From e14af5e12eb2d9f628e73f82dfe819d69e980454 Mon Sep 17 00:00:00 2001 From: Jonas Weinz Date: Mon, 4 Jun 2018 20:37:18 +0200 Subject: [PATCH] just updating naive approach --- Project/Tools/emoji_descriptions.csv | 2 +- Project/Tools/emoji_table.ipynb | 481 +++++++++++++++++++- Project/naive_approach/naive_approach.ipynb | 100 ++-- 3 files changed, 525 insertions(+), 58 deletions(-) diff --git a/Project/Tools/emoji_descriptions.csv b/Project/Tools/emoji_descriptions.csv index dc8f09f..08ffe75 100644 --- a/Project/Tools/emoji_descriptions.csv +++ b/Project/Tools/emoji_descriptions.csv @@ -1,4 +1,4 @@ -,code,character,description, +,code,character,description 0,126980,๐Ÿ€„,MAHJONG TILE RED DRAGON 1,129525,๐Ÿงต,SPOOL OF THREAD 2,129526,๐Ÿงถ,BALL OF YARN diff --git a/Project/Tools/emoji_table.ipynb b/Project/Tools/emoji_table.ipynb index f9184bf..21e536e 100644 --- a/Project/Tools/emoji_table.ipynb +++ b/Project/Tools/emoji_table.ipynb @@ -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": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
codecharacterdescription
0126980๐Ÿ€„MAHJONG TILE RED DRAGON
1129525๐ŸงตSPOOL OF THREAD
2129526๐ŸงถBALL OF YARN
3127183๐ŸƒPLAYING CARD BLACK JOKER
4129296๐ŸคZIPPER-MOUTH FACE
5129297๐Ÿค‘MONEY-MOUTH FACE
6129298๐Ÿค’FACE WITH THERMOMETER
7129299๐Ÿค“NERD FACE
8129300๐Ÿค”THINKING FACE
9129301๐Ÿค•FACE WITH HEAD-BANDAGE
10129302๐Ÿค–ROBOT FACE
11129303๐Ÿค—HUGGING FACE
12129304๐Ÿค˜SIGN OF THE HORNS
13129305๐Ÿค™CALL ME HAND
14129306๐ŸคšRAISED BACK OF HAND
15129307๐Ÿค›LEFT-FACING FIST
16129308๐ŸคœRIGHT-FACING FIST
17129309๐ŸคHANDSHAKE
18129310๐ŸคžHAND WITH INDEX AND MIDDLE FINGERS CROSSED
19129311๐ŸคŸI LOVE YOU HAND SIGN
20129312๐Ÿค FACE WITH COWBOY HAT
21129313๐ŸคกCLOWN FACE
22129314๐ŸคขNAUSEATED FACE
23129315๐ŸคฃROLLING ON THE FLOOR LAUGHING
24129316๐ŸคคDROOLING FACE
25129317๐ŸคฅLYING FACE
26129318๐ŸคฆFACE PALM
27129319๐ŸคงSNEEZING FACE
28129320๐ŸคจFACE WITH ONE EYEBROW RAISED
29129321๐ŸคฉGRINNING FACE WITH STAR EYES
............
9979995โœ‹RAISED HAND
998128581๐Ÿ™…FACE WITH NO GOOD GESTURE
999128582๐Ÿ™†FACE WITH OK GESTURE
1000128583๐Ÿ™‡PERSON BOWING DEEPLY
1001128584๐Ÿ™ˆSEE-NO-EVIL MONKEY
1002129511๐ŸงงRED GIFT ENVELOPE
1003128585๐Ÿ™‰HEAR-NO-EVIL MONKEY
1004127476๐Ÿ‡ดREGIONAL INDICATOR SYMBOL LETTER O
1005128586๐Ÿ™ŠSPEAK-NO-EVIL MONKEY
100610024โœจSPARKLES
1007129512๐ŸงจFIRECRACKER
1008127477๐Ÿ‡ตREGIONAL INDICATOR SYMBOL LETTER P
100910060โŒCROSS MARK
101010062โŽNEGATIVE SQUARED CROSS MARK
1011129513๐ŸงฉJIGSAW PUZZLE PIECE
1012127478๐Ÿ‡ถREGIONAL INDICATOR SYMBOL LETTER Q
101310067โ“BLACK QUESTION MARK ORNAMENT
101410068โ”WHITE QUESTION MARK ORNAMENT
101510069โ•WHITE EXCLAMATION MARK ORNAMENT
101610071โ—HEAVY EXCLAMATION MARK SYMBOL
1017129514๐ŸงชTEST TUBE
1018129515๐ŸงซPETRI DISH
101910133โž•HEAVY PLUS SIGN
102010134โž–HEAVY MINUS SIGN
102110135โž—HEAVY DIVISION SIGN
1022129424๐ŸฆSHRIMP
1023129425๐Ÿฆ‘SQUID
102410160โžฐCURLY LOOP
102510175โžฟDOUBLE CURLY LOOP
1026129520๐ŸงฐTOOLBOX
\n", + "

1027 rows ร— 3 columns

\n", + "
" + ], + "text/plain": [ + " code character description\n", + "0 126980 ๐Ÿ€„ MAHJONG TILE RED DRAGON\n", + "1 129525 ๐Ÿงต SPOOL OF THREAD\n", + "2 129526 ๐Ÿงถ BALL OF YARN\n", + "3 127183 ๐Ÿƒ PLAYING CARD BLACK JOKER\n", + "4 129296 ๐Ÿค ZIPPER-MOUTH FACE\n", + "5 129297 ๐Ÿค‘ MONEY-MOUTH FACE\n", + "6 129298 ๐Ÿค’ FACE WITH THERMOMETER\n", + "7 129299 ๐Ÿค“ NERD FACE\n", + "8 129300 ๐Ÿค” THINKING FACE\n", + "9 129301 ๐Ÿค• FACE WITH HEAD-BANDAGE\n", + "10 129302 ๐Ÿค– ROBOT FACE\n", + "11 129303 ๐Ÿค— HUGGING FACE\n", + "12 129304 ๐Ÿค˜ SIGN OF THE HORNS\n", + "13 129305 ๐Ÿค™ CALL ME HAND\n", + "14 129306 ๐Ÿคš RAISED BACK OF HAND\n", + "15 129307 ๐Ÿค› LEFT-FACING FIST\n", + "16 129308 ๐Ÿคœ RIGHT-FACING FIST\n", + "17 129309 ๐Ÿค HANDSHAKE\n", + "18 129310 ๐Ÿคž HAND WITH INDEX AND MIDDLE FINGERS CROSSED\n", + "19 129311 ๐ŸคŸ I LOVE YOU HAND SIGN\n", + "20 129312 ๐Ÿค  FACE WITH COWBOY HAT\n", + "21 129313 ๐Ÿคก CLOWN FACE\n", + "22 129314 ๐Ÿคข NAUSEATED FACE\n", + "23 129315 ๐Ÿคฃ ROLLING ON THE FLOOR LAUGHING\n", + "24 129316 ๐Ÿคค DROOLING FACE\n", + "25 129317 ๐Ÿคฅ LYING FACE\n", + "26 129318 ๐Ÿคฆ FACE PALM\n", + "27 129319 ๐Ÿคง SNEEZING FACE\n", + "28 129320 ๐Ÿคจ FACE WITH ONE EYEBROW RAISED\n", + "29 129321 ๐Ÿคฉ GRINNING FACE WITH STAR EYES\n", + "... ... ... ...\n", + "997 9995 โœ‹ RAISED HAND\n", + "998 128581 ๐Ÿ™… FACE WITH NO GOOD GESTURE\n", + "999 128582 ๐Ÿ™† FACE WITH OK GESTURE\n", + "1000 128583 ๐Ÿ™‡ PERSON BOWING DEEPLY\n", + "1001 128584 ๐Ÿ™ˆ SEE-NO-EVIL MONKEY\n", + "1002 129511 ๐Ÿงง RED GIFT ENVELOPE\n", + "1003 128585 ๐Ÿ™‰ HEAR-NO-EVIL MONKEY\n", + "1004 127476 ๐Ÿ‡ด REGIONAL INDICATOR SYMBOL LETTER O\n", + "1005 128586 ๐Ÿ™Š SPEAK-NO-EVIL MONKEY\n", + "1006 10024 โœจ SPARKLES\n", + "1007 129512 ๐Ÿงจ FIRECRACKER\n", + "1008 127477 ๐Ÿ‡ต REGIONAL INDICATOR SYMBOL LETTER P\n", + "1009 10060 โŒ CROSS MARK\n", + "1010 10062 โŽ NEGATIVE SQUARED CROSS MARK\n", + "1011 129513 ๐Ÿงฉ JIGSAW PUZZLE PIECE\n", + "1012 127478 ๐Ÿ‡ถ REGIONAL INDICATOR SYMBOL LETTER Q\n", + "1013 10067 โ“ BLACK QUESTION MARK ORNAMENT\n", + "1014 10068 โ” WHITE QUESTION MARK ORNAMENT\n", + "1015 10069 โ• WHITE EXCLAMATION MARK ORNAMENT\n", + "1016 10071 โ— HEAVY EXCLAMATION MARK SYMBOL\n", + "1017 129514 ๐Ÿงช TEST TUBE\n", + "1018 129515 ๐Ÿงซ PETRI DISH\n", + "1019 10133 โž• HEAVY PLUS SIGN\n", + "1020 10134 โž– HEAVY MINUS SIGN\n", + "1021 10135 โž— HEAVY DIVISION SIGN\n", + "1022 129424 ๐Ÿฆ SHRIMP\n", + "1023 129425 ๐Ÿฆ‘ SQUID\n", + "1024 10160 โžฐ CURLY LOOP\n", + "1025 10175 โžฟ DOUBLE CURLY LOOP\n", + "1026 129520 ๐Ÿงฐ 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, diff --git a/Project/naive_approach/naive_approach.ipynb b/Project/naive_approach/naive_approach.ipynb index e7e6f2c..b365d5c 100644 --- a/Project/naive_approach/naive_approach.ipynb +++ b/Project/naive_approach/naive_approach.ipynb @@ -273,11 +273,11 @@ }, { "cell_type": "code", - "execution_count": 130, + "execution_count": 177, "metadata": {}, "outputs": [], "source": [ - "result = evaluate_sentence(\"I like playing soccer\")" + "result = evaluate_sentence(\"horse back riding\")" ] }, { @@ -289,13 +289,17 @@ }, { "cell_type": "code", - "execution_count": 131, + "execution_count": 178, "metadata": {}, "outputs": [], "source": [ "lookup = {}\n", + "emoji_set = []\n", "for index, row in table.iterrows():\n", - " lookup[index] = row['character']" + " lookup[index] = row['character']\n", + " emoji_set.append(row['character'])\n", + "\n", + "emoji_set = set(emoji_set)" ] }, { @@ -307,7 +311,7 @@ }, { "cell_type": "code", - "execution_count": 139, + "execution_count": 179, "metadata": {}, "outputs": [], "source": [ @@ -321,7 +325,7 @@ }, { "cell_type": "code", - "execution_count": 156, + "execution_count": 180, "metadata": {}, "outputs": [], "source": [ @@ -332,55 +336,46 @@ }, { "cell_type": "code", - "execution_count": 157, + "execution_count": 181, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "[ 'โšฝ -- SOCCER BALL',\n", - " '๐Ÿ‰ -- RUGBY FOOTBALL',\n", - " '๐Ÿˆ -- AMERICAN FOOTBALL',\n", - " '๐ŸŽด -- FLOWER PLAYING CARDS',\n", - " '๐Ÿƒ -- PLAYING CARD BLACK JOKER',\n", - " '๐Ÿ‡ฎ -- REGIONAL INDICATOR SYMBOL LETTER I',\n", - " '\\U0001f91f -- I LOVE YOU HAND SIGN',\n", - " '๐Ÿ“ง -- E-MAIL SYMBOL',\n", - " '๐Ÿ“ญ -- OPEN MAILBOX WITH LOWERED FLAG',\n", - " '๐Ÿ“ฅ -- INBOX TRAY']\n", - "[ array([[0.25 , 0.28571429, 0.58333333, 1. ],\n", - " [0.26666667, 0.10526316, 0.1 , 0.1 ]]),\n", - " array([[0.25 , 0.28571429, 0.58333333, 0.84615385],\n", - " [0.26666667, 0.3 , 0.60869565, 0.96 ]]),\n", - " array([[0.33333333, 0.125 , 0.11764706, 0.11764706],\n", - " [0.26666667, 0.3 , 0.60869565, 0.96 ]]),\n", - " array([[0.23529412, 0.0952381 , 0.09090909, 0.09090909],\n", - " [0.25 , 0.47619048, 1. , 0.58333333],\n", - " [0.30769231, 0.33333333, 0.57142857, 0.7 ]]),\n", - " array([[0.25 , 0.47619048, 1. , 0.58333333],\n", - " [0.53333333, 0.22222222, 0.21052632, 0.21052632],\n", - " [0.30769231, 0.22222222, 0.21052632, 0.21052632],\n", - " [0.28571429, 0.11111111, 0.10526316, 0.10526316]]),\n", - " array([[0. , 0. , 0. , 0. ],\n", - " [0.33333333, 0.23529412, 0.22222222, 0.22222222],\n", - " [0.4 , 0.26666667, 0.25 , 0.25 ],\n", - " [0.30769231, 0.22222222, 0.21052632, 0.21052632],\n", - " [1. , 0.26666667, 0.25 , 0.25 ]]),\n", - " array([[1. , 0.26666667, 0.25 , 0.25 ],\n", - " [0.33333333, 0.23529412, 0.22222222, 0.22222222],\n", - " [0. , 0. , 0. , 0. ],\n", - " [0.28571429, 0.11111111, 0.10526316, 0.10526316],\n", - " [0.33333333, 0.23529412, 0.22222222, 0.22222222]]),\n", - " array([[0.28571429, 0.31578947, 0.45454545, 0.5 ],\n", - " [0.4 , 0.26666667, 0.25 , 0.25 ]]),\n", - " array([[0.30769231, 0.11764706, 0.11111111, 0.11111111],\n", - " [0.26666667, 0.10526316, 0.1 , 0.1 ],\n", - " [0. , 0. , 0. , 0. ],\n", - " [0.22222222, 0.14285714, 0.13333333, 0.13333333],\n", - " [0.26666667, 0.10526316, 0.1 , 0.1 ]]),\n", - " array([[0. , 0. , 0. , 0. ],\n", - " [0.26666667, 0.10526316, 0.1 , 0.1 ]])]\n" + "[ '๐ŸŽ -- HORSE',\n", + " '๐Ÿ‡ -- HORSE RACING',\n", + " '๐Ÿด -- HORSE FACE',\n", + " '\\U0001f993 -- ZEBRA FACE',\n", + " '๐Ÿ… -- SPORTS MEDAL',\n", + " '๐Ÿ—ป -- MOUNT FUJI',\n", + " '๐ŸŽ  -- CAROUSEL HORSE',\n", + " '๐Ÿคš -- RAISED BACK OF HAND',\n", + " '๐Ÿ”™ -- BACK WITH LEFTWARDS ARROW ABOVE',\n", + " '๐Ÿ“ฎ -- POSTBOX']\n", + "[ array([[1. , 0.19047619, 0.08333333]]),\n", + " array([[1. , 0.19047619, 0.08333333],\n", + " [0.08333333, 0.13333333, 0.88888889]]),\n", + " array([[1. , 0.19047619, 0.08333333],\n", + " [0.18181818, 0.76923077, 0.125 ]]),\n", + " array([[0.93333333, 0.19047619, 0.08333333],\n", + " [0.18181818, 0.76923077, 0.125 ]]),\n", + " array([[0.08695652, 0.14285714, 0.94117647],\n", + " [0.09090909, 0.15384615, 0.25 ]]),\n", + " array([[0.96774194, 0.18181818, 0.08 ],\n", + " [0.4 , 0.19047619, 0.08333333]]),\n", + " array([[0.07407407, 0.11111111, 0.19047619],\n", + " [1. , 0.19047619, 0.08333333]]),\n", + " array([[0.1 , 0.18181818, 0.14285714],\n", + " [0.19047619, 1. , 0.13333333],\n", + " [0. , 0. , 0. ],\n", + " [0.17391304, 0.71428571, 0.11764706]]),\n", + " array([[0.19047619, 1. , 0.13333333],\n", + " [0. , 0. , 0. ],\n", + " [0. , 0. , 0. ],\n", + " [0.08695652, 0.14285714, 0.23529412],\n", + " [0.09090909, 0.15384615, 0.25 ]]),\n", + " array([[0.32 , 0.25 , 0.10526316]])]\n" ] } ], @@ -388,13 +383,6 @@ "print_best_results(threshold)" ] }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] - }, { "cell_type": "code", "execution_count": null,