Untitled1.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Collecting pandasNote: you may need to restart the kernel to use updated packages.\n",
      "  Downloading pandas-1.2.0-cp38-cp38-win_amd64.whl (9.3 MB)\n",
      "Requirement already satisfied: python-dateutil>=2.7.3 in c:\\python38\\lib\\site-packages (from pandas) (2.8.1)\n",
      "Requirement already satisfied: numpy>=1.16.5 in c:\\python38\\lib\\site-packages (from pandas) (1.19.3)\n",
      "Requirement already satisfied: six>=1.5 in c:\\python38\\lib\\site-packages (from python-dateutil>=2.7.3->pandas) (1.15.0)\n",
      "Collecting pytz>=2017.3\n",
      "  Using cached pytz-2020.5-py2.py3-none-any.whl (510 kB)\n",
      "Installing collected packages: pytz, pandas\n",
      "Successfully installed pandas-1.2.0 pytz-2020.5\n",
      "\n"
     ]
    }
   ],
   "source": [
    "pip install pandas"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Collecting matplotlib\n",
      "  Downloading matplotlib-3.3.3-cp38-cp38-win_amd64.whl (8.5 MB)\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) (2.4.7)\n",
      "Requirement already satisfied: numpy>=1.15 in c:\\python38\\lib\\site-packages (from matplotlib) (1.19.3)\n",
      "Requirement already satisfied: python-dateutil>=2.1 in c:\\python38\\lib\\site-packages (from matplotlib) (2.8.1)\n",
      "Collecting cycler>=0.10\n",
      "  Downloading cycler-0.10.0-py2.py3-none-any.whl (6.5 kB)\n",
      "Requirement already satisfied: six in c:\\python38\\lib\\site-packages (from cycler>=0.10->matplotlib) (1.15.0)\n",
      "Collecting kiwisolver>=1.0.1\n",
      "  Downloading kiwisolver-1.3.1-cp38-cp38-win_amd64.whl (51 kB)\n",
      "Collecting pillow>=6.2.0\n",
      "  Downloading Pillow-8.1.0-cp38-cp38-win_amd64.whl (2.2 MB)\n",
      "Installing collected packages: pillow, kiwisolver, cycler, matplotlib\n",
      "Successfully installed cycler-0.10.0 kiwisolver-1.3.1 matplotlib-3.3.3 pillow-8.1.0\n",
      "Note: you may need to restart the kernel to use updated packages.\n"
     ]
    }
   ],
   "source": [
    "pip install matplotlib"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Collecting sklearn\n",
      "  Downloading sklearn-0.0.tar.gz (1.1 kB)\n",
      "Collecting scikit-learnNote: you may need to restart the kernel to use updated packages.\n",
      "  Downloading scikit_learn-0.24.0-cp38-cp38-win_amd64.whl (6.9 MB)\n",
      "Requirement already satisfied: numpy>=1.13.3 in c:\\python38\\lib\\site-packages (from scikit-learn->sklearn) (1.19.3)\n",
      "Collecting joblib>=0.11\n",
      "  Downloading joblib-1.0.0-py3-none-any.whl (302 kB)\n",
      "Collecting scipy>=0.19.1\n",
      "  Downloading scipy-1.6.0-cp38-cp38-win_amd64.whl (32.7 MB)\n",
      "Collecting threadpoolctl>=2.0.0\n",
      "  Downloading threadpoolctl-2.1.0-py3-none-any.whl (12 kB)\n",
      "Using legacy 'setup.py install' for sklearn, since package 'wheel' is not installed.\n",
      "Installing collected packages: threadpoolctl, scipy, joblib, scikit-learn, sklearn\n",
      "    Running setup.py install for sklearn: started\n",
      "    Running setup.py install for sklearn: finished with status 'done'\n",
      "Successfully installed joblib-1.0.0 scikit-learn-0.24.0 scipy-1.6.0 sklearn-0.0 threadpoolctl-2.1.0\n",
      "\n"
     ]
    }
   ],
   "source": [
    "pip install sklearn"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Collecting emoji\n",
      "  Downloading emoji-0.6.0.tar.gz (51 kB)\n",
      "Using legacy 'setup.py install' for emoji, since package 'wheel' is not installed.\n",
      "Installing collected packages: emoji\n",
      "    Running setup.py install for emoji: started\n",
      "    Running setup.py install for emoji: finished with status 'done'\n",
      "Successfully installed emoji-0.6.0\n",
      "Note: you may need to restart the kernel to use updated packages.\n"
     ]
    }
   ],
   "source": [
    "pip install emoji"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "from emo_utils import *\n",
    "import emoji\n",
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train, Y_train = read_csv('data/train_emoji.csv')\n",
    "X_test, Y_test = read_csv('data/tesss.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "maxLen = len(max(X_train, key=len).split())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "I am proud of your achievements 😄\n"
     ]
    }
   ],
   "source": [
    "index = 1\n",
    "print(X_train[index], label_to_emoji(Y_train[index]))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "Y_oh_train = convert_to_one_hot(Y_train, C = 5)\n",
    "Y_oh_test = convert_to_one_hot(Y_test, C = 5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0 is converted into one hot [1. 0. 0. 0. 0.]\n"
     ]
    }
   ],
   "source": [
    "index = 50\n",
    "print(Y_train[index], \"is converted into one hot\", Y_oh_train[index])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "ename": "TypeError",
     "evalue": "expected str, bytes or os.PathLike object, not _io.TextIOWrapper",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
      "\u001b[1;32m<ipython-input-27-19a2111e7390>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[0;32m      1\u001b[0m \u001b[0mf\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mopen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'data/glove.6B.50d.txt'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mencoding\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;34m\"utf8\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 2\u001b[1;33m \u001b[0mword_to_index\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mindex_to_word\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mword_to_vec_map\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mread_glove_vecs\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mf\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[1;32mD:\\ML-Project\\Emojify\\emo_utils.py\u001b[0m in \u001b[0;36mread_glove_vecs\u001b[1;34m(glove_file)\u001b[0m\n\u001b[0;32m      7\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      8\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0mread_glove_vecs\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mglove_file\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[1;32m----> 9\u001b[1;33m     \u001b[1;32mwith\u001b[0m \u001b[0mopen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mglove_file\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m'r'\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0mf\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     10\u001b[0m         \u001b[0mwords\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mset\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[0;32m     11\u001b[0m         \u001b[0mword_to_vec_map\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[1;31mTypeError\u001b[0m: expected str, bytes or os.PathLike object, not _io.TextIOWrapper"
     ]
    }
   ],
   "source": [
    "f = open('data/glove.6B.50d.txt', encoding=\"utf8\")\n",
    "word_to_index, index_to_word, word_to_vec_map = read_glove_vecs(f)"
   ]
  },
  {
   "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": []
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "f = open('data/glove.txt',encoding='utf-8')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "embeddings_index = {}\n",
    "for line in f:\n",
    "    values = line.split()\n",
    "    word = values[0]\n",
    "    coefs = np.asarray(values[1:],dtype='float')\n",
    "    embeddings_index[word] = coefs\n",
    "f.close()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [],
   "source": [
    "def embedding_output(X):\n",
    "    maxLen = 10\n",
    "    embedding_out = np.zeros((X.shape[0],maxLen,50))\n",
    "    for ix in range(X.shape[0]):\n",
    "        X[ix] = X[ix].split()\n",
    "        for jx in range(len(X[ix])):\n",
    "            embedding_out[ix][jx] = embeddings_index[X[ix][jx].lower()]\n",
    "    return embedding_out"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "ename": "ValueError",
     "evalue": "setting an array element with a sequence",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mValueError\u001b[0m                                Traceback (most recent call last)",
      "\u001b[1;32m<ipython-input-21-00a2ff0ee59a>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0membeddings_matrix_train\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0membedding_output\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mX_train\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      2\u001b[0m \u001b[0membeddings_matrix_test\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0membedding_output\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mX_test\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m<ipython-input-20-117bad1a5630>\u001b[0m in \u001b[0;36membedding_output\u001b[1;34m(X)\u001b[0m\n\u001b[0;32m      3\u001b[0m     \u001b[0membedding_out\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mzeros\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mX\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mshape\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;36m0\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mmaxLen\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;36m50\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[0;32m      4\u001b[0m     \u001b[1;32mfor\u001b[0m \u001b[0mix\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mrange\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mX\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mshape\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;36m0\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[1;32m----> 5\u001b[1;33m         \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;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\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;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      7\u001b[0m             \u001b[0membedding_out\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_index\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[1;31mValueError\u001b[0m: setting an array element with a sequence"
     ]
    }
   ],
   "source": [
    "embeddings_matrix_train = embedding_output(X_train)\n",
    "embeddings_matrix_test = embedding_output(X_test)"
   ]
  },
  {
   "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
}