├── .gitattributes
├── figs
    ├── KuaiRec.png
    ├── kuairec-long.png
    └── colab-badge.svg
├── .gitignore
├── loaddata.py
├── get_statistics_bak.ipynb
├── LICENSE
└── README.md


/.gitattributes:
--------------------------------------------------------------------------------
1 | # Auto detect text files and perform LF normalization
2 | * text=auto
3 | 


--------------------------------------------------------------------------------
/figs/KuaiRec.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/chongminggao/KuaiRec/HEAD/figs/KuaiRec.png


--------------------------------------------------------------------------------
/.gitignore:
--------------------------------------------------------------------------------
1 | data/
2 | .ipynb_checkpoints/
3 | get_statistcs_bak.ipynb
4 | .idea/
5 | .DS_Store


--------------------------------------------------------------------------------
/figs/kuairec-long.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/chongminggao/KuaiRec/HEAD/figs/kuairec-long.png


--------------------------------------------------------------------------------
/loaddata.py:
--------------------------------------------------------------------------------
 1 | import pandas as pd
 2 | 
 3 | print("Loading big matrix...")
 4 | big_matrix = pd.read_csv("data/big_matrix.csv")
 5 | print("Loading small matrix...")
 6 | small_matrix = pd.read_csv("data/small_matrix.csv")
 7 | 
 8 | print("Loading social network...")
 9 | social_network = pd.read_csv("data/social_network.csv")
10 | social_network["friend_list"] = social_network["friend_list"].map(eval)
11 | 
12 | print("Loading item features...")
13 | item_categories = pd.read_csv("data/item_categories.csv")
14 | item_categories["feat"] = item_categories["feat"].map(eval)
15 | 
16 | print("Loading user features...")
17 | user_features = pd.read_csv("data/user_features.csv")
18 | 
19 | print("Loading items' daily features...")
20 | item_daily_feat = pd.read_csv("data/item_daily_features.csv")
21 | 
22 | print("All data loaded.")
23 | print("1. Big matrix:")
24 | print(big_matrix)
25 | print("2. Small matrix:")
26 | print(small_matrix)
27 | print("3. Social network of users in big matrix:")
28 | print(social_network)
29 | print("4. Items' basic features of all items in big matrix")
30 | print(item_categories)
31 | print("5. User features of all users in big matrix. \nNote: this table is added in KuaiRec v2.0")
32 | print(user_features)
33 | print("6. Item daily features. \nNote: this table is added in KuaiRec v2.0")
34 | print(item_daily_feat)
35 | 
36 | 


--------------------------------------------------------------------------------
/figs/colab-badge.svg:
--------------------------------------------------------------------------------
1 | <svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" width="117" height="20"><linearGradient id="b" x2="0" y2="100%"><stop offset="0" stop-color="#bbb" stop-opacity=".1"/><stop offset="1" stop-opacity=".1"/></linearGradient><clipPath id="a"><rect width="117" height="20" rx="3" fill="#fff"/></clipPath><g clip-path="url(#a)"><path fill="#555" d="M0 0h30v20H0z"/><path fill="#007ec6" d="M30 0h87v20H30z"/><path fill="url(#b)" d="M0 0h117v20H0z"/></g><g fill="#fff" text-anchor="middle" font-family="DejaVu Sans,Verdana,Geneva,sans-serif" font-size="110"><svg x="4px" y="0px" width="22px" height="20px" viewBox="-2 0 28 24" style="background-color: #fff;border-radius: 1px;"><path style="fill:#e8710a;" d="M1.977,16.77c-2.667-2.277-2.605-7.079,0-9.357C2.919,8.057,3.522,9.075,4.49,9.691c-1.152,1.6-1.146,3.201-0.004,4.803C3.522,15.111,2.918,16.126,1.977,16.77z"/><path style="fill:#f9ab00;" d="M12.257,17.114c-1.767-1.633-2.485-3.658-2.118-6.02c0.451-2.91,2.139-4.893,4.946-5.678c2.565-0.718,4.964-0.217,6.878,1.819c-0.884,0.743-1.707,1.547-2.434,2.446C18.488,8.827,17.319,8.435,16,8.856c-2.404,0.767-3.046,3.241-1.494,5.644c-0.241,0.275-0.493,0.541-0.721,0.826C13.295,15.939,12.511,16.3,12.257,17.114z"/><path style="fill:#e8710a;" d="M19.529,9.682c0.727-0.899,1.55-1.703,2.434-2.446c2.703,2.783,2.701,7.031-0.005,9.764c-2.648,2.674-6.936,2.725-9.701,0.115c0.254-0.814,1.038-1.175,1.528-1.788c0.228-0.285,0.48-0.552,0.721-0.826c1.053,0.916,2.254,1.268,3.6,0.83C20.502,14.551,21.151,11.927,19.529,9.682z"/><path style="fill:#f9ab00;" d="M4.49,9.691C3.522,9.075,2.919,8.057,1.977,7.413c2.209-2.398,5.721-2.942,8.476-1.355c0.555,0.32,0.719,0.606,0.285,1.128c-0.157,0.188-0.258,0.422-0.391,0.631c-0.299,0.47-0.509,1.067-0.929,1.371C8.933,9.539,8.523,8.847,8.021,8.746C6.673,8.475,5.509,8.787,4.49,9.691z"/><path style="fill:#f9ab00;" d="M1.977,16.77c0.941-0.644,1.545-1.659,2.509-2.277c1.373,1.152,2.85,1.433,4.45,0.499c0.332-0.194,0.503-0.088,0.673,0.19c0.386,0.635,0.753,1.285,1.181,1.89c0.34,0.48,0.222,0.715-0.253,1.006C7.84,19.73,4.205,19.188,1.977,16.77z"/></svg><text x="245" y="140" transform="scale(.1)" textLength="30"> </text><text x="725" y="150" fill="#010101" fill-opacity=".3" transform="scale(.1)" textLength="770">Open in Colab</text><text x="725" y="140" transform="scale(.1)" textLength="770">Open in Colab</text></g> </svg>
2 | 


--------------------------------------------------------------------------------
/get_statistics_bak.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "markdown",
  5 |    "id": "977d952c-72dc-45aa-b6cf-9867bcf6c7cf",
  6 |    "metadata": {
  7 |     "pycharm": {
  8 |      "name": "#%% md\n"
  9 |     }
 10 |    },
 11 |    "source": [
 12 |     "# Statistics of KuaiRec"
 13 |    ]
 14 |   },
 15 |   {
 16 |    "cell_type": "markdown",
 17 |    "id": "d4c7a222-89d1-429a-9f7b-f6a2af0a816a",
 18 |    "metadata": {
 19 |     "pycharm": {
 20 |      "name": "#%% md\n"
 21 |     }
 22 |    },
 23 |    "source": [
 24 |     "## Load data"
 25 |    ]
 26 |   },
 27 |   {
 28 |    "cell_type": "code",
 29 |    "execution_count": null,
 30 |    "outputs": [],
 31 |    "source": [
 32 |     "import pandas as pd\n",
 33 |     "\n",
 34 |     "print(\"Loading big matrix...\")\n",
 35 |     "big_matrix = pd.read_csv(\"data/big_matrix.csv\")\n",
 36 |     "print(\"Loading small matrix...\")\n",
 37 |     "small_matrix = pd.read_csv(\"data/small_matrix.csv\")\n",
 38 |     "\n",
 39 |     "print(\"Loading social network...\")\n",
 40 |     "social_network = pd.read_csv(\"data/social_network.csv\")\n",
 41 |     "social_network[\"friend_list\"] = social_network[\"friend_list\"].map(eval)\n",
 42 |     "\n",
 43 |     "print(\"Loading item features...\")\n",
 44 |     "item_feat = pd.read_csv(\"data/item_categories.csv\")\n",
 45 |     "item_feat[\"feat\"] = item_feat[\"feat\"].map(eval)\n",
 46 |     "\n",
 47 |     "print(\"Loading user features...\")\n",
 48 |     "user_feat = pd.read_csv(\"data/user_features.csv\")\n",
 49 |     "\n",
 50 |     "print(\"Loading items' daily features...\")\n",
 51 |     "item_daily_feat = pd.read_csv(\"data/item_daily_feat.csv\")\n",
 52 |     "\n",
 53 |     "print(\"All data loaded.\")"
 54 |    ],
 55 |    "metadata": {
 56 |     "collapsed": false,
 57 |     "pycharm": {
 58 |      "name": "#%%\n"
 59 |     }
 60 |    }
 61 |   },
 62 |   {
 63 |    "cell_type": "markdown",
 64 |    "source": [
 65 |     "## Visualization of the four tables"
 66 |    ],
 67 |    "metadata": {
 68 |     "collapsed": false,
 69 |     "pycharm": {
 70 |      "name": "#%% md\n"
 71 |     }
 72 |    }
 73 |   },
 74 |   {
 75 |    "cell_type": "code",
 76 |    "execution_count": null,
 77 |    "outputs": [],
 78 |    "source": [
 79 |     "big_matrix"
 80 |    ],
 81 |    "metadata": {
 82 |     "collapsed": false,
 83 |     "pycharm": {
 84 |      "name": "#%%\n"
 85 |     }
 86 |    }
 87 |   },
 88 |   {
 89 |    "cell_type": "code",
 90 |    "execution_count": null,
 91 |    "outputs": [],
 92 |    "source": [
 93 |     "small_matrix"
 94 |    ],
 95 |    "metadata": {
 96 |     "collapsed": false,
 97 |     "pycharm": {
 98 |      "name": "#%%\n"
 99 |     }
100 |    }
101 |   },
102 |   {
103 |    "cell_type": "code",
104 |    "execution_count": null,
105 |    "outputs": [],
106 |    "source": [
107 |     "item_feat"
108 |    ],
109 |    "metadata": {
110 |     "collapsed": false,
111 |     "pycharm": {
112 |      "name": "#%%\n"
113 |     }
114 |    }
115 |   },
116 |   {
117 |    "cell_type": "code",
118 |    "execution_count": null,
119 |    "outputs": [],
120 |    "source": [
121 |     "social_network"
122 |    ],
123 |    "metadata": {
124 |     "collapsed": false,
125 |     "pycharm": {
126 |      "name": "#%%\n"
127 |     }
128 |    }
129 |   },
130 |   {
131 |    "cell_type": "code",
132 |    "execution_count": null,
133 |    "outputs": [],
134 |    "source": [
135 |     "item_daily_feat"
136 |    ],
137 |    "metadata": {
138 |     "collapsed": false,
139 |     "pycharm": {
140 |      "name": "#%%\n"
141 |     }
142 |    }
143 |   },
144 |   {
145 |    "cell_type": "code",
146 |    "execution_count": null,
147 |    "outputs": [],
148 |    "source": [
149 |     "user_feat"
150 |    ],
151 |    "metadata": {
152 |     "collapsed": false,
153 |     "pycharm": {
154 |      "name": "#%%\n"
155 |     }
156 |    }
157 |   },
158 |   {
159 |    "cell_type": "code",
160 |    "execution_count": null,
161 |    "outputs": [],
162 |    "source": [
163 |     "import seaborn as sns\n",
164 |     "import matplotlib.pyplot as plt\n",
165 |     "from matplotlib.font_manager import FontProperties\n",
166 |     "myfont = FontProperties(fname=\"./SimHei.ttf\")\n",
167 |     "\n",
168 |     "def visual_continue(df, func=None):\n",
169 |     "    ax = sns.distplot(df)\n",
170 |     "    if func:\n",
171 |     "        func(ax)\n",
172 |     "    \n",
173 |     "    gca = plt.gca()\n",
174 |     "    fig_title = \"Statistcis of {}\".format(df.name)\n",
175 |     "    gca.set_title(fig_title, fontsize=14)\n",
176 |     "    gca.set_ylabel(\"Density\", fontsize=14)\n",
177 |     "    gca.set_xlabel(df.name, fontsize=14)\n",
178 |     "    \n",
179 |     "    plt.show()\n",
180 |     "\n",
181 |     "def visual_statistics_discrete(df, var=\"my_variable\", display_ratio=True, func=None, order=None, size=(6, 4.5)):\n",
182 |     "    ncount = len(df)\n",
183 |     "\n",
184 |     "    fig = plt.figure(figsize=size)\n",
185 |     "    ax1 = fig.add_axes([0.14, 0.15, 0.74, 0.75])\n",
186 |     "    sns.countplot(x=df, color=\"#9fc5e8\", linewidth=.6, edgecolor='k', ax=ax1, order=order)\n",
187 |     "\n",
188 |     "\n",
189 |     "    plt.grid(axis='y', linestyle='-.')\n",
190 |     "\n",
191 |     "    gca = plt.gca()\n",
192 |     "    fig_title = \"Statistcis of {}\".format(var)\n",
193 |     "    gca.set_title(fig_title, fontsize=14)\n",
194 |     "    gca.set_ylabel(\"Count\", fontsize=14)\n",
195 |     "    gca.set_xlabel(var, fontsize=14)\n",
196 |     "    \n",
197 |     "    if func:\n",
198 |     "        func(ax1)\n",
199 |     "\n",
200 |     "    if display_ratio:\n",
201 |     "        # Make twin axis\n",
202 |     "        ax2 = ax1.twinx()\n",
203 |     "        ax2.set_ylabel(\"ratio (%)\", fontsize=14)\n",
204 |     "\n",
205 |     "\n",
206 |     "        for p in ax1.patches:\n",
207 |     "            x = p.get_bbox().get_points()[:, 0]\n",
208 |     "            y = p.get_bbox().get_points()[1, 1]\n",
209 |     "            ax1.annotate('{:.1f}%'.format(100. * y / ncount), (x.mean(), y),\n",
210 |     "                         ha='center', va='bottom', fontsize=10, rotation=30)  # set the alignment of the text\n",
211 |     "\n",
212 |     "        ax2.set_ylim(0, ax1.get_ylim()[1] / ncount * 100)\n",
213 |     "\n",
214 |     "    plt.savefig(\"f{var}.png\")\n",
215 |     "    plt.show()\n",
216 |     "    "
217 |    ],
218 |    "metadata": {
219 |     "collapsed": false,
220 |     "pycharm": {
221 |      "name": "#%%\n"
222 |     }
223 |    }
224 |   },
225 |   {
226 |    "cell_type": "code",
227 |    "execution_count": null,
228 |    "outputs": [],
229 |    "source": [
230 |     "import warnings; warnings.simplefilter('ignore')"
231 |    ],
232 |    "metadata": {
233 |     "collapsed": false,
234 |     "pycharm": {
235 |      "name": "#%%\n"
236 |     }
237 |    }
238 |   },
239 |   {
240 |    "cell_type": "markdown",
241 |    "source": [
242 |     "## Statistics of social network"
243 |    ],
244 |    "metadata": {
245 |     "collapsed": false,
246 |     "pycharm": {
247 |      "name": "#%% md\n"
248 |     }
249 |    }
250 |   },
251 |   {
252 |    "cell_type": "code",
253 |    "execution_count": null,
254 |    "outputs": [],
255 |    "source": [
256 |     "print(social_network.friend_list.map(len).describe())\n",
257 |     "visual_statistics_discrete(social_network.friend_list.map(len), \"number of friends\")"
258 |    ],
259 |    "metadata": {
260 |     "collapsed": false,
261 |     "pycharm": {
262 |      "name": "#%%\n"
263 |     }
264 |    }
265 |   },
266 |   {
267 |    "cell_type": "markdown",
268 |    "source": [
269 |     "## Statistics of video features"
270 |    ],
271 |    "metadata": {
272 |     "collapsed": false,
273 |     "pycharm": {
274 |      "name": "#%% md\n"
275 |     }
276 |    }
277 |   },
278 |   {
279 |    "cell_type": "code",
280 |    "execution_count": null,
281 |    "outputs": [],
282 |    "source": [
283 |     "num_feat = item_feat.feat.map(len)\n",
284 |     "print(num_feat)\n",
285 |     "visual_statistics_discrete(num_feat, \"number of tags\")"
286 |    ],
287 |    "metadata": {
288 |     "collapsed": false,
289 |     "pycharm": {
290 |      "name": "#%%\n"
291 |     }
292 |    }
293 |   },
294 |   {
295 |    "cell_type": "markdown",
296 |    "source": [
297 |     "## Count of 31 tags "
298 |    ],
299 |    "metadata": {
300 |     "collapsed": false,
301 |     "pycharm": {
302 |      "name": "#%% md\n"
303 |     }
304 |    }
305 |   },
306 |   {
307 |    "cell_type": "code",
308 |    "execution_count": null,
309 |    "outputs": [],
310 |    "source": [
311 |     "import collections\n",
312 |     "import itertools\n",
313 |     "\n",
314 |     "cnt = item_feat.feat.map(collections.Counter)\n",
315 |     "cnt_all = collections.Counter()\n",
316 |     "for d in cnt:\n",
317 |     "    cnt_all.update(d)\n",
318 |     "# print(dict(cnt_all))\n",
319 |     "all_feat = pd.Series(sorted(list(itertools.chain.from_iterable([[i]*k for i,k in cnt_all.items()]))),name=\"feat\")\n",
320 |     "# print(all_feat)\n",
321 |     "visual_statistics_discrete(all_feat, \"tag\", size=(12,4.5))"
322 |    ],
323 |    "metadata": {
324 |     "collapsed": false,
325 |     "pycharm": {
326 |      "name": "#%%\n"
327 |     }
328 |    }
329 |   },
330 |   {
331 |    "cell_type": "markdown",
332 |    "source": [
333 |     "## Watch_ratio in big matrix"
334 |    ],
335 |    "metadata": {
336 |     "collapsed": false,
337 |     "pycharm": {
338 |      "name": "#%% md\n"
339 |     }
340 |    }
341 |   },
342 |   {
343 |    "cell_type": "code",
344 |    "execution_count": null,
345 |    "outputs": [],
346 |    "source": [
347 |     "big_watch_ratio = big_matrix.watch_ratio[big_matrix.watch_ratio <= 5]\n",
348 |     "print(big_watch_ratio.describe())\n",
349 |     "visual_continue(big_watch_ratio)"
350 |    ],
351 |    "metadata": {
352 |     "collapsed": false,
353 |     "pycharm": {
354 |      "name": "#%%\n"
355 |     }
356 |    }
357 |   },
358 |   {
359 |    "cell_type": "markdown",
360 |    "source": [
361 |     "## Watch_ratio in small matrix"
362 |    ],
363 |    "metadata": {
364 |     "collapsed": false,
365 |     "pycharm": {
366 |      "name": "#%% md\n"
367 |     }
368 |    }
369 |   },
370 |   {
371 |    "cell_type": "code",
372 |    "execution_count": null,
373 |    "outputs": [],
374 |    "source": [
375 |     "small_watch_ratio = small_matrix.watch_ratio[small_matrix.watch_ratio <= 5]\n",
376 |     "print(\"watch_ratio in small matrix\")\n",
377 |     "print(small_watch_ratio.describe())\n",
378 |     "visual_continue(small_watch_ratio)"
379 |    ],
380 |    "metadata": {
381 |     "collapsed": false,
382 |     "pycharm": {
383 |      "name": "#%%\n"
384 |     }
385 |    }
386 |   },
387 |   {
388 |    "cell_type": "markdown",
389 |    "source": [
390 |     "## Video duration of the big matrix (in millisecond)"
391 |    ],
392 |    "metadata": {
393 |     "collapsed": false,
394 |     "pycharm": {
395 |      "name": "#%% md\n"
396 |     }
397 |    }
398 |   },
399 |   {
400 |    "cell_type": "code",
401 |    "execution_count": null,
402 |    "outputs": [],
403 |    "source": [
404 |     "big_video_duration = big_matrix.video_duration\n",
405 |     "print(big_video_duration.describe())\n",
406 |     "# visual_continue(big_video_duration)\n",
407 |     "visual_continue(big_video_duration[big_video_duration < 100000])"
408 |    ],
409 |    "metadata": {
410 |     "collapsed": false,
411 |     "pycharm": {
412 |      "name": "#%%\n"
413 |     }
414 |    }
415 |   },
416 |   {
417 |    "cell_type": "markdown",
418 |    "source": [
419 |     "## Video duration of the small matrix (in millisecond)"
420 |    ],
421 |    "metadata": {
422 |     "collapsed": false,
423 |     "pycharm": {
424 |      "name": "#%% md\n"
425 |     }
426 |    }
427 |   },
428 |   {
429 |    "cell_type": "code",
430 |    "execution_count": null,
431 |    "outputs": [],
432 |    "source": [
433 |     "small_video_duration = small_matrix.video_duration\n",
434 |     "print(small_video_duration.describe())\n",
435 |     "# visual_continue(small_video_duration)\n",
436 |     "visual_continue(small_video_duration[small_video_duration < 100000])"
437 |    ],
438 |    "metadata": {
439 |     "collapsed": false,
440 |     "pycharm": {
441 |      "name": "#%%\n"
442 |     }
443 |    }
444 |   },
445 |   {
446 |    "cell_type": "markdown",
447 |    "source": [
448 |     "## 大矩阵中每个用户的总播放次数"
449 |    ],
450 |    "metadata": {
451 |     "collapsed": false,
452 |     "pycharm": {
453 |      "name": "#%% md\n"
454 |     }
455 |    }
456 |   },
457 |   {
458 |    "cell_type": "code",
459 |    "execution_count": null,
460 |    "outputs": [],
461 |    "source": [
462 |     "big_play_time = big_matrix.groupby('user_id').agg({\"date\":len})\n",
463 |     "big_play_time.name = \"play times\"\n",
464 |     "print(big_play_time.describe())\n",
465 |     "visual_continue(big_play_time)"
466 |    ],
467 |    "metadata": {
468 |     "collapsed": false,
469 |     "pycharm": {
470 |      "name": "#%%\n"
471 |     }
472 |    }
473 |   },
474 |   {
475 |    "cell_type": "markdown",
476 |    "source": [
477 |     "## 小矩阵中每个用户的总播放次数"
478 |    ],
479 |    "metadata": {
480 |     "collapsed": false,
481 |     "pycharm": {
482 |      "name": "#%% md\n"
483 |     }
484 |    }
485 |   },
486 |   {
487 |    "cell_type": "code",
488 |    "execution_count": null,
489 |    "outputs": [],
490 |    "source": [
491 |     "small_play_time = small_matrix.groupby('user_id').agg({\"date\":len})\n",
492 |     "small_play_time.name = \"play times\"\n",
493 |     "print(small_play_time.describe())\n",
494 |     "visual_continue(small_play_time)"
495 |    ],
496 |    "metadata": {
497 |     "collapsed": false,
498 |     "pycharm": {
499 |      "name": "#%%\n"
500 |     }
501 |    }
502 |   },
503 |   {
504 |    "cell_type": "markdown",
505 |    "source": [
506 |     "## 大矩阵中每个用户的日播放次数"
507 |    ],
508 |    "metadata": {
509 |     "collapsed": false,
510 |     "pycharm": {
511 |      "name": "#%% md\n"
512 |     }
513 |    }
514 |   },
515 |   {
516 |    "cell_type": "code",
517 |    "execution_count": null,
518 |    "outputs": [],
519 |    "source": [
520 |     "big_daily_play_time = big_matrix.groupby(['user_id', 'date']).size()\n",
521 |     "big_daily_play_time.name = \"play times\"\n",
522 |     "print(big_daily_play_time.describe())\n",
523 |     "visual_continue(big_daily_play_time)"
524 |    ],
525 |    "metadata": {
526 |     "collapsed": false,
527 |     "pycharm": {
528 |      "name": "#%%\n"
529 |     }
530 |    }
531 |   },
532 |   {
533 |    "cell_type": "markdown",
534 |    "source": [
535 |     "## 小矩阵中每个用户的日播放次数"
536 |    ],
537 |    "metadata": {
538 |     "collapsed": false,
539 |     "pycharm": {
540 |      "name": "#%% md\n"
541 |     }
542 |    }
543 |   },
544 |   {
545 |    "cell_type": "code",
546 |    "execution_count": null,
547 |    "outputs": [],
548 |    "source": [
549 |     "small_daily_play_time = small_matrix.groupby(['user_id', 'date']).size()\n",
550 |     "small_daily_play_time.name = \"play times\"\n",
551 |     "print(small_daily_play_time.describe())\n",
552 |     "visual_continue(small_daily_play_time)"
553 |    ],
554 |    "metadata": {
555 |     "collapsed": false,
556 |     "pycharm": {
557 |      "name": "#%%\n"
558 |     }
559 |    }
560 |   },
561 |   {
562 |    "cell_type": "markdown",
563 |    "source": [
564 |     "## 大矩阵中播放日期分布"
565 |    ],
566 |    "metadata": {
567 |     "collapsed": false,
568 |     "pycharm": {
569 |      "name": "#%% md\n"
570 |     }
571 |    }
572 |   },
573 |   {
574 |    "cell_type": "code",
575 |    "execution_count": null,
576 |    "outputs": [],
577 |    "source": [
578 |     "import functools\n",
579 |     "def adjust_xticks(ax):\n",
580 |     "    # print(ax.get_xticklabels())\n",
581 |     "    ax.set_xticks(list(range(0,len(ax.get_xticklabels()),3)))\n",
582 |     "    # print(ax.get_xticklabels())\n",
583 |     "    # ax.set_xticklabels(rotation = 45)\n",
584 |     "    for tick in ax.get_xticklabels():\n",
585 |     "        tick.set_rotation(45)\n",
586 |     "    # plt.xticks(fontsize=8)\n",
587 |     "    # ax.set_xticklabels([\"{}\".format(str(i)) for i in ax.get_xticks()])"
588 |    ],
589 |    "metadata": {
590 |     "collapsed": false,
591 |     "pycharm": {
592 |      "name": "#%%\n"
593 |     }
594 |    }
595 |   },
596 |   {
597 |    "cell_type": "code",
598 |    "execution_count": null,
599 |    "outputs": [],
600 |    "source": [
601 |     "visual_statistics_discrete(big_matrix.date, \"date\", display_ratio=False, func=adjust_xticks, order=small_matrix.date[~small_matrix.date.isna()].map(int).unique())"
602 |    ],
603 |    "metadata": {
604 |     "collapsed": false,
605 |     "pycharm": {
606 |      "name": "#%%\n"
607 |     }
608 |    }
609 |   },
610 |   {
611 |    "cell_type": "markdown",
612 |    "source": [
613 |     "## 小矩阵中播放日期分布"
614 |    ],
615 |    "metadata": {
616 |     "collapsed": false,
617 |     "pycharm": {
618 |      "name": "#%% md\n"
619 |     }
620 |    }
621 |   },
622 |   {
623 |    "cell_type": "code",
624 |    "execution_count": null,
625 |    "outputs": [],
626 |    "source": [
627 |     "visual_statistics_discrete(small_matrix.date[~small_matrix.date.isna()].map(int), \"date\", display_ratio=False, func=adjust_xticks)"
628 |    ],
629 |    "metadata": {
630 |     "collapsed": false,
631 |     "pycharm": {
632 |      "name": "#%%\n"
633 |     }
634 |    }
635 |   },
636 |   {
637 |    "cell_type": "code",
638 |    "execution_count": null,
639 |    "outputs": [],
640 |    "source": [],
641 |    "metadata": {
642 |     "collapsed": false,
643 |     "pycharm": {
644 |      "name": "#%%\n"
645 |     }
646 |    }
647 |   },
648 |   {
649 |    "cell_type": "code",
650 |    "execution_count": null,
651 |    "id": "54567a88-88ae-4060-bd67-78f39601e59c",
652 |    "metadata": {
653 |     "pycharm": {
654 |      "name": "#%%\n"
655 |     }
656 |    },
657 |    "outputs": [],
658 |    "source": []
659 |   }
660 |  ],
661 |  "metadata": {
662 |   "kernelspec": {
663 |    "display_name": "Python 3 (ipykernel)",
664 |    "language": "python",
665 |    "name": "python3"
666 |   },
667 |   "language_info": {
668 |    "codemirror_mode": {
669 |     "name": "ipython",
670 |     "version": 3
671 |    },
672 |    "file_extension": ".py",
673 |    "mimetype": "text/x-python",
674 |    "name": "python",
675 |    "nbconvert_exporter": "python",
676 |    "pygments_lexer": "ipython3",
677 |    "version": "3.9.1"
678 |   }
679 |  },
680 |  "nbformat": 4,
681 |  "nbformat_minor": 5
682 | }


--------------------------------------------------------------------------------
/LICENSE:
--------------------------------------------------------------------------------
  1 | Attribution-ShareAlike 4.0 International
  2 | 
  3 | =======================================================================
  4 | 
  5 | Creative Commons Corporation ("Creative Commons") is not a law firm and
  6 | does not provide legal services or legal advice. Distribution of
  7 | Creative Commons public licenses does not create a lawyer-client or
  8 | other relationship. Creative Commons makes its licenses and related
  9 | information available on an "as-is" basis. Creative Commons gives no
 10 | warranties regarding its licenses, any material licensed under their
 11 | terms and conditions, or any related information. Creative Commons
 12 | disclaims all liability for damages resulting from their use to the
 13 | fullest extent possible.
 14 | 
 15 | Using Creative Commons Public Licenses
 16 | 
 17 | Creative Commons public licenses provide a standard set of terms and
 18 | conditions that creators and other rights holders may use to share
 19 | original works of authorship and other material subject to copyright
 20 | and certain other rights specified in the public license below. The
 21 | following considerations are for informational purposes only, are not
 22 | exhaustive, and do not form part of our licenses.
 23 | 
 24 |      Considerations for licensors: Our public licenses are
 25 |      intended for use by those authorized to give the public
 26 |      permission to use material in ways otherwise restricted by
 27 |      copyright and certain other rights. Our licenses are
 28 |      irrevocable. Licensors should read and understand the terms
 29 |      and conditions of the license they choose before applying it.
 30 |      Licensors should also secure all rights necessary before
 31 |      applying our licenses so that the public can reuse the
 32 |      material as expected. Licensors should clearly mark any
 33 |      material not subject to the license. This includes other CC-
 34 |      licensed material, or material used under an exception or
 35 |      limitation to copyright. More considerations for licensors:
 36 |      wiki.creativecommons.org/Considerations_for_licensors
 37 | 
 38 |      Considerations for the public: By using one of our public
 39 |      licenses, a licensor grants the public permission to use the
 40 |      licensed material under specified terms and conditions. If
 41 |      the licensor's permission is not necessary for any reason--for
 42 |      example, because of any applicable exception or limitation to
 43 |      copyright--then that use is not regulated by the license. Our
 44 |      licenses grant only permissions under copyright and certain
 45 |      other rights that a licensor has authority to grant. Use of
 46 |      the licensed material may still be restricted for other
 47 |      reasons, including because others have copyright or other
 48 |      rights in the material. A licensor may make special requests,
 49 |      such as asking that all changes be marked or described.
 50 |      Although not required by our licenses, you are encouraged to
 51 |      respect those requests where reasonable. More considerations
 52 |      for the public:
 53 |      wiki.creativecommons.org/Considerations_for_licensees
 54 | 
 55 | =======================================================================
 56 | 
 57 | Creative Commons Attribution-ShareAlike 4.0 International Public
 58 | License
 59 | 
 60 | By exercising the Licensed Rights (defined below), You accept and agree
 61 | to be bound by the terms and conditions of this Creative Commons
 62 | Attribution-ShareAlike 4.0 International Public License ("Public
 63 | License"). To the extent this Public License may be interpreted as a
 64 | contract, You are granted the Licensed Rights in consideration of Your
 65 | acceptance of these terms and conditions, and the Licensor grants You
 66 | such rights in consideration of benefits the Licensor receives from
 67 | making the Licensed Material available under these terms and
 68 | conditions.
 69 | 
 70 | 
 71 | Section 1 -- Definitions.
 72 | 
 73 |   a. Adapted Material means material subject to Copyright and Similar
 74 |      Rights that is derived from or based upon the Licensed Material
 75 |      and in which the Licensed Material is translated, altered,
 76 |      arranged, transformed, or otherwise modified in a manner requiring
 77 |      permission under the Copyright and Similar Rights held by the
 78 |      Licensor. For purposes of this Public License, where the Licensed
 79 |      Material is a musical work, performance, or sound recording,
 80 |      Adapted Material is always produced where the Licensed Material is
 81 |      synched in timed relation with a moving image.
 82 | 
 83 |   b. Adapter's License means the license You apply to Your Copyright
 84 |      and Similar Rights in Your contributions to Adapted Material in
 85 |      accordance with the terms and conditions of this Public License.
 86 | 
 87 |   c. BY-SA Compatible License means a license listed at
 88 |      creativecommons.org/compatiblelicenses, approved by Creative
 89 |      Commons as essentially the equivalent of this Public License.
 90 | 
 91 |   d. Copyright and Similar Rights means copyright and/or similar rights
 92 |      closely related to copyright including, without limitation,
 93 |      performance, broadcast, sound recording, and Sui Generis Database
 94 |      Rights, without regard to how the rights are labeled or
 95 |      categorized. For purposes of this Public License, the rights
 96 |      specified in Section 2(b)(1)-(2) are not Copyright and Similar
 97 |      Rights.
 98 | 
 99 |   e. Effective Technological Measures means those measures that, in the
100 |      absence of proper authority, may not be circumvented under laws
101 |      fulfilling obligations under Article 11 of the WIPO Copyright
102 |      Treaty adopted on December 20, 1996, and/or similar international
103 |      agreements.
104 | 
105 |   f. Exceptions and Limitations means fair use, fair dealing, and/or
106 |      any other exception or limitation to Copyright and Similar Rights
107 |      that applies to Your use of the Licensed Material.
108 | 
109 |   g. License Elements means the license attributes listed in the name
110 |      of a Creative Commons Public License. The License Elements of this
111 |      Public License are Attribution and ShareAlike.
112 | 
113 |   h. Licensed Material means the artistic or literary work, database,
114 |      or other material to which the Licensor applied this Public
115 |      License.
116 | 
117 |   i. Licensed Rights means the rights granted to You subject to the
118 |      terms and conditions of this Public License, which are limited to
119 |      all Copyright and Similar Rights that apply to Your use of the
120 |      Licensed Material and that the Licensor has authority to license.
121 | 
122 |   j. Licensor means the individual(s) or entity(ies) granting rights
123 |      under this Public License.
124 | 
125 |   k. Share means to provide material to the public by any means or
126 |      process that requires permission under the Licensed Rights, such
127 |      as reproduction, public display, public performance, distribution,
128 |      dissemination, communication, or importation, and to make material
129 |      available to the public including in ways that members of the
130 |      public may access the material from a place and at a time
131 |      individually chosen by them.
132 | 
133 |   l. Sui Generis Database Rights means rights other than copyright
134 |      resulting from Directive 96/9/EC of the European Parliament and of
135 |      the Council of 11 March 1996 on the legal protection of databases,
136 |      as amended and/or succeeded, as well as other essentially
137 |      equivalent rights anywhere in the world.
138 | 
139 |   m. You means the individual or entity exercising the Licensed Rights
140 |      under this Public License. Your has a corresponding meaning.
141 | 
142 | 
143 | Section 2 -- Scope.
144 | 
145 |   a. License grant.
146 | 
147 |        1. Subject to the terms and conditions of this Public License,
148 |           the Licensor hereby grants You a worldwide, royalty-free,
149 |           non-sublicensable, non-exclusive, irrevocable license to
150 |           exercise the Licensed Rights in the Licensed Material to:
151 | 
152 |             a. reproduce and Share the Licensed Material, in whole or
153 |                in part; and
154 | 
155 |             b. produce, reproduce, and Share Adapted Material.
156 | 
157 |        2. Exceptions and Limitations. For the avoidance of doubt, where
158 |           Exceptions and Limitations apply to Your use, this Public
159 |           License does not apply, and You do not need to comply with
160 |           its terms and conditions.
161 | 
162 |        3. Term. The term of this Public License is specified in Section
163 |           6(a).
164 | 
165 |        4. Media and formats; technical modifications allowed. The
166 |           Licensor authorizes You to exercise the Licensed Rights in
167 |           all media and formats whether now known or hereafter created,
168 |           and to make technical modifications necessary to do so. The
169 |           Licensor waives and/or agrees not to assert any right or
170 |           authority to forbid You from making technical modifications
171 |           necessary to exercise the Licensed Rights, including
172 |           technical modifications necessary to circumvent Effective
173 |           Technological Measures. For purposes of this Public License,
174 |           simply making modifications authorized by this Section 2(a)
175 |           (4) never produces Adapted Material.
176 | 
177 |        5. Downstream recipients.
178 | 
179 |             a. Offer from the Licensor -- Licensed Material. Every
180 |                recipient of the Licensed Material automatically
181 |                receives an offer from the Licensor to exercise the
182 |                Licensed Rights under the terms and conditions of this
183 |                Public License.
184 | 
185 |             b. Additional offer from the Licensor -- Adapted Material.
186 |                Every recipient of Adapted Material from You
187 |                automatically receives an offer from the Licensor to
188 |                exercise the Licensed Rights in the Adapted Material
189 |                under the conditions of the Adapter's License You apply.
190 | 
191 |             c. No downstream restrictions. You may not offer or impose
192 |                any additional or different terms or conditions on, or
193 |                apply any Effective Technological Measures to, the
194 |                Licensed Material if doing so restricts exercise of the
195 |                Licensed Rights by any recipient of the Licensed
196 |                Material.
197 | 
198 |        6. No endorsement. Nothing in this Public License constitutes or
199 |           may be construed as permission to assert or imply that You
200 |           are, or that Your use of the Licensed Material is, connected
201 |           with, or sponsored, endorsed, or granted official status by,
202 |           the Licensor or others designated to receive attribution as
203 |           provided in Section 3(a)(1)(A)(i).
204 | 
205 |   b. Other rights.
206 | 
207 |        1. Moral rights, such as the right of integrity, are not
208 |           licensed under this Public License, nor are publicity,
209 |           privacy, and/or other similar personality rights; however, to
210 |           the extent possible, the Licensor waives and/or agrees not to
211 |           assert any such rights held by the Licensor to the limited
212 |           extent necessary to allow You to exercise the Licensed
213 |           Rights, but not otherwise.
214 | 
215 |        2. Patent and trademark rights are not licensed under this
216 |           Public License.
217 | 
218 |        3. To the extent possible, the Licensor waives any right to
219 |           collect royalties from You for the exercise of the Licensed
220 |           Rights, whether directly or through a collecting society
221 |           under any voluntary or waivable statutory or compulsory
222 |           licensing scheme. In all other cases the Licensor expressly
223 |           reserves any right to collect such royalties.
224 | 
225 | 
226 | Section 3 -- License Conditions.
227 | 
228 | Your exercise of the Licensed Rights is expressly made subject to the
229 | following conditions.
230 | 
231 |   a. Attribution.
232 | 
233 |        1. If You Share the Licensed Material (including in modified
234 |           form), You must:
235 | 
236 |             a. retain the following if it is supplied by the Licensor
237 |                with the Licensed Material:
238 | 
239 |                  i. identification of the creator(s) of the Licensed
240 |                     Material and any others designated to receive
241 |                     attribution, in any reasonable manner requested by
242 |                     the Licensor (including by pseudonym if
243 |                     designated);
244 | 
245 |                 ii. a copyright notice;
246 | 
247 |                iii. a notice that refers to this Public License;
248 | 
249 |                 iv. a notice that refers to the disclaimer of
250 |                     warranties;
251 | 
252 |                  v. a URI or hyperlink to the Licensed Material to the
253 |                     extent reasonably practicable;
254 | 
255 |             b. indicate if You modified the Licensed Material and
256 |                retain an indication of any previous modifications; and
257 | 
258 |             c. indicate the Licensed Material is licensed under this
259 |                Public License, and include the text of, or the URI or
260 |                hyperlink to, this Public License.
261 | 
262 |        2. You may satisfy the conditions in Section 3(a)(1) in any
263 |           reasonable manner based on the medium, means, and context in
264 |           which You Share the Licensed Material. For example, it may be
265 |           reasonable to satisfy the conditions by providing a URI or
266 |           hyperlink to a resource that includes the required
267 |           information.
268 | 
269 |        3. If requested by the Licensor, You must remove any of the
270 |           information required by Section 3(a)(1)(A) to the extent
271 |           reasonably practicable.
272 | 
273 |   b. ShareAlike.
274 | 
275 |      In addition to the conditions in Section 3(a), if You Share
276 |      Adapted Material You produce, the following conditions also apply.
277 | 
278 |        1. The Adapter's License You apply must be a Creative Commons
279 |           license with the same License Elements, this version or
280 |           later, or a BY-SA Compatible License.
281 | 
282 |        2. You must include the text of, or the URI or hyperlink to, the
283 |           Adapter's License You apply. You may satisfy this condition
284 |           in any reasonable manner based on the medium, means, and
285 |           context in which You Share Adapted Material.
286 | 
287 |        3. You may not offer or impose any additional or different terms
288 |           or conditions on, or apply any Effective Technological
289 |           Measures to, Adapted Material that restrict exercise of the
290 |           rights granted under the Adapter's License You apply.
291 | 
292 | 
293 | Section 4 -- Sui Generis Database Rights.
294 | 
295 | Where the Licensed Rights include Sui Generis Database Rights that
296 | apply to Your use of the Licensed Material:
297 | 
298 |   a. for the avoidance of doubt, Section 2(a)(1) grants You the right
299 |      to extract, reuse, reproduce, and Share all or a substantial
300 |      portion of the contents of the database;
301 | 
302 |   b. if You include all or a substantial portion of the database
303 |      contents in a database in which You have Sui Generis Database
304 |      Rights, then the database in which You have Sui Generis Database
305 |      Rights (but not its individual contents) is Adapted Material,
306 |      including for purposes of Section 3(b); and
307 | 
308 |   c. You must comply with the conditions in Section 3(a) if You Share
309 |      all or a substantial portion of the contents of the database.
310 | 
311 | For the avoidance of doubt, this Section 4 supplements and does not
312 | replace Your obligations under this Public License where the Licensed
313 | Rights include other Copyright and Similar Rights.
314 | 
315 | 
316 | Section 5 -- Disclaimer of Warranties and Limitation of Liability.
317 | 
318 |   a. UNLESS OTHERWISE SEPARATELY UNDERTAKEN BY THE LICENSOR, TO THE
319 |      EXTENT POSSIBLE, THE LICENSOR OFFERS THE LICENSED MATERIAL AS-IS
320 |      AND AS-AVAILABLE, AND MAKES NO REPRESENTATIONS OR WARRANTIES OF
321 |      ANY KIND CONCERNING THE LICENSED MATERIAL, WHETHER EXPRESS,
322 |      IMPLIED, STATUTORY, OR OTHER. THIS INCLUDES, WITHOUT LIMITATION,
323 |      WARRANTIES OF TITLE, MERCHANTABILITY, FITNESS FOR A PARTICULAR
324 |      PURPOSE, NON-INFRINGEMENT, ABSENCE OF LATENT OR OTHER DEFECTS,
325 |      ACCURACY, OR THE PRESENCE OR ABSENCE OF ERRORS, WHETHER OR NOT
326 |      KNOWN OR DISCOVERABLE. WHERE DISCLAIMERS OF WARRANTIES ARE NOT
327 |      ALLOWED IN FULL OR IN PART, THIS DISCLAIMER MAY NOT APPLY TO YOU.
328 | 
329 |   b. TO THE EXTENT POSSIBLE, IN NO EVENT WILL THE LICENSOR BE LIABLE
330 |      TO YOU ON ANY LEGAL THEORY (INCLUDING, WITHOUT LIMITATION,
331 |      NEGLIGENCE) OR OTHERWISE FOR ANY DIRECT, SPECIAL, INDIRECT,
332 |      INCIDENTAL, CONSEQUENTIAL, PUNITIVE, EXEMPLARY, OR OTHER LOSSES,
333 |      COSTS, EXPENSES, OR DAMAGES ARISING OUT OF THIS PUBLIC LICENSE OR
334 |      USE OF THE LICENSED MATERIAL, EVEN IF THE LICENSOR HAS BEEN
335 |      ADVISED OF THE POSSIBILITY OF SUCH LOSSES, COSTS, EXPENSES, OR
336 |      DAMAGES. WHERE A LIMITATION OF LIABILITY IS NOT ALLOWED IN FULL OR
337 |      IN PART, THIS LIMITATION MAY NOT APPLY TO YOU.
338 | 
339 |   c. The disclaimer of warranties and limitation of liability provided
340 |      above shall be interpreted in a manner that, to the extent
341 |      possible, most closely approximates an absolute disclaimer and
342 |      waiver of all liability.
343 | 
344 | 
345 | Section 6 -- Term and Termination.
346 | 
347 |   a. This Public License applies for the term of the Copyright and
348 |      Similar Rights licensed here. However, if You fail to comply with
349 |      this Public License, then Your rights under this Public License
350 |      terminate automatically.
351 | 
352 |   b. Where Your right to use the Licensed Material has terminated under
353 |      Section 6(a), it reinstates:
354 | 
355 |        1. automatically as of the date the violation is cured, provided
356 |           it is cured within 30 days of Your discovery of the
357 |           violation; or
358 | 
359 |        2. upon express reinstatement by the Licensor.
360 | 
361 |      For the avoidance of doubt, this Section 6(b) does not affect any
362 |      right the Licensor may have to seek remedies for Your violations
363 |      of this Public License.
364 | 
365 |   c. For the avoidance of doubt, the Licensor may also offer the
366 |      Licensed Material under separate terms or conditions or stop
367 |      distributing the Licensed Material at any time; however, doing so
368 |      will not terminate this Public License.
369 | 
370 |   d. Sections 1, 5, 6, 7, and 8 survive termination of this Public
371 |      License.
372 | 
373 | 
374 | Section 7 -- Other Terms and Conditions.
375 | 
376 |   a. The Licensor shall not be bound by any additional or different
377 |      terms or conditions communicated by You unless expressly agreed.
378 | 
379 |   b. Any arrangements, understandings, or agreements regarding the
380 |      Licensed Material not stated herein are separate from and
381 |      independent of the terms and conditions of this Public License.
382 | 
383 | 
384 | Section 8 -- Interpretation.
385 | 
386 |   a. For the avoidance of doubt, this Public License does not, and
387 |      shall not be interpreted to, reduce, limit, restrict, or impose
388 |      conditions on any use of the Licensed Material that could lawfully
389 |      be made without permission under this Public License.
390 | 
391 |   b. To the extent possible, if any provision of this Public License is
392 |      deemed unenforceable, it shall be automatically reformed to the
393 |      minimum extent necessary to make it enforceable. If the provision
394 |      cannot be reformed, it shall be severed from this Public License
395 |      without affecting the enforceability of the remaining terms and
396 |      conditions.
397 | 
398 |   c. No term or condition of this Public License will be waived and no
399 |      failure to comply consented to unless expressly agreed to by the
400 |      Licensor.
401 | 
402 |   d. Nothing in this Public License constitutes or may be interpreted
403 |      as a limitation upon, or waiver of, any privileges and immunities
404 |      that apply to the Licensor or You, including from the legal
405 |      processes of any jurisdiction or authority.
406 | 
407 | 
408 | =======================================================================
409 | 
410 | Creative Commons is not a party to its public licenses.
411 | Notwithstanding, Creative Commons may elect to apply one of its public
412 | licenses to material it publishes and in those instances will be
413 | considered the “Licensor.” The text of the Creative Commons public
414 | licenses is dedicated to the public domain under the CC0 Public Domain
415 | Dedication. Except for the limited purpose of indicating that material
416 | is shared under a Creative Commons public license or as otherwise
417 | permitted by the Creative Commons policies published at
418 | creativecommons.org/policies, Creative Commons does not authorize the
419 | use of the trademark "Creative Commons" or any other trademark or logo
420 | of Creative Commons without its prior written consent including,
421 | without limitation, in connection with any unauthorized modifications
422 | to any of its public licenses or any other arrangements,
423 | understandings, or agreements concerning use of licensed material. For
424 | the avoidance of doubt, this paragraph does not form part of the public
425 | licenses.
426 | 
427 | Creative Commons may be contacted at creativecommons.org.


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
  1 | # KuaiRec: A Fully-observed Dataset for Recommender Systems (Density: Almost 100%)
  2 | 
  3 | [![LICENSE](https://img.shields.io/badge/license-CC%20BY--SA%204.0-green)](https://github.com/chongminggao/KuaiRec/blob/main/LICENSE)
  4 | 
  5 | *KuaiRec* is a real-world dataset collected from the recommendation logs of the video-sharing mobile app [Kuaishou](https://www.kuaishou.com/cn). For now, it is the first dataset that contains a fully observed user-item interaction matrix. For the term "fully observed", we mean there are almost no missing values in the user-item matrix,  i.e., each user has viewed each video and then left feedback. 
  6 | 
  7 | Other related **open-sourced** datasets are **[KuaiRand](https://kuairand.com/)** and **[KuaiSAR](https://kuaisar.github.io/)**.
  8 | 
  9 | The following figure illustrates the user-item matrices in traditional datasets and *KuaiRec*.
 10 | 
 11 | ![kuaidata](figs/kuairec-long.png)
 12 | 
 13 | With all user preferences known, KuaiRec can used in offline evaluation (i.e., offline A/B test) for recommendation models. It can benefit lots of research directions, such as unbiased recommendation, interactive/conversational recommendation, reinforcement learning (RL), and off-policy evaluation (OPE) for recommendation.
 14 | 
 15 | If you use it in your work, please cite our paper:
 16 |  [![LINK](https://img.shields.io/badge/-Paper%20Link-lightgrey)](https://arxiv.org/abs/2202.10842) [![PDF](https://img.shields.io/badge/-PDF-red)](https://arxiv.org/pdf/2202.10842.pdf)
 17 | 
 18 | ```
 19 | @inproceedings{gao2022kuairec,
 20 |   author = {Gao, Chongming and Li, Shijun and Lei, Wenqiang and Chen, Jiawei and Li, Biao and Jiang, Peng and He, Xiangnan and Mao, Jiaxin and Chua, Tat-Seng},
 21 |   title = {KuaiRec: A Fully-Observed Dataset and Insights for Evaluating Recommender Systems},
 22 |   booktitle = {Proceedings of the 31st ACM International Conference on Information \& Knowledge Management},
 23 |   series = {CIKM '22},
 24 |   location = {Atlanta, GA, USA},
 25 |   url = {https://doi.org/10.1145/3511808.3557220},
 26 |   doi = {10.1145/3511808.3557220},
 27 |   numpages = {11},
 28 |   year = {2022},
 29 |   pages = {540–550}
 30 | }
 31 | ```
 32 | 
 33 | [This repository](https://github.com/xiwenchao/fully_observed_demo) lists the example codes in evaluating conversational recommendations as described in the paper.
 34 | 
 35 | We provide some simple statistics of this dataset [here](https://kuairec.com/Statistics_KuaiRec.html). It is generated by [Statistics_KuaiRec.ipynb](https://github.com/chongminggao/KuaiRec/blob/main/Statistics_KuaiRec.ipynb). You can do it online at Google Colab [![colab](./figs/colab-badge.svg)](https://colab.research.google.com/github/chongminggao/KuaiRec/blob/main/Statistics_KuaiRec.ipynb).
 36 | 
 37 | ---
 38 | 
 39 | ## News!
 40 | 
 41 | **2024.06.02: To facilitate the application of large language models (LLM) in recommendation systems, we collect caption information and category information for all videos and presented them in text format!** 
 42 | 
 43 | - The corresponding caption and category information can be downloaded here: [kuairec_caption_category.csv](https://github.com/chongminggao/KuaiRec/blob/main/kuairec_caption_category.csv). Additionally, we have packaged them into the `KuaiRec.zip` file, which can be downloaded from the download section below.  
 44 | - The descriptions of the caption and category information are available [here](#6-descriptions-of-the-caption-and-category-fields-in-kuairec_caption_categorycsv-added-on-20240602).
 45 | 
 46 | **2022.05.16: We update the dataset to version 2.0.** We made the following changes:
 47 | 
 48 | - We removed the unused video `ID=1225` from all tables having the field `video_id` and re-indexed the rest videos, i.e., `ID = ID - 1 if ID > 1225`. 
 49 | - We added two tables to enhance the side information for users and videos, respectively. See `4.item_daily_features.csv` and `5. user_features.csv` under the data description section for details.
 50 | 
 51 | 
 52 | 
 53 | 
 54 | ## Download the data
 55 | 
 56 | We provide several options to download this dataset:
 57 | 
 58 |   Option 1. Download via the "wget" command.
 59 | 
 60 | ```shell
 61 |  wget https://nas.chongminggao.top:4430/datasets/KuaiRec.zip --no-check-certificate
 62 |  unzip KuaiRec.zip
 63 | ```
 64 |   Option 2. Download manually through the following links:
 65 | 
 66 |   - Optional link 1: [Google Drive](https://drive.google.com/file/d/1qe5hOSBxzIuxBb1G_Ih5X-O65QElollE/view?usp=sharing)
 67 | 
 68 |   - Optional link 2: [USTC Drive (中科大)](https://rec.ustc.edu.cn/share/00cc9940-aa72-11ec-aa7d-d38daca349cb)
 69 | 
 70 | The script `loaddata.py` provides a simple way to load the data via Pandas in Python.
 71 | 
 72 | ---
 73 | 
 74 | ## Data Descriptions
 75 | 
 76 | *KuaiRec* contains millions of user-item interactions as well as side information including the item categories and a social network. Six files are included in the download data: 
 77 | 
 78 |   ```shell
 79 |   KuaiRec
 80 |   ├── data
 81 |   │   ├── big_matrix.csv          
 82 |   │   ├── small_matrix.csv
 83 |   │   ├── social_network.csv
 84 |   │   ├── user_features.csv
 85 |   │   ├── item_daily_features.csv
 86 |   │   └── item_categories.csv
 87 |   │   └── kuairec_caption_category.csv
 88 |   ```
 89 | 
 90 | The statistics of the small matrix and big matrix in *KuaiRec*.
 91 | 
 92 | |                | #Users | #Items | #Interactions | Density |
 93 | | -------------- | :----: | :----: | :-----------: | :-----: |
 94 | | *small matrix* | 1,411  | 3,327  |   4,676,570   |  99.6%  |
 95 | | *big matrix*   | 7,176  | 10,728 |  12,530,806   |  16.3%  |
 96 | 
 97 | Note that the density of the small matrix is 99.6% instead of 100% because some users have explicitly indicated that they would not be willing to receive recommendations from certain authors. I.e., They blocked these videos.
 98 | 
 99 | #### 1. Descriptions of the fields in `big_matrix.csv` and `small_matrix.csv`. 
100 | 
101 | | Field Name:    | Description                                              | Type    | Example                   |
102 | | -------------- | -------------------------------------------------------- | ------- | ------------------------- |
103 | | user_id        | The ID of the user.                                      | int64   | 0                         |
104 | | video_id       | The ID of the viewed video.                              | int64   | 3650                      |
105 | | play_duration  | Time of video viewing of this interaction (millisecond). | int64   | 13838                     |
106 | | video_duration | Time of this video (millisecond).                        | int64   | 10867                     |
107 | | time           | Human-readable date for this interaction                 | str     | "2020-07-05 00:08:23.438" |
108 | | date           | Date of this interaction                                 | int64   | 20200705                  |
109 | | timestamp      | Unix timestamp                                           | float64 | 1593878903.438            |
110 | | watch_ratio    | The video watching ratio (=play_duration/video_duration) | float64 | 1.273397                  |
111 | 
112 | The "watch_ratio" can be deemed as the label of the interaction. Note: there is no "like" signal for this dataset. If you need this binary signal in your scenarios, you can create it yourself. E.g., `like = 1 if watch_ratio > 2.0`.
113 | 
114 | #### 2. Descriptions of the fields in `social_network.csv`
115 | 
116 | | Field Name: | Description                                  | Type  | Example     |
117 | | ----------- | -------------------------------------------- | ----- | ----------- |
118 | | user_id     | The ID of the user.                          | int64 | 5352        |
119 | | friend_list | The list of IDs of the friends of this user. | list  | [4202,7126] |
120 | 
121 | #### 3. Descriptions of the fields in `item_categories.csv`. 
122 | 
123 | | Field Name: | Description                     | Type  | Example |
124 | | ----------- | ------------------------------- | ----- | ------- |
125 | | video_id    | The ID of the video.            | int64 | 1       |
126 | | feat        | The list of tags of this video. | list  | [27,9]  |
127 | 
128 | #### 4. Descriptions of the fields in `item_daily_features.csv`. (Added on 2022.05.16)
129 | 
130 | | Field Name:              | Description                                                                                                                    | Type    | Example       |
131 | | ------------------------ | ------------------------------------------------------------------------------------------------------------------------------ | ------- | ------------- |
132 | | video_id                 | The ID of the video.                                                                                                           | int64   | 3784          |
133 | | date                     | Date of the statistics of this video.                                                                                          | int64   | 20200730      |
134 | | author_id                | The ID of the author of this video.                                                                                            | int64   | 441           |
135 | | video_type               | Type of this video (NORMAL or AD).                                                                                             | str     | "NORMAL"      |
136 | | upload_dt                | Upload date of this video.                                                                                                     | str     | "2020-07-08"  |
137 | | upload_type              | The upload type of this video.                                                                                                 | str     | "ShortImport" |
138 | | visible_status           | The visible state of this video on the APP now.                                                                                | str     | "public"      |
139 | | video_duration           | The time duration of this duration (in milliseconds).                                                                          | float64 | 17200.0       |
140 | | video_width              | The width of this video on the server.                                                                                         | int64   | 720           |
141 | | video_height             | The height of this video on the server.                                                                                        | int64   | 1280          |
142 | | music_id                 | Background music ID of this video.                                                                                             | int64   | 989206467     |
143 | | video_tag_id             | The ID of the tag of this video.                                                                                               | int64   | 2522          |
144 | | video_tag_name           | The name of the tag of this video.                                                                                             | string  | "祝福"        |
145 | | show_cnt                 | The number of shows of this video **within this day (the same with all following fields)**                                     | int64   | 7716          |
146 | | show_user_num            | The number of users who received the recommendation of this video.                                                             | int64   | 5256          |
147 | | play_cnt                 | The number of plays.                                                                                                           | int64   | 7701          |
148 | | play_user_num            | The number of users who play this video.                                                                                       | int64   | 5034          |
149 | | play_duration            | The total time duration of playing this video (in milliseconds).                                                               | int64   | 138333346     |
150 | | complete_play_cnt        | The number of complete plays. *complete play*: finishing playing the whole video, i.e., `#(play_duration >= video_duration)`.  | int64   | 3446          |
151 | | complete_play_user_num   | The number of users who perform the *complete play*.                                                                           | int64   | 2033          |
152 | | valid_play_cnt           | *valid play*: `play_duration >= video_duration if video_duration <= 7s`, or `play_duration > 7 if video_duration > 7s`.        | int64   | 5099          |
153 | | valid_play_user_num      | The number of users who perform the *complete play*.                                                                           | int64   | 3195          |
154 | | long_time_play_cnt       | *long time play*: `play_duration >= video_duration if video_duration <= 18s`, or `play_duration >=18 if video_duration > 18s`. | int64   | 3299          |
155 | | long_time_play_user_num  | The number of users who perform the *long time play*.                                                                          | int64   | 1940          |
156 | | short_time_play_cnt      | *short time play*: `play_duration < min(3s, video_duration)`.                                                                  | int64   | 1538          |
157 | | short_time_play_user_num | The number of users who perform the *short time play*.                                                                         | int64   | 1190          |
158 | | play_progress            | The average video playing ratio (`=play_duration/video_duration`)                                                              | int64   | 0.579695      |
159 | | comment_stay_duration    | Total time of staying in the comments section                                                                                  | int64   | 467865        |
160 | | like_cnt                 | Total likes                                                                                                                    | int64   | 659           |
161 | | like_user_num            | The number of users who hit the "like" button.                                                                                 | int64   | 657           |
162 | | click_like_cnt           | The number of the "like" resulted from double click                                                                            | int64   | 496           |
163 | | double_click_cnt         | The number of users who double-click the video.                                                                                | int64   | 163           |
164 | | cancel_like_cnt          | The number of likes that are canceled by users.                                                                                | int64   | 15            |
165 | | cancel_like_user_num     | The number of users who cancel their likes.                                                                                    | int64   | 15            |
166 | | comment_cnt              | The number of comments within this day.                                                                                        | int64   | 13            |
167 | | comment_user_num         | The number of users who comment on this video.                                                                                 | int64   | 12            |
168 | | direct_comment_cnt       | The number of direct comments (depth=1).                                                                                       | int64   | 13            |
169 | | reply_comment_cnt        | The number of reply comments (depth>1).                                                                                        | int64   | 0             |
170 | | delete_comment_cnt       | The number of deleted comments.                                                                                                | int64   | 0             |
171 | | delete_comment_user_num  | The number of users who delete their comments.                                                                                 | int64   | 0             |
172 | | comment_like_cnt         | The number of comment likes.                                                                                                   | int64   | 2             |
173 | | comment_like_user_num    | The number of users who like the comments.                                                                                     | int64   | 2             |
174 | | follow_cnt               | The number of increased follows from this video.                                                                               | int64   | 151           |
175 | | follow_user_num          | The number of users who follow the author of this video due to this video.                                                     | int64   | 151           |
176 | | cancel_follow_cnt        | The number of decreased follows from this video.                                                                               | int64   | 0             |
177 | | cancel_follow_user_num   | The number of users who cancel their following of the author of this video due to this video.                                  | int64   | 0             |
178 | | share_cnt                | The times of sharing this video.                                                                                               | int64   | 1             |
179 | | share_user_num           | The number of users who share this video.                                                                                      | int64   | 1             |
180 | | download_cnt             | The times of downloading this video.                                                                                           | int64   | 2             |
181 | | download_user_num        | The number of users who download this video.                                                                                   | int64   | 2             |
182 | | report_cnt               | The times of reporting this video.                                                                                             | int64   | 0             |
183 | | report_user_num          | The number of users who report this video.                                                                                     | int64   | 0             |
184 | | reduce_similar_cnt       | The times of reducing similar content of this video.                                                                           | int64   | 2             |
185 | | reduce_similar_user_num  | The number of users who choose to reduce similar content of this video.                                                        | int64   | 2             |
186 | | collect_cnt              | The times of adding this video to favorite videos.                                                                             | int64   | 0             |
187 | | collect_user_num         | The number of users who add this video to their favorite videos.                                                               | int64   | 0             |
188 | | cancel_collect_cnt       | The times of removing this video from favorite videos.                                                                         | int64   | 0             |
189 | | cancel_collect_user_num  | The number of users who remove this video from their favorite videos                                                           | int64   | 0             |
190 | 
191 | 
192 | #### 5. Descriptions of the fields in `user_features.csv` (Added on 2022.05.16)
193 | 
194 | | Field Name:           | Description                                                                                                                                                  | Type  | Example       |
195 | | --------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------ | ----- | ------------- |
196 | | user_id               | The ID of the user.                                                                                                                                          | int64 | 0             |
197 | | user_active_degree    | In the set of {'high_active', 'full_active', 'middle_active', 'UNKNOWN'}.                                                                                    | str   | "high_active" |
198 | | is_lowactive_period   | Is this user in its low active period                                                                                                                        | int64 | 0             |
199 | | is_live_streamer      | Is this user a live streamer？                                                                                                                               | int64 | 0             |
200 | | is_video_author       | Has this user uploaded any video？                                                                                                                           | int64 | 0             |
201 | | follow_user_num       | The number of users that this user follows.                                                                                                                  | int64 | 5             |
202 | | follow_user_num_range | The range of the number of users that this user follows. In the set of {'0', '(0,10]', '(10,50]', '(100,150]', '(150,250]', '(250,500]', '(50,100]', '500+'} | str   | "(0,10]"      |
203 | | fans_user_num         | The number of the fans of this user.                                                                                                                         | int64 | 0             |
204 | | fans_user_num_range   | The range of the number of fans of this user. In the set of {'0', '[1,10)', '[10,100)', '[100,1k)', '[1k,5k)',  '[5k,1w)', '[1w,10w)'}                       | str   | "0"           |
205 | | friend_user_num       | The number of friends that this user has.                                                                                                                    | int64 | 0             |
206 | | friend_user_num_range | The range of the number of friends that this user has.  In the set of {'0', '[1,5)', '[5,30)', '[30,60)', '[60,120)', '[120,250)', '250+'}                   | str   | "0"           |
207 | | register_days         | The days since this user has registered.                                                                                                                     | int64 | 107           |
208 | | register_days_range   | The range of the registered days. In the set of {'15-30', '31-60', '61-90', '91-180', '181-365', '366-730', '730+'}.                                         | str   | "61-90"       |
209 | | onehot_feat0          | An encrypted feature of the user. Each value indicate the position of "1" in the one-hot vector. Range: {0,1}                                                | int64 | 0             |
210 | | onehot_feat1          | An encrypted feature. Range: {0, 1, ..., 7}                                                                                                                  | int64 | 1             |
211 | | onehot_feat2          | An encrypted feature. Range: {0, 1, ..., 29}                                                                                                                 | int64 | 17            |
212 | | onehot_feat3          | An encrypted feature. Range: {0, 1, ..., 1075}                                                                                                               | int64 | 638           |
213 | | onehot_feat4          | An encrypted feature. Range: {0, 1, ..., 11}                                                                                                                 | int64 | 2             |
214 | | onehot_feat5          | An encrypted feature. Range: {0, 1, ..., 9}                                                                                                                  | int64 | 0             |
215 | | onehot_feat6          | An encrypted feature. Range: {0, 1, 2}                                                                                                                       | int64 | 1             |
216 | | onehot_feat7          | An encrypted feature. Range: {0, 1, ..., 46}                                                                                                                 | int64 | 6             |
217 | | onehot_feat8          | An encrypted feature. Range: {0, 1, ..., 339}                                                                                                                | int64 | 184           |
218 | | onehot_feat9          | An encrypted feature. Range: {0, 1, ..., 6}                                                                                                                  | int64 | 6             |
219 | | onehot_feat10         | An encrypted feature. Range: {0, 1, ..., 4}                                                                                                                  | int64 | 3             |
220 | | onehot_feat11         | An encrypted feature. Range: {0, 1, ..., 2}                                                                                                                  | int64 | 0             |
221 | | onehot_feat12         | An encrypted feature. Range: {0, 1}                                                                                                                          | int64 | 0             |
222 | | onehot_feat13         | An encrypted feature. Range: {0, 1}                                                                                                                          | int64 | 0             |
223 | | onehot_feat14         | An encrypted feature. Range: {0, 1}                                                                                                                          | int64 | 0             |
224 | | onehot_feat15         | An encrypted feature. Range: {0, 1}                                                                                                                          | int64 | 0             |
225 | | onehot_feat16         | An encrypted feature. Range: {0, 1}                                                                                                                          | int64 | 0             |
226 | | onehot_feat17         | An encrypted feature. Range: {0, 1}                                                                                                                          | int64 | 0             |
227 | 
228 | 
229 | #### 6. Descriptions of the caption and category fields in `kuairec_caption_category.csv` (Added on 2024.06.02)
230 | 
231 | 
232 | | Field Name:                | Description                                            | Type  | Example                                                      |
233 | | -------------------------- | ------------------------------------------------------ | ----- | ------------------------------------------------------------ |
234 | | video_id                   | The ID of the video                                    | int64 | 2418                                                         |
235 | | manual_cover_text          | 封面文字 (added by its author)                         | str   | "被小可爱发现了"                                             |
236 | | caption                    | 简介标题 (added by its author)                         | str   | "这是什么狗狗，这么可爱真的可以这么遛吗？#喜欢的双击加关注 #直播 #博美俊介 #萌宠驾到" |
237 | | topic_tag                  | Tags of the topics of this video (added by its author) | str   | "[博美俊介,喜欢的双击加关注,直播,萌宠驾到]"                  |
238 | | first_level_category_id    | First-level category ID                                | int64 | 17                                                           |
239 | | first_level_category_name  | First-level category name                              | str   | "宠物"                                                       |
240 | | second_level_category_id   | Second-level category ID                               | int64 | 233                                                          |
241 | | second_level_category_name | Second-level category name                             | str   | "宠物日常记录"                                               |
242 | | third_level_category_id    | Thrid-level category ID                                | int64 | 1169                                                         |
243 | | third_level_category_name  | Third-level category name                              | str   | "宠物狗"                                                     |


--------------------------------------------------------------------------------