linear regression keras

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Using TensorFlow backend.\n"
     ]
    }
   ],
   "source": [
    "from matplotlib import pyplot as plt\n",
    "import numpy as np\n",
    "from keras.models import Sequential\n",
    "from keras.layers import Dense, Activation\n",
    "\n",
    "# fix random seed for reproducibility\n",
    "np.random.seed(7)\n",
    "\n",
    "# function\n",
    "curve = np.vectorize(lambda x: x*10)\n",
    "\n",
    "# data\n",
    "Xideal = np.arange(1, 15.5, 0.005)\n",
    "Yideal = curve(Xideal)\n",
    "X = Xideal[1::5]\n",
    "Y = curve(X)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(580,)"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Y.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": false,
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/20\n",
      "580/580 [==============================] - 1s - loss: 297.2352 - mean_squared_error: 297.2352     \n",
      "Epoch 2/20\n",
      "580/580 [==============================] - 1s - loss: 0.0385 - mean_squared_error: 0.0385     \n",
      "Epoch 3/20\n",
      "580/580 [==============================] - 1s - loss: 0.0331 - mean_squared_error: 0.0331     \n",
      "Epoch 4/20\n",
      "580/580 [==============================] - 1s - loss: 0.0215 - mean_squared_error: 0.0215     \n",
      "Epoch 5/20\n",
      "580/580 [==============================] - 0s - loss: 0.0165 - mean_squared_error: 0.0165     \n",
      "Epoch 6/20\n",
      "580/580 [==============================] - 0s - loss: 0.0078 - mean_squared_error: 0.0078     \n",
      "Epoch 7/20\n",
      "580/580 [==============================] - 0s - loss: 0.0048 - mean_squared_error: 0.0048     \n",
      "Epoch 8/20\n",
      "580/580 [==============================] - 0s - loss: 0.0033 - mean_squared_error: 0.0033     \n",
      "Epoch 9/20\n",
      "580/580 [==============================] - 0s - loss: 0.0034 - mean_squared_error: 0.0034     \n",
      "Epoch 10/20\n",
      "580/580 [==============================] - 1s - loss: 0.0013 - mean_squared_error: 0.0013     \n",
      "Epoch 11/20\n",
      "580/580 [==============================] - 1s - loss: 8.1617e-04 - mean_squared_error: 8.1617e-04     \n",
      "Epoch 12/20\n",
      "580/580 [==============================] - 1s - loss: 5.0212e-04 - mean_squared_error: 5.0212e-04     \n",
      "Epoch 13/20\n",
      "580/580 [==============================] - 1s - loss: 3.5598e-04 - mean_squared_error: 3.5598e-04     \n",
      "Epoch 14/20\n",
      "580/580 [==============================] - 0s - loss: 2.4538e-04 - mean_squared_error: 2.4538e-04     \n",
      "Epoch 15/20\n",
      "580/580 [==============================] - 1s - loss: 1.1763e-04 - mean_squared_error: 1.1763e-04     \n",
      "Epoch 16/20\n",
      "580/580 [==============================] - 1s - loss: 6.2288e-05 - mean_squared_error: 6.2288e-05     \n",
      "Epoch 17/20\n",
      "580/580 [==============================] - 0s - loss: 4.9650e-05 - mean_squared_error: 4.9650e-05     \n",
      "Epoch 18/20\n",
      "580/580 [==============================] - 1s - loss: 2.5441e-05 - mean_squared_error: 2.5441e-05     \n",
      "Epoch 19/20\n",
      "580/580 [==============================] - 0s - loss: 1.4274e-05 - mean_squared_error: 1.4274e-05     \n",
      "Epoch 20/20\n",
      "580/580 [==============================] - 1s - loss: 1.0052e-05 - mean_squared_error: 1.0052e-05     \n",
      "2900/2900 [==============================] - 0s     \n",
      "\n",
      "mean_squared_error: 0.00%\n",
      "\n",
      "loss: 0.00%\n"
     ]
    }
   ],
   "source": [
    "# Model \n",
    "model = Sequential()\n",
    "model.add(Dense(1, activation='linear', input_dim=1))\n",
    "\n",
    "model.compile(loss='mse', optimizer='sgd', metrics=['mse'])\n",
    "\n",
    "# Fit\n",
    "\n",
    "model.fit(X, Y, nb_epoch=20, batch_size=10, verbose=1)\n",
    "# Evaluate\n",
    "\n",
    "# evaluate the model\n",
    "scores = model.evaluate(Xideal, Yideal)\n",
    "\n",
    "preds=model.predict(Xideal)\n",
    "print(\"\\n%s: %.2f%%\" % (model.metrics_names[1], scores[1]*100))\n",
    "print(\"\\n%s: %.2f%%\" % (model.metrics_names[0], scores[0]*100))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAgoAAAFkCAYAAABB1xPiAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nkiRJkiRJkiRJkiRJkiRJkhrH/wNAlx0duYlBigAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7f4542950d50>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "%matplotlib inline\n",
    "\n",
    "plt.figure(\"two plots\")\n",
    "plt.plot(Xideal, Yideal)\n",
    "plt.plot(Xideal, preds-2)\n",
    "plt.show()"
   ]
  },
  {
   "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": "2.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}