{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "_cell_guid": "6f8609ef-fd70-1b48-2aa0-406f70691117"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "additional\n",
      "sample_submission.csv\n",
      "test\n",
      "train\n",
      "\n"
     ]
    }
   ],
   "source": [
    "# This Python 3 environment comes with many helpful analytics libraries installed\n",
    "# It is defined by the kaggle/python docker image: https://github.com/kaggle/docker-python\n",
    "# For example, here's several helpful packages to load in \n",
    "\n",
    "import numpy as np # linear algebra\n",
    "import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n",
    "\n",
    "# Input data files are available in the \"../input/\" directory.\n",
    "# For example, running this (by clicking run or pressing Shift+Enter) will list the files in the input directory\n",
    "\n",
    "from subprocess import check_output\n",
    "print(check_output([\"ls\", \"../input\"]).decode(\"utf8\"))\n",
    "\n",
    "# Any results you write to the current directory are saved as output."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "_cell_guid": "6676d8ca-80c5-5bc7-da9c-200d852390b4"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "250 781 450\n",
      "Type 1 ['0' '10' '1013' '1014' '1019' '102' '1023' '1024' '1026' '1027']\n",
      "Type 2 ['1' '100' '1001' '1002' '1005' '1006' '101' '1010' '1011' '1012']\n",
      "Type 3 ['1000' '1003' '1004' '1007' '1008' '1009' '1015' '1020' '1028' '1029']\n"
     ]
    }
   ],
   "source": [
    "import os\n",
    "from glob import glob\n",
    "TRAIN_DATA = \"../input/train\"\n",
    "type_1_files = glob(os.path.join(TRAIN_DATA, \"Type_1\", \"*.jpg\"))\n",
    "type_1_ids = np.array([s[len(os.path.join(TRAIN_DATA, \"Type_1\"))+1:-4] for s in type_1_files])\n",
    "type_2_files = glob(os.path.join(TRAIN_DATA, \"Type_2\", \"*.jpg\"))\n",
    "type_2_ids = np.array([s[len(os.path.join(TRAIN_DATA, \"Type_2\"))+1:-4] for s in type_2_files])\n",
    "type_3_files = glob(os.path.join(TRAIN_DATA, \"Type_3\", \"*.jpg\"))\n",
    "type_3_ids = np.array([s[len(os.path.join(TRAIN_DATA, \"Type_3\"))+1:-4] for s in type_3_files])\n",
    "\n",
    "print(len(type_1_files), len(type_2_files), len(type_3_files))\n",
    "print(\"Type 1\", type_1_ids[:10])\n",
    "print(\"Type 2\", type_2_ids[:10])\n",
    "print(\"Type 3\", type_3_ids[:10])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "_cell_guid": "10fb799e-7f05-9757-5a3c-d67d2eb56b1d"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1191 3567 3567\n",
      "Type 1 ['2475' '4045' '10' '1000' '1001' '1003' '1004' '1005' '1009' '1011']\n",
      "Type 2 ['0' '1' '1002' '1006' '1007' '1008' '101' '1013' '1016' '1017']\n",
      "Type 3 ['100' '1010' '1012' '1014' '1019' '1021' '1027' '1041' '1048' '1051']\n"
     ]
    }
   ],
   "source": [
    "ADDITIONAL_DATA = \"../input/additional\"\n",
    "additional_type_1_files = glob(os.path.join(ADDITIONAL_DATA, \"Type_1\", \"*.jpg\"))\n",
    "additional_type_1_ids = np.array([s[len(os.path.join(ADDITIONAL_DATA, \"Type_1\"))+1:-4] for s in additional_type_1_files])\n",
    "additional_type_2_files = glob(os.path.join(ADDITIONAL_DATA, \"Type_2\", \"*.jpg\"))\n",
    "additional_type_2_ids = np.array([s[len(os.path.join(ADDITIONAL_DATA, \"Type_2\"))+1:-4] for s in additional_type_2_files])\n",
    "additional_type_3_files = glob(os.path.join(ADDITIONAL_DATA, \"Type_3\", \"*.jpg\"))\n",
    "additional_type_3_ids = np.array([s[len(os.path.join(ADDITIONAL_DATA, \"Type_3\"))+1:-4] for s in additional_type_3_files])\n",
    "\n",
    "print(len(additional_type_1_files), len(additional_type_2_files), len(additional_type_2_files))\n",
    "print(\"Type 1\", additional_type_1_ids[:10])\n",
    "print(\"Type 2\", additional_type_2_ids[:10])\n",
    "print(\"Type 3\", additional_type_3_ids[:10])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "_cell_guid": "a73065db-239e-8a52-08a7-ba41fbd2484c"
   },
   "outputs": [],
   "source": [
    "def get_filename(image_id, image_type):\n",
    "    \"\"\"\n",
    "    Method to get image file path from its id and type   \n",
    "    \"\"\"\n",
    "    if image_type == \"Type_1\" or \\\n",
    "        image_type == \"Type_2\" or \\\n",
    "        image_type == \"Type_3\":\n",
    "        data_path = os.path.join(TRAIN_DATA, image_type)\n",
    "    elif image_type == \"Test\":\n",
    "        data_path = TEST_DATA\n",
    "    elif image_type == \"AType_1\" or \\\n",
    "          image_type == \"AType_2\" or \\\n",
    "          image_type == \"AType_3\":\n",
    "        data_path = os.path.join(ADDITIONAL_DATA, image_type[1:])\n",
    "    else:\n",
    "        raise Exception(\"Image type '%s' is not recognized\" % image_type)\n",
    "\n",
    "    ext = 'jpg'\n",
    "    return os.path.join(data_path, \"{}.{}\".format(image_id, ext))\n",
    "\n",
    "\n",
    "def get_image_data(image_id, image_type):\n",
    "    \"\"\"\n",
    "    Method to get image data as np.array specifying image id and type\n",
    "    \"\"\"\n",
    "    fname = get_filename(image_id, image_type)\n",
    "    img = cv2.imread(fname)\n",
    "    assert img is not None, \"Failed to read image : %s, %s\" % (image_id, image_type)\n",
    "    img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)\n",
    "    return img"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "_cell_guid": "b2b68e17-6610-81ad-b34a-482139751a0a"
   },
   "outputs": [],
   "source": [
    "import matplotlib.pylab as plt\n",
    "\n",
    "def plt_st(l1,l2):\n",
    "    plt.figure(figsize=(l1,l2))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "_cell_guid": "2b0a65c4-eaf1-325d-90d0-ea3d1c7bcd58"
   },
   "outputs": [
    {
     "ename": "NameError",
     "evalue": "name 'cv2' is not defined",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-6-1b9f0067f183>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m     17\u001b[0m                 \u001b[0;32mbreak\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     18\u001b[0m             \u001b[0mimage_id\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtrain_ids\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mcounter\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m;\u001b[0m \u001b[0mcounter\u001b[0m\u001b[0;34m+=\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 19\u001b[0;31m             \u001b[0mimg\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mget_image_data\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mimage_id\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'Type_%i'\u001b[0m \u001b[0;34m%\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0mk\u001b[0m\u001b[0;34m+\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     20\u001b[0m             \u001b[0mimg\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mcv2\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mresize\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mimg\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdsize\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mtile_size\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     21\u001b[0m             \u001b[0mimg\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mcv2\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mputText\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mimg\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mimage_id\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0;36m5\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0mimg\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mshape\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m-\u001b[0m \u001b[0;36m5\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcv2\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mFONT_HERSHEY_SIMPLEX\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m2.0\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0;36m255\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m255\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m255\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mthickness\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m3\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m<ipython-input-4-3d9c5d7344e9>\u001b[0m in \u001b[0;36mget_image_data\u001b[0;34m(image_id, image_type)\u001b[0m\n\u001b[1;32m     21\u001b[0m     \"\"\"\n\u001b[1;32m     22\u001b[0m     \u001b[0mfname\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mget_filename\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mimage_id\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mimage_type\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 23\u001b[0;31m     \u001b[0mimg\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mcv2\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mimread\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfname\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     24\u001b[0m     \u001b[0;32massert\u001b[0m \u001b[0mimg\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m\"Failed to read image : %s, %s\"\u001b[0m \u001b[0;34m%\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0mimage_id\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mimage_type\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     25\u001b[0m     \u001b[0mimg\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mcv2\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcvtColor\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mimg\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcv2\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mCOLOR_BGR2RGB\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mNameError\u001b[0m: name 'cv2' is not defined"
     ]
    }
   ],
   "source": [
    "tile_size = (256, 256)\n",
    "n = 15\n",
    "\n",
    "complete_images = []\n",
    "for k, type_ids in enumerate([type_1_ids, type_2_ids, type_3_ids]):\n",
    "    m = int(np.ceil(len(type_ids) * 1.0 / n))\n",
    "    complete_image = np.zeros((m*(tile_size[0]+2), n*(tile_size[1]+2), 3), dtype=np.uint8)\n",
    "    train_ids = sorted(type_ids)\n",
    "    counter = 0\n",
    "    for i in range(m):\n",
    "        ys = i*(tile_size[1] + 2)\n",
    "        ye = ys + tile_size[1]\n",
    "        for j in range(n):\n",
    "            xs = j*(tile_size[0] + 2)\n",
    "            xe = xs + tile_size[0]\n",
    "            if counter == len(train_ids):\n",
    "                break\n",
    "            image_id = train_ids[counter]; counter+=1\n",
    "            img = get_image_data(image_id, 'Type_%i' % (k+1))\n",
    "            img = cv2.resize(img, dsize=tile_size)\n",
    "            img = cv2.putText(img, image_id, (5,img.shape[0] - 5), cv2.FONT_HERSHEY_SIMPLEX, 2.0, (255, 255, 255), thickness=3)\n",
    "            complete_image[ys:ye, xs:xe, :] = img[:,:,:]\n",
    "        if counter == len(train_ids):\n",
    "            break\n",
    "    complete_images.append(complete_image)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "_cell_guid": "6f1cb074-f2cd-b32a-0eee-e876d7cf721a"
   },
   "outputs": [
    {
     "ename": "NameError",
     "evalue": "name 'cv2' is not defined",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-7-b569a084dbc8>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m     17\u001b[0m                 \u001b[0;32mbreak\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     18\u001b[0m             \u001b[0mimage_id\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtrain_ids\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mcounter\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m;\u001b[0m \u001b[0mcounter\u001b[0m\u001b[0;34m+=\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 19\u001b[0;31m             \u001b[0mimg\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mget_image_data\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mimage_id\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'AType_%i'\u001b[0m \u001b[0;34m%\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0mk\u001b[0m\u001b[0;34m+\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     20\u001b[0m             \u001b[0mimg\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mcv2\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mresize\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mimg\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdsize\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mtile_size\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     21\u001b[0m             \u001b[0mimg\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mcv2\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mputText\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mimg\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mimage_id\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0;36m5\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0mimg\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mshape\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m-\u001b[0m \u001b[0;36m5\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcv2\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mFONT_HERSHEY_SIMPLEX\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m2.0\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0;36m255\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m255\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m255\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mthickness\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m3\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m<ipython-input-4-3d9c5d7344e9>\u001b[0m in \u001b[0;36mget_image_data\u001b[0;34m(image_id, image_type)\u001b[0m\n\u001b[1;32m     21\u001b[0m     \"\"\"\n\u001b[1;32m     22\u001b[0m     \u001b[0mfname\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mget_filename\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mimage_id\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mimage_type\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 23\u001b[0;31m     \u001b[0mimg\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mcv2\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mimread\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfname\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     24\u001b[0m     \u001b[0;32massert\u001b[0m \u001b[0mimg\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m\"Failed to read image : %s, %s\"\u001b[0m \u001b[0;34m%\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0mimage_id\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mimage_type\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     25\u001b[0m     \u001b[0mimg\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mcv2\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcvtColor\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mimg\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcv2\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mCOLOR_BGR2RGB\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mNameError\u001b[0m: name 'cv2' is not defined"
     ]
    }
   ],
   "source": [
    "tile_size = (256, 256)\n",
    "n = 15\n",
    "ll = 500\n",
    "#complete_images = []\n",
    "for k, type_ids in enumerate([additional_type_1_ids[:ll], additional_type_2_ids[:ll], additional_type_3_ids[:ll]]):\n",
    "    m = int(np.ceil(len(type_ids) * 1.0 / n))\n",
    "    complete_image = np.zeros((m*(tile_size[0]+2), n*(tile_size[1]+2), 3), dtype=np.uint8)\n",
    "    train_ids = sorted(type_ids)\n",
    "    counter = 0\n",
    "    for i in range(m):\n",
    "        ys = i*(tile_size[1] + 2)\n",
    "        ye = ys + tile_size[1]\n",
    "        for j in range(n):\n",
    "            xs = j*(tile_size[0] + 2)\n",
    "            xe = xs + tile_size[0]\n",
    "            if counter == len(train_ids):\n",
    "                break\n",
    "            image_id = train_ids[counter]; counter+=1\n",
    "            img = get_image_data(image_id, 'AType_%i' % (k+1))\n",
    "            img = cv2.resize(img, dsize=tile_size)\n",
    "            img = cv2.putText(img, image_id, (5,img.shape[0] - 5), cv2.FONT_HERSHEY_SIMPLEX, 2.0, (255, 255, 255), thickness=3)\n",
    "            complete_image[ys:ye, xs:xe, :] = img[:,:,:]\n",
    "        if counter == len(train_ids):\n",
    "            break\n",
    "    complete_images.append(complete_image)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "_cell_guid": "42d3f87b-ba6d-8ef5-7ae4-21f50ec7f1ec"
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/opt/conda/lib/python3.6/site-packages/sklearn/cross_validation.py:43: DeprecationWarning: This module was deprecated in version 0.18 in favor of the model_selection module into which all the refactored classes and functions are moved. Also note that the interface of the new CV iterators are different from that of this module. This module will be removed in 0.20.\n",
      "  \"This module will be removed in 0.20.\", DeprecationWarning)\n",
      "Using TensorFlow backend.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Keras version: 2.0.3\n",
      "Read train images\n",
      "Load folder Type_1 (Index: 0)\n",
      "Load folder Type_2 (Index: 1)\n",
      "Load folder Type_3 (Index: 2)\n",
      "Read train data time: 183.18 seconds\n",
      "Convert to numpy...\n",
      "Reshape...\n"
     ]
    },
    {
     "ename": "ValueError",
     "evalue": "axes don't match array",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mValueError\u001b[0m                                Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-8-e53ef5a85e42>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m    216\u001b[0m     \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'Keras version: {}'\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mformat\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkeras_version\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    217\u001b[0m     \u001b[0mnum_folds\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;36m3\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 218\u001b[0;31m     \u001b[0minfo_string\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmodels\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mrun_cross_validation_create_models\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mnum_folds\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    219\u001b[0m     \u001b[0mrun_cross_validation_process_test\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0minfo_string\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmodels\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m<ipython-input-8-e53ef5a85e42>\u001b[0m in \u001b[0;36mrun_cross_validation_create_models\u001b[0;34m(nfolds)\u001b[0m\n\u001b[1;32m    159\u001b[0m     \u001b[0mnb_epoch\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;36m30\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    160\u001b[0m     \u001b[0mrandom_state\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;36m51\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 161\u001b[0;31m     \u001b[0mtrain_data\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtrain_target\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtrain_id\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mread_and_normalize_train_data\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    162\u001b[0m     \u001b[0myfull_train\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mdict\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    163\u001b[0m     \u001b[0mkf\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mKFold\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtrain_id\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mn_folds\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mnfolds\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mshuffle\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mTrue\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mrandom_state\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mrandom_state\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m<ipython-input-8-e53ef5a85e42>\u001b[0m in \u001b[0;36mread_and_normalize_train_data\u001b[0;34m()\u001b[0m\n\u001b[1;32m     85\u001b[0m     \u001b[0mtrain_target\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0marray\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtrain_target\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdtype\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0muint8\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     86\u001b[0m     \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'Reshape...'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 87\u001b[0;31m     \u001b[0mtrain_data\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtrain_data\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtranspose\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m3\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m1\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m2\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     88\u001b[0m     \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'Convert to float...'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     89\u001b[0m     \u001b[0mtrain_data\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtrain_data\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mastype\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'float32'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mValueError\u001b[0m: axes don't match array"
     ]
    }
   ],
   "source": [
    "import numpy as np\n",
    "np.random.seed(2016)\n",
    "\n",
    "import os\n",
    "#import glob\n",
    "import cv2\n",
    "import datetime\n",
    "import pandas as pd\n",
    "import time\n",
    "import warnings\n",
    "warnings.filterwarnings(\"ignore\")\n",
    "\n",
    "from sklearn.cross_validation import KFold\n",
    "from keras.models import Sequential\n",
    "from keras.layers.core import Dense, Dropout, Flatten\n",
    "from keras.layers.convolutional import Convolution2D, MaxPooling2D, ZeroPadding2D\n",
    "from keras.optimizers import SGD\n",
    "from keras.callbacks import EarlyStopping\n",
    "from keras.utils import np_utils\n",
    "from sklearn.metrics import log_loss\n",
    "from keras import __version__ as keras_version\n",
    "\n",
    "\n",
    "\n",
    "def get_im_cv2(path):\n",
    "    img = cv2.imread(path)\n",
    "    resized = cv2.resize(img, (256, 256), cv2.INTER_LINEAR)\n",
    "    \n",
    "    return resized\n",
    "\n",
    "\n",
    "def load_train():\n",
    "    X_train = complete_images\n",
    "    X_train_id = []\n",
    "    y_train = []\n",
    "    start_time = time.time()\n",
    "    print('Read train images')\n",
    "    folders = ['Type_1', 'Type_2', 'Type_3']\n",
    "    for fld in folders:\n",
    "        index = folders.index(fld)\n",
    "        print('Load folder {} (Index: {})'.format(fld, index))\n",
    "        path = os.path.join('..', 'input', 'train', fld, '*.jpg')\n",
    "        #path = os.path.join('..', 'input', 'additional', fld, '*.jpg')\n",
    "        files = glob(path)\n",
    "        #files2 = glob.glob(path2)\n",
    "        \n",
    "        for fl in files:\n",
    "            flbase = os.path.basename(fl)\n",
    "            img = get_im_cv2(fl)\n",
    "            #X_train.append(img)\n",
    "            X_train_id.append(flbase)\n",
    "            y_train.append(index)\n",
    "            \n",
    "        \n",
    "\n",
    "    print('Read train data time: {} seconds'.format(round(time.time() - start_time, 2)))\n",
    "    return X_train, y_train, X_train_id\n",
    "\n",
    "\n",
    "def load_test():\n",
    "    path = os.path.join('..', 'input', 'test', '*.jpg')\n",
    "    files = sorted(glob(path))\n",
    "    X_test = []\n",
    "    X_test_id = []\n",
    "    for fl in files:\n",
    "        flbase = os.path.basename(fl)\n",
    "        img = get_im_cv2(fl)\n",
    "        X_test.append(img)\n",
    "        X_test_id.append(flbase)\n",
    "    return X_test, X_test_id\n",
    "\n",
    "\n",
    "def create_submission(predictions, test_id, info):\n",
    "    result1 = pd.DataFrame(predictions, columns=['Type_1', 'Type_2', 'Type_3'])\n",
    "    result1.loc[:, 'image_name'] = pd.Series(test_id, index=result1.index)\n",
    "    now = datetime.datetime.now()\n",
    "    sub_file = 'submission_' + info + '_' + str(now.strftime(\"%Y-%m-%d-%H-%M\")) + '.csv'\n",
    "    result1.to_csv(sub_file, index=False)\n",
    "\n",
    "\n",
    "def read_and_normalize_train_data():\n",
    "    train_data, train_target, train_id = load_train()\n",
    "    print('Convert to numpy...')\n",
    "    train_data = np.array(train_data, dtype=np.uint8)\n",
    "    train_target = np.array(train_target, dtype=np.uint8)\n",
    "    print('Reshape...')\n",
    "    train_data = train_data.transpose((0, 3, 1, 2))\n",
    "    print('Convert to float...')\n",
    "    train_data = train_data.astype('float32')\n",
    "    train_data = train_data / 255\n",
    "    train_target = np_utils.to_categorical(train_target, 3)\n",
    "    print('Train shape:', train_data.shape)\n",
    "    print(train_data.shape[0], 'train samples')\n",
    "    return train_data, train_target, train_id\n",
    "\n",
    "\n",
    "def read_and_normalize_test_data():\n",
    "    start_time = time.time()\n",
    "    test_data, test_id = load_test()\n",
    "    test_data = np.array(test_data, dtype=np.uint8)\n",
    "    test_data = test_data.transpose((0, 3, 1, 2))\n",
    "    test_data = test_data.astype('float32')\n",
    "    test_data = test_data / 255\n",
    "    print('Test shape:', test_data.shape)\n",
    "    print(test_data.shape[0], 'test samples')\n",
    "    print('Read and process test data time: {} seconds'.format(round(time.time() - start_time, 2)))\n",
    "    return test_data, test_id\n",
    "\n",
    "\n",
    "def dict_to_list(d):\n",
    "    ret = []\n",
    "    for i in d.items():\n",
    "        ret.append(i[1])\n",
    "    return ret\n",
    "\n",
    "\n",
    "def merge_several_folds_mean(data, nfolds):\n",
    "    a = np.array(data[0])\n",
    "    for i in range(1, nfolds):\n",
    "        a += np.array(data[i])\n",
    "    a /= nfolds\n",
    "    return a.tolist()\n",
    "\n",
    "\n",
    "def create_model():\n",
    "    model = Sequential()\n",
    "    model.add(ZeroPadding2D((1, 1), input_shape=(3, 32, 32), dim_ordering='th'))\n",
    "    model.add(Convolution2D(4, 3, 3, activation='relu', dim_ordering='th'))\n",
    "    model.add(ZeroPadding2D((1, 1), dim_ordering='th'))\n",
    "    model.add(Convolution2D(4, 3, 3, activation='relu', dim_ordering='th'))\n",
    "    model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2), dim_ordering='th'))\n",
    "    model.add(ZeroPadding2D((1, 1), dim_ordering='th'))\n",
    "    model.add(Convolution2D(8, 3, 3, activation='relu', dim_ordering='th'))\n",
    "    model.add(ZeroPadding2D((1, 1), dim_ordering='th'))\n",
    "    model.add(Convolution2D(8, 3, 3, activation='relu', dim_ordering='th'))\n",
    "    model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2), dim_ordering='th'))\n",
    "    model.add(Flatten())\n",
    "    model.add(Dense(32, activation='relu'))\n",
    "    model.add(Dropout(0.5))\n",
    "    model.add(Dense(32, activation='relu'))\n",
    "    model.add(Dropout(0.5))\n",
    "    model.add(Dense(3, activation='softmax'))\n",
    "    sgd = SGD(lr=1e-2, decay=1e-6, momentum=0.9, nesterov=True)\n",
    "    model.compile(optimizer=sgd, loss='categorical_crossentropy',\n",
    "    metrics=['accuracy'])\n",
    "    return model\n",
    "\n",
    "\n",
    "def get_validation_predictions(train_data, predictions_valid):\n",
    "    pv = []\n",
    "    for i in range(len(train_data)):\n",
    "        pv.append(predictions_valid[i])\n",
    "    return pv\n",
    "\n",
    "\n",
    "def run_cross_validation_create_models(nfolds=10):\n",
    "    # input image dimensions\n",
    "    batch_size = 16\n",
    "    nb_epoch = 30\n",
    "    random_state = 51\n",
    "    train_data, train_target, train_id = read_and_normalize_train_data()\n",
    "    yfull_train = dict()\n",
    "    kf = KFold(len(train_id), n_folds=nfolds, shuffle=True, random_state=random_state)\n",
    "    num_fold = 0\n",
    "    sum_score = 0\n",
    "    models = []\n",
    "    for train_index, test_index in kf:\n",
    "        model = create_model()\n",
    "        X_train = train_data[train_index]\n",
    "        Y_train = train_target[train_index]\n",
    "        X_valid = train_data[test_index]\n",
    "        Y_valid = train_target[test_index]\n",
    "        num_fold += 1\n",
    "        print('Start KFold number {} from {}'.format(num_fold, nfolds))\n",
    "        print('Split train: ', len(X_train), len(Y_train))\n",
    "        print('Split valid: ', len(X_valid), len(Y_valid))\n",
    "        callbacks = [\n",
    "            EarlyStopping(monitor='val_loss', patience=3, verbose=0),\n",
    "        ]\n",
    "        model.fit(X_train, Y_train, batch_size=batch_size, nb_epoch=nb_epoch,\n",
    "              shuffle=True, verbose=2, validation_data=(X_valid, Y_valid),\n",
    "              callbacks=callbacks)\n",
    "        predictions_valid = model.predict(X_valid.astype('float32'), batch_size=batch_size, verbose=2)\n",
    "        score = log_loss(Y_valid, predictions_valid)\n",
    "        print('Score log_loss: ', score)\n",
    "        sum_score += score*len(test_index)\n",
    "        # Store valid predictions\n",
    "        for i in range(len(test_index)):\n",
    "            yfull_train[test_index[i]] = predictions_valid[i]\n",
    "        models.append(model)\n",
    "    score = sum_score/len(train_data)\n",
    "    print(\"Log_loss train independent avg: \", score)\n",
    "    info_string = 'loss_' + str(score) + '_folds_' + str(nfolds) + '_ep_' + str(nb_epoch)\n",
    "    return info_string, models\n",
    "\n",
    "\n",
    "def run_cross_validation_process_test(info_string, models):\n",
    "    batch_size = 16\n",
    "    num_fold = 0\n",
    "    yfull_test = []\n",
    "    test_id = []\n",
    "    nfolds = len(models)\n",
    "    for i in range(nfolds):\n",
    "        model = models[i]\n",
    "        num_fold += 1\n",
    "        print('Start KFold number {} from {}'.format(num_fold, nfolds))\n",
    "        test_data, test_id = read_and_normalize_test_data()\n",
    "        test_prediction = model.predict(test_data, batch_size=batch_size, verbose=2)\n",
    "        yfull_test.append(test_prediction)\n",
    "    test_res = merge_several_folds_mean(yfull_test, nfolds)\n",
    "    info_string = 'loss_' + info_string \\\n",
    "                + '_folds_' + str(nfolds)\n",
    "    create_submission(test_res, test_id, info_string)\n",
    "\n",
    "\n",
    "if __name__ == '__main__':\n",
    "    print('Keras version: {}'.format(keras_version))\n",
    "    num_folds = 3\n",
    "    info_string, models = run_cross_validation_create_models(num_folds)\n",
    "    run_cross_validation_process_test(info_string, models)"
   ]
  }
 ],
 "metadata": {
  "_change_revision": 118,
  "_is_fork": false,
  "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": "3.6.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}