \n", "0 0.031216 0.028970 0.021179 0.050489 0.019185 0.123856 \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 0.001602 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 0.000463 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",
" LAUC HR Reco in test Test coverage Shannon Gini \n", " LAUC HR Reco in test Test coverage Shannon Gini \n",
"0 0.593544 0.875928 1.000000 0.077201 3.875892 0.974947 \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 0.520459 0.499470 0.992047 0.217893 4.405246 0.953484 \n",
"0 0.517696 0.469777 1.000000 0.058442 3.085857 0.988824 \n",
"0 0.516515 0.441145 0.997455 0.167388 4.235348 0.962085 \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 0.512485 0.414634 0.981866 0.080087 3.858982 0.975271 \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 0.508570 0.353128 0.987699 0.183261 5.093805 0.908215 \n", "0 0.506812 0.322375 0.987805 0.184704 5.103172 0.906873 \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 0.496724 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 0.496424 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 "
] ]
}, },
"execution_count": 8, "execution_count": 6,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -802,7 +552,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 9, "execution_count": 10,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -828,7 +578,7 @@
"algo = sp.KNNBasic(sim_options=sim_options)\n", "algo = sp.KNNBasic(sim_options=sim_options)\n",
"\n", "\n",
"helpers.ready_made(algo, reco_path='Recommendations generated/ml-100k/Ready_I-KNN_reco.csv',\n", "helpers.ready_made(algo, reco_path='Recommendations generated/ml-100k/Ready_I-KNN_reco.csv',\n",
" estimations_path='Recommendations generated/ml-100k/Ready_Baseline_I-KNN_estimations.csv')" " estimations_path='Recommendations generated/ml-100k/Ready_I-KNN_estimations.csv')"
] ]
}, },
{ {
@ -840,7 +590,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 10, "execution_count": 11,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -849,27 +599,10 @@
"text": [ "text": [
"Computing the cosine similarity matrix...\n", "Computing the cosine similarity matrix...\n",
"Done computing similarity matrix.\n", "Done computing similarity matrix.\n",
"Generating predictions...\n",
"Generating top N recommendations...\n",
"Generating predictions...\n" "Generating predictions...\n"
] ]
},
{
"ename": "KeyboardInterrupt",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m<ipython-input-10-dd4f59625a08>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m 9\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 10\u001b[0m helpers.ready_made(algo, reco_path='Recommendations generated/ml-100k/Ready_U-KNN_reco.csv',\n\u001b[0;32m---> 11\u001b[0;31m estimations_path='Recommendations generated/ml-100k/Ready_Baseline_U-KNN_estimations.csv')\n\u001b[0m",
"\u001b[0;32m/mnt/c/Users/rkwie/Repositories/Warsztaty z uczenia maszynowego - systemy rekomendacyjne/helpers.py\u001b[0m in \u001b[0;36mready_made\u001b[0;34m(algo, reco_path, estimations_path)\u001b[0m\n\u001b[1;32m 61\u001b[0m \u001b[0mantitrainset\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtrainset\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mbuild_anti_testset\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;31m# We want to predict ratings of pairs (user, item) which are not in train set\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 62\u001b[0m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'Generating predictions...'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 63\u001b[0;31m \u001b[0mpredictions\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0malgo\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtest\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mantitrainset\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 64\u001b[0m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'Generating top N recommendations...'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 65\u001b[0m \u001b[0mtop_n\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mget_top_n\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mpredictions\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mn\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m10\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/.local/lib/python3.6/site-packages/surprise/prediction_algorithms/algo_base.py\u001b[0m in \u001b[0;36mtest\u001b[0;34m(self, testset, verbose)\u001b[0m\n\u001b[1;32m 165\u001b[0m \u001b[0mr_ui_trans\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 166\u001b[0m verbose=verbose)\n\u001b[0;32m--> 167\u001b[0;31m for (uid, iid, r_ui_trans) in testset]\n\u001b[0m\u001b[1;32m 168\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mpredictions\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 169\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/.local/lib/python3.6/site-packages/surprise/prediction_algorithms/algo_base.py\u001b[0m in \u001b[0;36m<listcomp>\u001b[0;34m(.0)\u001b[0m\n\u001b[1;32m 165\u001b[0m \u001b[0mr_ui_trans\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 166\u001b[0m verbose=verbose)\n\u001b[0;32m--> 167\u001b[0;31m for (uid, iid, r_ui_trans) in testset]\n\u001b[0m\u001b[1;32m 168\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mpredictions\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 169\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/.local/lib/python3.6/site-packages/surprise/prediction_algorithms/algo_base.py\u001b[0m in \u001b[0;36mpredict\u001b[0;34m(self, uid, iid, r_ui, clip, verbose)\u001b[0m\n\u001b[1;32m 103\u001b[0m \u001b[0mdetails\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m{\u001b[0m\u001b[0;34m}\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 104\u001b[0m \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 105\u001b[0;31m \u001b[0mest\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mestimate\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0miuid\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0miiid\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 106\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 107\u001b[0m \u001b[0;31m# If the details dict was also returned\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/.local/lib/python3.6/site-packages/surprise/prediction_algorithms/knns.py\u001b[0m in \u001b[0;36mestimate\u001b[0;34m(self, u, i)\u001b[0m\n\u001b[1;32m 109\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 110\u001b[0m \u001b[0mneighbors\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msim\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mx\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mx2\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mr\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0mx2\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mr\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0myr\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0my\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 111\u001b[0;31m \u001b[0mk_neighbors\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mheapq\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mnlargest\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mk\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mneighbors\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkey\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mlambda\u001b[0m \u001b[0mt\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mt\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 112\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 113\u001b[0m \u001b[0;31m# compute weighted average\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/lib/python3.6/heapq.py\u001b[0m in \u001b[0;36mnlargest\u001b[0;34m(n, iterable, key)\u001b[0m\n\u001b[1;32m 567\u001b[0m \u001b[0;31m# General case, slowest method\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 568\u001b[0m \u001b[0mit\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0miter\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0miterable\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 569\u001b[0;31m \u001b[0mresult\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0melem\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mi\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0melem\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mi\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0melem\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mzip\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mrange\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m-\u001b[0m\u001b[0mn\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m-\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mit\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 570\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mresult\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 571\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mresult\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/lib/python3.6/heapq.py\u001b[0m in \u001b[0;36m<listcomp>\u001b[0;34m(.0)\u001b[0m\n\u001b[1;32m 567\u001b[0m \u001b[0;31m# General case, slowest method\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 568\u001b[0m \u001b[0mit\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0miter\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0miterable\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 569\u001b[0;31m \u001b[0mresult\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0melem\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mi\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0melem\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mi\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0melem\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mzip\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mrange\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m-\u001b[0m\u001b[0mn\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m-\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mit\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 570\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mresult\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 571\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mresult\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/.local/lib/python3.6/site-packages/surprise/prediction_algorithms/knns.py\u001b[0m in \u001b[0;36m<lambda>\u001b[0;34m(t)\u001b[0m\n\u001b[1;32m 109\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 110\u001b[0m \u001b[0mneighbors\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msim\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mx\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mx2\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mr\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0mx2\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mr\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0myr\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0my\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 111\u001b[0;31m \u001b[0mk_neighbors\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mheapq\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mnlargest\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mk\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mneighbors\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkey\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mlambda\u001b[0m \u001b[0mt\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mt\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 112\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 113\u001b[0m \u001b[0;31m# compute weighted average\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;31mKeyboardInterrupt\u001b[0m: "
]
} }
], ],
"source": [ "source": [
@ -883,7 +616,7 @@
"algo = sp.KNNBasic(sim_options=sim_options)\n", "algo = sp.KNNBasic(sim_options=sim_options)\n",
"\n", "\n",
"helpers.ready_made(algo, reco_path='Recommendations generated/ml-100k/Ready_U-KNN_reco.csv',\n", "helpers.ready_made(algo, reco_path='Recommendations generated/ml-100k/Ready_U-KNN_reco.csv',\n",
" estimations_path='Recommendations generated/ml-100k/Ready_Baseline_U-KNN_estimations.csv')" " estimations_path='Recommendations generated/ml-100k/Ready_U-KNN_estimations.csv')"
] ]
}, },
{ {
@ -895,9 +628,22 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": 9,
"metadata": {}, "metadata": {},
"outputs": [], "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": [ "source": [
"import helpers\n", "import helpers\n",
"import surprise as sp\n", "import surprise as sp\n",

BIN
P3. k-nearest neighbours.pdf Normal file
View File

Binary file not shown.

12
P4. Appendix - embeddings in high demensional spaces.ipynb
View File

@ -2,7 +2,7 @@
"cells": [ "cells": [
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 4, "execution_count": 1,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -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: 10.0%',\n", " 'dimensions: 10, cases when observation is the nearest: 14.000000000000002%',\n",
" 'dimensions: 20, cases when observation is the nearest: 61.0%',\n", " 'dimensions: 20, cases when observation is the nearest: 65.0%',\n",
" 'dimensions: 30, cases when observation is the nearest: 96.0%',\n", " 'dimensions: 30, cases when observation is the nearest: 100.0%',\n",
" 'dimensions: 40, cases when observation is the nearest: 98.0%',\n", " 'dimensions: 40, cases when observation is the nearest: 100.0%',\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",
@ -22,7 +22,7 @@
" 'dimensions: 90, cases when observation is the nearest: 100.0%']" " 'dimensions: 90, cases when observation is the nearest: 100.0%']"
] ]
}, },
"execution_count": 4, "execution_count": 1,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }

814
P4. Matrix Factorization.ipynb
View File

File diff suppressed because one or more lines are too long

BIN
P4. Matrix Factorization.pdf Normal file
View File

Binary file not shown.

BIN
P5. Graph-based models.pdf Normal file
View File

Binary file not shown.

453
P5. Graph-based.ipynb
View File

File diff suppressed because one or more lines are too long