just updating naive approach

This commit is contained in:
Jonas Weinz
2018-06-04 20:37:18 +02:00
parent 72f2700b66
commit e14af5e12e
3 changed files with 525 additions and 58 deletions

View File

@ -1,4 +1,4 @@
,code,character,description,
,code,character,description
0,126980,🀄,MAHJONG TILE RED DRAGON
1,129525,🧵,SPOOL OF THREAD
2,129526,🧶,BALL OF YARN

1 ,code,character,description, code character description
2 0,126980,🀄,MAHJONG TILE RED DRAGON 0 126980 🀄 MAHJONG TILE RED DRAGON
3 1,129525,🧵,SPOOL OF THREAD 1 129525 🧵 SPOOL OF THREAD
4 2,129526,🧶,BALL OF YARN 2 129526 🧶 BALL OF YARN

View File

@ -1232,10 +1232,489 @@
"metadata": {},
"outputs": [],
"source": [
"emoji_frame = pd.DataFrame(emoji_array, columns=['code', 'character','descripion,'])\n",
"emoji_frame = pd.DataFrame(emoji_array, columns=['code', 'character','description'])\n",
"emoji_frame.to_csv(\"emoji_descriptions.csv\")"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>code</th>\n",
" <th>character</th>\n",
" <th>description</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>126980</td>\n",
" <td>🀄</td>\n",
" <td>MAHJONG TILE RED DRAGON</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>129525</td>\n",
" <td>🧵</td>\n",
" <td>SPOOL OF THREAD</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>129526</td>\n",
" <td>🧶</td>\n",
" <td>BALL OF YARN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>127183</td>\n",
" <td>🃏</td>\n",
" <td>PLAYING CARD BLACK JOKER</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>129296</td>\n",
" <td>🤐</td>\n",
" <td>ZIPPER-MOUTH FACE</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>129297</td>\n",
" <td>🤑</td>\n",
" <td>MONEY-MOUTH FACE</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>129298</td>\n",
" <td>🤒</td>\n",
" <td>FACE WITH THERMOMETER</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>129299</td>\n",
" <td>🤓</td>\n",
" <td>NERD FACE</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>129300</td>\n",
" <td>🤔</td>\n",
" <td>THINKING FACE</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>129301</td>\n",
" <td>🤕</td>\n",
" <td>FACE WITH HEAD-BANDAGE</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>129302</td>\n",
" <td>🤖</td>\n",
" <td>ROBOT FACE</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>129303</td>\n",
" <td>🤗</td>\n",
" <td>HUGGING FACE</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>129304</td>\n",
" <td>🤘</td>\n",
" <td>SIGN OF THE HORNS</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>129305</td>\n",
" <td>🤙</td>\n",
" <td>CALL ME HAND</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14</th>\n",
" <td>129306</td>\n",
" <td>🤚</td>\n",
" <td>RAISED BACK OF HAND</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
" <td>129307</td>\n",
" <td>🤛</td>\n",
" <td>LEFT-FACING FIST</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16</th>\n",
" <td>129308</td>\n",
" <td>🤜</td>\n",
" <td>RIGHT-FACING FIST</td>\n",
" </tr>\n",
" <tr>\n",
" <th>17</th>\n",
" <td>129309</td>\n",
" <td>🤝</td>\n",
" <td>HANDSHAKE</td>\n",
" </tr>\n",
" <tr>\n",
" <th>18</th>\n",
" <td>129310</td>\n",
" <td>🤞</td>\n",
" <td>HAND WITH INDEX AND MIDDLE FINGERS CROSSED</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19</th>\n",
" <td>129311</td>\n",
" <td>🤟</td>\n",
" <td>I LOVE YOU HAND SIGN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20</th>\n",
" <td>129312</td>\n",
" <td>🤠</td>\n",
" <td>FACE WITH COWBOY HAT</td>\n",
" </tr>\n",
" <tr>\n",
" <th>21</th>\n",
" <td>129313</td>\n",
" <td>🤡</td>\n",
" <td>CLOWN FACE</td>\n",
" </tr>\n",
" <tr>\n",
" <th>22</th>\n",
" <td>129314</td>\n",
" <td>🤢</td>\n",
" <td>NAUSEATED FACE</td>\n",
" </tr>\n",
" <tr>\n",
" <th>23</th>\n",
" <td>129315</td>\n",
" <td>🤣</td>\n",
" <td>ROLLING ON THE FLOOR LAUGHING</td>\n",
" </tr>\n",
" <tr>\n",
" <th>24</th>\n",
" <td>129316</td>\n",
" <td>🤤</td>\n",
" <td>DROOLING FACE</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25</th>\n",
" <td>129317</td>\n",
" <td>🤥</td>\n",
" <td>LYING FACE</td>\n",
" </tr>\n",
" <tr>\n",
" <th>26</th>\n",
" <td>129318</td>\n",
" <td>🤦</td>\n",
" <td>FACE PALM</td>\n",
" </tr>\n",
" <tr>\n",
" <th>27</th>\n",
" <td>129319</td>\n",
" <td>🤧</td>\n",
" <td>SNEEZING FACE</td>\n",
" </tr>\n",
" <tr>\n",
" <th>28</th>\n",
" <td>129320</td>\n",
" <td>🤨</td>\n",
" <td>FACE WITH ONE EYEBROW RAISED</td>\n",
" </tr>\n",
" <tr>\n",
" <th>29</th>\n",
" <td>129321</td>\n",
" <td>🤩</td>\n",
" <td>GRINNING FACE WITH STAR EYES</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>997</th>\n",
" <td>9995</td>\n",
" <td>✋</td>\n",
" <td>RAISED HAND</td>\n",
" </tr>\n",
" <tr>\n",
" <th>998</th>\n",
" <td>128581</td>\n",
" <td>🙅</td>\n",
" <td>FACE WITH NO GOOD GESTURE</td>\n",
" </tr>\n",
" <tr>\n",
" <th>999</th>\n",
" <td>128582</td>\n",
" <td>🙆</td>\n",
" <td>FACE WITH OK GESTURE</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1000</th>\n",
" <td>128583</td>\n",
" <td>🙇</td>\n",
" <td>PERSON BOWING DEEPLY</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1001</th>\n",
" <td>128584</td>\n",
" <td>🙈</td>\n",
" <td>SEE-NO-EVIL MONKEY</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1002</th>\n",
" <td>129511</td>\n",
" <td>🧧</td>\n",
" <td>RED GIFT ENVELOPE</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1003</th>\n",
" <td>128585</td>\n",
" <td>🙉</td>\n",
" <td>HEAR-NO-EVIL MONKEY</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1004</th>\n",
" <td>127476</td>\n",
" <td>🇴</td>\n",
" <td>REGIONAL INDICATOR SYMBOL LETTER O</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1005</th>\n",
" <td>128586</td>\n",
" <td>🙊</td>\n",
" <td>SPEAK-NO-EVIL MONKEY</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1006</th>\n",
" <td>10024</td>\n",
" <td>✨</td>\n",
" <td>SPARKLES</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1007</th>\n",
" <td>129512</td>\n",
" <td>🧨</td>\n",
" <td>FIRECRACKER</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1008</th>\n",
" <td>127477</td>\n",
" <td>🇵</td>\n",
" <td>REGIONAL INDICATOR SYMBOL LETTER P</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1009</th>\n",
" <td>10060</td>\n",
" <td>❌</td>\n",
" <td>CROSS MARK</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1010</th>\n",
" <td>10062</td>\n",
" <td>❎</td>\n",
" <td>NEGATIVE SQUARED CROSS MARK</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1011</th>\n",
" <td>129513</td>\n",
" <td>🧩</td>\n",
" <td>JIGSAW PUZZLE PIECE</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1012</th>\n",
" <td>127478</td>\n",
" <td>🇶</td>\n",
" <td>REGIONAL INDICATOR SYMBOL LETTER Q</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1013</th>\n",
" <td>10067</td>\n",
" <td>❓</td>\n",
" <td>BLACK QUESTION MARK ORNAMENT</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1014</th>\n",
" <td>10068</td>\n",
" <td>❔</td>\n",
" <td>WHITE QUESTION MARK ORNAMENT</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1015</th>\n",
" <td>10069</td>\n",
" <td>❕</td>\n",
" <td>WHITE EXCLAMATION MARK ORNAMENT</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1016</th>\n",
" <td>10071</td>\n",
" <td>❗</td>\n",
" <td>HEAVY EXCLAMATION MARK SYMBOL</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1017</th>\n",
" <td>129514</td>\n",
" <td>🧪</td>\n",
" <td>TEST TUBE</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1018</th>\n",
" <td>129515</td>\n",
" <td>🧫</td>\n",
" <td>PETRI DISH</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1019</th>\n",
" <td>10133</td>\n",
" <td></td>\n",
" <td>HEAVY PLUS SIGN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1020</th>\n",
" <td>10134</td>\n",
" <td></td>\n",
" <td>HEAVY MINUS SIGN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1021</th>\n",
" <td>10135</td>\n",
" <td>➗</td>\n",
" <td>HEAVY DIVISION SIGN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1022</th>\n",
" <td>129424</td>\n",
" <td>🦐</td>\n",
" <td>SHRIMP</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1023</th>\n",
" <td>129425</td>\n",
" <td>🦑</td>\n",
" <td>SQUID</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1024</th>\n",
" <td>10160</td>\n",
" <td>➰</td>\n",
" <td>CURLY LOOP</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1025</th>\n",
" <td>10175</td>\n",
" <td>➿</td>\n",
" <td>DOUBLE CURLY LOOP</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1026</th>\n",
" <td>129520</td>\n",
" <td>🧰</td>\n",
" <td>TOOLBOX</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>1027 rows × 3 columns</p>\n",
"</div>"
],
"text/plain": [
" code character description\n",
"0 126980 🀄 MAHJONG TILE RED DRAGON\n",
"1 129525 🧵 SPOOL OF THREAD\n",
"2 129526 🧶 BALL OF YARN\n",
"3 127183 🃏 PLAYING CARD BLACK JOKER\n",
"4 129296 🤐 ZIPPER-MOUTH FACE\n",
"5 129297 🤑 MONEY-MOUTH FACE\n",
"6 129298 🤒 FACE WITH THERMOMETER\n",
"7 129299 🤓 NERD FACE\n",
"8 129300 🤔 THINKING FACE\n",
"9 129301 🤕 FACE WITH HEAD-BANDAGE\n",
"10 129302 🤖 ROBOT FACE\n",
"11 129303 🤗 HUGGING FACE\n",
"12 129304 🤘 SIGN OF THE HORNS\n",
"13 129305 🤙 CALL ME HAND\n",
"14 129306 🤚 RAISED BACK OF HAND\n",
"15 129307 🤛 LEFT-FACING FIST\n",
"16 129308 🤜 RIGHT-FACING FIST\n",
"17 129309 🤝 HANDSHAKE\n",
"18 129310 🤞 HAND WITH INDEX AND MIDDLE FINGERS CROSSED\n",
"19 129311 🤟 I LOVE YOU HAND SIGN\n",
"20 129312 🤠 FACE WITH COWBOY HAT\n",
"21 129313 🤡 CLOWN FACE\n",
"22 129314 🤢 NAUSEATED FACE\n",
"23 129315 🤣 ROLLING ON THE FLOOR LAUGHING\n",
"24 129316 🤤 DROOLING FACE\n",
"25 129317 🤥 LYING FACE\n",
"26 129318 🤦 FACE PALM\n",
"27 129319 🤧 SNEEZING FACE\n",
"28 129320 🤨 FACE WITH ONE EYEBROW RAISED\n",
"29 129321 🤩 GRINNING FACE WITH STAR EYES\n",
"... ... ... ...\n",
"997 9995 ✋ RAISED HAND\n",
"998 128581 🙅 FACE WITH NO GOOD GESTURE\n",
"999 128582 🙆 FACE WITH OK GESTURE\n",
"1000 128583 🙇 PERSON BOWING DEEPLY\n",
"1001 128584 🙈 SEE-NO-EVIL MONKEY\n",
"1002 129511 🧧 RED GIFT ENVELOPE\n",
"1003 128585 🙉 HEAR-NO-EVIL MONKEY\n",
"1004 127476 🇴 REGIONAL INDICATOR SYMBOL LETTER O\n",
"1005 128586 🙊 SPEAK-NO-EVIL MONKEY\n",
"1006 10024 ✨ SPARKLES\n",
"1007 129512 🧨 FIRECRACKER\n",
"1008 127477 🇵 REGIONAL INDICATOR SYMBOL LETTER P\n",
"1009 10060 ❌ CROSS MARK\n",
"1010 10062 ❎ NEGATIVE SQUARED CROSS MARK\n",
"1011 129513 🧩 JIGSAW PUZZLE PIECE\n",
"1012 127478 🇶 REGIONAL INDICATOR SYMBOL LETTER Q\n",
"1013 10067 ❓ BLACK QUESTION MARK ORNAMENT\n",
"1014 10068 ❔ WHITE QUESTION MARK ORNAMENT\n",
"1015 10069 ❕ WHITE EXCLAMATION MARK ORNAMENT\n",
"1016 10071 ❗ HEAVY EXCLAMATION MARK SYMBOL\n",
"1017 129514 🧪 TEST TUBE\n",
"1018 129515 🧫 PETRI DISH\n",
"1019 10133 HEAVY PLUS SIGN\n",
"1020 10134 HEAVY MINUS SIGN\n",
"1021 10135 ➗ HEAVY DIVISION SIGN\n",
"1022 129424 🦐 SHRIMP\n",
"1023 129425 🦑 SQUID\n",
"1024 10160 ➰ CURLY LOOP\n",
"1025 10175 ➿ DOUBLE CURLY LOOP\n",
"1026 129520 🧰 TOOLBOX\n",
"\n",
"[1027 rows x 3 columns]"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"emoji_frame"
]
},
{
"cell_type": "code",
"execution_count": null,