diff --git a/sfw_tags/e621_filter.ipynb b/sfw_tags/e621_filter.ipynb deleted file mode 100644 index 753f947..0000000 --- a/sfw_tags/e621_filter.ipynb +++ /dev/null @@ -1,2348 +0,0 @@ -{ - "cells": [ - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "Download the dataset here [Index of /db_export/](https://e621.net/db_export/). It should look something like `posts-2023-11-03.csv.gz`." - ] - }, - { - "cell_type": "code", - "execution_count": 3, - "id": "82071b51", - "metadata": {}, - "outputs": [], - "source": [ - "import pandas as pd\n", - "\n", - "# Replace 'your_file.csv' with the actual file name and path if it's not in the current directory\n", - "df = pd.read_csv('posts-2023-11-03.csv')" - ] - }, - { - "cell_type": "code", - "execution_count": 10, - "id": "62d24603", - "metadata": {}, - "outputs": [ - { - "data": { - "text/html": [ - "
| \n", - " | id | \n", - "uploader_id | \n", - "created_at | \n", - "md5 | \n", - "source | \n", - "rating | \n", - "image_width | \n", - "image_height | \n", - "tag_string | \n", - "locked_tags | \n", - "... | \n", - "updated_at | \n", - "is_deleted | \n", - "is_pending | \n", - "is_flagged | \n", - "score | \n", - "up_score | \n", - "down_score | \n", - "is_rating_locked | \n", - "is_status_locked | \n", - "is_note_locked | \n", - "
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | \n", - "13 | \n", - "6 | \n", - "2007-02-10 06:20:51.823829 | \n", - "c884231ca9bb7bd294dff4d6463e2f54 | \n", - "cbee | \n", - "e | \n", - "994 | \n", - "768 | \n", - "<3 avoid_posting big_breasts black_and_white b... | \n", - "avoid_posting | \n", - "... | \n", - "2023-11-01 18:40:14.525427 | \n", - "t | \n", - "f | \n", - "f | \n", - "76 | \n", - "79 | \n", - "-6 | \n", - "t | \n", - "f | \n", - "t | \n", - "
| 1 | \n", - "14 | \n", - "7 | \n", - "2007-02-10 07:17:30.687994 | \n", - "3e47080200fbde2d7d2ccf419343ab0a | \n", - "https://www.furaffinity.net/view/267581/\\nhttp... | \n", - "e | \n", - "581 | \n", - "793 | \n", - "2006 4_toes accessory animal_genitalia animal_... | \n", - "NaN | \n", - "... | \n", - "2023-11-02 21:38:26.840561 | \n", - "f | \n", - "f | \n", - "f | \n", - "923 | \n", - "954 | \n", - "-33 | \n", - "t | \n", - "f | \n", - "t | \n", - "
| 2 | \n", - "15 | \n", - "7 | \n", - "2007-02-10 18:50:40.09919 | \n", - "326065d926185463f00b684e3c763cee | \n", - "https://www.furaffinity.net/view/90528/\\nhttps... | \n", - "e | \n", - "592 | \n", - "811 | \n", - "2006 4_toes abs after_masturbation animal_geni... | \n", - "NaN | \n", - "... | \n", - "2023-10-30 06:59:35.193615 | \n", - "f | \n", - "f | \n", - "f | \n", - "177 | \n", - "191 | \n", - "-14 | \n", - "t | \n", - "f | \n", - "f | \n", - "
| 3 | \n", - "16 | \n", - "8 | \n", - "2007-02-10 18:57:18.54022 | \n", - "3070e4234dd36148149508bd24ccb59d | \n", - "NaN | \n", - "q | \n", - "831 | \n", - "648 | \n", - "breasts cub female heterochromia male mellis p... | \n", - "NaN | \n", - "... | \n", - "2023-06-03 08:34:57.873522 | \n", - "t | \n", - "f | \n", - "f | \n", - "2 | \n", - "2 | \n", - "-1 | \n", - "t | \n", - "f | \n", - "t | \n", - "
| 4 | \n", - "17 | \n", - "17633 | \n", - "2007-02-10 19:57:56.809237 | \n", - "9fceaae92efc38ef8d975b6401bd44f5 | \n", - "https://www.furaffinity.net/view/2598065/\\nhtt... | \n", - "e | \n", - "750 | \n", - "759 | \n", - "2007 4_claws 4_fingers anal anal_penetration a... | \n", - "avoid_posting | \n", - "... | \n", - "2023-04-20 02:36:23.490887 | \n", - "t | \n", - "f | \n", - "f | \n", - "11 | \n", - "30 | \n", - "-20 | \n", - "t | \n", - "f | \n", - "t | \n", - "
| ... | \n", - "... | \n", - "... | \n", - "... | \n", - "... | \n", - "... | \n", - "... | \n", - "... | \n", - "... | \n", - "... | \n", - "... | \n", - "... | \n", - "... | \n", - "... | \n", - "... | \n", - "... | \n", - "... | \n", - "... | \n", - "... | \n", - "... | \n", - "... | \n", - "... | \n", - "
| 4383040 | \n", - "4391235 | \n", - "1290215 | \n", - "2023-11-03 07:31:39.787594 | \n", - "b3a7cb39ebc5bd5f4864b32c2d6b1d58 | \n", - "https://twitter.com/nightlyflare/status/172014... | \n", - "s | \n", - "2569 | \n", - "3000 | \n", - "absurd_res animal_humanoid anthro big_breasts ... | \n", - "NaN | \n", - "... | \n", - "2023-11-03 07:39:11.629566 | \n", - "f | \n", - "t | \n", - "f | \n", - "0 | \n", - "0 | \n", - "0 | \n", - "f | \n", - "f | \n", - "f | \n", - "
| 4383041 | \n", - "4391236 | \n", - "476767 | \n", - "2023-11-03 07:33:44.110026 | \n", - "d4d6a05400080844d3c3c8df93ecfa18 | \n", - "https://twitter.com/gorarati/status/1713728743... | \n", - "s | \n", - "1721 | \n", - "2048 | \n", - "blue_archive clothed clothing female gorarati ... | \n", - "NaN | \n", - "... | \n", - "2023-11-03 07:38:38.863137 | \n", - "f | \n", - "t | \n", - "f | \n", - "1 | \n", - "1 | \n", - "0 | \n", - "f | \n", - "f | \n", - "f | \n", - "
| 4383042 | \n", - "4391237 | \n", - "476767 | \n", - "2023-11-03 07:35:32.205753 | \n", - "65d7597a89bab8cf72f2a646e4d612c4 | \n", - "https://twitter.com/gorarati/status/1716868836... | \n", - "s | \n", - "2048 | \n", - "1689 | \n", - "<3 animal_humanoid burger canid canid_humanoid... | \n", - "NaN | \n", - "... | \n", - "2023-11-03 07:39:23.345716 | \n", - "f | \n", - "t | \n", - "f | \n", - "1 | \n", - "1 | \n", - "0 | \n", - "f | \n", - "f | \n", - "f | \n", - "
| 4383043 | \n", - "4391238 | \n", - "732974 | \n", - "2023-11-03 07:36:45.096775 | \n", - "95d17431e93c54b24f3ce09404b13ed7 | \n", - "https://inkbunny.net/s/559208\\nhttps://www.sof... | \n", - "s | \n", - "1485 | \n", - "1642 | \n", - ":3 alternate_version_at_source ambiguous_gende... | \n", - "NaN | \n", - "... | \n", - "2023-11-03 07:40:01.385491 | \n", - "f | \n", - "t | \n", - "f | \n", - "0 | \n", - "0 | \n", - "0 | \n", - "f | \n", - "f | \n", - "f | \n", - "
| 4383044 | \n", - "4391239 | \n", - "476767 | \n", - "2023-11-03 07:38:08.342394 | \n", - "f0e8594fd235c1bd974dedb740873bc7 | \n", - "https://twitter.com/gorarati/status/1714662635... | \n", - "q | \n", - "1511 | \n", - "2048 | \n", - "animal_humanoid bodily_fluids cat_humanoid clo... | \n", - "NaN | \n", - "... | \n", - "2023-11-03 07:39:37.003747 | \n", - "f | \n", - "t | \n", - "f | \n", - "0 | \n", - "0 | \n", - "0 | \n", - "f | \n", - "f | \n", - "f | \n", - "
4383045 rows × 29 columns
\n", - "| \n", - " | id | \n", - "uploader_id | \n", - "created_at | \n", - "md5 | \n", - "source | \n", - "rating | \n", - "image_width | \n", - "image_height | \n", - "tag_string | \n", - "locked_tags | \n", - "... | \n", - "updated_at | \n", - "is_deleted | \n", - "is_pending | \n", - "is_flagged | \n", - "score | \n", - "up_score | \n", - "down_score | \n", - "is_rating_locked | \n", - "is_status_locked | \n", - "is_note_locked | \n", - "
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 27 | \n", - "41 | \n", - "17633 | \n", - "2007-02-10 20:25:47.58374 | \n", - "7f341ce17a775951afc69b898d7f8cd8 | \n", - "https://chan.sankakucomplex.com/post/show/2296448 | \n", - "s | \n", - "748 | \n", - "785 | \n", - "ambiguous_gender ankle_strap anthro armchair a... | \n", - "NaN | \n", - "... | \n", - "2023-10-31 14:27:13.350878 | \n", - "f | \n", - "f | \n", - "f | \n", - "91 | \n", - "96 | \n", - "-6 | \n", - "f | \n", - "f | \n", - "f | \n", - "
| 28 | \n", - "42 | \n", - "17633 | \n", - "2007-02-10 20:26:35.174688 | \n", - "b9ef00dc6dd5c38364a839203abd991f | \n", - "https://sonichan.free.fr/index.php?dir=\\nhttps... | \n", - "s | \n", - "800 | \n", - "600 | \n", - "4:3 anthro bed biped cuddling detailed_backgro... | \n", - "NaN | \n", - "... | \n", - "2023-10-10 20:19:54.289908 | \n", - "f | \n", - "f | \n", - "f | \n", - "134 | \n", - "140 | \n", - "-7 | \n", - "f | \n", - "f | \n", - "f | \n", - "
| 29 | \n", - "43 | \n", - "17633 | \n", - "2007-02-10 20:27:48.227559 | \n", - "cf03be41aac70e8d6ccd1a2501ec845b | \n", - "https://j-fujita.deviantart.com/art/Miyu-2006-... | \n", - "s | \n", - "720 | \n", - "1050 | \n", - "2006 24:35 anthro belted_boots bent_arm bent_o... | \n", - "NaN | \n", - "... | \n", - "2023-10-22 07:35:52.058007 | \n", - "f | \n", - "f | \n", - "f | \n", - "115 | \n", - "123 | \n", - "-8 | \n", - "t | \n", - "f | \n", - "f | \n", - "
| 46 | \n", - "63 | \n", - "17633 | \n", - "2007-02-10 22:29:25.699311 | \n", - "75f2112ed16719cb88686573d015f40b | \n", - "https://www.deviantart.com/jayaxer/art/Let-Sle... | \n", - "s | \n", - "763 | \n", - "998 | \n", - "2006 4_toes 5_fingers anthro barefoot bed bed_... | \n", - "NaN | \n", - "... | \n", - "2023-10-14 19:42:33.936519 | \n", - "f | \n", - "f | \n", - "f | \n", - "124 | \n", - "127 | \n", - "-4 | \n", - "t | \n", - "f | \n", - "f | \n", - "
| 123 | \n", - "147 | \n", - "17633 | \n", - "2007-02-14 01:28:30.869838 | \n", - "f287864fe32af50f7ed6a036d61dd2d8 | \n", - "-https://aquabunny.creativeworlds.net/media/gi... | \n", - "s | \n", - "160 | \n", - "120 | \n", - "2006 2d_animation 4:3 animated aquabunny biped... | \n", - "NaN | \n", - "... | \n", - "2023-10-28 06:27:23.2087 | \n", - "f | \n", - "f | \n", - "f | \n", - "424 | \n", - "429 | \n", - "-7 | \n", - "f | \n", - "f | \n", - "f | \n", - "
| ... | \n", - "... | \n", - "... | \n", - "... | \n", - "... | \n", - "... | \n", - "... | \n", - "... | \n", - "... | \n", - "... | \n", - "... | \n", - "... | \n", - "... | \n", - "... | \n", - "... | \n", - "... | \n", - "... | \n", - "... | \n", - "... | \n", - "... | \n", - "... | \n", - "... | \n", - "
| 4381238 | \n", - "4389433 | \n", - "134487 | \n", - "2023-11-02 06:55:33.836896 | \n", - "c540c854df0337b04da285392d9e5609 | \n", - "https://twitter.com/hufy926_2/status/165303905... | \n", - "s | \n", - "2048 | \n", - "1690 | \n", - "2023 4_toes 5_fingers ahoge anthro ass_up bipe... | \n", - "NaN | \n", - "... | \n", - "2023-11-03 07:13:08.178163 | \n", - "f | \n", - "f | \n", - "f | \n", - "84 | \n", - "84 | \n", - "0 | \n", - "f | \n", - "f | \n", - "f | \n", - "
| 4381698 | \n", - "4389893 | \n", - "340613 | \n", - "2023-11-02 16:19:44.720595 | \n", - "5a664d4d9052bcde4f9a40fd4f8a98ab | \n", - "https://twitter.com/Whygena_Draws/status/17201... | \n", - "s | \n", - "1000 | \n", - "2667 | \n", - "absurd_res angry anthro apron clothing comic c... | \n", - "conditional_dnp | \n", - "... | \n", - "2023-11-03 07:16:02.064184 | \n", - "f | \n", - "f | \n", - "f | \n", - "70 | \n", - "70 | \n", - "0 | \n", - "f | \n", - "f | \n", - "f | \n", - "
| 4381844 | \n", - "4390039 | \n", - "362418 | \n", - "2023-11-02 18:05:51.347835 | \n", - "697fd38c3179cabe253a1d71f71ce00d | \n", - "https://x.com/ArtOfZue/status/1720099174270771... | \n", - "s | \n", - "1080 | \n", - "936 | \n", - "albino_raccoon alibi-cami animated anthro arto... | \n", - "NaN | \n", - "... | \n", - "2023-11-03 07:30:40.142009 | \n", - "f | \n", - "f | \n", - "f | \n", - "59 | \n", - "61 | \n", - "-2 | \n", - "f | \n", - "f | \n", - "f | \n", - "
| 4382128 | \n", - "4390323 | \n", - "10799 | \n", - "2023-11-02 20:18:08.782584 | \n", - "81251b60dc669cbde1045fa8dc3f2ce5 | \n", - "https://www.deviantart.com/painterdreamer/art/... | \n", - "s | \n", - "900 | \n", - "1125 | \n", - "2023 anthro anthro_focus artist_name blue_clot... | \n", - "NaN | \n", - "... | \n", - "2023-11-03 07:24:07.803882 | \n", - "f | \n", - "f | \n", - "f | \n", - "55 | \n", - "56 | \n", - "-1 | \n", - "f | \n", - "f | \n", - "f | \n", - "
| 4382875 | \n", - "4391070 | \n", - "846033 | \n", - "2023-11-03 04:32:04.036776 | \n", - "a5ded886fb4ce0299829125e8b05bbfa | \n", - "https://www.furaffinity.net/view/54294845/\\nht... | \n", - "s | \n", - "900 | \n", - "1286 | \n", - "2023 anthro black_nose bolt_(bolt) bolt_(film)... | \n", - "NaN | \n", - "... | \n", - "2023-11-03 07:33:49.555735 | \n", - "f | \n", - "f | \n", - "f | \n", - "68 | \n", - "69 | \n", - "-1 | \n", - "f | \n", - "f | \n", - "f | \n", - "
117407 rows × 29 columns
\n", - "| \n", - " | name | \n", - "type | \n", - "postCount | \n", - "aliases | \n", - "
|---|---|---|---|---|
| 0 | \n", - "mammal | \n", - "5 | \n", - "2411289 | \n", - "mammal_(species),mammale,mammalian,mammals,pan... | \n", - "
| 1 | \n", - "anthro | \n", - "0 | \n", - "2238650 | \n", - "anhtro,anthrofur,anthromorph,anthromorphic,ant... | \n", - "
| 2 | \n", - "hi_res | \n", - "7 | \n", - "1948793 | \n", - "hd,hi-res,hi_def,hi_resolution,high-res,high_d... | \n", - "
| 3 | \n", - "female | \n", - "0 | \n", - "1812633 | \n", - "1_girl,1girl,2_girl,2_girls,2girl,2girls,3_gir... | \n", - "
| 4 | \n", - "male | \n", - "0 | \n", - "1713089 | \n", - "1_boy,1_guys,1boy,1guy,1male,2_boys,2_guys,2bo... | \n", - "
| ... | \n", - "... | \n", - "... | \n", - "... | \n", - "... | \n", - "
| 99995 | \n", - "meeko_(pixiv) | \n", - "1 | \n", - "14 | \n", - "NaN | \n", - "
| 99996 | \n", - "medama_yagi | \n", - "4 | \n", - "14 | \n", - "NaN | \n", - "
| 99997 | \n", - "mechasheep | \n", - "1 | \n", - "14 | \n", - "NaN | \n", - "
| 99998 | \n", - "mechadendrites | \n", - "0 | \n", - "14 | \n", - "NaN | \n", - "
| 99999 | \n", - "mechacockzilla | \n", - "1 | \n", - "14 | \n", - "NaN | \n", - "
100000 rows × 4 columns
\n", - "| \n", - " | name | \n", - "type | \n", - "postCount | \n", - "aliases | \n", - "
|---|---|---|---|---|
| 0 | \n", - "mammal | \n", - "5 | \n", - "2411289 | \n", - "mammal_(species),mammale,mammalian,mammals,pan... | \n", - "
| 1 | \n", - "anthro | \n", - "0 | \n", - "2238650 | \n", - "anhtro,anthrofur,anthromorph,anthromorphic,ant... | \n", - "
| 2 | \n", - "hi_res | \n", - "7 | \n", - "1948793 | \n", - "hd,hi-res,hi_def,hi_resolution,high-res,high_d... | \n", - "
| 3 | \n", - "female | \n", - "0 | \n", - "1812633 | \n", - "1_girl,1girl,2_girl,2_girls,2girl,2girls,3_gir... | \n", - "
| 4 | \n", - "male | \n", - "0 | \n", - "1713089 | \n", - "1_boy,1_guys,1boy,1guy,1male,2_boys,2_guys,2bo... | \n", - "
| ... | \n", - "... | \n", - "... | \n", - "... | \n", - "... | \n", - "
| 99773 | \n", - "neck_expansion | \n", - "0 | \n", - "14 | \n", - "NaN | \n", - "
| 99842 | \n", - "mrs._poodle_(hladilnik) | \n", - "4 | \n", - "14 | \n", - "NaN | \n", - "
| 99903 | \n", - "miyu_hamada | \n", - "4 | \n", - "14 | \n", - "NaN | \n", - "
| 99922 | \n", - "mirial_mon_siviel | \n", - "4 | \n", - "14 | \n", - "NaN | \n", - "
| 99946 | \n", - "mii_brawler | \n", - "4 | \n", - "14 | \n", - "NaN | \n", - "
22419 rows × 4 columns
\n", - "