training_vertical_landing.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "import os\n",
    "import tensorflow as tf\n",
    "from tensorflow import keras\n",
    "import numpy as np\n",
    "from sklearn.model_selection import train_test_split\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "data_file = pd.read_csv('data/landingData.csv')\n",
    "column_names = ['pos_z','index']\n",
    "feature_names = column_names[0]\n",
    "label_name = ['index']\n",
    "print(\"Feature: {}\".format(feature_names))\n",
    "print(\"Label: {}\".format(label_name))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "Vx_train, Vx_test, labelVx_train, labelVx_test = train_test_split(data_file[feature_names], data_file[label_name[0]], test_size=0.1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "modelVx = keras.Sequential([\n",
    "        keras.layers.Dense(16, activation=tf.nn.relu,input_shape=(1,)),\n",
    "        keras.layers.Dense(32,activation=tf.nn.relu),\n",
    "        keras.layers.Dense(32,activation=tf.nn.relu),\n",
    "        keras.layers.Dense(1)\n",
    "    ])\n",
    "optimizer = tf.keras.optimizers.RMSprop(0.001)\n",
    "modelVx.compile(loss='mse',\n",
    "              optimizer=optimizer,\n",
    "              metrics=['mae']             \n",
    "             )\n",
    "modelVx.summary()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "\n",
    "def plot_history(history):\n",
    "    plt.figure()\n",
    "    plt.xlabel('Epoch')\n",
    "    plt.ylabel(\"Mean Abs Error [1000$]\")\n",
    "    plt.plot(history.epoch, np.array(history.history['mean_absolute_error']),\n",
    "            label='Train Loss')\n",
    "    plt.plot(history.epoch, np.array(history.history['val_mean_absolute_error']),\n",
    "            label='Val Loss')\n",
    "    plt.legend()\n",
    "    plt.ylim([0,5])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false,
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "EPOCHS = 60\n",
    "history=modelVx.fit(Vx_train,\n",
    "                  labelVx_train,\n",
    "                  epochs=EPOCHS,\n",
    "                  validation_split=0.1,\n",
    "                  verbose=1\n",
    "                 )\n",
    "plot_history(history)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "[loss, mae] = modelVx.evaluate(Vx_test, labelVx_test, verbose=1)\n",
    "print(\"Testing set Mean Abs Error: ${:7.2f}\".format(mae * 1000))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "modelVx.save(\"models/modelVerticalNN.h5\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "anaconda-cloud": {},
  "kernelspec": {
   "display_name": "Python [cntk-py35]",
   "language": "python",
   "name": "Python [cntk-py35]"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.5.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}