Untitled2.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "ename": "ModuleNotFoundError",
     "evalue": "No module named 'seaborn'",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mModuleNotFoundError\u001b[0m                       Traceback (most recent call last)",
      "\u001b[1;32m<ipython-input-1-d0f2cbd9beba>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[0;32m     13\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     14\u001b[0m \u001b[1;32mfrom\u001b[0m \u001b[0mmatplotlib\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mpyplot\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0mplt\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 15\u001b[1;33m \u001b[1;32mimport\u001b[0m \u001b[0mseaborn\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0msns\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     16\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     17\u001b[0m \u001b[0mprint\u001b[0m \u001b[1;33m(\u001b[0m\u001b[1;34m\"Imports ready!\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;31mModuleNotFoundError\u001b[0m: No module named 'seaborn'"
     ]
    }
   ],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import emoji\n",
    "\n",
    "from tensorflow.keras.utils import to_categorical\n",
    "from tensorflow.keras.models import Sequential\n",
    "from tensorflow.keras.layers import Dense, Input, Dropout, LSTM, Activation\n",
    "from tensorflow.keras.layers import Embedding\n",
    "from tensorflow.keras.callbacks import ReduceLROnPlateau, ModelCheckpoint\n",
    "\n",
    "from sklearn.metrics import confusion_matrix\n",
    "from sklearn.metrics import precision_score, recall_score\n",
    "\n",
    "from matplotlib import pyplot as plt\n",
    "import seaborn as sns\n",
    "\n",
    "print (\"Imports ready!\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Collecting seaborn\n",
      "  Downloading seaborn-0.11.1-py3-none-any.whl (285 kB)\n",
      "Requirement already satisfied: scipy>=1.0 in c:\\python38\\lib\\site-packages (from seaborn) (1.6.0)\n",
      "Requirement already satisfied: numpy>=1.15 in c:\\python38\\lib\\site-packages (from seaborn) (1.19.3)\n",
      "Requirement already satisfied: pandas>=0.23 in c:\\python38\\lib\\site-packages (from seaborn) (1.2.0)\n",
      "Requirement already satisfied: matplotlib>=2.2 in c:\\python38\\lib\\site-packages (from seaborn) (3.3.3)\n",
      "Requirement already satisfied: python-dateutil>=2.1 in c:\\python38\\lib\\site-packages (from matplotlib>=2.2->seaborn) (2.8.1)\n",
      "Requirement already satisfied: pillow>=6.2.0 in c:\\python38\\lib\\site-packages (from matplotlib>=2.2->seaborn) (8.1.0)\n",
      "Requirement already satisfied: cycler>=0.10 in c:\\python38\\lib\\site-packages (from matplotlib>=2.2->seaborn) (0.10.0)\n",
      "Requirement already satisfied: pyparsing!=2.0.4,!=2.1.2,!=2.1.6,>=2.0.3 in c:\\python38\\lib\\site-packages (from matplotlib>=2.2->seaborn) (2.4.7)\n",
      "Requirement already satisfied: kiwisolver>=1.0.1 in c:\\python38\\lib\\site-packages (from matplotlib>=2.2->seaborn) (1.3.1)\n",
      "Requirement already satisfied: six in c:\\python38\\lib\\site-packages (from cycler>=0.10->matplotlib>=2.2->seaborn) (1.15.0)\n",
      "Note: you may need to restart the kernel to use updated packages.\n",
      "Requirement already satisfied: pytz>=2017.3 in c:\\python38\\lib\\site-packages (from pandas>=0.23->seaborn) (2020.5)\n",
      "Installing collected packages: seaborn\n",
      "Successfully installed seaborn-0.11.1\n"
     ]
    }
   ],
   "source": [
    "pip install seaborn"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "import seaborn as sns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [],
   "source": [
    "train = pd.read_csv ('datasets/train_emoji.csv', usecols = [0, 1], header = None)\n",
    "test = pd.read_csv ('datasets/test_emoji.csv', usecols = [0, 1], header = None)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Training data shape = (131, 2), Validation data shape = (56, 2)\n"
     ]
    },
    {
     "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>0</th>\n",
       "      <th>1</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>never talk to me again</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>I am proud of your achievements</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>It is the worst day in my life</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                 0  1\n",
       "0           never talk to me again  3\n",
       "1  I am proud of your achievements  2\n",
       "2   It is the worst day in my life  3"
      ]
     },
     "execution_count": 40,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "print (f'Training data shape = {train.shape}, Validation data shape = {test.shape}')\n",
    "\n",
    "train.head (3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "2    38\n",
       "3    36\n",
       "0    21\n",
       "1    19\n",
       "4    17\n",
       "Name: 1, dtype: int64"
      ]
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train[1].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "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>0</th>\n",
       "      <th>1</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>I want to eat\\t</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>he did not answer\\t</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>he got a raise\\t</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                     0  1\n",
       "0      I want to eat\\t  4\n",
       "1  he did not answer\\t  3\n",
       "2     he got a raise\\t  2"
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test.head(3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [],
   "source": [
    "emoji_dictionary = {\"0\": \"\\u2764\\uFE0F\",    # 🖤\n",
    "                    \"1\": \":baseball:\", # ⚾\n",
    "                    \"2\": \":beaming_face_with_smiling_eyes:\", # 😁\n",
    "                    \"3\": \":downcast_face_with_sweat:\", # 😓\n",
    "                    \"4\": \":fork_and_knife:\", # 🍴\n",
    "                   }"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'0': '❤️', '1': ':baseball:', '2': ':beaming_face_with_smiling_eyes:', '3': ':downcast_face_with_sweat:', '4': ':fork_and_knife:'}\n"
     ]
    }
   ],
   "source": [
    "print(emoji_dictionary)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0 ❤️\n",
      "1 :baseball:\n",
      "2 :beaming_face_with_smiling_eyes:\n",
      "3 :downcast_face_with_sweat:\n",
      "4 :fork_and_knife:\n"
     ]
    }
   ],
   "source": [
    "for i in emoji_dictionary:\n",
    "    print(i, emoji_dictionary[i])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0 ❤️\n",
      "1 ⚾\n",
      "2 😁\n",
      "3 😓\n",
      "4 🍴\n"
     ]
    }
   ],
   "source": [
    "for i in emoji_dictionary:\n",
    "    print(i, emoji.emojize(emoji_dictionary[i]))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {},
   "outputs": [],
   "source": [
    "x_train = train.values[:, 0]\n",
    "y_train = to_categorical (train.values[:, 1])\n",
    "\n",
    "x_test = test.values[:, 0]\n",
    "y_test = to_categorical (test.values[:, 1])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Length of longest sentence (by number of words) is : 10\n"
     ]
    }
   ],
   "source": [
    "maxLen = 0 # Len of longest sentence (by number of words)\n",
    "\n",
    "for sent in x_train:\n",
    "    maxLen = max (maxLen, len (sent.split (' ')))\n",
    "\n",
    "for sent in x_test:\n",
    "    maxLen = max (maxLen, len (sent.split (' ')))\n",
    "    \n",
    "print (f\"Length of longest sentence (by number of words) is : {maxLen}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Sentence : never talk to me again \n",
      " Emoji : 😓 \n",
      "\n",
      "Sentence : I am proud of your achievements \n",
      " Emoji : 😁 \n",
      "\n",
      "Sentence : It is the worst day in my life \n",
      " Emoji : 😓 \n",
      "\n",
      "Sentence : Miss you so much \n",
      " Emoji : ❤️ \n",
      "\n",
      "Sentence : food is life \n",
      " Emoji : 🍴 \n",
      "\n",
      "Sentence : Stop saying bullshit \n",
      " Emoji : 😓 \n",
      "\n",
      "Sentence : congratulations on your acceptance \n",
      " Emoji : 😁 \n",
      "\n",
      "Sentence : The assignment is too long  \n",
      " Emoji : 😓 \n",
      "\n",
      "Sentence : I want to go play \n",
      " Emoji : ⚾ \n",
      "\n",
      "Sentence : she did not answer my text  \n",
      " Emoji : 😓 \n",
      "\n"
     ]
    }
   ],
   "source": [
    "for i, sent in enumerate (x_train):\n",
    "    if i == 10:\n",
    "        break\n",
    "    label = str (np.argmax (y_train[i]))\n",
    "    print (f\"Sentence : {sent} \\n Emoji : {emoji.emojize (emoji_dictionary[label])} \\n\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Sentence : never talk to me again \n",
      " Emoji : 😓 \n",
      "\n",
      "Sentence : I am proud of your achievements \n",
      " Emoji : 😁 \n",
      "\n",
      "Sentence : It is the worst day in my life \n",
      " Emoji : 😓 \n",
      "\n",
      "Sentence : Miss you so much \n",
      " Emoji : ❤️ \n",
      "\n",
      "Sentence : food is life \n",
      " Emoji : 🍴 \n",
      "\n",
      "Sentence : Stop saying bullshit \n",
      " Emoji : 😓 \n",
      "\n",
      "Sentence : congratulations on your acceptance \n",
      " Emoji : 😁 \n",
      "\n",
      "Sentence : The assignment is too long  \n",
      " Emoji : 😓 \n",
      "\n",
      "Sentence : I want to go play \n",
      " Emoji : ⚾ \n",
      "\n",
      "Sentence : she did not answer my text  \n",
      " Emoji : 😓 \n",
      "\n",
      "Sentence : Your stupidity has no limit \n",
      " Emoji : 😓 \n",
      "\n",
      "Sentence : how many points did he score \n",
      " Emoji : ⚾ \n",
      "\n",
      "Sentence : my algorithm performs poorly \n",
      " Emoji : 😓 \n",
      "\n",
      "Sentence : I got approved \n",
      " Emoji : 😁 \n",
      "\n",
      "Sentence : Stop shouting at me \n",
      " Emoji : 😓 \n",
      "\n",
      "Sentence : Sounds like a fun plan ha ha \n",
      " Emoji : 😁 \n",
      "\n",
      "Sentence : no one likes him \n",
      " Emoji : 😓 \n",
      "\n",
      "Sentence : the game just finished \n",
      " Emoji : ⚾ \n",
      "\n",
      "Sentence : I will celebrate soon \n",
      " Emoji : 😁 \n",
      "\n",
      "Sentence : So sad you are not coming \n",
      " Emoji : 😓 \n",
      "\n",
      "Sentence : She is my dearest love \n",
      " Emoji : ❤️ \n",
      "\n",
      "Sentence : Good job \n",
      " Emoji : 😁 \n",
      "\n",
      "Sentence : It was funny lol \n",
      " Emoji : 😁 \n",
      "\n",
      "Sentence : candy is life  \n",
      " Emoji : 😁 \n",
      "\n",
      "Sentence : The chicago cubs won again \n",
      " Emoji : ⚾ \n",
      "\n",
      "Sentence : I am hungry \n",
      " Emoji : 🍴 \n",
      "\n",
      "Sentence : I am so excited to see you after so long \n",
      " Emoji : 😁 \n",
      "\n",
      "Sentence : you did well on you exam \n",
      " Emoji : 😁 \n",
      "\n",
      "Sentence : lets brunch some day \n",
      " Emoji : 🍴 \n",
      "\n",
      "Sentence : he is so cute \n",
      " Emoji : ❤️ \n",
      "\n",
      "Sentence : How dare you ask that \n",
      " Emoji : 😓 \n",
      "\n",
      "Sentence : do you want to join me for dinner  \n",
      " Emoji : 🍴 \n",
      "\n",
      "Sentence : I said yes \n",
      " Emoji : 😁 \n",
      "\n",
      "Sentence : she is attractive \n",
      " Emoji : ❤️ \n",
      "\n",
      "Sentence : you suck \n",
      " Emoji : 😓 \n",
      "\n",
      "Sentence : she smiles a lot \n",
      " Emoji : 😁 \n",
      "\n",
      "Sentence : he is laughing \n",
      " Emoji : 😁 \n",
      "\n",
      "Sentence : she takes forever to get ready  \n",
      " Emoji : 😓 \n",
      "\n",
      "Sentence : French macaroon is so tasty \n",
      " Emoji : 🍴 \n",
      "\n",
      "Sentence : we made it \n",
      " Emoji : 😁 \n",
      "\n",
      "Sentence : I am excited \n",
      " Emoji : 😁 \n",
      "\n",
      "Sentence : I adore my dogs \n",
      " Emoji : ❤️ \n",
      "\n",
      "Sentence : Congratulations \n",
      " Emoji : 😁 \n",
      "\n",
      "Sentence : this girl was mean \n",
      " Emoji : 😓 \n",
      "\n",
      "Sentence : you two are cute \n",
      " Emoji : ❤️ \n",
      "\n",
      "Sentence : my code is working but the grader gave me zero \n",
      " Emoji : 😓 \n",
      "\n",
      "Sentence : this joke is killing me haha \n",
      " Emoji : 😁 \n",
      "\n",
      "Sentence : do you like pizza  \n",
      " Emoji : 🍴 \n",
      "\n",
      "Sentence : you got a down grade \n",
      " Emoji : 😓 \n",
      "\n",
      "Sentence : I missed you \n",
      " Emoji : ❤️ \n",
      "\n",
      "Sentence : I think I will end up alone \n",
      " Emoji : 😓 \n",
      "\n",
      "Sentence : I got humiliated by my sister \n",
      " Emoji : 😓 \n",
      "\n",
      "Sentence : you are awful \n",
      " Emoji : 😓 \n",
      "\n",
      "Sentence : I cooked meat \n",
      " Emoji : 🍴 \n",
      "\n",
      "Sentence : This is so funny \n",
      " Emoji : 😁 \n",
      "\n",
      "Sentence : lets exercise \n",
      " Emoji : ⚾ \n",
      "\n",
      "Sentence : he is the best player \n",
      " Emoji : ⚾ \n",
      "\n",
      "Sentence : I am going to the stadium \n",
      " Emoji : ⚾ \n",
      "\n",
      "Sentence : You are incredibly intelligent and talented \n",
      " Emoji : 😁 \n",
      "\n",
      "Sentence : Stop shouting at me \n",
      " Emoji : 😓 \n",
      "\n",
      "Sentence : Who is your favorite player \n",
      " Emoji : ⚾ \n",
      "\n",
      "Sentence : I like you a lot \n",
      " Emoji : ❤️ \n",
      "\n",
      "Sentence : i miss him \n",
      " Emoji : ❤️ \n",
      "\n",
      "Sentence : my dog just had a few puppies \n",
      " Emoji : ❤️ \n",
      "\n",
      "Sentence : I hate him \n",
      " Emoji : 😓 \n",
      "\n",
      "Sentence : I want chinese food \n",
      " Emoji : 🍴 \n",
      "\n",
      "Sentence : cookies are good \n",
      " Emoji : 🍴 \n",
      "\n",
      "Sentence : her smile is so charming \n",
      " Emoji : 😁 \n",
      "\n",
      "Sentence : Bravo for the announcement it got a lot of traction \n",
      " Emoji : 😁 \n",
      "\n",
      "Sentence : she plays baseball \n",
      " Emoji : ⚾ \n",
      "\n",
      "Sentence : he did an amazing job \n",
      " Emoji : 😁 \n",
      "\n",
      "Sentence : The baby is adorable \n",
      " Emoji : ❤️ \n",
      "\n",
      "Sentence : I was waiting for her for two hours  \n",
      " Emoji : 😓 \n",
      "\n",
      "Sentence : funny \n",
      " Emoji : 😁 \n",
      "\n",
      "Sentence : I like it when people smile \n",
      " Emoji : 😁 \n",
      "\n",
      "Sentence : I love dogs \n",
      " Emoji : ❤️ \n",
      "\n",
      "Sentence : they are so kind and friendly \n",
      " Emoji : ❤️ \n",
      "\n",
      "Sentence : So bad that you cannot come with us \n",
      " Emoji : 😓 \n",
      "\n",
      "Sentence : he likes baseball \n",
      " Emoji : ⚾ \n",
      "\n",
      "Sentence : I am so impressed by your dedication to this project \n",
      " Emoji : 😁 \n",
      "\n",
      "Sentence : I am at the baseball game \n",
      " Emoji : ⚾ \n",
      "\n",
      "Sentence : Bravo \n",
      " Emoji : 😁 \n",
      "\n",
      "Sentence : What a fun moment \n",
      " Emoji : 😁 \n",
      "\n",
      "Sentence : I want to have sushi for dinner \n",
      " Emoji : 🍴 \n",
      "\n",
      "Sentence : I am very disappointed \n",
      " Emoji : 😓 \n",
      "\n",
      "Sentence : he can not do anything \n",
      " Emoji : 😓 \n",
      "\n",
      "Sentence : lol \n",
      " Emoji : 😁 \n",
      "\n",
      "Sentence : Lets have food together \n",
      " Emoji : 🍴 \n",
      "\n",
      "Sentence : she is so cute \n",
      " Emoji : ❤️ \n",
      "\n",
      "Sentence : miss you my dear \n",
      " Emoji : ❤️ \n",
      "\n",
      "Sentence : I am looking for a date \n",
      " Emoji : ❤️ \n",
      "\n",
      "Sentence : I am frustrated \n",
      " Emoji : 😓 \n",
      "\n",
      "Sentence : I lost my wallet \n",
      " Emoji : 😓 \n",
      "\n",
      "Sentence : you failed the midterm \n",
      " Emoji : 😓 \n",
      "\n",
      "Sentence : ha ha ha it was so funny \n",
      " Emoji : 😁 \n",
      "\n",
      "Sentence : Do you want to give me a hug \n",
      " Emoji : ❤️ \n",
      "\n",
      "Sentence : who is playing in the final \n",
      " Emoji : ⚾ \n",
      "\n",
      "Sentence : she is happy \n",
      " Emoji : 😁 \n",
      "\n",
      "Sentence : You are not qualified for this position \n",
      " Emoji : 😓 \n",
      "\n",
      "Sentence : I love my dad \n",
      " Emoji : ❤️ \n",
      "\n",
      "Sentence : this guy was such a joke \n",
      " Emoji : 😁 \n",
      "\n",
      "Sentence : Good joke \n",
      " Emoji : 😁 \n",
      "\n",
      "Sentence : This specialization is great \n",
      " Emoji : 😁 \n",
      "\n",
      "Sentence : you could not solve it \n",
      " Emoji : 😓 \n",
      "\n",
      "Sentence : I am so happy for you \n",
      " Emoji : 😁 \n",
      "\n",
      "Sentence : Congrats on the new job \n",
      " Emoji : 😁 \n",
      "\n",
      "Sentence : I am proud of you forever \n",
      " Emoji : 😁 \n",
      "\n",
      "Sentence : I want to eat \n",
      " Emoji : 🍴 \n",
      "\n",
      "Sentence : That catcher sucks  \n",
      " Emoji : ⚾ \n",
      "\n",
      "Sentence : The first base man got the ball \n",
      " Emoji : ⚾ \n",
      "\n",
      "Sentence : this is bad \n",
      " Emoji : 😓 \n",
      "\n",
      "Sentence : you did not do your homework \n",
      " Emoji : 😓 \n",
      "\n",
      "Sentence : I will have a cheese cake \n",
      " Emoji : 🍴 \n",
      "\n",
      "Sentence : do you have a ball \n",
      " Emoji : ⚾ \n",
      "\n",
      "Sentence : the lectures are great though  \n",
      " Emoji : 😁 \n",
      "\n",
      "Sentence : Are you down for baseball this afternoon \n",
      " Emoji : ⚾ \n",
      "\n",
      "Sentence : what are the rules of the game \n",
      " Emoji : ⚾ \n",
      "\n",
      "Sentence : I am always working \n",
      " Emoji : 😓 \n",
      "\n",
      "Sentence : where is the stadium \n",
      " Emoji : ⚾ \n",
      "\n",
      "Sentence : She is the cutest person I have ever seen \n",
      " Emoji : ❤️ \n",
      "\n",
      "Sentence : vegetables are healthy \n",
      " Emoji : 🍴 \n",
      "\n",
      "Sentence : he is handsome \n",
      " Emoji : ❤️ \n",
      "\n",
      "Sentence : too bad that you were not here \n",
      " Emoji : 😓 \n",
      "\n",
      "Sentence : you are a loser \n",
      " Emoji : 😓 \n",
      "\n",
      "Sentence : I love indian food \n",
      " Emoji : 🍴 \n",
      "\n",
      "Sentence : Who is down for a restaurant \n",
      " Emoji : 🍴 \n",
      "\n",
      "Sentence : he had to make a home run \n",
      " Emoji : ⚾ \n",
      "\n",
      "Sentence : I am ordering food \n",
      " Emoji : 🍴 \n",
      "\n",
      "Sentence : What is wrong with you \n",
      " Emoji : 😓 \n",
      "\n",
      "Sentence : I love you \n",
      " Emoji : ❤️ \n",
      "\n",
      "Sentence : great job \n",
      " Emoji : 😁 \n",
      "\n"
     ]
    }
   ],
   "source": [
    "for i, sent in enumerate (x_train):\n",
    "    label = str (np.argmax (y_train[i]))\n",
    "    print (f\"Sentence : {sent} \\n Emoji : {emoji.emojize (emoji_dictionary[label])} \\n\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {},
   "outputs": [],
   "source": [
    "embeddings = {}\n",
    "with open ('glove.6B.50D.txt', encoding = 'utf-8') as f:\n",
    "    for line in f:\n",
    "        values = line.split () # splits the word and coeff\n",
    "        word = values[0] # word\n",
    "        coeffs = np.asarray (values[1 : ], dtype = 'float32') # makes a word vector of len 50 for each word\n",
    "        embeddings[word] = coeffs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {},
   "outputs": [],
   "source": [
    "def getOutputEmbeddings(X):\n",
    "    \n",
    "    embedding_matrix_output = np.zeros ((X.shape[0], 10, 50)) # X.shape (num_of_sentences, max_len, embedding_dim)\n",
    "    for ix in range (X.shape[0]): # go to every sentence\n",
    "        X[ix] = X[ix].split () # get a list of words of the sentence\n",
    "        for jx in range (len(X[ix])): # go to every word\n",
    "            embedding_matrix_output[ix][jx] = embeddings[X[ix][jx].lower ()]\n",
    "            \n",
    "    return embedding_matrix_output"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "metadata": {},
   "outputs": [
    {
     "ename": "KeyError",
     "evalue": "'bullshit'",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mKeyError\u001b[0m                                  Traceback (most recent call last)",
      "\u001b[1;32m<ipython-input-53-5b085ef3b65f>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0memb_x_train\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mgetOutputEmbeddings\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mx_train\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;31m# getting embeddings for train data\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m      2\u001b[0m \u001b[0memb_x_test\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mgetOutputEmbeddings\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mx_test\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;31m# getting embeddings for test data\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      3\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      4\u001b[0m \u001b[0memb_x_train\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mshape\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0memb_x_test\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mshape\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m<ipython-input-52-7b809b3755aa>\u001b[0m in \u001b[0;36mgetOutputEmbeddings\u001b[1;34m(X)\u001b[0m\n\u001b[0;32m      5\u001b[0m         \u001b[0mX\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mix\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mX\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mix\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msplit\u001b[0m \u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;31m# get a list of words of the sentence\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      6\u001b[0m         \u001b[1;32mfor\u001b[0m \u001b[0mjx\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mrange\u001b[0m \u001b[1;33m(\u001b[0m\u001b[0mlen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mX\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mix\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m \u001b[1;31m# go to every word\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 7\u001b[1;33m             \u001b[0membedding_matrix_output\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mix\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mjx\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0membeddings\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mX\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mix\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mjx\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mlower\u001b[0m \u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m      8\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      9\u001b[0m     \u001b[1;32mreturn\u001b[0m \u001b[0membedding_matrix_output\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;31mKeyError\u001b[0m: 'bullshit'"
     ]
    }
   ],
   "source": [
    "emb_x_train = getOutputEmbeddings(x_train) # getting embeddings for train data\n",
    "emb_x_test = getOutputEmbeddings(x_test) # getting embeddings for test data\n",
    "\n",
    "emb_x_train.shape, emb_x_test.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "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": "3.8.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}