Advanced Level Task 3 - Handwritten equation solver using CNN Part-1.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# LetsGrowMoreVIP - Data Science Internship\n",
    "Advanced Level Task 3 - Handwritten equation solver using CNN \n",
    "\n",
    "Completed by - Siddharth Maheshwar Wagh"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "from os.path import isfile, join\n",
    "from os import listdir\n",
    "import os\n",
    "import numpy as np\n",
    "import cv2\n",
    "from PIL import Image\n",
    "from matplotlib import pyplot as plt\n",
    "%matplotlib inline\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "def load_images_from_folder(folder):\n",
    "    train_data = []\n",
    "    for filename in os.listdir(folder):\n",
    "        img = cv2.imread(os.path.join(folder, filename), cv2.IMREAD_GRAYSCALE)\n",
    "        img = ~img\n",
    "        if img is not None:\n",
    "            ret, thresh = cv2.threshold(img, 127, 255, cv2.THRESH_BINARY)\n",
    "\n",
    "            ctrs, ret = cv2.findContours(\n",
    "                thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)\n",
    "            cnt = sorted(ctrs, key=lambda ctr: cv2.boundingRect(ctr)[0])\n",
    "            w = int(28)\n",
    "            h = int(28)\n",
    "            maxi = 0\n",
    "            for c in cnt:\n",
    "                x, y, w, h = cv2.boundingRect(c)\n",
    "                maxi = max(w*h, maxi)\n",
    "                if maxi == w*h:\n",
    "                    x_max = x\n",
    "                    y_max = y\n",
    "                    w_max = w\n",
    "                    h_max = h\n",
    "            im_crop = thresh[y_max:y_max+h_max+10, x_max:x_max+w_max+10]\n",
    "            im_resize = cv2.resize(im_crop, (28, 28))\n",
    "            im_resize = np.reshape(im_resize, (784, 1))\n",
    "            train_data.append(im_resize)\n",
    "    return train_data\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "data=[]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Assign '-' = 10\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "33997\n"
     ]
    }
   ],
   "source": [
    "data=load_images_from_folder('C://Users//Asus//OneDrive//Desktop//LGMVIP//Advanced Level Task 3//extracted_images//-')\n",
    "len(data)\n",
    "for i in range(0,len(data)):\n",
    "    data[i]=np.append(data[i],['10'])\n",
    "    \n",
    "print(len(data))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Assign + = 11"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "84221\n"
     ]
    }
   ],
   "source": [
    "data11=load_images_from_folder('C://Users//Asus//OneDrive//Desktop//LGMVIP//Advanced Level Task 3//extracted_images//+')\n",
    "\n",
    "for i in range(0,len(data11)):\n",
    "    data11[i]=np.append(data11[i],['11'])\n",
    "data=np.concatenate((data,data11))\n",
    "print(len(data))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "91135\n"
     ]
    }
   ],
   "source": [
    "data0 = load_images_from_folder('C://Users//Asus//OneDrive//Desktop//LGMVIP//Advanced Level Task 3//extracted_images//0')\n",
    "\n",
    "for i in range(0, len(data0)):\n",
    "    data0[i] = np.append(data0[i], ['0'])\n",
    "data = np.concatenate((data, data0))\n",
    "print(len(data))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "117655\n"
     ]
    }
   ],
   "source": [
    "data1 = load_images_from_folder(\n",
    "    'C://Users//Asus//OneDrive//Desktop//LGMVIP//Advanced Level Task 3//extracted_images//1')\n",
    "\n",
    "for i in range(0, len(data1)):\n",
    "    data1[i] = np.append(data1[i], ['1'])\n",
    "data = np.concatenate((data, data1))\n",
    "print(len(data))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "143796\n"
     ]
    }
   ],
   "source": [
    "data2 = load_images_from_folder('C://Users//Asus//OneDrive//Desktop//LGMVIP//Advanced Level Task 3//extracted_images//2')\n",
    "\n",
    "for i in range(0, len(data2)):\n",
    "    data2[i] = np.append(data2[i], ['2'])\n",
    "data = np.concatenate((data, data2))\n",
    "print(len(data))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "154705\n"
     ]
    }
   ],
   "source": [
    "data3 = load_images_from_folder(\n",
    "    'C://Users//Asus//OneDrive//Desktop//LGMVIP//Advanced Level Task 3//extracted_images//3')\n",
    "\n",
    "for i in range(0, len(data3)):\n",
    "    data3[i] = np.append(data3[i], ['3'])\n",
    "data = np.concatenate((data, data3))\n",
    "print(len(data))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "162101\n"
     ]
    }
   ],
   "source": [
    "data4 = load_images_from_folder(\n",
    "    'C://Users//Asus//OneDrive//Desktop//LGMVIP//Advanced Level Task 3//extracted_images//4')\n",
    "\n",
    "for i in range(0, len(data4)):\n",
    "    data4[i] = np.append(data4[i], ['4'])\n",
    "data = np.concatenate((data, data4))\n",
    "print(len(data))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "165646\n"
     ]
    }
   ],
   "source": [
    "data5 = load_images_from_folder(\n",
    "    'C://Users//Asus//OneDrive//Desktop//LGMVIP//Advanced Level Task 3//extracted_images//5')\n",
    "\n",
    "for i in range(0, len(data5)):\n",
    "    data5[i] = np.append(data5[i], ['5'])\n",
    "data = np.concatenate((data, data5))\n",
    "print(len(data))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "168764\n"
     ]
    }
   ],
   "source": [
    "data6 = load_images_from_folder(\n",
    "    'C://Users//Asus//OneDrive//Desktop//LGMVIP//Advanced Level Task 3//extracted_images//6')\n",
    "\n",
    "for i in range(0, len(data6)):\n",
    "    data6[i] = np.append(data6[i], ['6'])\n",
    "data = np.concatenate((data, data6))\n",
    "print(len(data))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "171673\n"
     ]
    }
   ],
   "source": [
    "data7 = load_images_from_folder(\n",
    "    'C://Users//Asus//OneDrive//Desktop//LGMVIP//Advanced Level Task 3//extracted_images//7')\n",
    "\n",
    "for i in range(0, len(data7)):\n",
    "    data7[i] = np.append(data7[i], ['7'])\n",
    "data = np.concatenate((data, data7))\n",
    "print(len(data))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "177650\n"
     ]
    }
   ],
   "source": [
    "data8 = load_images_from_folder(\n",
    "    'C://Users//Asus//OneDrive//Desktop//LGMVIP//Advanced Level Task 3//extracted_images//8')\n",
    "\n",
    "for i in range(0, len(data8)):\n",
    "    data8[i] = np.append(data8[i], ['8'])\n",
    "data = np.concatenate((data, data8))\n",
    "print(len(data))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "181387\n"
     ]
    }
   ],
   "source": [
    "data9 = load_images_from_folder(\n",
    "    'C://Users//Asus//OneDrive//Desktop//LGMVIP//Advanced Level Task 3//extracted_images//9')\n",
    "\n",
    "for i in range(0, len(data9)):\n",
    "    data9[i] = np.append(data9[i], ['9'])\n",
    "data = np.concatenate((data, data9))\n",
    "print(len(data))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "184638\n"
     ]
    }
   ],
   "source": [
    "data12 = load_images_from_folder(\n",
    "    'C://Users//Asus//OneDrive//Desktop//LGMVIP//Advanced Level Task 3//extracted_images//times')\n",
    "\n",
    "for i in range(0, len(data12)):\n",
    "    data12[i] = np.append(data12[i], ['12'])\n",
    "data = np.concatenate((data, data12))\n",
    "print(len(data))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "df=pd.DataFrame(data,index=None)\n",
    "df.to_csv('train_final.csv',index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3.10.0 64-bit",
   "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": "3.10.0"
  },
  "orig_nbformat": 4,
  "vscode": {
   "interpreter": {
    "hash": "107d7b120a5b68773a87d4067e673630b35702e55ebab3138143d08b1c4d7cbc"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}