{ "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "import pandas as pd\n", "from IPython.display import clear_output, Markdown, Math\n", "import ipywidgets as widgets\n", "import os\n", "import glob\n", "import json\n", "import numpy as np\n", "import itertools\n", "import sklearn.utils as sku\n", "from sklearn.feature_extraction.text import CountVectorizer, TfidfVectorizer, HashingVectorizer\n", "from sklearn.model_selection import train_test_split\n", "from sklearn.preprocessing import MultiLabelBinarizer" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [], "source": [ "import sys\n", "sys.path.append(\"..\")\n", "\n", "from Tools.Emoji_Distance import sentiment_vector_to_emoji\n", "from Tools.Emoji_Distance import emoji_to_sentiment_vector\n", "\n", "def emoji2sent(emoji_arr):\n", " return np.array([emoji_to_sentiment_vector(e) for e in emoji_arr])\n", "\n", "def sent2emoji(sent_arr):\n", " return [sentiment_vector_to_emoji(s) for s in sent_arr]" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [], "source": [ "SINGLE_LABEL = True" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# simple twitter approach\n", "*for learning emoji usage by single (in the meaning of unconnected) twitter messages*" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## loading train data" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [], "source": [ "data_root_folder = \"./data_en/\" # i created a symlink here" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "* get all json files in `data_root_folder`" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [], "source": [ "json_files = sorted(glob.glob(data_root_folder + \"/*.json\"))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "----" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "* so far, only load the first file" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", " | EMOJI | \n", "HASHTAGS | \n", "LINKED_USER | \n", "datetime | \n", "id | \n", "lang | \n", "person | \n", "reply_to | \n", "text | \n", "
---|---|---|---|---|---|---|---|---|---|
0 | \n", "[π₯, π] | \n", "[] | \n", "[] | \n", "2017-11-01 13:29:00 | \n", "925716304635547600 | \n", "en | \n", "31507978 | \n", "NaN | \n", "fashionbombdaily's photo <EMOJI><EMOJI>πΌ | \n", "
1 | \n", "[π€¦] | \n", "[] | \n", "[] | \n", "2017-11-01 13:29:00 | \n", "925716304664911900 | \n", "en | \n", "231994649 | \n", "NaN | \n", "Itβs scary how on point my horoscope be <EMOJI... | \n", "
2 | \n", "[π] | \n", "[] | \n", "[] | \n", "2017-11-01 13:29:03 | \n", "925716317214089200 | \n", "en | \n", "2592765104 | \n", "NaN | \n", "Woooaaaahhh <EMOJI> | \n", "
3 | \n", "[π·] | \n", "[] | \n", "[] | \n", "2017-11-01 13:29:04 | \n", "925716321416949800 | \n", "en | \n", "278737933 | \n", "NaN | \n", "<EMOJI> vivalcli: Portraits by Zhao Guojing an... | \n", "
4 | \n", "[π©, π©] | \n", "[] | \n", "[@hiphopphiIes] | \n", "2017-11-01 13:29:06 | \n", "925716329801310200 | \n", "en | \n", "824586253634981900 | \n", "9.257162e+17 | \n", "<USER> i wanna know too<EMOJI><EMOJI> | \n", "
5 | \n", "[π, π] | \n", "[] | \n", "[@WizMommma] | \n", "2017-11-01 13:29:02 | \n", "925716313019965400 | \n", "en | \n", "1581953814 | \n", "9.257088e+17 | \n", "<USER> veda was yoda too <EMOJI><EMOJI> | \n", "
6 | \n", "[π] | \n", "[] | \n", "[] | \n", "2017-11-01 13:29:05 | \n", "925716325607133200 | \n", "en | \n", "1001999683 | \n", "NaN | \n", "Iβm less stressed about turning 30 now <EMOJI>... | \n", "
7 | \n", "[π―] | \n", "[] | \n", "[] | \n", "2017-11-01 13:29:07 | \n", "925716334008082400 | \n", "en | \n", "745222369183043600 | \n", "NaN | \n", "Full charged. <EMOJI> | \n", "
8 | \n", "[π] | \n", "[] | \n", "[@SeaDimon, @lsarsour] | \n", "2017-11-01 13:29:09 | \n", "925716342401052700 | \n", "en | \n", "798557155217539100 | \n", "9.257147e+17 | \n", "<USER> Thatβs part of the problem, (they) <USE... | \n", "
9 | \n", "[π, π₯, π’] | \n", "[] | \n", "[@Ian_khetye] | \n", "2017-11-01 13:29:10 | \n", "925716346570240000 | \n", "en | \n", "744396039126421500 | \n", "9.250629e+17 | \n", "<USER> got me emotional there<EMOJI><EMOJI><EM... | \n", "
10 | \n", "[π»] | \n", "[] | \n", "[] | \n", "2017-11-01 13:29:13 | \n", "925716359182520300 | \n", "en | \n", "721490010118205400 | \n", "8.965900e+17 | \n", "back to the yellow <EMOJI> | \n", "
11 | \n", "[π, πΊ, π] | \n", "[] | \n", "[@Dimafadma] | \n", "2017-11-01 13:29:15 | \n", "925716367558545400 | \n", "en | \n", "520536723 | \n", "9.257159e+17 | \n", "<USER> Happy month to you and your loved ones ... | \n", "
12 | \n", "[π] | \n", "[#mortdale, #partofthefamily, #gorgeousboy] | \n", "[] | \n", "2017-11-01 13:29:16 | \n", "925716371735900200 | \n", "en | \n", "850852815941517300 | \n", "NaN | \n", "Maxx and Patricia. Family hangs at For Good He... | \n", "
13 | \n", "[π, π€¦] | \n", "[] | \n", "[] | \n", "2017-11-01 13:29:20 | \n", "925716388513230800 | \n", "en | \n", "914145041588867100 | \n", "NaN | \n", "I need to STOP beating myself up with my thoug... | \n", "
14 | \n", "[π, π] | \n", "[#7YearsOfKMH2] | \n", "[] | \n", "2017-11-01 13:29:20 | \n", "925716388525645800 | \n", "en | \n", "2425405622 | \n", "NaN | \n", "Cutest Son <EMOJI>Roll no. 31 <EMOJI> <HASHTAG> | \n", "
15 | \n", "[π] | \n", "[] | \n", "[] | \n", "2017-11-01 13:29:22 | \n", "925716396931240000 | \n", "en | \n", "4614871873 | \n", "NaN | \n", "By the summer I should have everything up and ... | \n", "
16 | \n", "[π, π₯] | \n", "[] | \n", "[] | \n", "2017-11-01 13:29:23 | \n", "925716401125331000 | \n", "en | \n", "2831608345 | \n", "NaN | \n", "I know my English is not that good but that do... | \n", "
17 | \n", "[π] | \n", "[] | \n", "[@yungbabytate] | \n", "2017-11-01 13:29:23 | \n", "925716401133948900 | \n", "en | \n", "788571974633009200 | \n", "9.255778e+17 | \n", "<USER> I <EMOJI> u mama | \n", "
18 | \n", "[π] | \n", "[] | \n", "[@cmckenney] | \n", "2017-11-01 13:29:23 | \n", "925716401125544000 | \n", "en | \n", "218307802 | \n", "9.257115e+17 | \n", "<USER> That picture was NOT taken this morning... | \n", "
19 | \n", "[π ] | \n", "[#footfetishnation] | \n", "[] | \n", "2017-11-01 13:29:25 | \n", "925716409489002500 | \n", "en | \n", "885261166146179100 | \n", "NaN | \n", "Welcome to <HASHTAG> <EMOJI> | \n", "
20 | \n", "[π, π] | \n", "[] | \n", "[] | \n", "2017-11-01 13:29:25 | \n", "925716409497272300 | \n", "en | \n", "831437760833609700 | \n", "NaN | \n", "Awkward <EMOJI><EMOJI> | \n", "
21 | \n", "[π€, πΊ] | \n", "[] | \n", "[] | \n", "2017-11-01 13:29:26 | \n", "925716413699854300 | \n", "en | \n", "231664542 | \n", "NaN | \n", "back at it with supernatural <EMOJI><EMOJI> | \n", "
22 | \n", "[π―] | \n", "[] | \n", "[] | \n", "2017-11-01 13:29:26 | \n", "925716413679009800 | \n", "en | \n", "3196847035 | \n", "NaN | \n", "One of the best things I've learned was to sto... | \n", "
23 | \n", "[π , π¦, π] | \n", "[] | \n", "[@ctrlpurp] | \n", "2017-11-01 13:29:29 | \n", "925716426278735900 | \n", "en | \n", "918492858352635900 | \n", "9.257161e+17 | \n", "<USER> Can I taste?<EMOJI><EMOJI><EMOJI> | \n", "
24 | \n", "[π] | \n", "[] | \n", "[@saunders_court1] | \n", "2017-11-01 13:29:30 | \n", "925716430473039900 | \n", "en | \n", "3471187337 | \n", "9.257163e+17 | \n", "<USER> we miss you βΉοΈ<EMOJI> | \n", "
25 | \n", "[π€, π€, π€] | \n", "[] | \n", "[] | \n", "2017-11-01 13:29:31 | \n", "925716434667184100 | \n", "en | \n", "780060488600199200 | \n", "NaN | \n", "Actually my bias in WJSN are Eunseo & Bona... | \n", "
26 | \n", "[π΄] | \n", "[] | \n", "[] | \n", "2017-11-01 13:29:32 | \n", "925716438853345300 | \n", "en | \n", "388380690 | \n", "NaN | \n", "I so cannot be bothered with the rest of the d... | \n", "
27 | \n", "[π] | \n", "[] | \n", "[@xxxtentacion] | \n", "2017-11-01 13:29:35 | \n", "925716451457163300 | \n", "en | \n", "899320696869974000 | \n", "NaN | \n", "<USER> 2lit4life<EMOJI> | \n", "
28 | \n", "[π, π] | \n", "[] | \n", "[] | \n", "2017-11-01 13:29:35 | \n", "925716451461357600 | \n", "en | \n", "784790670 | \n", "NaN | \n", "Iβm not stop saying that!<EMOJI><EMOJI> | \n", "
29 | \n", "[π, π, π, π, π, π] | \n", "[] | \n", "[@justinerooney_] | \n", "2017-11-01 13:29:37 | \n", "925716459828936700 | \n", "en | \n", "3051266655 | \n", "NaN | \n", "<USER> HAPPY BIHDAY <EMOJI><EMOJI><EMOJI><EMOJ... | \n", "
... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "
68703 | \n", "[π] | \n", "[#halloweencostumes] | \n", "[] | \n", "2017-11-01 07:23:04 | \n", "925624214522036200 | \n", "en | \n", "1672876458 | \n", "NaN | \n", "<HASHTAG> this one falls under the weird crazy... | \n", "
68704 | \n", "[π, π©] | \n", "[] | \n", "[] | \n", "2017-11-01 07:23:05 | \n", "925624218682777600 | \n", "en | \n", "382473866 | \n", "NaN | \n", "I'm not allowed to have chocolates yet, then I... | \n", "
68705 | \n", "[π] | \n", "[#MUFC] | \n", "[] | \n", "2017-11-01 07:23:06 | \n", "925624222889766900 | \n", "en | \n", "893145405457911800 | \n", "NaN | \n", "Manchester United manager Mourinho slams 'spec... | \n", "
68706 | \n", "[π] | \n", "[] | \n", "[] | \n", "2017-11-01 07:23:07 | \n", "925624227088121900 | \n", "en | \n", "240378516 | \n", "NaN | \n", "<EMOJI> en Bushwhick | \n", "
68707 | \n", "[π, π, π, π] | \n", "[#BurkeCentre] | \n", "[] | \n", "2017-11-01 07:23:18 | \n", "925624273237983200 | \n", "en | \n", "784620573209002000 | \n", "NaN | \n", ": <HASHTAG> <EMOJI> <EMOJI><EMOJI> For Taxi <E... | \n", "
68708 | \n", "[π] | \n", "[] | \n", "[@mychosliaheart, @BarrettoJulia, @iamjoshuaga... | \n", "2017-11-01 07:23:18 | \n", "925624273212805100 | \n", "en | \n", "170998187 | \n", "9.254136e+17 | \n", "<USER> <USER> <USER> Look, Mammeh and Daddeh! ... | \n", "
68709 | \n", "[π] | \n", "[] | \n", "[] | \n", "2017-11-01 07:23:24 | \n", "925624298395533300 | \n", "en | \n", "1348667816 | \n", "NaN | \n", "Life is so good with you <EMOJI> | \n", "
68710 | \n", "[π, π, π] | \n", "[#portlandoregon, #portlandhalloween, #carrieβ¦] | \n", "[] | \n", "2017-11-01 07:23:24 | \n", "925624298378801200 | \n", "en | \n", "722481645765300200 | \n", "NaN | \n", "Happy Halloween! <EMOJI>π½<EMOJI><EMOJI> <HASHT... | \n", "
68711 | \n", "[π] | \n", "[] | \n", "[@8limbsbondi...] | \n", "2017-11-01 07:23:26 | \n", "925624306779897900 | \n", "en | \n", "2443251500 | \n", "NaN | \n", "Some work on the ropes in todayβs boxing class... | \n", "
68712 | \n", "[π] | \n", "[] | \n", "[] | \n", "2017-11-01 07:23:27 | \n", "925624310974136300 | \n", "en | \n", "2406186390 | \n", "NaN | \n", "Scotty and Kristenβs halloween costumes <EMOJI> | \n", "
68713 | \n", "[π] | \n", "[] | \n", "[@rfrandrea, @AdaaanAndyyy] | \n", "2017-11-01 07:23:30 | \n", "925624323557146600 | \n", "en | \n", "1039448149 | \n", "9.256150e+17 | \n", "<USER> <USER> May pre-month celebration sis <E... | \n", "
68714 | \n", "[π, π, π] | \n", "[] | \n", "[@peachshua1230] | \n", "2017-11-01 07:23:31 | \n", "925624327755591700 | \n", "en | \n", "845085544589672400 | \n", "9.256009e+17 | \n", "<USER> Awww <EMOJI> Ajsksjdjd im smiling like ... | \n", "
68715 | \n", "[π«, β] | \n", "[] | \n", "[] | \n", "2017-11-01 07:23:34 | \n", "925624340342812700 | \n", "en | \n", "924752524871131100 | \n", "NaN | \n", "I hate when I send a text or snap n I'm so anx... | \n", "
68716 | \n", "[π, π] | \n", "[] | \n", "[] | \n", "2017-11-01 07:23:34 | \n", "925624340355280900 | \n", "en | \n", "419493819 | \n", "NaN | \n", "The answer is no I have no plans and I never l... | \n", "
68717 | \n", "[π] | \n", "[] | \n", "[@BeachBoy_Gab] | \n", "2017-11-01 07:23:34 | \n", "925624340346937300 | \n", "en | \n", "2457745952 | \n", "9.256219e+17 | \n", "<USER> LMAOOO I'm so proud <EMOJI> | \n", "
68718 | \n", "[π’, π] | \n", "[] | \n", "[] | \n", "2017-11-01 07:23:34 | \n", "925624340338507800 | \n", "en | \n", "1955767531 | \n", "NaN | \n", "My cousin/little sister is leaving to San Fran... | \n", "
68719 | \n", "[π] | \n", "[] | \n", "[] | \n", "2017-11-01 07:23:35 | \n", "925624344524361700 | \n", "en | \n", "796490344581898200 | \n", "NaN | \n", "Can't be alone w my thoughts tonight so just g... | \n", "
68720 | \n", "[π, π, π, π, π] | \n", "[] | \n", "[] | \n", "2017-11-01 07:23:36 | \n", "925624348710285300 | \n", "en | \n", "907808317124177900 | \n", "NaN | \n", "<EMOJI><EMOJI><EMOJI><EMOJI><EMOJI> ambot!!! | \n", "
68721 | \n", "[π, π, π] | \n", "[] | \n", "[] | \n", "2017-11-01 07:23:37 | \n", "925624352929910800 | \n", "en | \n", "262162415 | \n", "NaN | \n", "<EMOJI>π½<EMOJI>π½ 1st of the month!!Happy 1st o... | \n", "
68722 | \n", "[π΄] | \n", "[#WednesdayWisdom] | \n", "[] | \n", "2017-11-01 07:23:41 | \n", "925624369715515400 | \n", "en | \n", "574882525 | \n", "NaN | \n", "<HASHTAG> ... stay in bed <EMOJI> | \n", "
68723 | \n", "[π, π, π, π] | \n", "[] | \n", "[@Louis_Tomlinson, @NiallOfficial] | \n", "2017-11-01 07:23:44 | \n", "925624382269124600 | \n", "en | \n", "556175173 | \n", "9.254038e+17 | \n", "<USER> <USER> THIS IS GOLD. GOLD. <EMOJI><EMOJ... | \n", "
68724 | \n", "[π] | \n", "[] | \n", "[] | \n", "2017-11-01 07:23:45 | \n", "925624386455031800 | \n", "en | \n", "1610265588 | \n", "NaN | \n", "<EMOJI> thank you for the kind compliment | \n", "
68725 | \n", "[π] | \n", "[] | \n", "[] | \n", "2017-11-01 07:23:45 | \n", "925624386454937600 | \n", "en | \n", "4760724450 | \n", "NaN | \n", "Enjoyed the silence <EMOJI> | \n", "
68726 | \n", "[β¨] | \n", "[] | \n", "[] | \n", "2017-11-01 07:23:46 | \n", "925624390657572900 | \n", "en | \n", "882858115636514800 | \n", "NaN | \n", "OS: Spiderman Homecoming <EMOJI> | \n", "
68727 | \n", "[π€·] | \n", "[] | \n", "[] | \n", "2017-11-01 07:23:46 | \n", "925624390682849300 | \n", "en | \n", "188129628 | \n", "NaN | \n", "Go to hell <EMOJI>π½ββοΈ | \n", "
68728 | \n", "[π] | \n", "[] | \n", "[] | \n", "2017-11-01 07:23:46 | \n", "925624390666129400 | \n", "en | \n", "2473135939 | \n", "NaN | \n", "Thank you Yomi! <EMOJI> | \n", "
68729 | \n", "[π] | \n", "[] | \n", "[@discopiggu] | \n", "2017-11-01 07:23:46 | \n", "925624390670106600 | \n", "en | \n", "2373584209 | \n", "9.256241e+17 | \n", "<USER> Lol. Just enjoy the stars. Music Kidhar... | \n", "
68730 | \n", "[π] | \n", "[#NYCStrong] | \n", "[] | \n", "2017-11-01 07:23:50 | \n", "925624407459971100 | \n", "en | \n", "181689756 | \n", "NaN | \n", "Thoughts and prayers for NY<EMOJI>π» <HASHTAG> | \n", "
68731 | \n", "[π] | \n", "[#GreatSuccess] | \n", "[@BrianyH] | \n", "2017-11-01 07:23:50 | \n", "925624407460057100 | \n", "en | \n", "60160788 | \n", "9.254610e+17 | \n", "<USER> I searched COCK, PENIS, SHLONG, WINKY, ... | \n", "
68732 | \n", "[π, π», π», π, π, π, π, π, π] | \n", "[] | \n", "[@amitbarman520] | \n", "2017-11-01 07:23:53 | \n", "925624420022063100 | \n", "en | \n", "3792290725 | \n", "9.256215e+17 | \n", "<USER> Thank you so much<EMOJI><EMOJI><EMOJI><... | \n", "
68733 rows Γ 9 columns
\n", "\n", " | predict | \n", "teacher | \n", "text | \n", "
---|---|---|---|
62474 | \n", "π | \n", "π | \n", "Lovely | \n", "
11750 | \n", "π | \n", "π | \n", "β child they told that to slaves and look what... | \n", "
316 | \n", "π | \n", "π | \n", "Only in Wisconsin | \n", "
33553 | \n", "π | \n", "π | \n", ": Barboursville For Taxi 703-445-4450 | \n", "
1566 | \n", "π | \n", "π | \n", "who cares anyway | \n", "
54842 | \n", "π | \n", "π | \n", "<USER> first it was spratt then faze spratt th... | \n", "
16711 | \n", "π | \n", "π | \n", "I will forever love the Dodgers! BLEED BLUE t... | \n", "
52129 | \n", "π | \n", "π | \n", "ok she nailed this βοΈ | \n", "
66914 | \n", "π | \n", "π | \n", "time to create the Christmas playlist | \n", "
42046 | \n", "π | \n", "π | \n", "Penultimate <HASHTAG> of the 2017 race season!... | \n", "
13783 | \n", "π | \n", "π | \n", "hey friends i need space 2nite. happy 11-1! lo... | \n", "
4034 | \n", "π | \n", "π | \n", "Sombitch! 3.5 secs left an the goddamn 2K serv... | \n", "
9773 | \n", "π | \n", "π | \n", "sounds great.. | \n", "
27593 | \n", "π | \n", "π΄ | \n", "what happens after I give babe a massage | \n", "
22601 | \n", "π | \n", "π | \n", "<USER> Thank you | \n", "
64332 | \n", "π | \n", "π | \n", "<USER> I love you I'm so proud of you | \n", "
23677 | \n", "π | \n", "π | \n", "<USER> <USER> Love how your coffee bags pop up... | \n", "
1530 | \n", "π | \n", "π | \n", "<USER> I know | \n", "
38375 | \n", "π | \n", "π | \n", "<USER> Xmas songs all the way! I got a new chr... | \n", "
37403 | \n", "π | \n", "π | \n", "54 days until Christmas!! | \n", "
52706 | \n", "π | \n", "π | \n", "\"November comesAnd November goes,Β With the las... | \n", "
9628 | \n", "π | \n", "π | \n", "<USER> You want me dead | \n", "
41270 | \n", "π | \n", "π | \n", "Finally arrived Thank you so much <USER> So ... | \n", "
56276 | \n", "π | \n", "π | \n", "Omfg this is amazing | \n", "
14805 | \n", "π | \n", "π | \n", "Finding my <HASHTAG> need it now | \n", "
1275 | \n", "π | \n", "π | \n", "<USER> happy birthday | \n", "
30821 | \n", "π | \n", "π | \n", "<USER> better stock up, quenouille season is c... | \n", "
36974 | \n", "π | \n", "π | \n", "i always think miguel is saying \"black power\" ... | \n", "
31270 | \n", "π | \n", "π | \n", "<USER> so proud | \n", "
21672 | \n", "π | \n", "π | \n", "<USER> snapchat chick ? | \n", "
... | \n", "... | \n", "... | \n", "... | \n", "
6464 | \n", "π | \n", "π | \n", "<USER> <USER> Actually I donβt think that woul... | \n", "
14439 | \n", "π | \n", "π | \n", "happy birthday to a really great friend, hope ... | \n", "
30789 | \n", "π | \n", "π | \n", "Might fuck around and not turn in my library b... | \n", "
37129 | \n", "π | \n", "π | \n", "My lil baby sick and itβs making me sad, I den... | \n", "
61305 | \n", "π | \n", "π | \n", "Love our customers...always on the go! β€οΈ TRO... | \n", "
4821 | \n", "π | \n", "π | \n", "God bless whoever you marry! | \n", "
6509 | \n", "π | \n", "πΈ | \n", "j-u-v-e: On 1 November, Juventus turns 120! H... | \n", "
41347 | \n", "π | \n", "π | \n", "<USER> Yeah, sunshine, I promise I love you a... | \n", "
15368 | \n", "π | \n", "π | \n", "You ain't ever made love, You just wanted some... | \n", "
22594 | \n", "π | \n", "π | \n", "This whole lingerie thing is funny sha | \n", "
61471 | \n", "π | \n", "π | \n", "<USER> Wooo congrats buddy! | \n", "
63724 | \n", "π | \n", "π | \n", "Early mornings | \n", "
7399 | \n", "π | \n", "π | \n", "<USER> <USER> So Sad | \n", "
8262 | \n", "π | \n", "π | \n", "But opening up means trusting others.And that'... | \n", "
61430 | \n", "π | \n", "π | \n", "bambam pink hairβ€οΈ | \n", "
59747 | \n", "π | \n", "π | \n", "Nah last nights game was well worth my months ... | \n", "
47655 | \n", "π | \n", "π | \n", "<USER> wish your many more happy returns of th... | \n", "
30992 | \n", "π | \n", "πΆ | \n", "my heart breaks into a million pieces every mo... | \n", "
2204 | \n", "π | \n", "π | \n", "Call Congress (202) 224-3121 <HASHTAG> <HASHTA... | \n", "
41224 | \n", "π | \n", "π | \n", "I love Lucasβs sister! β€οΈ Erica is so funny! | \n", "
65180 | \n", "π | \n", "π | \n", "<USER> PULL THRU JELLYBEAN | \n", "
48319 | \n", "π | \n", "π | \n", "i miss the snickerdoodle swirl from <USER> so ... | \n", "
19825 | \n", "π | \n", "π | \n", "I love you- and I really do. | \n", "
63387 | \n", "π | \n", "πΉ | \n", "Love huvin Mason, can steal aw his Halloween s... | \n", "
33798 | \n", "π | \n", "π | \n", "80/0 at the end of 10 overs - Shikhar Dhawan ... | \n", "
63144 | \n", "π | \n", "π | \n", "Stoping for a few in between 12 hr shifts is p... | \n", "
5185 | \n", "π | \n", "π | \n", "When a band member of Volumes actually adds yo... | \n", "
65919 | \n", "π | \n", "πΆ | \n", "<USER> <USER> Evil sick humans what a world we... | \n", "
27834 | \n", "π | \n", "π | \n", "<USER> I always thought it was <USER> | \n", "
57241 | \n", "π | \n", "π | \n", "<USER> <USER> I thought u meant the show neve... | \n", "
5831 rows Γ 3 columns
\n", "Failed to display Jupyter Widget of type Text
.
\n", " If you're reading this message in the Jupyter Notebook or JupyterLab Notebook, it may mean\n", " that the widgets JavaScript is still loading. If this message persists, it\n", " likely means that the widgets JavaScript library is either not installed or\n", " not enabled. See the Jupyter\n", " Widgets Documentation for setup instructions.\n", "
\n", "\n", " If you're reading this message in another frontend (for example, a static\n", " rendering on GitHub or NBViewer),\n", " it may mean that your frontend doesn't currently support widgets.\n", "
\n" ], "text/plain": [ "Text(value='')" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "d34382a5e13c4be396303afc6b138c2a", "version_major": 2, "version_minor": 0 }, "text/html": [ "Failed to display Jupyter Widget of type VBox
.
\n", " If you're reading this message in the Jupyter Notebook or JupyterLab Notebook, it may mean\n", " that the widgets JavaScript is still loading. If this message persists, it\n", " likely means that the widgets JavaScript library is either not installed or\n", " not enabled. See the Jupyter\n", " Widgets Documentation for setup instructions.\n", "
\n", "\n", " If you're reading this message in another frontend (for example, a static\n", " rendering on GitHub or NBViewer),\n", " it may mean that your frontend doesn't currently support widgets.\n", "
\n" ], "text/plain": [ "VBox(children=(Button(description='get smiley', icon='check', style=ButtonStyle(), tooltip='Click me'), Output()))" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "out = widgets.Output()\n", "\n", "t = widgets.Text()\n", "b = widgets.Button(\n", " description='get smiley',\n", " disabled=False,\n", " button_style='', # 'success', 'info', 'warning', 'danger' or ''\n", " tooltip='Click me',\n", " icon='check'\n", ")\n", "\n", "\n", "\n", "def handle_submit(sender):\n", " with out:\n", " clear_output()\n", " with out:\n", " pred = clf.predict(vectorizer.transform([t.value]))\n", " \n", " display(Markdown(\"# \" + str(sent2emoji(pred))))\n", "\n", "b.on_click(handle_submit)\n", " \n", "display(t)\n", "display(widgets.VBox([b, out])) " ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "import numpy as np\n", "\n", "y_trans = mlb.inverse_transform(yt1)\n", "pred_trans = mlb.inverse_transform(yt1)\n", "\n", "# evaluate accuracy\n", "pos = 0\n", "neg = 0\n", "all = 0\n", "for entry in range(len(y_trans)):\n", " if len(np.intersect1d(y_trans[entry], pred_trans[entry])) > 0:\n", " pos += 1\n", " else:\n", " neg += 1\n", " all += 1\n", "print(pos/all)\n", "print(neg)" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.6.5" } }, "nbformat": 4, "nbformat_minor": 2 }