Skip to content

Instantly share code, notes, and snippets.

@rjpower

rjpower/fizzbuzz.ipynb

Created June 28, 2016 18:01
Show Gist options

  • Select an option

    Learn more about clone URLs
  • Save rjpower/b84bb06a7e5909090d41db99feb73be0 to your computer and use it in GitHub Desktop.

Select an option

Learn more about clone URLs
Save rjpower/b84bb06a7e5909090d41db99feb73be0 to your computer and use it in GitHub Desktop.
Download ZIP
fizzbuzz with one-hot encoding
Display the source blob
Display the rendered blob
Raw
fizzbuzz.ipynb
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Using TensorFlow backend.\n"
]
}
],
"source": [
"import json\n",
"import sys\n",
"import os\n",
"\n",
"import pandas as pd\n",
"import numpy as np\n",
"\n",
"import keras\n",
"from keras.layers import Dense\n",
"from keras.models import Sequential\n",
"from keras.utils import np_utils\n",
"from __future__ import print_function"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"collapsed": false
},
"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.]]), array([[0, 1, 0, 0],\n",
" [1, 0, 0, 0],\n",
" [0, 0, 0, 1],\n",
" [0, 0, 0, 1],\n",
" [0, 0, 1, 0],\n",
" [1, 0, 0, 0],\n",
" [0, 1, 0, 0],\n",
" [1, 0, 0, 0],\n",
" [0, 0, 1, 0],\n",
" [1, 0, 0, 0],\n",
" [0, 0, 1, 0],\n",
" [0, 1, 0, 0],\n",
" [0, 1, 0, 0],\n",
" [1, 0, 0, 0],\n",
" [1, 0, 0, 0],\n",
" [0, 1, 0, 0],\n",
" [0, 1, 0, 0],\n",
" [0, 1, 0, 0],\n",
" [1, 0, 0, 0],\n",
" [1, 0, 0, 0],\n",
" [1, 0, 0, 0],\n",
" [1, 0, 0, 0],\n",
" [1, 0, 0, 0],\n",
" [1, 0, 0, 0],\n",
" [1, 0, 0, 0],\n",
" [0, 1, 0, 0],\n",
" [0, 0, 0, 1],\n",
" [1, 0, 0, 0],\n",
" [0, 0, 1, 0],\n",
" [0, 0, 1, 0],\n",
" [0, 0, 1, 0],\n",
" [1, 0, 0, 0]]))"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"N = 1000\n",
"\n",
"def _fizzdata():\n",
" while True:\n",
" batch_x = []\n",
" batch_y = []\n",
"\n",
" idx = np.arange(N)\n",
" np.random.shuffle(idx)\n",
" for i in idx:\n",
" batch_x.append(i)\n",
" if i % 15 == 0: batch_y.append(np.asarray([0, 0, 0, 1]))\n",
" elif i % 5 == 0: batch_y.append(np.asarray([0, 0, 1, 0]))\n",
" elif i % 3 == 0: batch_y.append(np.asarray([0, 1, 0, 0]))\n",
" else: batch_y.append(np.asarray([1, 0, 0, 0]))\n",
"\n",
" if len(batch_x) >= 32:\n",
" yield np_utils.to_categorical(batch_x, N), np.asarray(batch_y)\n",
" batch_x = []\n",
" batch_y = []\n",
"\n",
" yield np_utils.to_categorical(batch_x, N), np.asarray(batch_y)\n",
" \n",
"_fizzdata().next()"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"collapsed": false,
"scrolled": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"____________________________________________________________________________________________________\n",
"Layer (type) Output Shape Param # Connected to \n",
"====================================================================================================\n",
"dense_2 (Dense) (None, 4) 4004 dense_input_2[0][0] \n",
"====================================================================================================\n",
"Total params: 4004\n",
"____________________________________________________________________________________________________\n"
]
}
],
"source": [
"def model():\n",
" m = Sequential()\n",
" m.add(Dense(4, input_shape=(N,), activation='sigmoid'))\n",
" m.compile(loss='binary_crossentropy', optimizer='rmsprop', metrics=['accuracy'])\n",
" return m\n",
"\n",
"training_model = model()\n",
"training_model.summary()"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Epoch 1/500\n",
"0s - loss: 0.3885 - acc: 0.5330\n",
"Epoch 2/500\n",
"0s - loss: 0.3876 - acc: 0.5330\n",
"Epoch 3/500\n",
"0s - loss: 0.3868 - acc: 0.5330\n",
"Epoch 4/500\n",
"0s - loss: 0.3859 - acc: 0.5330\n",
"Epoch 5/500\n",
"0s - loss: 0.3851 - acc: 0.5330\n",
"Epoch 6/500\n",
"0s - loss: 0.3843 - acc: 0.5330\n",
"Epoch 7/500\n",
"0s - loss: 0.3834 - acc: 0.5330\n",
"Epoch 8/500\n",
"0s - loss: 0.3826 - acc: 0.5330\n",
"Epoch 9/500\n",
"0s - loss: 0.3818 - acc: 0.5330\n",
"Epoch 10/500\n",
"0s - loss: 0.3810 - acc: 0.5330\n",
"Epoch 11/500\n",
"0s - loss: 0.3802 - acc: 0.5330\n",
"Epoch 12/500\n",
"0s - loss: 0.3793 - acc: 0.5330\n",
"Epoch 13/500\n",
"0s - loss: 0.3785 - acc: 0.5330\n",
"Epoch 14/500\n",
"0s - loss: 0.3777 - acc: 0.5330\n",
"Epoch 15/500\n",
"0s - loss: 0.3769 - acc: 0.5330\n",
"Epoch 16/500\n",
"0s - loss: 0.3761 - acc: 0.5330\n",
"Epoch 17/500\n",
"0s - loss: 0.3753 - acc: 0.5330\n",
"Epoch 18/500\n",
"0s - loss: 0.3744 - acc: 0.5330\n",
"Epoch 19/500\n",
"0s - loss: 0.3736 - acc: 0.5330\n",
"Epoch 20/500\n",
"0s - loss: 0.3728 - acc: 0.5330\n",
"Epoch 21/500\n",
"0s - loss: 0.3720 - acc: 0.5330\n",
"Epoch 22/500\n",
"0s - loss: 0.3712 - acc: 0.5330\n",
"Epoch 23/500\n",
"0s - loss: 0.3704 - acc: 0.5330\n",
"Epoch 24/500\n",
"0s - loss: 0.3696 - acc: 0.5330\n",
"Epoch 25/500\n",
"0s - loss: 0.3688 - acc: 0.5330\n",
"Epoch 26/500\n",
"0s - loss: 0.3680 - acc: 0.5330\n",
"Epoch 27/500\n",
"0s - loss: 0.3672 - acc: 0.5330\n",
"Epoch 28/500\n",
"0s - loss: 0.3664 - acc: 0.5330\n",
"Epoch 29/500\n",
"0s - loss: 0.3656 - acc: 0.5330\n",
"Epoch 30/500\n",
"0s - loss: 0.3648 - acc: 0.5330\n",
"Epoch 31/500\n",
"0s - loss: 0.3640 - acc: 0.5330\n",
"Epoch 32/500\n",
"0s - loss: 0.3632 - acc: 0.5330\n",
"Epoch 33/500\n",
"0s - loss: 0.3624 - acc: 0.5330\n",
"Epoch 34/500\n",
"0s - loss: 0.3616 - acc: 0.5330\n",
"Epoch 35/500\n",
"0s - loss: 0.3608 - acc: 0.5330\n",
"Epoch 36/500\n",
"0s - loss: 0.3600 - acc: 0.5330\n",
"Epoch 37/500\n",
"0s - loss: 0.3592 - acc: 0.5340\n",
"Epoch 38/500\n",
"0s - loss: 0.3584 - acc: 0.5340\n",
"Epoch 39/500\n",
"0s - loss: 0.3576 - acc: 0.5400\n",
"Epoch 40/500\n",
"0s - loss: 0.3568 - acc: 0.5410\n",
"Epoch 41/500\n",
"0s - loss: 0.3561 - acc: 0.5480\n",
"Epoch 42/500\n",
"0s - loss: 0.3553 - acc: 0.5490\n",
"Epoch 43/500\n",
"0s - loss: 0.3545 - acc: 0.5540\n",
"Epoch 44/500\n",
"0s - loss: 0.3537 - acc: 0.5510\n",
"Epoch 45/500\n",
"0s - loss: 0.3529 - acc: 0.5590\n",
"Epoch 46/500\n",
"0s - loss: 0.3521 - acc: 0.5660\n",
"Epoch 47/500\n",
"0s - loss: 0.3514 - acc: 0.5680\n",
"Epoch 48/500\n",
"0s - loss: 0.3506 - acc: 0.5700\n",
"Epoch 49/500\n",
"0s - loss: 0.3498 - acc: 0.5780\n",
"Epoch 50/500\n",
"0s - loss: 0.3490 - acc: 0.5960\n",
"Epoch 51/500\n",
"0s - loss: 0.3483 - acc: 0.5940\n",
"Epoch 52/500\n",
"0s - loss: 0.3475 - acc: 0.6140\n",
"Epoch 53/500\n",
"0s - loss: 0.3467 - acc: 0.6250\n",
"Epoch 54/500\n",
"0s - loss: 0.3459 - acc: 0.6250\n",
"Epoch 55/500\n",
"0s - loss: 0.3452 - acc: 0.6410\n",
"Epoch 56/500\n",
"0s - loss: 0.3444 - acc: 0.6550\n",
"Epoch 57/500\n",
"0s - loss: 0.3436 - acc: 0.6630\n",
"Epoch 58/500\n",
"0s - loss: 0.3429 - acc: 0.6870\n",
"Epoch 59/500\n",
"0s - loss: 0.3421 - acc: 0.7050\n",
"Epoch 60/500\n",
"0s - loss: 0.3413 - acc: 0.7130\n",
"Epoch 61/500\n",
"0s - loss: 0.3406 - acc: 0.7140\n",
"Epoch 62/500\n",
"0s - loss: 0.3398 - acc: 0.7190\n",
"Epoch 63/500\n",
"0s - loss: 0.3390 - acc: 0.7300\n",
"Epoch 64/500\n",
"0s - loss: 0.3383 - acc: 0.7520\n",
"Epoch 65/500\n",
"0s - loss: 0.3375 - acc: 0.7570\n",
"Epoch 66/500\n",
"0s - loss: 0.3368 - acc: 0.7590\n",
"Epoch 67/500\n",
"0s - loss: 0.3360 - acc: 0.7680\n",
"Epoch 68/500\n",
"0s - loss: 0.3353 - acc: 0.7740\n",
"Epoch 69/500\n",
"0s - loss: 0.3345 - acc: 0.7740\n",
"Epoch 70/500\n",
"0s - loss: 0.3337 - acc: 0.7800\n",
"Epoch 71/500\n",
"0s - loss: 0.3330 - acc: 0.7800\n",
"Epoch 72/500\n",
"0s - loss: 0.3323 - acc: 0.7780\n",
"Epoch 73/500\n",
"0s - loss: 0.3315 - acc: 0.7900\n",
"Epoch 74/500\n",
"0s - loss: 0.3308 - acc: 0.7930\n",
"Epoch 75/500\n",
"0s - loss: 0.3300 - acc: 0.7920\n",
"Epoch 76/500\n",
"0s - loss: 0.3293 - acc: 0.7970\n",
"Epoch 77/500\n",
"0s - loss: 0.3285 - acc: 0.7970\n",
"Epoch 78/500\n",
"0s - loss: 0.3278 - acc: 0.7970\n",
"Epoch 79/500\n",
"0s - loss: 0.3270 - acc: 0.8000\n",
"Epoch 80/500\n",
"0s - loss: 0.3263 - acc: 0.8000\n",
"Epoch 81/500\n",
"0s - loss: 0.3256 - acc: 0.8000\n",
"Epoch 82/500\n",
"0s - loss: 0.3248 - acc: 0.8000\n",
"Epoch 83/500\n",
"0s - loss: 0.3241 - acc: 0.8000\n",
"Epoch 84/500\n",
"0s - loss: 0.3233 - acc: 0.8000\n",
"Epoch 85/500\n",
"0s - loss: 0.3226 - acc: 0.8000\n",
"Epoch 86/500\n",
"0s - loss: 0.3219 - acc: 0.8000\n",
"Epoch 87/500\n",
"0s - loss: 0.3211 - acc: 0.8000\n",
"Epoch 88/500\n",
"0s - loss: 0.3204 - acc: 0.8000\n",
"Epoch 89/500\n",
"0s - loss: 0.3197 - acc: 0.8000\n",
"Epoch 90/500\n",
"0s - loss: 0.3189 - acc: 0.8000\n",
"Epoch 91/500\n",
"0s - loss: 0.3182 - acc: 0.8000\n",
"Epoch 92/500\n",
"0s - loss: 0.3175 - acc: 0.8000\n",
"Epoch 93/500\n",
"0s - loss: 0.3168 - acc: 0.8000\n",
"Epoch 94/500\n",
"0s - loss: 0.3161 - acc: 0.8000\n",
"Epoch 95/500\n",
"0s - loss: 0.3153 - acc: 0.8000\n",
"Epoch 96/500\n",
"0s - loss: 0.3146 - acc: 0.8000\n",
"Epoch 97/500\n",
"0s - loss: 0.3139 - acc: 0.8000\n",
"Epoch 98/500\n",
"0s - loss: 0.3132 - acc: 0.8000\n",
"Epoch 99/500\n",
"0s - loss: 0.3124 - acc: 0.8000\n",
"Epoch 100/500\n",
"0s - loss: 0.3117 - acc: 0.8000\n",
"Epoch 101/500\n",
"0s - loss: 0.3110 - acc: 0.8000\n",
"Epoch 102/500\n",
"0s - loss: 0.3103 - acc: 0.8000\n",
"Epoch 103/500\n",
"0s - loss: 0.3096 - acc: 0.8000\n",
"Epoch 104/500\n",
"0s - loss: 0.3089 - acc: 0.8000\n",
"Epoch 105/500\n",
"0s - loss: 0.3082 - acc: 0.8000\n",
"Epoch 106/500\n",
"0s - loss: 0.3075 - acc: 0.8000\n",
"Epoch 107/500\n",
"0s - loss: 0.3067 - acc: 0.8000\n",
"Epoch 108/500\n",
"0s - loss: 0.3060 - acc: 0.8000\n",
"Epoch 109/500\n",
"0s - loss: 0.3053 - acc: 0.8000\n",
"Epoch 110/500\n",
"0s - loss: 0.3046 - acc: 0.8000\n",
"Epoch 111/500\n",
"0s - loss: 0.3039 - acc: 0.8000\n",
"Epoch 112/500\n",
"0s - loss: 0.3032 - acc: 0.8000\n",
"Epoch 113/500\n",
"0s - loss: 0.3025 - acc: 0.8000\n",
"Epoch 114/500\n",
"0s - loss: 0.3018 - acc: 0.8000\n",
"Epoch 115/500\n",
"0s - loss: 0.3011 - acc: 0.8000\n",
"Epoch 116/500\n",
"0s - loss: 0.3004 - acc: 0.8000\n",
"Epoch 117/500\n",
"0s - loss: 0.2997 - acc: 0.8000\n",
"Epoch 118/500\n",
"0s - loss: 0.2990 - acc: 0.8000\n",
"Epoch 119/500\n",
"0s - loss: 0.2983 - acc: 0.8000\n",
"Epoch 120/500\n",
"0s - loss: 0.2976 - acc: 0.8000\n",
"Epoch 121/500\n",
"0s - loss: 0.2969 - acc: 0.8000\n",
"Epoch 122/500\n",
"0s - loss: 0.2962 - acc: 0.8000\n",
"Epoch 123/500\n",
"0s - loss: 0.2955 - acc: 0.8000\n",
"Epoch 124/500\n",
"0s - loss: 0.2949 - acc: 0.8000\n",
"Epoch 125/500\n",
"0s - loss: 0.2942 - acc: 0.8000\n",
"Epoch 126/500\n",
"0s - loss: 0.2935 - acc: 0.8000\n",
"Epoch 127/500\n",
"0s - loss: 0.2928 - acc: 0.8000\n",
"Epoch 128/500\n",
"0s - loss: 0.2921 - acc: 0.8000\n",
"Epoch 129/500\n",
"0s - loss: 0.2914 - acc: 0.8000\n",
"Epoch 130/500\n",
"0s - loss: 0.2907 - acc: 0.8000\n",
"Epoch 131/500\n",
"0s - loss: 0.2901 - acc: 0.8000\n",
"Epoch 132/500\n",
"0s - loss: 0.2894 - acc: 0.8000\n",
"Epoch 133/500\n",
"0s - loss: 0.2887 - acc: 0.8000\n",
"Epoch 134/500\n",
"0s - loss: 0.2880 - acc: 0.8000\n",
"Epoch 135/500\n",
"0s - loss: 0.2874 - acc: 0.8000\n",
"Epoch 136/500\n",
"0s - loss: 0.2867 - acc: 0.8010\n",
"Epoch 137/500\n",
"0s - loss: 0.2860 - acc: 0.8010\n",
"Epoch 138/500\n",
"0s - loss: 0.2853 - acc: 0.8030\n",
"Epoch 139/500\n",
"0s - loss: 0.2847 - acc: 0.8050\n",
"Epoch 140/500\n",
"0s - loss: 0.2840 - acc: 0.8050\n",
"Epoch 141/500\n",
"0s - loss: 0.2833 - acc: 0.8070\n",
"Epoch 142/500\n",
"0s - loss: 0.2827 - acc: 0.8090\n",
"Epoch 143/500\n",
"0s - loss: 0.2820 - acc: 0.8090\n",
"Epoch 144/500\n",
"0s - loss: 0.2813 - acc: 0.8110\n",
"Epoch 145/500\n",
"0s - loss: 0.2807 - acc: 0.8130\n",
"Epoch 146/500\n",
"0s - loss: 0.2800 - acc: 0.8140\n",
"Epoch 147/500\n",
"0s - loss: 0.2793 - acc: 0.8220\n",
"Epoch 148/500\n",
"0s - loss: 0.2787 - acc: 0.8250\n",
"Epoch 149/500\n",
"0s - loss: 0.2780 - acc: 0.8290\n",
"Epoch 150/500\n",
"0s - loss: 0.2774 - acc: 0.8290\n",
"Epoch 151/500\n",
"0s - loss: 0.2767 - acc: 0.8400\n",
"Epoch 152/500\n",
"0s - loss: 0.2761 - acc: 0.8400\n",
"Epoch 153/500\n",
"0s - loss: 0.2754 - acc: 0.8470\n",
"Epoch 154/500\n",
"0s - loss: 0.2747 - acc: 0.8520\n",
"Epoch 155/500\n",
"0s - loss: 0.2741 - acc: 0.8560\n",
"Epoch 156/500\n",
"0s - loss: 0.2734 - acc: 0.8660\n",
"Epoch 157/500\n",
"0s - loss: 0.2728 - acc: 0.8680\n",
"Epoch 158/500\n",
"0s - loss: 0.2721 - acc: 0.8770\n",
"Epoch 159/500\n",
"0s - loss: 0.2715 - acc: 0.8810\n",
"Epoch 160/500\n",
"0s - loss: 0.2708 - acc: 0.8840\n",
"Epoch 161/500\n",
"0s - loss: 0.2702 - acc: 0.8850\n",
"Epoch 162/500\n",
"0s - loss: 0.2695 - acc: 0.8980\n",
"Epoch 163/500\n",
"0s - loss: 0.2689 - acc: 0.9070\n",
"Epoch 164/500\n",
"0s - loss: 0.2683 - acc: 0.9100\n",
"Epoch 165/500\n",
"0s - loss: 0.2676 - acc: 0.9110\n",
"Epoch 166/500\n",
"0s - loss: 0.2670 - acc: 0.9130\n",
"Epoch 167/500\n",
"0s - loss: 0.2663 - acc: 0.9190\n",
"Epoch 168/500\n",
"0s - loss: 0.2657 - acc: 0.9210\n",
"Epoch 169/500\n",
"0s - loss: 0.2651 - acc: 0.9230\n",
"Epoch 170/500\n",
"0s - loss: 0.2644 - acc: 0.9250\n",
"Epoch 171/500\n",
"0s - loss: 0.2638 - acc: 0.9270\n",
"Epoch 172/500\n",
"0s - loss: 0.2632 - acc: 0.9270\n",
"Epoch 173/500\n",
"0s - loss: 0.2625 - acc: 0.9280\n",
"Epoch 174/500\n",
"0s - loss: 0.2619 - acc: 0.9280\n",
"Epoch 175/500\n",
"0s - loss: 0.2613 - acc: 0.9320\n",
"Epoch 176/500\n",
"0s - loss: 0.2607 - acc: 0.9320\n",
"Epoch 177/500\n",
"0s - loss: 0.2600 - acc: 0.9330\n",
"Epoch 178/500\n",
"0s - loss: 0.2594 - acc: 0.9330\n",
"Epoch 179/500\n",
"0s - loss: 0.2588 - acc: 0.9330\n",
"Epoch 180/500\n",
"0s - loss: 0.2581 - acc: 0.9330\n",
"Epoch 181/500\n",
"0s - loss: 0.2575 - acc: 0.9330\n",
"Epoch 182/500\n",
"0s - loss: 0.2569 - acc: 0.9330\n",
"Epoch 183/500\n",
"0s - loss: 0.2563 - acc: 0.9330\n",
"Epoch 184/500\n",
"0s - loss: 0.2557 - acc: 0.9330\n",
"Epoch 185/500\n",
"0s - loss: 0.2550 - acc: 0.9330\n",
"Epoch 186/500\n",
"0s - loss: 0.2544 - acc: 0.9330\n",
"Epoch 187/500\n",
"0s - loss: 0.2538 - acc: 0.9330\n",
"Epoch 188/500\n",
"0s - loss: 0.2532 - acc: 0.9330\n",
"Epoch 189/500\n",
"0s - loss: 0.2526 - acc: 0.9330\n",
"Epoch 190/500\n",
"0s - loss: 0.2520 - acc: 0.9330\n",
"Epoch 191/500\n",
"0s - loss: 0.2514 - acc: 0.9330\n",
"Epoch 192/500\n",
"0s - loss: 0.2508 - acc: 0.9330\n",
"Epoch 193/500\n",
"0s - loss: 0.2501 - acc: 0.9330\n",
"Epoch 194/500\n",
"0s - loss: 0.2495 - acc: 0.9330\n",
"Epoch 195/500\n",
"0s - loss: 0.2489 - acc: 0.9330\n",
"Epoch 196/500\n",
"0s - loss: 0.2483 - acc: 0.9330\n",
"Epoch 197/500\n",
"0s - loss: 0.2477 - acc: 0.9330\n",
"Epoch 198/500\n",
"0s - loss: 0.2471 - acc: 0.9330\n",
"Epoch 199/500\n",
"0s - loss: 0.2465 - acc: 0.9330\n",
"Epoch 200/500\n",
"0s - loss: 0.2459 - acc: 0.9330\n",
"Epoch 201/500\n",
"0s - loss: 0.2453 - acc: 0.9330\n",
"Epoch 202/500\n",
"0s - loss: 0.2447 - acc: 0.9330\n",
"Epoch 203/500\n",
"0s - loss: 0.2441 - acc: 0.9330\n",
"Epoch 204/500\n",
"0s - loss: 0.2435 - acc: 0.9330\n",
"Epoch 205/500\n",
"0s - loss: 0.2429 - acc: 0.9330\n",
"Epoch 206/500\n",
"0s - loss: 0.2423 - acc: 0.9330\n",
"Epoch 207/500\n",
"0s - loss: 0.2417 - acc: 0.9330\n",
"Epoch 208/500\n",
"0s - loss: 0.2411 - acc: 0.9330\n",
"Epoch 209/500\n",
"0s - loss: 0.2405 - acc: 0.9330\n",
"Epoch 210/500\n",
"0s - loss: 0.2400 - acc: 0.9330\n",
"Epoch 211/500\n",
"0s - loss: 0.2394 - acc: 0.9330\n",
"Epoch 212/500\n",
"0s - loss: 0.2388 - acc: 0.9330\n",
"Epoch 213/500\n",
"0s - loss: 0.2382 - acc: 0.9330\n",
"Epoch 214/500\n",
"0s - loss: 0.2376 - acc: 0.9330\n",
"Epoch 215/500\n",
"0s - loss: 0.2370 - acc: 0.9330\n",
"Epoch 216/500\n",
"0s - loss: 0.2364 - acc: 0.9330\n",
"Epoch 217/500\n",
"0s - loss: 0.2359 - acc: 0.9330\n",
"Epoch 218/500\n",
"0s - loss: 0.2353 - acc: 0.9330\n",
"Epoch 219/500\n",
"0s - loss: 0.2347 - acc: 0.9360\n",
"Epoch 220/500\n",
"0s - loss: 0.2341 - acc: 0.9360\n",
"Epoch 221/500\n",
"0s - loss: 0.2335 - acc: 0.9360\n",
"Epoch 222/500\n",
"0s - loss: 0.2330 - acc: 0.9360\n",
"Epoch 223/500\n",
"0s - loss: 0.2324 - acc: 0.9370\n",
"Epoch 224/500\n",
"0s - loss: 0.2318 - acc: 0.9370\n",
"Epoch 225/500\n",
"0s - loss: 0.2313 - acc: 0.9380\n",
"Epoch 226/500\n",
"0s - loss: 0.2307 - acc: 0.9380\n",
"Epoch 227/500\n",
"0s - loss: 0.2301 - acc: 0.9420\n",
"Epoch 228/500\n",
"0s - loss: 0.2295 - acc: 0.9420\n",
"Epoch 229/500\n",
"0s - loss: 0.2290 - acc: 0.9450\n",
"Epoch 230/500\n",
"0s - loss: 0.2284 - acc: 0.9460\n",
"Epoch 231/500\n",
"0s - loss: 0.2278 - acc: 0.9480\n",
"Epoch 232/500\n",
"0s - loss: 0.2273 - acc: 0.9520\n",
"Epoch 233/500\n",
"0s - loss: 0.2267 - acc: 0.9550\n",
"Epoch 234/500\n",
"0s - loss: 0.2262 - acc: 0.9570\n",
"Epoch 235/500\n",
"0s - loss: 0.2256 - acc: 0.9600\n",
"Epoch 236/500\n",
"0s - loss: 0.2250 - acc: 0.9620\n",
"Epoch 237/500\n",
"0s - loss: 0.2245 - acc: 0.9640\n",
"Epoch 238/500\n",
"0s - loss: 0.2239 - acc: 0.9710\n",
"Epoch 239/500\n",
"0s - loss: 0.2234 - acc: 0.9730\n",
"Epoch 240/500\n",
"0s - loss: 0.2228 - acc: 0.9750\n",
"Epoch 241/500\n",
"0s - loss: 0.2222 - acc: 0.9780\n",
"Epoch 242/500\n",
"0s - loss: 0.2217 - acc: 0.9810\n",
"Epoch 243/500\n",
"0s - loss: 0.2211 - acc: 0.9810\n",
"Epoch 244/500\n",
"0s - loss: 0.2206 - acc: 0.9830\n",
"Epoch 245/500\n",
"0s - loss: 0.2200 - acc: 0.9840\n",
"Epoch 246/500\n",
"0s - loss: 0.2195 - acc: 0.9860\n",
"Epoch 247/500\n",
"0s - loss: 0.2189 - acc: 0.9890\n",
"Epoch 248/500\n",
"0s - loss: 0.2184 - acc: 0.9920\n",
"Epoch 249/500\n",
"0s - loss: 0.2178 - acc: 0.9920\n",
"Epoch 250/500\n",
"0s - loss: 0.2173 - acc: 0.9950\n",
"Epoch 251/500\n",
"0s - loss: 0.2168 - acc: 0.9950\n",
"Epoch 252/500\n",
"0s - loss: 0.2162 - acc: 0.9950\n",
"Epoch 253/500\n",
"0s - loss: 0.2157 - acc: 0.9970\n",
"Epoch 254/500\n",
"0s - loss: 0.2151 - acc: 0.9980\n",
"Epoch 255/500\n",
"0s - loss: 0.2146 - acc: 0.9980\n",
"Epoch 256/500\n",
"0s - loss: 0.2141 - acc: 0.9990\n",
"Epoch 257/500\n",
"0s - loss: 0.2135 - acc: 0.9990\n",
"Epoch 258/500\n",
"0s - loss: 0.2130 - acc: 1.0000\n",
"Epoch 259/500\n",
"0s - loss: 0.2124 - acc: 1.0000\n",
"Epoch 260/500\n",
"0s - loss: 0.2119 - acc: 1.0000\n",
"Epoch 261/500\n",
"0s - loss: 0.2114 - acc: 1.0000\n",
"Epoch 262/500\n",
"0s - loss: 0.2108 - acc: 1.0000\n",
"Epoch 263/500\n",
"0s - loss: 0.2103 - acc: 1.0000\n",
"Epoch 264/500\n",
"0s - loss: 0.2098 - acc: 1.0000\n",
"Epoch 265/500\n",
"0s - loss: 0.2093 - acc: 1.0000\n",
"Epoch 266/500\n",
"0s - loss: 0.2087 - acc: 1.0000\n",
"Epoch 267/500\n",
"0s - loss: 0.2082 - acc: 1.0000\n",
"Epoch 268/500\n",
"0s - loss: 0.2077 - acc: 1.0000\n",
"Epoch 269/500\n",
"0s - loss: 0.2072 - acc: 1.0000\n",
"Epoch 270/500\n",
"0s - loss: 0.2066 - acc: 1.0000\n",
"Epoch 271/500\n",
"0s - loss: 0.2061 - acc: 1.0000\n",
"Epoch 272/500\n",
"0s - loss: 0.2056 - acc: 1.0000\n",
"Epoch 273/500\n",
"0s - loss: 0.2051 - acc: 1.0000\n",
"Epoch 274/500\n",
"0s - loss: 0.2045 - acc: 1.0000\n",
"Epoch 275/500\n",
"0s - loss: 0.2040 - acc: 1.0000\n",
"Epoch 276/500\n",
"0s - loss: 0.2035 - acc: 1.0000\n",
"Epoch 277/500\n",
"0s - loss: 0.2030 - acc: 1.0000\n",
"Epoch 278/500\n",
"0s - loss: 0.2025 - acc: 1.0000\n",
"Epoch 279/500\n",
"0s - loss: 0.2020 - acc: 1.0000\n",
"Epoch 280/500\n",
"0s - loss: 0.2015 - acc: 1.0000\n",
"Epoch 281/500\n",
"0s - loss: 0.2009 - acc: 1.0000\n",
"Epoch 282/500\n",
"0s - loss: 0.2004 - acc: 1.0000\n",
"Epoch 283/500\n",
"0s - loss: 0.1999 - acc: 1.0000\n",
"Epoch 284/500\n",
"0s - loss: 0.1994 - acc: 1.0000\n",
"Epoch 285/500\n"
]
},
{
"ename": "KeyboardInterrupt",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[1;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)",
"\u001b[1;32m<ipython-input-6-3fcdf9c4da85>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m()\u001b[0m\n\u001b[0;32m 3\u001b[0m \u001b[0msamples_per_epoch\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mN\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 4\u001b[0m \u001b[0mverbose\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;36m2\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 5\u001b[1;33m nb_epoch=500)\n\u001b[0m",
"\u001b[1;32m/home/russellp/anaconda2/lib/python2.7/site-packages/keras/models.pyc\u001b[0m in \u001b[0;36mfit_generator\u001b[1;34m(self, generator, samples_per_epoch, nb_epoch, verbose, callbacks, validation_data, nb_val_samples, class_weight, max_q_size, **kwargs)\u001b[0m\n\u001b[0;32m 654\u001b[0m \u001b[0mnb_val_samples\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mnb_val_samples\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 655\u001b[0m \u001b[0mclass_weight\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mclass_weight\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 656\u001b[1;33m max_q_size=max_q_size)\n\u001b[0m\u001b[0;32m 657\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 658\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0mevaluate_generator\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mgenerator\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mval_samples\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mmax_q_size\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;36m10\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;32m/home/russellp/anaconda2/lib/python2.7/site-packages/keras/engine/training.pyc\u001b[0m in \u001b[0;36mfit_generator\u001b[1;34m(self, generator, samples_per_epoch, nb_epoch, verbose, callbacks, validation_data, nb_val_samples, class_weight, max_q_size)\u001b[0m\n\u001b[0;32m 1382\u001b[0m outs = self.train_on_batch(x, y,\n\u001b[0;32m 1383\u001b[0m \u001b[0msample_weight\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0msample_weight\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1384\u001b[1;33m class_weight=class_weight)\n\u001b[0m\u001b[0;32m 1385\u001b[0m \u001b[1;32mexcept\u001b[0m \u001b[0mException\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 1386\u001b[0m \u001b[0m_stop\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[0m\n",
"\u001b[1;32m/home/russellp/anaconda2/lib/python2.7/site-packages/keras/engine/training.pyc\u001b[0m in \u001b[0;36mtrain_on_batch\u001b[1;34m(self, x, y, sample_weight, class_weight)\u001b[0m\n\u001b[0;32m 1166\u001b[0m \u001b[0mins\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mx\u001b[0m \u001b[1;33m+\u001b[0m \u001b[0my\u001b[0m \u001b[1;33m+\u001b[0m \u001b[0msample_weights\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 1167\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_make_train_function\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1168\u001b[1;33m \u001b[0moutputs\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mtrain_function\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mins\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 1169\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mlen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0moutputs\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;33m==\u001b[0m \u001b[1;36m1\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 1170\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0moutputs\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;36m0\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;32m/home/russellp/anaconda2/lib/python2.7/site-packages/keras/backend/tensorflow_backend.pyc\u001b[0m in \u001b[0;36m__call__\u001b[1;34m(self, inputs)\u001b[0m\n\u001b[0;32m 657\u001b[0m \u001b[0mfeed_dict\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mdict\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mzip\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mnames\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0minputs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 658\u001b[0m \u001b[0msession\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mget_session\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 659\u001b[1;33m \u001b[0mupdated\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0msession\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mrun\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0moutputs\u001b[0m \u001b[1;33m+\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mupdates\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mfeed_dict\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mfeed_dict\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 660\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mupdated\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;33m:\u001b[0m\u001b[0mlen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0moutputs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 661\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;32m/home/russellp/anaconda2/lib/python2.7/site-packages/tensorflow/python/client/session.pyc\u001b[0m in \u001b[0;36mrun\u001b[1;34m(self, fetches, feed_dict, options, run_metadata)\u001b[0m\n\u001b[0;32m 365\u001b[0m \u001b[1;32mtry\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 366\u001b[0m result = self._run(None, fetches, feed_dict, options_ptr,\n\u001b[1;32m--> 367\u001b[1;33m run_metadata_ptr)\n\u001b[0m\u001b[0;32m 368\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mrun_metadata\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 369\u001b[0m \u001b[0mproto_data\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mtf_session\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mTF_GetBuffer\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mrun_metadata_ptr\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;32m/home/russellp/anaconda2/lib/python2.7/site-packages/tensorflow/python/client/session.pyc\u001b[0m in \u001b[0;36m_run\u001b[1;34m(self, handle, fetches, feed_dict, options, run_metadata)\u001b[0m\n\u001b[0;32m 638\u001b[0m \u001b[0mmovers\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_update_with_movers\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mfeed_dict_string\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mfeed_map\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 639\u001b[0m results = self._do_run(handle, target_list, unique_fetches,\n\u001b[1;32m--> 640\u001b[1;33m feed_dict_string, options, run_metadata)\n\u001b[0m\u001b[0;32m 641\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 642\u001b[0m \u001b[1;31m# User may have fetched the same tensor multiple times, but we\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;32m/home/russellp/anaconda2/lib/python2.7/site-packages/tensorflow/python/client/session.pyc\u001b[0m in \u001b[0;36m_do_run\u001b[1;34m(self, handle, target_list, fetch_list, feed_dict, options, run_metadata)\u001b[0m\n\u001b[0;32m 706\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mhandle\u001b[0m \u001b[1;32mis\u001b[0m \u001b[0mNone\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 707\u001b[0m return self._do_call(_run_fn, self._session, feed_dict, fetch_list,\n\u001b[1;32m--> 708\u001b[1;33m target_list, options, run_metadata)\n\u001b[0m\u001b[0;32m 709\u001b[0m \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 710\u001b[0m return self._do_call(_prun_fn, self._session, handle, feed_dict,\n",
"\u001b[1;32m/home/russellp/anaconda2/lib/python2.7/site-packages/tensorflow/python/client/session.pyc\u001b[0m in \u001b[0;36m_do_call\u001b[1;34m(self, fn, *args)\u001b[0m\n\u001b[0;32m 713\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0m_do_call\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mfn\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 714\u001b[0m \u001b[1;32mtry\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 715\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mfn\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 716\u001b[0m \u001b[1;32mexcept\u001b[0m \u001b[0merrors\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mOpError\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 717\u001b[0m \u001b[0mmessage\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mcompat\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mas_text\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0me\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mmessage\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;32m/home/russellp/anaconda2/lib/python2.7/site-packages/tensorflow/python/client/session.pyc\u001b[0m in \u001b[0;36m_run_fn\u001b[1;34m(session, feed_dict, fetch_list, target_list, options, run_metadata)\u001b[0m\n\u001b[0;32m 695\u001b[0m return tf_session.TF_Run(session, options,\n\u001b[0;32m 696\u001b[0m \u001b[0mfeed_dict\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mfetch_list\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mtarget_list\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 697\u001b[1;33m status, run_metadata)\n\u001b[0m\u001b[0;32m 698\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 699\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0m_prun_fn\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0msession\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mhandle\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mfeed_dict\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mfetch_list\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;31mKeyboardInterrupt\u001b[0m: "
]
}
],
"source": [
"training_model.fit_generator(\n",
" _fizzdata(),\n",
" samples_per_epoch=N,\n",
" verbose=2,\n",
" nb_epoch=500)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 2",
"language": "python",
"name": "python2"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 2
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython2",
"version": "2.7.11"
}
},
"nbformat": 4,
"nbformat_minor": 0
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment