{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/m/.local/lib/python3.7/site-packages/tensorflow/python/framework/dtypes.py:516: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  _np_qint8 = np.dtype([(\"qint8\", np.int8, 1)])\n",
      "/home/m/.local/lib/python3.7/site-packages/tensorflow/python/framework/dtypes.py:517: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  _np_quint8 = np.dtype([(\"quint8\", np.uint8, 1)])\n",
      "/home/m/.local/lib/python3.7/site-packages/tensorflow/python/framework/dtypes.py:518: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  _np_qint16 = np.dtype([(\"qint16\", np.int16, 1)])\n",
      "/home/m/.local/lib/python3.7/site-packages/tensorflow/python/framework/dtypes.py:519: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  _np_quint16 = np.dtype([(\"quint16\", np.uint16, 1)])\n",
      "/home/m/.local/lib/python3.7/site-packages/tensorflow/python/framework/dtypes.py:520: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  _np_qint32 = np.dtype([(\"qint32\", np.int32, 1)])\n",
      "/home/m/.local/lib/python3.7/site-packages/tensorflow/python/framework/dtypes.py:525: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  np_resource = np.dtype([(\"resource\", np.ubyte, 1)])\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2.0.0-beta1\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/m/.local/lib/python3.7/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:541: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  _np_qint8 = np.dtype([(\"qint8\", np.int8, 1)])\n",
      "/home/m/.local/lib/python3.7/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:542: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  _np_quint8 = np.dtype([(\"quint8\", np.uint8, 1)])\n",
      "/home/m/.local/lib/python3.7/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:543: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  _np_qint16 = np.dtype([(\"qint16\", np.int16, 1)])\n",
      "/home/m/.local/lib/python3.7/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:544: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  _np_quint16 = np.dtype([(\"quint16\", np.uint16, 1)])\n",
      "/home/m/.local/lib/python3.7/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:545: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  _np_qint32 = np.dtype([(\"qint32\", np.int32, 1)])\n",
      "/home/m/.local/lib/python3.7/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:550: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  np_resource = np.dtype([(\"resource\", np.ubyte, 1)])\n"
     ]
    }
   ],
   "source": [
    "import tensorflow as tf\n",
    "from tensorflow import keras\n",
    "\n",
    "# Helper libraries\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "print(tf.__version__)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "from numpy import genfromtxt\n",
    "data = genfromtxt('data.csv', delimiter=',')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "data_input = data[:,0:3]\n",
    "data_labels = data[:,3]\n",
    "\n",
    "#data_input = np.transpose(data_input)\n",
    "#data_labels = np.transpose(data_labels)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(600, 3)\n",
      "[1.e-01 1.e+00 3.e+02]\n"
     ]
    }
   ],
   "source": [
    "print(np.shape(data_input))\n",
    "print(data_input[2])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "print(len(data_input))\n",
    "print(len(data_labels))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(500, 3)\n",
      "(100, 3)\n",
      "(500,)\n",
      "(100,)\n"
     ]
    }
   ],
   "source": [
    "data_input_train = data_input[0:500,:]\n",
    "data_input_test = data_input[500:,:]\n",
    "\n",
    "data_labels_train = data_labels[0:500]\n",
    "data_labels_test = data_labels[500:]\n",
    "\n",
    "print(np.shape(data_input_train))\n",
    "print(np.shape(data_input_test))\n",
    "\n",
    "print(np.shape(data_labels_train))\n",
    "print(np.shape(data_labels_test))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "model = keras.Sequential([\n",
    "    keras.layers.Dense(128, activation='relu', input_shape=[3]),\n",
    "    keras.layers.Dense(512, activation='relu'),\n",
    "    keras.layers.Dense(512, activation='relu'),\n",
    "    keras.layers.Dense(512, activation='relu'),\n",
    "    keras.layers.Dense(128, activation='relu'),\n",
    "    keras.layers.Dense(1)\n",
    "])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "optimizer = tf.keras.optimizers.RMSprop(0.001)\n",
    "model.compile(loss='mse',\n",
    "                optimizer=optimizer,\n",
    "                metrics=['accuracy'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Train on 500 samples\n",
      "Epoch 1/100\n",
      "500/500 [==============================] - 0s 399us/sample - loss: 247.2794 - accuracy: 0.0040\n",
      "Epoch 2/100\n",
      "500/500 [==============================] - 0s 121us/sample - loss: 4.2495 - accuracy: 0.0060\n",
      "Epoch 3/100\n",
      "500/500 [==============================] - 0s 131us/sample - loss: 1.8787 - accuracy: 0.0040\n",
      "Epoch 4/100\n",
      "500/500 [==============================] - 0s 121us/sample - loss: 0.4284 - accuracy: 0.0060\n",
      "Epoch 5/100\n",
      "500/500 [==============================] - 0s 107us/sample - loss: 4.7904 - accuracy: 0.0080\n",
      "Epoch 6/100\n",
      "500/500 [==============================] - 0s 113us/sample - loss: 0.0819 - accuracy: 0.0040\n",
      "Epoch 7/100\n",
      "500/500 [==============================] - 0s 108us/sample - loss: 1.6904 - accuracy: 0.0040\n",
      "Epoch 8/100\n",
      "500/500 [==============================] - 0s 116us/sample - loss: 0.1761 - accuracy: 0.0040\n",
      "Epoch 9/100\n",
      "500/500 [==============================] - 0s 142us/sample - loss: 0.1135 - accuracy: 0.0040\n",
      "Epoch 10/100\n",
      "500/500 [==============================] - 0s 124us/sample - loss: 0.4387 - accuracy: 0.0040\n",
      "Epoch 11/100\n",
      "500/500 [==============================] - 0s 112us/sample - loss: 0.0815 - accuracy: 0.0040\n",
      "Epoch 12/100\n",
      "500/500 [==============================] - 0s 117us/sample - loss: 0.1725 - accuracy: 0.0040\n",
      "Epoch 13/100\n",
      "500/500 [==============================] - 0s 119us/sample - loss: 0.1487 - accuracy: 0.0040\n",
      "Epoch 14/100\n",
      "500/500 [==============================] - 0s 111us/sample - loss: 0.0720 - accuracy: 0.0040\n",
      "Epoch 15/100\n",
      "500/500 [==============================] - 0s 111us/sample - loss: 0.3110 - accuracy: 0.0040\n",
      "Epoch 16/100\n",
      "500/500 [==============================] - 0s 128us/sample - loss: 0.0947 - accuracy: 0.0040\n",
      "Epoch 17/100\n",
      "500/500 [==============================] - 0s 133us/sample - loss: 0.0739 - accuracy: 0.0040\n",
      "Epoch 18/100\n",
      "500/500 [==============================] - 0s 131us/sample - loss: 0.1353 - accuracy: 0.0060\n",
      "Epoch 19/100\n",
      "500/500 [==============================] - 0s 135us/sample - loss: 0.0837 - accuracy: 0.0040\n",
      "Epoch 20/100\n",
      "500/500 [==============================] - 0s 130us/sample - loss: 0.0754 - accuracy: 0.0040\n",
      "Epoch 21/100\n",
      "500/500 [==============================] - 0s 118us/sample - loss: 0.0840 - accuracy: 0.0040\n",
      "Epoch 22/100\n",
      "500/500 [==============================] - 0s 115us/sample - loss: 0.1105 - accuracy: 0.0040\n",
      "Epoch 23/100\n",
      "500/500 [==============================] - 0s 116us/sample - loss: 0.0651 - accuracy: 0.0040\n",
      "Epoch 24/100\n",
      "500/500 [==============================] - 0s 109us/sample - loss: 0.0615 - accuracy: 0.0040\n",
      "Epoch 25/100\n",
      "500/500 [==============================] - 0s 118us/sample - loss: 0.0656 - accuracy: 0.0040\n",
      "Epoch 26/100\n",
      "500/500 [==============================] - 0s 113us/sample - loss: 0.0695 - accuracy: 0.0040\n",
      "Epoch 27/100\n",
      "500/500 [==============================] - 0s 116us/sample - loss: 0.0585 - accuracy: 0.0040\n",
      "Epoch 28/100\n",
      "500/500 [==============================] - 0s 118us/sample - loss: 0.1300 - accuracy: 0.0040\n",
      "Epoch 29/100\n",
      "500/500 [==============================] - 0s 112us/sample - loss: 0.0567 - accuracy: 0.0040\n",
      "Epoch 30/100\n",
      "500/500 [==============================] - 0s 137us/sample - loss: 0.0647 - accuracy: 0.0040\n",
      "Epoch 31/100\n",
      "500/500 [==============================] - 0s 130us/sample - loss: 0.0559 - accuracy: 0.0040\n",
      "Epoch 32/100\n",
      "500/500 [==============================] - 0s 130us/sample - loss: 0.0576 - accuracy: 0.0040\n",
      "Epoch 33/100\n",
      "500/500 [==============================] - 0s 128us/sample - loss: 0.0578 - accuracy: 0.0040\n",
      "Epoch 34/100\n",
      "500/500 [==============================] - 0s 130us/sample - loss: 0.0512 - accuracy: 0.0040\n",
      "Epoch 35/100\n",
      "500/500 [==============================] - 0s 114us/sample - loss: 0.0601 - accuracy: 0.0040\n",
      "Epoch 36/100\n",
      "500/500 [==============================] - 0s 111us/sample - loss: 0.0531 - accuracy: 0.0040\n",
      "Epoch 37/100\n",
      "500/500 [==============================] - 0s 130us/sample - loss: 0.0532 - accuracy: 0.0040\n",
      "Epoch 38/100\n",
      "500/500 [==============================] - 0s 131us/sample - loss: 0.0480 - accuracy: 0.0040\n",
      "Epoch 39/100\n",
      "500/500 [==============================] - 0s 136us/sample - loss: 0.0503 - accuracy: 0.0040\n",
      "Epoch 40/100\n",
      "500/500 [==============================] - 0s 134us/sample - loss: 0.0468 - accuracy: 0.0040\n",
      "Epoch 41/100\n",
      "500/500 [==============================] - 0s 115us/sample - loss: 0.0509 - accuracy: 0.0040\n",
      "Epoch 42/100\n",
      "500/500 [==============================] - 0s 109us/sample - loss: 0.0453 - accuracy: 0.0040\n",
      "Epoch 43/100\n",
      "500/500 [==============================] - 0s 111us/sample - loss: 0.0484 - accuracy: 0.0040\n",
      "Epoch 44/100\n",
      "500/500 [==============================] - 0s 104us/sample - loss: 0.0458 - accuracy: 0.0040\n",
      "Epoch 45/100\n",
      "500/500 [==============================] - 0s 110us/sample - loss: 0.0481 - accuracy: 0.0040\n",
      "Epoch 46/100\n",
      "500/500 [==============================] - 0s 114us/sample - loss: 0.0468 - accuracy: 0.0060\n",
      "Epoch 47/100\n",
      "500/500 [==============================] - 0s 124us/sample - loss: 0.0473 - accuracy: 0.0060\n",
      "Epoch 48/100\n",
      "500/500 [==============================] - 0s 137us/sample - loss: 0.0455 - accuracy: 0.0040\n",
      "Epoch 49/100\n",
      "500/500 [==============================] - 0s 125us/sample - loss: 0.0431 - accuracy: 0.0060\n",
      "Epoch 50/100\n",
      "500/500 [==============================] - 0s 132us/sample - loss: 0.0432 - accuracy: 0.0060\n",
      "Epoch 51/100\n",
      "500/500 [==============================] - 0s 116us/sample - loss: 0.0484 - accuracy: 0.0060\n",
      "Epoch 52/100\n",
      "500/500 [==============================] - 0s 112us/sample - loss: 0.0482 - accuracy: 0.0040\n",
      "Epoch 53/100\n",
      "500/500 [==============================] - 0s 117us/sample - loss: 0.0444 - accuracy: 0.0060\n",
      "Epoch 54/100\n",
      "500/500 [==============================] - 0s 109us/sample - loss: 0.0469 - accuracy: 0.0060\n",
      "Epoch 55/100\n",
      "500/500 [==============================] - 0s 106us/sample - loss: 0.0427 - accuracy: 0.0040\n",
      "Epoch 56/100\n",
      "500/500 [==============================] - 0s 110us/sample - loss: 0.0433 - accuracy: 0.0040\n",
      "Epoch 57/100\n",
      "500/500 [==============================] - 0s 102us/sample - loss: 0.0437 - accuracy: 0.0060\n",
      "Epoch 58/100\n",
      "500/500 [==============================] - 0s 117us/sample - loss: 0.0425 - accuracy: 0.0040\n",
      "Epoch 59/100\n",
      "500/500 [==============================] - 0s 105us/sample - loss: 0.0418 - accuracy: 0.0040\n",
      "Epoch 60/100\n",
      "500/500 [==============================] - 0s 109us/sample - loss: 0.0397 - accuracy: 0.0040\n",
      "Epoch 61/100\n",
      "500/500 [==============================] - 0s 119us/sample - loss: 0.0507 - accuracy: 0.0040\n",
      "Epoch 62/100\n",
      "500/500 [==============================] - 0s 112us/sample - loss: 0.0402 - accuracy: 0.0060\n",
      "Epoch 63/100\n",
      "500/500 [==============================] - 0s 133us/sample - loss: 0.0397 - accuracy: 0.0040\n",
      "Epoch 64/100\n",
      "500/500 [==============================] - 0s 132us/sample - loss: 0.0427 - accuracy: 0.0060\n",
      "Epoch 65/100\n",
      "500/500 [==============================] - 0s 138us/sample - loss: 0.0398 - accuracy: 0.0040\n",
      "Epoch 66/100\n",
      "500/500 [==============================] - 0s 145us/sample - loss: 0.0375 - accuracy: 0.0060\n",
      "Epoch 67/100\n",
      "500/500 [==============================] - 0s 138us/sample - loss: 0.0402 - accuracy: 0.0060\n",
      "Epoch 68/100\n",
      "500/500 [==============================] - 0s 132us/sample - loss: 0.0388 - accuracy: 0.0080\n",
      "Epoch 69/100\n",
      "500/500 [==============================] - 0s 115us/sample - loss: 0.0375 - accuracy: 0.0080\n",
      "Epoch 70/100\n",
      "500/500 [==============================] - 0s 113us/sample - loss: 0.0384 - accuracy: 0.0040\n",
      "Epoch 71/100\n",
      "500/500 [==============================] - 0s 109us/sample - loss: 0.0360 - accuracy: 0.0080\n",
      "Epoch 72/100\n",
      "500/500 [==============================] - 0s 111us/sample - loss: 0.0350 - accuracy: 0.0080\n",
      "Epoch 73/100\n",
      "500/500 [==============================] - 0s 118us/sample - loss: 0.0370 - accuracy: 0.0060\n",
      "Epoch 74/100\n",
      "500/500 [==============================] - 0s 95us/sample - loss: 0.0354 - accuracy: 0.0080\n",
      "Epoch 75/100\n",
      "500/500 [==============================] - 0s 102us/sample - loss: 0.0376 - accuracy: 0.0060\n",
      "Epoch 76/100\n",
      "500/500 [==============================] - 0s 106us/sample - loss: 0.0371 - accuracy: 0.0080\n",
      "Epoch 77/100\n",
      "500/500 [==============================] - 0s 100us/sample - loss: 0.0369 - accuracy: 0.0060\n",
      "Epoch 78/100\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "500/500 [==============================] - 0s 98us/sample - loss: 0.0315 - accuracy: 0.0060\n",
      "Epoch 79/100\n",
      "500/500 [==============================] - 0s 97us/sample - loss: 0.0355 - accuracy: 0.0060\n",
      "Epoch 80/100\n",
      "500/500 [==============================] - 0s 100us/sample - loss: 0.0278 - accuracy: 0.0080\n",
      "Epoch 81/100\n",
      "500/500 [==============================] - 0s 99us/sample - loss: 0.0320 - accuracy: 0.0080\n",
      "Epoch 82/100\n",
      "500/500 [==============================] - 0s 99us/sample - loss: 0.0321 - accuracy: 0.0080\n",
      "Epoch 83/100\n",
      "500/500 [==============================] - 0s 94us/sample - loss: 0.0332 - accuracy: 0.0060\n",
      "Epoch 84/100\n",
      "500/500 [==============================] - 0s 106us/sample - loss: 0.0317 - accuracy: 0.0060\n",
      "Epoch 85/100\n",
      "500/500 [==============================] - 0s 103us/sample - loss: 0.0293 - accuracy: 0.0080\n",
      "Epoch 86/100\n",
      "500/500 [==============================] - 0s 107us/sample - loss: 0.0304 - accuracy: 0.0060\n",
      "Epoch 87/100\n",
      "500/500 [==============================] - 0s 101us/sample - loss: 0.0327 - accuracy: 0.0040\n",
      "Epoch 88/100\n",
      "500/500 [==============================] - 0s 100us/sample - loss: 0.0290 - accuracy: 0.0080\n",
      "Epoch 89/100\n",
      "500/500 [==============================] - 0s 123us/sample - loss: 0.0293 - accuracy: 0.0060\n",
      "Epoch 90/100\n",
      "500/500 [==============================] - 0s 104us/sample - loss: 0.0246 - accuracy: 0.0060\n",
      "Epoch 91/100\n",
      "500/500 [==============================] - 0s 124us/sample - loss: 0.0303 - accuracy: 0.0060\n",
      "Epoch 92/100\n",
      "500/500 [==============================] - 0s 129us/sample - loss: 0.0376 - accuracy: 0.0080\n",
      "Epoch 93/100\n",
      "500/500 [==============================] - 0s 122us/sample - loss: 0.0264 - accuracy: 0.0080\n",
      "Epoch 94/100\n",
      "500/500 [==============================] - 0s 102us/sample - loss: 0.0265 - accuracy: 0.0080\n",
      "Epoch 95/100\n",
      "500/500 [==============================] - 0s 108us/sample - loss: 0.0291 - accuracy: 0.0080\n",
      "Epoch 96/100\n",
      "500/500 [==============================] - 0s 101us/sample - loss: 0.0314 - accuracy: 0.0080\n",
      "Epoch 97/100\n",
      "500/500 [==============================] - 0s 95us/sample - loss: 0.0257 - accuracy: 0.0060\n",
      "Epoch 98/100\n",
      "500/500 [==============================] - 0s 100us/sample - loss: 0.0248 - accuracy: 0.0080\n",
      "Epoch 99/100\n",
      "500/500 [==============================] - 0s 94us/sample - loss: 0.0250 - accuracy: 0.0040\n",
      "Epoch 100/100\n",
      "500/500 [==============================] - 0s 106us/sample - loss: 0.0312 - accuracy: 0.0060\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<tensorflow.python.keras.callbacks.History at 0x7f55a3853f60>"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#model.fit(data_input_train, data_labels_train, validation_data=(data_input_test, data_labels_test), epochs=100)\n",
    "model.fit(data_input_train, data_labels_train, epochs=100)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "100/100 - 0s - loss: 0.0470 - accuracy: 0.0100\n",
      "\n",
      "Test accuracy: 0.01\n"
     ]
    }
   ],
   "source": [
    "test_loss, test_acc = model.evaluate(data_input_test,  data_labels_test, verbose=2)\n",
    "\n",
    "print('\\nTest accuracy:', test_acc)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[0.3141548]]\n"
     ]
    }
   ],
   "source": [
    "input = np.array([0.46,2,136])\n",
    "input.shape = (1,3)\n",
    "\n",
    "prediction = model.predict(input)\n",
    "print(prediction)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "predictions = model.predict(data_input_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "%matplotlib qt \n",
    "plt.plot(predictions)\n",
    "plt.plot(data_labels_test, 'r')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 204,
   "metadata": {},
   "outputs": [],
   "source": [
    "%matplotlib qt\n",
    "a = data_labels_test - predictions\n",
    "plt.plot(a[0])\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 207,
   "metadata": {},
   "outputs": [],
   "source": [
    "%matplotlib qt\n",
    "a = data_labels_test - predictions\n",
    "plt.plot(predictions)\n",
    "plt.plot(data_labels_test, 'r')\n",
    "plt.plot(a[0], 'g')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 180,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "-0.08489150602276586"
      ]
     },
     "execution_count": 180,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.average(a[0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 182,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model: \"sequential_13\"\n",
      "_________________________________________________________________\n",
      "Layer (type)                 Output Shape              Param #   \n",
      "=================================================================\n",
      "dense_38 (Dense)             (None, 128)               512       \n",
      "_________________________________________________________________\n",
      "dense_39 (Dense)             (None, 512)               66048     \n",
      "_________________________________________________________________\n",
      "dense_40 (Dense)             (None, 512)               262656    \n",
      "_________________________________________________________________\n",
      "dense_41 (Dense)             (None, 512)               262656    \n",
      "_________________________________________________________________\n",
      "dense_42 (Dense)             (None, 128)               65664     \n",
      "_________________________________________________________________\n",
      "dense_43 (Dense)             (None, 1)                 129       \n",
      "=================================================================\n",
      "Total params: 657,665\n",
      "Trainable params: 657,665\n",
      "Non-trainable params: 0\n",
      "_________________________________________________________________\n"
     ]
    }
   ],
   "source": [
    "model.summary()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 183,
   "metadata": {},
   "outputs": [],
   "source": [
    "model.save('my_model.h5')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}