{"cells":[
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "import numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\ntrain = pd.read_csv(\"../input/train.csv\")"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "train = train[train.x<=.2]\ntrain = train[train.y<=.2]"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "import matplotlib.pyplot as plt\nplt.figure(figsize=(20,20))\nplt.scatter(train.x,train.y,c=train.place_id,s=train.accuracy,alpha=0.5)\n#for accuracy, x, y in zip(small_train.accuracy,small_train.x,small_train.y):\n #   plt.annotate(\n  #      accuracy,\n   #     xy = (x,y), xytext = (-20,20),\n    #    textcoords = 'offset points', ha = 'right', va = 'bottom',\n     #   bbox = dict(boxstyle = 'round,pad=0.5', fc = 'yellow', alpha = 0.5),\n      #  arrowprops = dict(arrowstyle = '->', connectionstyle = 'arc3,rad=0'))\nplt.show()"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "small_train.place_id.value_counts()"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "small_train_largest=pd.concat([small_train[small_train.place_id==5445221293],\n                               small_train[small_train.place_id==3804306710],\n                               small_train[small_train.place_id==1006316884],\n                               small_train[small_train.place_id==2148728558],\n                               small_train[small_train.place_id==3027578816],\n                               small_train[small_train.place_id==4492862780],\n                               small_train[small_train.place_id==8370753254],\n                               small_train[small_train.place_id==6007444822],\n                               small_train[small_train.place_id==8555966805],\n                               small_train[small_train.place_id==7065354365],\n                               small_train[small_train.place_id==9727638738],\n                              ])"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "import matplotlib.pyplot as plt\nplt.figure(figsize=(20,20))\nplt.scatter(small_train_largest.x,small_train_largest.y,c=small_train_largest.place_id,s=small_train_largest.accuracy,alpha=0.5)\nplt.show()"
 }
],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"}}, "nbformat": 4, "nbformat_minor": 0}