copyfun/linear_regression.ipynb

## linear_regression.ipynb
{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# A linear regression learning algorithm example using TensorFlow library.\n",
    "\n",
    "# Author: Aymeric Damien\n",
    "# Project: https://github.com/aymericdamien/TensorFlow-Examples/"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import tensorflow as tf\n",
    "import numpy\n",
    "import matplotlib.pyplot as plt\n",
    "rng = numpy.random"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# Parameters\n",
    "learning_rate = 0.01\n",
    "training_epochs = 2000\n",
    "display_step = 50"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# Training Data\n",
    "train_X = numpy.asarray([3.3,4.4,5.5,6.71,6.93,4.168,9.779,6.182,7.59,2.167,7.042,10.791,5.313,7.997,5.654,9.27,3.1])\n",
    "train_Y = numpy.asarray([1.7,2.76,2.09,3.19,1.694,1.573,3.366,2.596,2.53,1.221,2.827,3.465,1.65,2.904,2.42,2.94,1.3])\n",
    "n_samples = train_X.shape[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 71,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# tf Graph Input\n",
    "X = tf.placeholder(\"float\")\n",
    "Y = tf.placeholder(\"float\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 72,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# Create Model\n",
    "\n",
    "# Set model weights\n",
    "W = tf.Variable(rng.randn(), name=\"weight\")\n",
    "b = tf.Variable(rng.randn(), name=\"bias\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 73,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# Construct a linear model\n",
    "activation = tf.add(tf.mul(X, W), b)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# Minimize the squared errors\n",
    "cost = tf.reduce_sum(tf.pow(activation-Y, 2))/(2*n_samples) #L2 loss\n",
    "optimizer = tf.train.GradientDescentOptimizer(0.0008).minimize(cost) #Gradient descent"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# Initializing the variables\n",
    "init = tf.initialize_all_variables()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 76,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXUAAAEACAYAAABMEua6AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nREREREREREREREREREREREQkKv4f23OEUvookTAAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x10aafd290>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "<matplotlib.figure.Figure at 0x10aafd290>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "%matplotlib inline  \n",
    "from IPython import display\n",
    "import time\n",
    "\n",
    "ses = tf.Session()\n",
    "ses.run(init)\n",
    "\n",
    "for i in range(1000):\n",
    "    for x,y in zip(train_X,train_Y):\n",
    "        ses.run(optimizer,feed_dict={X:x,Y:y})\n",
    "\n",
    "\n",
    "    \n",
    "    plt.plot(train_X, train_Y, 'ro', label='Original data')\n",
    "    plt.plot(train_X, ses.run(W) * train_X + ses.run(b), label='Fitted line')\n",
    "    display.clear_output(wait=True)\n",
    "    display.display(plt.gcf())\n",
    "    time.sleep(0.0001)\n",
    "    plt.clf()\n",
    "\n",
    "#     print ses.run(W), ses.run(b), ses.run(cost,feed_dict={X:train_X,Y:train_Y})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  },
  {
   "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": "2.7.10"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}
	{
	"cells": [
	{
	"cell_type": "code",
	"execution_count": null,
	"metadata": {
	"collapsed": true
	},
	"outputs": [],
	"source": [
	"# A linear regression learning algorithm example using TensorFlow library.\n",
	"\n",
	"# Author: Aymeric Damien\n",
	"# Project: https://github.com/aymericdamien/TensorFlow-Examples/"
	]
	},
	{
	"cell_type": "code",
	"execution_count": 68,
	"metadata": {
	"collapsed": true
	},
	"outputs": [],
	"source": [
	"import tensorflow as tf\n",
	"import numpy\n",
	"import matplotlib.pyplot as plt\n",
	"rng = numpy.random"
	]
	},
	{
	"cell_type": "code",
	"execution_count": 69,
	"metadata": {
	"collapsed": true
	},
	"outputs": [],
	"source": [
	"# Parameters\n",
	"learning_rate = 0.01\n",
	"training_epochs = 2000\n",
	"display_step = 50"
	]
	},
	{
	"cell_type": "code",
	"execution_count": 70,
	"metadata": {
	"collapsed": true
	},
	"outputs": [],
	"source": [
	"# Training Data\n",
	"train_X = numpy.asarray([3.3,4.4,5.5,6.71,6.93,4.168,9.779,6.182,7.59,2.167,7.042,10.791,5.313,7.997,5.654,9.27,3.1])\n",
	"train_Y = numpy.asarray([1.7,2.76,2.09,3.19,1.694,1.573,3.366,2.596,2.53,1.221,2.827,3.465,1.65,2.904,2.42,2.94,1.3])\n",
	"n_samples = train_X.shape[0]"
	]
	},
	{
	"cell_type": "code",
	"execution_count": 71,
	"metadata": {
	"collapsed": true
	},
	"outputs": [],
	"source": [
	"# tf Graph Input\n",
	"X = tf.placeholder(\"float\")\n",
	"Y = tf.placeholder(\"float\")"
	]
	},
	{
	"cell_type": "code",
	"execution_count": 72,
	"metadata": {
	"collapsed": true
	},
	"outputs": [],
	"source": [
	"# Create Model\n",
	"\n",
	"# Set model weights\n",
	"W = tf.Variable(rng.randn(), name=\"weight\")\n",
	"b = tf.Variable(rng.randn(), name=\"bias\")"
	]
	},
	{
	"cell_type": "code",
	"execution_count": 73,
	"metadata": {
	"collapsed": true
	},
	"outputs": [],
	"source": [
	"# Construct a linear model\n",
	"activation = tf.add(tf.mul(X, W), b)"
	]
	},
	{
	"cell_type": "code",
	"execution_count": 74,
	"metadata": {
	"collapsed": true
	},
	"outputs": [],
	"source": [
	"# Minimize the squared errors\n",
	"cost = tf.reduce_sum(tf.pow(activation-Y, 2))/(2*n_samples) #L2 loss\n",
	"optimizer = tf.train.GradientDescentOptimizer(0.0008).minimize(cost) #Gradient descent"
	]
	},
	{
	"cell_type": "code",
	"execution_count": 75,
	"metadata": {
	"collapsed": true
	},
	"outputs": [],
	"source": [
	"# Initializing the variables\n",
	"init = tf.initialize_all_variables()"
	]
	},
	{
	"cell_type": "code",
	"execution_count": 76,
	"metadata": {
	"collapsed": false
	},
	"outputs": [
	{
	"data": {
	"image/png": "iVBORw0KGgoAAAANSUhEUgAAAXUAAAEACAYAAABMEua6AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nREREREREREREREREREREREQkKv4f23OEUvookTAAAAAASUVORK5CYII=\n",
	"text/plain": [
	"<matplotlib.figure.Figure at 0x10aafd290>"
	]
	},
	"metadata": {},
	"output_type": "display_data"
	},
	{
	"data": {
	"text/plain": [
	"<matplotlib.figure.Figure at 0x10aafd290>"
	]
	},
	"metadata": {},
	"output_type": "display_data"
	}
	],
	"source": [
	"%matplotlib inline \n",
	"from IPython import display\n",
	"import time\n",
	"\n",
	"ses = tf.Session()\n",
	"ses.run(init)\n",
	"\n",
	"for i in range(1000):\n",
	" for x,y in zip(train_X,train_Y):\n",
	" ses.run(optimizer,feed_dict={X:x,Y:y})\n",
	"\n",
	"\n",
	" \n",
	" plt.plot(train_X, train_Y, 'ro', label='Original data')\n",
	" plt.plot(train_X, ses.run(W) * train_X + ses.run(b), label='Fitted line')\n",
	" display.clear_output(wait=True)\n",
	" display.display(plt.gcf())\n",
	" time.sleep(0.0001)\n",
	" plt.clf()\n",
	"\n",
	"# print ses.run(W), ses.run(b), ses.run(cost,feed_dict={X:train_X,Y:train_Y})"
	]
	},
	{
	"cell_type": "code",
	"execution_count": null,
	"metadata": {
	"collapsed": true
	},
	"outputs": [],
	"source": []
	},
	{
	"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": "2.7.10"
	}
	},
	"nbformat": 4,
	"nbformat_minor": 0
	}