automationkeras.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [],
   "source": [
    "df=pd.read_excel(\"FeatureData.xlsx\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(1114, 3)"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X=df[['mean','std','var']]\n",
    "X.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(1114,)"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y= df['state']\n",
    "y.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Import required libraries \n",
    "import keras #library for neural network\n",
    "import pandas as pd #loading data in table form  \n",
    "#import seaborn as sns #visualisation \n",
    "#import matplotlib.pyplot as plt #visualisation\n",
    "import numpy as np # linear algebra\n",
    "from sklearn.preprocessing import normalize #machine learning algorithm library"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(188, 3)"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "F= df.iloc[:94]\n",
    "L=df.iloc[1020:]\n",
    "new_df=F.append(L)\n",
    "new_df=new_df.reset_index(drop=True)\n",
    "s11=0\n",
    "s22=1\n",
    "new_df[\"state\"]=new_df[\"state\"].map({'state1':s11,'state2':s22})\n",
    "new_df=new_df.iloc[np.random.permutation(len(new_df))]\n",
    "new_df=new_df.reset_index(drop=True)\n",
    "newX=new_df[['mean','std','var']]\n",
    "newy=new_df[['state']]\n",
    "X_normalized=newX\n",
    "X_normalized.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [],
   "source": [
    "total_length=len(new_df)\n",
    "train_length=int(0.8*total_length)\n",
    "test_length=int(0.2*total_length)\n",
    "\n",
    "X_train=X_normalized[:train_length]\n",
    "X_test=X_normalized[train_length:]\n",
    "y_train=newy[:train_length]\n",
    "y_test=newy[train_length:]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [],
   "source": [
    "from keras.models import Sequential \n",
    "from keras.layers import Dense,Activation,Dropout \n",
    "from keras.layers.normalization import BatchNormalization \n",
    "from keras.utils import np_utils"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Length of train set x: 150 y: 150\nLength of test set x: 38 y: 38\n"
     ]
    }
   ],
   "source": [
    "print(\"Length of train set x:\",X_train.shape[0],\"y:\",y_train.shape[0])\n",
    "print(\"Length of test set x:\",X_test.shape[0],\"y:\",y_test.shape[0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(38, 2)"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_train=np_utils.to_categorical(y_train,num_classes=2)\n",
    "y_test=np_utils.to_categorical(y_test,num_classes=2)\n",
    "y_test.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [],
   "source": [
    "model=Sequential()\n",
    "model.add(Dense(1000,input_dim=3,activation='relu'))\n",
    "model.add(Dense(500,activation='relu'))\n",
    "model.add(Dense(300,activation='relu'))\n",
    "model.add(Dropout(0.5))\n",
    "model.add(Dense(2,activation='softmax'))\n",
    "model.compile(loss='categorical_crossentropy',optimizer='adam',metrics=['accuracy'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "_________________________________________________________________\nLayer (type)                 Output Shape              Param #   \n=================================================================\ndense_5 (Dense)              (None, 1000)              4000      \n_________________________________________________________________\ndense_6 (Dense)              (None, 500)               500500    \n_________________________________________________________________\ndense_7 (Dense)              (None, 300)               150300    \n_________________________________________________________________\ndropout_2 (Dropout)          (None, 300)               0         \n_________________________________________________________________\ndense_8 (Dense)              (None, 2)                 602       \n=================================================================\nTotal params: 655,402\nTrainable params: 655,402\nNon-trainable params: 0\n_________________________________________________________________\n"
     ]
    }
   ],
   "source": [
    "model.summary()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {
    "collapsed": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Train on 150 samples, validate on 38 samples\nEpoch 1/10\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\r 20/150 [===>..........................] - ETA: 2s - loss: 0.6913 - acc: 0.4000"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r 60/150 [===========>..................] - ETA: 0s - loss: 0.8351 - acc: 0.5667"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r120/150 [=======================>......] - ETA: 0s - loss: 0.7435 - acc: 0.4917"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r150/150 [==============================] - 1s 4ms/step - loss: 0.8094 - acc: 0.5133 - val_loss: 1.0117 - val_acc: 0.6316\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 2/10\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\r 20/150 [===>..........................] - ETA: 0s - loss: 0.4684 - acc: 0.7500"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r 60/150 [===========>..................] - ETA: 0s - loss: 0.4935 - acc: 0.7333"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r120/150 [=======================>......] - ETA: 0s - loss: 0.6007 - acc: 0.7833"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r150/150 [==============================] - 0s 1ms/step - loss: 0.6444 - acc: 0.8133 - val_loss: 0.8812 - val_acc: 0.8421\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 3/10\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\r 20/150 [===>..........................] - ETA: 0s - loss: 0.2207 - acc: 1.0000"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r 60/150 [===========>..................] - ETA: 0s - loss: 0.5765 - acc: 0.9167"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r120/150 [=======================>......] - ETA: 0s - loss: 0.5603 - acc: 0.8917"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r150/150 [==============================] - 0s 1ms/step - loss: 0.4900 - acc: 0.9067 - val_loss: 0.7695 - val_acc: 0.8947\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 4/10\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\r 20/150 [===>..........................] - ETA: 0s - loss: 0.1218 - acc: 1.0000"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r 60/150 [===========>..................] - ETA: 0s - loss: 0.1618 - acc: 0.9667"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r120/150 [=======================>......] - ETA: 0s - loss: 0.4399 - acc: 0.9333"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r150/150 [==============================] - 0s 1ms/step - loss: 0.3921 - acc: 0.9333 - val_loss: 0.7845 - val_acc: 0.8947\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 5/10\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\r 20/150 [===>..........................] - ETA: 0s - loss: 0.2010 - acc: 0.9500"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r 60/150 [===========>..................] - ETA: 0s - loss: 0.5417 - acc: 0.9167"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r100/150 [===================>..........] - ETA: 0s - loss: 0.5154 - acc: 0.9300"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r140/150 [===========================>..] - ETA: 0s - loss: 0.3972 - acc: 0.9429"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r150/150 [==============================] - 0s 2ms/step - loss: 0.3896 - acc: 0.9400 - val_loss: 1.0015 - val_acc: 0.8684\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 6/10\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\r 20/150 [===>..........................] - ETA: 0s - loss: 0.1617 - acc: 0.9500"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r 60/150 [===========>..................] - ETA: 0s - loss: 0.2093 - acc: 0.9167"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r120/150 [=======================>......] - ETA: 0s - loss: 0.4809 - acc: 0.9250"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r150/150 [==============================] - 0s 1ms/step - loss: 0.4063 - acc: 0.9333 - val_loss: 0.7984 - val_acc: 0.9211\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 7/10\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\r 20/150 [===>..........................] - ETA: 0s - loss: 0.2507 - acc: 0.9500"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r 60/150 [===========>..................] - ETA: 0s - loss: 0.4757 - acc: 0.9333"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r120/150 [=======================>......] - ETA: 0s - loss: 0.3102 - acc: 0.9500"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r150/150 [==============================] - 0s 1ms/step - loss: 0.3880 - acc: 0.9400 - val_loss: 0.9449 - val_acc: 0.8947\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 8/10\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\r 20/150 [===>..........................] - ETA: 0s - loss: 0.0410 - acc: 1.0000"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r 60/150 [===========>..................] - ETA: 0s - loss: 0.1216 - acc: 0.9667"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r120/150 [=======================>......] - ETA: 0s - loss: 0.2757 - acc: 0.9417"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r150/150 [==============================] - 0s 1ms/step - loss: 0.3731 - acc: 0.9400 - val_loss: 0.8539 - val_acc: 0.8947\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 9/10\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\r 20/150 [===>..........................] - ETA: 0s - loss: 0.2343 - acc: 0.9000"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r 60/150 [===========>..................] - ETA: 0s - loss: 0.2038 - acc: 0.9333"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r120/150 [=======================>......] - ETA: 0s - loss: 0.4488 - acc: 0.9250"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r150/150 [==============================] - 0s 1ms/step - loss: 0.3695 - acc: 0.9400 - val_loss: 0.8384 - val_acc: 0.8947\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 10/10\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\r 20/150 [===>..........................] - ETA: 0s - loss: 0.0478 - acc: 1.0000"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r 60/150 [===========>..................] - ETA: 0s - loss: 0.3936 - acc: 0.9500"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r120/150 [=======================>......] - ETA: 0s - loss: 0.4100 - acc: 0.9417"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r150/150 [==============================] - 0s 1ms/step - loss: 0.3603 - acc: 0.9400 - val_loss: 0.8831 - val_acc: 0.8947\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<keras.callbacks.History at 0x7f8eb9db40b8>"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.fit(X_train,y_train,validation_data=(X_test,y_test),batch_size=20,epochs=10,verbose=1)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\r32/38 [========================>.....] - ETA: 0s"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r38/38 [==============================] - 0s 190us/step\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Test accuracy: 0.8947368421052632\n"
     ]
    }
   ],
   "source": [
    "score = model.evaluate(X_test, y_test, verbose=1)\n",
    "print('Test accuracy:', score[1])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [],
   "source": [
    "from keras.models import load_model\n",
    "from importlib import reload\n",
    "reload(keras.models)\n",
    "model.save('my_model.h5')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0, 0, 0, 0, 1, 0, 1, 1])"
      ]
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.predict_classes(newX[0:8])\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "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": "2.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}