current pos and dir detection

Untitled.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from PIL import Image"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "img = Image.open('map1.bmp', 'r')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "IOPub data rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_data_rate_limit`.\n"
     ]
    }
   ],
   "source": [
    "img"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "a=list(img.getdata())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "104650"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(a)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import cv2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 103,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "img_rgb = cv2.imread('source/7.jpg')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 104,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "for x in range(0,420):\n",
    "    for y in range(0,1080):\n",
    "            img_rgb[y,x] = (0,0,0)\n",
    "            img_rgb[y,1919-x] = (0,0,0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 112,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'numpy.ndarray'>\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 112,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "res = cv2.bilateralFilter(img_rgb,9,80,80)\n",
    "\n",
    "res = cv2.GaussianBlur(res,(5,5),0)\n",
    "\n",
    "res = cv2.bilateralFilter(res,9,80,80)\n",
    "\n",
    "res = cv2.GaussianBlur(res,(5,5),0)\n",
    "\n",
    "cv2.imwrite('res34.png',res)\n",
    "\n",
    "#%run ./mul.py\n",
    "\n",
    "#'''\n",
    "gray = cv2.cvtColor(res, cv2.COLOR_BGR2GRAY)\n",
    "\n",
    "\n",
    "result = cv2.Canny(gray, 200, 20)\n",
    "#result = cv2.Laplacian(res,cv2.CV_64F)\n",
    "\n",
    "img_none = cv2.imread('empty.png')\n",
    "\n",
    "print(type(result))\n",
    "\n",
    "for x in range(0,1920):\n",
    "    for y in range(0,1080):\n",
    "        #y,x\n",
    "        if all(result[y,x] == (255,255,255)) and all(img_none[y,x] == (255,255,255)):\n",
    "            result[y,x] -=  result[y,x]\n",
    "        \n",
    "\n",
    "cv2.imwrite('res33.png',result)\n",
    "\n",
    "#result = cv2.cvtColor(result, cv2.COLOR_BGR2GRAY)\n",
    "\n",
    "#'''\n",
    "#result = cv2.imread('res33.png')\n",
    "#circles = cv2.HoughCircles(result, cv2.HOUGH_GRADIENT, 1, 40)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 113,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1100.5 833.5 275.348\n",
      "1117.5 853.5 273.065\n",
      "1084.5 864.5 308.436\n",
      "1099.5 859.5 292.151\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 113,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "result1 = cv2.imread('res33.png')\n",
    "result = cv2.cvtColor(result1, cv2.COLOR_BGR2GRAY)\n",
    "param2_t = 120\n",
    "flag = False\n",
    "circles = None\n",
    "while not flag :\n",
    "    param2_t -= 5\n",
    "    circles = cv2.HoughCircles(result, cv2.HOUGH_GRADIENT, dp=1, minDist=10, param1=80, param2=param2_t)\n",
    "    \n",
    "    try:\n",
    "        for (x,y,r) in circles[0]:\n",
    "            if r > 330 :\n",
    "                pass\n",
    "            elif r < 250 :\n",
    "                pass\n",
    "            else :\n",
    "                flag = True\n",
    "    except TypeError :\n",
    "        pass\n",
    "#circles\n",
    "output = result1.copy()\n",
    "for (x,y,r) in circles[0]:\n",
    "    \n",
    "    if r > 330 :\n",
    "        pass\n",
    "    elif r < 250 :\n",
    "        pass\n",
    "    \n",
    "    #f 0 :\n",
    "    #   pass\n",
    "    else :\n",
    "        cv2.circle(output, (x,y), r, (0, 255, 0), 2)\n",
    "        print (x,y,r)\n",
    "cv2.imwrite('res666.png',output)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 114,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1178.5 853.5 212.59\n",
      "1100.5 833.5 275.348\n",
      "1117.5 853.5 273.065\n",
      "1084.5 864.5 308.436\n",
      "1099.5 859.5 292.151\n",
      "1026.5 808.5 234.479\n",
      "1105.5 881.5 335.634\n",
      "1101.78571429 850.642857143\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 114,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "output = img_rgb.copy()\n",
    "for (x,y,r) in circles[0]:\n",
    "    '''\n",
    "    if r > 330 :\n",
    "        pass\n",
    "    elif r < 250 :\n",
    "        pass\n",
    "    '''\n",
    "    if 0 :\n",
    "        pass\n",
    "    else :\n",
    "        cv2.circle(output, (x,y), r, (0, 255, 0), 2)\n",
    "        print (x,y,r)\n",
    "xsum = 0.0\n",
    "ysum = 0.0\n",
    "for (x,y,r) in circles[0]:\n",
    "    xsum+=x\n",
    "    ysum+=y\n",
    "xsum/=len(circles[0])\n",
    "ysum/=len(circles[0])\n",
    "print(xsum,ysum)\n",
    "cv2.circle(output, (int(xsum),int(ysum)), 306, (0, 0, 255), 4)\n",
    "cv2.imwrite('res44.png',output)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 175,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "img_3333 = cv2.imread('res33.png')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 191,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "res3333 = cv2.GaussianBlur(img_3333,(15,15),0)\n",
    "\n",
    "res3333 = gray = cv2.cvtColor(res3333, cv2.COLOR_BGR2GRAY)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 194,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "circles = cv2.HoughCircles(res3333, cv2.HOUGH_GRADIENT, 1, 40)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 195,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "circles"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 185,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 185,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cv2.imwrite('res3334.png',res3333)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 125,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 125,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\n",
    "cv2.imwrite('res33.png',result)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "temp = cv2.imread('temp.bmp')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "res = cv2.matchTemplate(img_rgb,temp,cv2.TM_CCOEFF_NORMED)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[-0.01178034, -0.01962119, -0.02975524, ..., -0.038022  ,\n",
       "        -0.03149711, -0.02691574],\n",
       "       [-0.01594876, -0.02231932, -0.03238218, ..., -0.0259725 ,\n",
       "        -0.01762902, -0.01573199],\n",
       "       [-0.04249095, -0.04583302, -0.05361817, ..., -0.01204339,\n",
       "         0.00043032,  0.00436186],\n",
       "       ..., \n",
       "       [ 0.11109395,  0.12578124,  0.14391096, ..., -0.02656269,\n",
       "         0.00156921,  0.07241241],\n",
       "       [ 0.15072724,  0.16819492,  0.18066916, ...,  0.02713473,\n",
       "         0.07004382,  0.12981163],\n",
       "       [ 0.1916292 ,  0.20746163,  0.21573578, ...,  0.11084837,\n",
       "         0.15856628,  0.17211723]], dtype=float32)"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "res"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "threshold = 0.7"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "loc = np.where( res >= threshold)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(array([17, 17, 18, 18]), array([70, 71, 70, 71]))"
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "loc"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from matplotlib import pyplot as plt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(3, 24, 39)"
      ]
     },
     "execution_count": 44,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\n",
    "temp.shape[::-1]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "for pt in zip(*loc[::-1]):\n",
    "    cv2.rectangle(img_rgb, pt, (pt[0] + 24, pt[1] + 39), (0,0,255), 2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 46,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cv2.imwrite('res1.png',img_rgb)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import cv2\n",
    "timg = cv2.imread('res3333.bmp')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "c1 = 0\n",
    "c2 = 0"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "for (y,x) in [(x,y) for x in range(32) for y in range(31)]:\n",
    "    if all(timg[x,y] == (255,255,255)):\n",
    "        c1 +=1\n",
    "    c2 += 1\n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "404"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "c1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1984"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "c2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.20362903225806453"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "c1/c2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [],
   "source": [
    "hist=cv2.equalizeHist(cv2.cvtColor(timg, cv2.COLOR_BGR2GRAY))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 155,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYAAAADfCAYAAAD/aAQpAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nGT5jt8sAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x20133ca84e0>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.imshow(hist)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 153,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "hist = cv2.imread('res33.png')\n",
    "timg = cv2.cvtColor(hist, cv2.COLOR_BGR2GRAY)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 156,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 156,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cv2.imwrite('res1234.png',hist)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "hist=cv2.GaussianBlur(timg,(15,15),0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 116,
   "metadata": {},
   "outputs": [],
   "source": [
    "ret, contours, hierarchy = cv2.findContours(timg.copy(), cv2.RETR_TREE, cv2.CHAIN_APPROX_NONE )\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[0, 0, 0, ..., 0, 0, 0],\n",
       "       [0, 0, 0, ..., 0, 0, 0],\n",
       "       [0, 0, 0, ..., 0, 0, 0],\n",
       "       ..., \n",
       "       [0, 0, 0, ..., 0, 0, 0],\n",
       "       [0, 0, 0, ..., 0, 0, 0],\n",
       "       [0, 0, 0, ..., 0, 0, 0]], dtype=uint8)"
      ]
     },
     "execution_count": 46,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ret"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 126,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "contours= 1462 hierarchy= 1\n"
     ]
    }
   ],
   "source": [
    "print(\"contours=\",len(contours),  \"hierarchy=\",len(hierarchy) )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 154,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "6.670932292938232\n",
      "6.670932292938232\n"
     ]
    }
   ],
   "source": [
    "for _ in contours:\n",
    "    (x,y),radius = cv2.minEnclosingCircle(_)\n",
    "    if  radius > 12 and radius < 16:\n",
    "        #cv2.drawContours(hist, _, -1,(  0,255,  0),1)\n",
    "        #(x,y),radius = cv2.minEnclosingCircle(_)\n",
    "        #print(x,y)\n",
    "        flag = False\n",
    "        for k in contours:\n",
    "            if k is not _ :\n",
    "                (x1,y1),radius1 = cv2.minEnclosingCircle(k)\n",
    "                if  radius1 > 4 and radius1 < 8 and (x1-x)**2 + (y1-y)**2 < radius**2:\n",
    "                    flag = True\n",
    "                    print(radius1)\n",
    "                    \n",
    "                    rows,cols = hist.shape[:2]\n",
    "                    [vx,vy,x,y] = cv2.fitLine(k, cv2.DIST_L2,0,0.01,0.01)\n",
    "                    lefty = int((-x*vy/vx) + y)\n",
    "                    righty = int(((cols-x)*vy/vx)+y)\n",
    "                    hist = cv2.line(hist,(cols-1,righty),(0,lefty),(0,255,0),2)\n",
    "        if flag:\n",
    "            cv2.drawContours(hist, _, -1,(  0,255,  0),1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "14.922653198242188"
      ]
     },
     "execution_count": 75,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "radius"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 77,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(850.1032104492188, 180.1234893798828)"
      ]
     },
     "execution_count": 77,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "(x,y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 98,
   "metadata": {},
   "outputs": [],
   "source": [
    "center = (int(x),int(y))\n",
    "radius = int(radius)\n",
    "hist = cv2.circle(hist,center,radius,(0,255,0),3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 89,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.0\n",
      "0.0\n",
      "0.5\n",
      "0.0\n",
      "1.5\n",
      "1.5\n",
      "0.0\n",
      "0.5\n",
      "5.5\n",
      "11.5\n",
      "14.0\n"
     ]
    }
   ],
   "source": [
    "for _ in contours:\n",
    "    area = cv2.contourArea(_)\n",
    "    print(area)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 90,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[[0, 0, 0],\n",
       "        [0, 0, 0],\n",
       "        [0, 0, 0],\n",
       "        ..., \n",
       "        [0, 0, 0],\n",
       "        [0, 0, 0],\n",
       "        [0, 0, 0]],\n",
       "\n",
       "       [[0, 0, 0],\n",
       "        [0, 0, 0],\n",
       "        [0, 0, 0],\n",
       "        ..., \n",
       "        [0, 0, 0],\n",
       "        [0, 0, 0],\n",
       "        [0, 0, 0]],\n",
       "\n",
       "       [[0, 0, 0],\n",
       "        [0, 0, 0],\n",
       "        [0, 0, 0],\n",
       "        ..., \n",
       "        [0, 0, 0],\n",
       "        [0, 0, 0],\n",
       "        [0, 0, 0]],\n",
       "\n",
       "       ..., \n",
       "       [[0, 0, 0],\n",
       "        [0, 0, 0],\n",
       "        [0, 0, 0],\n",
       "        ..., \n",
       "        [0, 0, 0],\n",
       "        [0, 0, 0],\n",
       "        [0, 0, 0]],\n",
       "\n",
       "       [[0, 0, 0],\n",
       "        [0, 0, 0],\n",
       "        [0, 0, 0],\n",
       "        ..., \n",
       "        [0, 0, 0],\n",
       "        [0, 0, 0],\n",
       "        [0, 0, 0]],\n",
       "\n",
       "       [[0, 0, 0],\n",
       "        [0, 0, 0],\n",
       "        [0, 0, 0],\n",
       "        ..., \n",
       "        [0, 0, 0],\n",
       "        [0, 0, 0],\n",
       "        [0, 0, 0]]], dtype=uint8)"
      ]
     },
     "execution_count": 90,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cv2.drawContours(hist, contours[8], -1,(  0,255,  0),1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 95,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "rows,cols = hist.shape[:2]\n",
    "[vx,vy,x,y] = cv2.fitLine(contours[8], cv2.DIST_L2,0,0.01,0.01)\n",
    "lefty = int((-x*vy/vx) + y)\n",
    "righty = int(((cols-x)*vy/vx)+y)\n",
    "hist = cv2.line(hist,(cols-1,righty),(0,lefty),(0,255,0),2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "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": "3.5.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}