Predicting House Prices with Regression.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Task 1: Introduction\n",
    "\n",
    "---\n",
    "\n",
    "For this project, we are going to work on evaluating price of houses given the following features:\n",
    "\n",
    "1. Year of sale of the house\n",
    "2. The age of the house at the time of sale\n",
    "3. Distance from city center\n",
    "4. Number of stores in the locality\n",
    "5. The latitude\n",
    "6. The longitude\n",
    "\n",
    "![Regression](images/regression.png)\n",
    "\n",
    "Note: This notebook uses `python 3` and these packages: `tensorflow`, `pandas`, `matplotlib`, `scikit-learn`."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 1.1: Importing Libraries & Helper Functions\n",
    "\n",
    "First of all, we will need to import some libraries and helper functions. This includes TensorFlow and some utility functions that I've written to save time."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Libraries imported.\n"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import tensorflow as tf\n",
    "\n",
    "from utils import *\n",
    "from sklearn.model_selection import train_test_split\n",
    "from tensorflow.keras.models import Sequential\n",
    "from tensorflow.keras.layers import Dense, Dropout\n",
    "from tensorflow.keras.callbacks import EarlyStopping, LambdaCallback\n",
    "\n",
    "%matplotlib inline\n",
    "tf.logging.set_verbosity(tf.logging.ERROR)\n",
    "\n",
    "print('Libraries imported.')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Task 2: Importing the Data"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 2.1: Importing the Data\n",
    "\n",
    "The dataset is saved in a `data.csv` file. We will use `pandas` to take a look at some of the rows."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>serial</th>\n",
       "      <th>date</th>\n",
       "      <th>age</th>\n",
       "      <th>distance</th>\n",
       "      <th>stores</th>\n",
       "      <th>latitude</th>\n",
       "      <th>longitude</th>\n",
       "      <th>price</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>2009</td>\n",
       "      <td>21</td>\n",
       "      <td>9</td>\n",
       "      <td>6</td>\n",
       "      <td>84</td>\n",
       "      <td>121</td>\n",
       "      <td>14264</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>2007</td>\n",
       "      <td>4</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>86</td>\n",
       "      <td>121</td>\n",
       "      <td>12032</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2</td>\n",
       "      <td>2016</td>\n",
       "      <td>18</td>\n",
       "      <td>3</td>\n",
       "      <td>7</td>\n",
       "      <td>90</td>\n",
       "      <td>120</td>\n",
       "      <td>13560</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3</td>\n",
       "      <td>2002</td>\n",
       "      <td>13</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>80</td>\n",
       "      <td>128</td>\n",
       "      <td>12029</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>4</td>\n",
       "      <td>2014</td>\n",
       "      <td>25</td>\n",
       "      <td>5</td>\n",
       "      <td>8</td>\n",
       "      <td>81</td>\n",
       "      <td>122</td>\n",
       "      <td>14157</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   serial  date  age  distance  stores  latitude  longitude  price\n",
       "0       0  2009   21         9       6        84        121  14264\n",
       "1       1  2007    4         2       3        86        121  12032\n",
       "2       2  2016   18         3       7        90        120  13560\n",
       "3       3  2002   13         2       2        80        128  12029\n",
       "4       4  2014   25         5       8        81        122  14157"
      ]
     },
     "execution_count": 46,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.read_csv('data.csv',names =column_names)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 2.2: Check Missing Data\n",
    "\n",
    "It's a good practice to check if the data has any missing values. In real world data, this is quite common and must be taken care of before any data pre-processing or model training."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "serial       0\n",
       "date         0\n",
       "age          0\n",
       "distance     0\n",
       "stores       0\n",
       "latitude     0\n",
       "longitude    0\n",
       "price        0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 47,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.isna().sum()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Task 3: Data Normalization"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 3.1: Data Normalization\n",
    "\n",
    "We can make it easier for optimization algorithms to find minimas by normalizing the data before training a model."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>date</th>\n",
       "      <th>age</th>\n",
       "      <th>distance</th>\n",
       "      <th>stores</th>\n",
       "      <th>latitude</th>\n",
       "      <th>longitude</th>\n",
       "      <th>price</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.015978</td>\n",
       "      <td>0.181384</td>\n",
       "      <td>1.257002</td>\n",
       "      <td>0.345224</td>\n",
       "      <td>-0.307212</td>\n",
       "      <td>-1.260799</td>\n",
       "      <td>0.350088</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>-0.350485</td>\n",
       "      <td>-1.319118</td>\n",
       "      <td>-0.930610</td>\n",
       "      <td>-0.609312</td>\n",
       "      <td>0.325301</td>\n",
       "      <td>-1.260799</td>\n",
       "      <td>-1.836486</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1.298598</td>\n",
       "      <td>-0.083410</td>\n",
       "      <td>-0.618094</td>\n",
       "      <td>0.663402</td>\n",
       "      <td>1.590328</td>\n",
       "      <td>-1.576456</td>\n",
       "      <td>-0.339584</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>-1.266643</td>\n",
       "      <td>-0.524735</td>\n",
       "      <td>-0.930610</td>\n",
       "      <td>-0.927491</td>\n",
       "      <td>-1.572238</td>\n",
       "      <td>0.948803</td>\n",
       "      <td>-1.839425</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.932135</td>\n",
       "      <td>0.534444</td>\n",
       "      <td>0.006938</td>\n",
       "      <td>0.981581</td>\n",
       "      <td>-1.255981</td>\n",
       "      <td>-0.945141</td>\n",
       "      <td>0.245266</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       date       age  distance    stores  latitude  longitude     price\n",
       "0  0.015978  0.181384  1.257002  0.345224 -0.307212  -1.260799  0.350088\n",
       "1 -0.350485 -1.319118 -0.930610 -0.609312  0.325301  -1.260799 -1.836486\n",
       "2  1.298598 -0.083410 -0.618094  0.663402  1.590328  -1.576456 -0.339584\n",
       "3 -1.266643 -0.524735 -0.930610 -0.927491 -1.572238   0.948803 -1.839425\n",
       "4  0.932135  0.534444  0.006938  0.981581 -1.255981  -0.945141  0.245266"
      ]
     },
     "execution_count": 48,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = df.iloc[:,1:]\n",
    "df_norm=(df-df.mean())/df.std()\n",
    "df_norm.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 3.2: Convert Label Value\n",
    "\n",
    "Because we are using normalized values for the labels, we will get the predictions back from a trained model in the same distribution. So, we need to convert the predicted values back to the original distribution if we want predicted prices."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "12028\n"
     ]
    }
   ],
   "source": [
    "y_mean=df['price'].mean()\n",
    "y_std=df['price'].std()\n",
    "\n",
    "def convert_label_value(pred):\n",
    "    return int(pred*y_std+y_mean)\n",
    "print(convert_label_value(-1.839425))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Task 4: Create Training and Test Sets"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 4.1: Select Features\n",
    "\n",
    "Make sure to remove the column __price__ from the list of features as it is the label and should not be used as a feature."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>date</th>\n",
       "      <th>age</th>\n",
       "      <th>distance</th>\n",
       "      <th>stores</th>\n",
       "      <th>latitude</th>\n",
       "      <th>longitude</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.015978</td>\n",
       "      <td>0.181384</td>\n",
       "      <td>1.257002</td>\n",
       "      <td>0.345224</td>\n",
       "      <td>-0.307212</td>\n",
       "      <td>-1.260799</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>-0.350485</td>\n",
       "      <td>-1.319118</td>\n",
       "      <td>-0.930610</td>\n",
       "      <td>-0.609312</td>\n",
       "      <td>0.325301</td>\n",
       "      <td>-1.260799</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1.298598</td>\n",
       "      <td>-0.083410</td>\n",
       "      <td>-0.618094</td>\n",
       "      <td>0.663402</td>\n",
       "      <td>1.590328</td>\n",
       "      <td>-1.576456</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>-1.266643</td>\n",
       "      <td>-0.524735</td>\n",
       "      <td>-0.930610</td>\n",
       "      <td>-0.927491</td>\n",
       "      <td>-1.572238</td>\n",
       "      <td>0.948803</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.932135</td>\n",
       "      <td>0.534444</td>\n",
       "      <td>0.006938</td>\n",
       "      <td>0.981581</td>\n",
       "      <td>-1.255981</td>\n",
       "      <td>-0.945141</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       date       age  distance    stores  latitude  longitude\n",
       "0  0.015978  0.181384  1.257002  0.345224 -0.307212  -1.260799\n",
       "1 -0.350485 -1.319118 -0.930610 -0.609312  0.325301  -1.260799\n",
       "2  1.298598 -0.083410 -0.618094  0.663402  1.590328  -1.576456\n",
       "3 -1.266643 -0.524735 -0.930610 -0.927491 -1.572238   0.948803\n",
       "4  0.932135  0.534444  0.006938  0.981581 -1.255981  -0.945141"
      ]
     },
     "execution_count": 50,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x = df_norm.iloc[:, :6]\n",
    "x.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 4.2: Select Labels"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>price</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.350088</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>-1.836486</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>-0.339584</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>-1.839425</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.245266</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      price\n",
       "0  0.350088\n",
       "1 -1.836486\n",
       "2 -0.339584\n",
       "3 -1.839425\n",
       "4  0.245266"
      ]
     },
     "execution_count": 55,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y=df_norm.iloc[:, -1:]\n",
    "y.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 4.3: Feature and Label Values\n",
    "\n",
    "We will need to extract just the numeric values for the features and labels as the TensorFlow model will expect just numeric values as input."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "features array shape: (5000, 6)\n",
      "labels array shape: (5000, 1)\n"
     ]
    }
   ],
   "source": [
    "x_arr =x.values\n",
    "y_arr=y.values\n",
    "print('features array shape:',x_arr.shape)\n",
    "print('labels array shape:',y_arr.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 4.4: Train and Test Split\n",
    "\n",
    "We will keep some part of the data aside as a __test__ set. The model will not use this set during training and it will be used only for checking the performance of the model in trained and un-trained states. This way, we can make sure that we are going in the right direction with our model training."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Traning set: (4750, 6) (4750, 1)\n",
      "Test Set: (250, 6) (250, 1)\n"
     ]
    }
   ],
   "source": [
    "x_train,x_test,y_train,y_test=train_test_split(x_arr,y_arr,test_size=0.05,random_state=0)\n",
    "print('Traning set:',x_train.shape,y_train.shape)\n",
    "print('Test Set:',x_test.shape,y_test.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Task 5: Create the Model"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 5.1: Create the Model\n",
    "\n",
    "Let's write a function that returns an untrained model of a certain architecture."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "_________________________________________________________________\n",
      "Layer (type)                 Output Shape              Param #   \n",
      "=================================================================\n",
      "dense_12 (Dense)             (None, 10)                70        \n",
      "_________________________________________________________________\n",
      "dense_13 (Dense)             (None, 20)                220       \n",
      "_________________________________________________________________\n",
      "dense_14 (Dense)             (None, 5)                 105       \n",
      "_________________________________________________________________\n",
      "dense_15 (Dense)             (None, 1)                 6         \n",
      "=================================================================\n",
      "Total params: 401\n",
      "Trainable params: 401\n",
      "Non-trainable params: 0\n",
      "_________________________________________________________________\n"
     ]
    }
   ],
   "source": [
    "def get_model():\n",
    "    model = Sequential([\n",
    "        Dense(10,input_shape=(6,),activation='relu'),\n",
    "        Dense(20, activation ='relu'),\n",
    "         Dense(5, activation ='relu'),\n",
    "        Dense(1) \n",
    "    ])\n",
    "    model.compile(\n",
    "    loss='mse',\n",
    "    optimizer='adam'\n",
    "    )\n",
    "    return model\n",
    "get_model().summary()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Task 6: Model Training"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 6.1: Model Training\n",
    "\n",
    "We can use an `EarlyStopping` callback from Keras to stop the model training if the validation loss stops decreasing for a few epochs."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Train on 4750 samples, validate on 250 samples\n",
      "Epoch 1/100\n",
      "4750/4750 [==============================] - 1s 144us/sample - loss: 0.8533 - val_loss: 0.4833\n",
      "Epoch 2/100\n",
      "4750/4750 [==============================] - 0s 46us/sample - loss: 0.3305 - val_loss: 0.2086\n",
      "Epoch 3/100\n",
      "4750/4750 [==============================] - 0s 51us/sample - loss: 0.1847 - val_loss: 0.1764\n",
      "Epoch 4/100\n",
      "4750/4750 [==============================] - 0s 62us/sample - loss: 0.1694 - val_loss: 0.1678\n",
      "Epoch 5/100\n",
      "4750/4750 [==============================] - 0s 43us/sample - loss: 0.1639 - val_loss: 0.1642\n",
      "Epoch 6/100\n",
      "4750/4750 [==============================] - 0s 43us/sample - loss: 0.1611 - val_loss: 0.1582\n",
      "Epoch 7/100\n",
      "4750/4750 [==============================] - 0s 57us/sample - loss: 0.1596 - val_loss: 0.1582\n",
      "Epoch 8/100\n",
      "4750/4750 [==============================] - 0s 50us/sample - loss: 0.1584 - val_loss: 0.1578\n",
      "Epoch 9/100\n",
      "4750/4750 [==============================] - 0s 43us/sample - loss: 0.1572 - val_loss: 0.1553\n",
      "Epoch 10/100\n",
      "4750/4750 [==============================] - 0s 54us/sample - loss: 0.1568 - val_loss: 0.1544\n",
      "Epoch 11/100\n",
      "4750/4750 [==============================] - 0s 51us/sample - loss: 0.1559 - val_loss: 0.1565\n",
      "Epoch 12/100\n",
      "4750/4750 [==============================] - 0s 42us/sample - loss: 0.1555 - val_loss: 0.1548\n",
      "Epoch 13/100\n",
      "4750/4750 [==============================] - 0s 46us/sample - loss: 0.1546 - val_loss: 0.1512\n",
      "Epoch 14/100\n",
      "4750/4750 [==============================] - 0s 70us/sample - loss: 0.1540 - val_loss: 0.1539\n",
      "Epoch 15/100\n",
      "4750/4750 [==============================] - 0s 49us/sample - loss: 0.1542 - val_loss: 0.1532\n",
      "Epoch 16/100\n",
      "4750/4750 [==============================] - 0s 42us/sample - loss: 0.1536 - val_loss: 0.1509\n",
      "Epoch 17/100\n",
      "4750/4750 [==============================] - 0s 65us/sample - loss: 0.1537 - val_loss: 0.1514\n",
      "Epoch 18/100\n",
      "4750/4750 [==============================] - 0s 49us/sample - loss: 0.1536 - val_loss: 0.1515\n",
      "Epoch 19/100\n",
      "4750/4750 [==============================] - 0s 42us/sample - loss: 0.1519 - val_loss: 0.1571\n",
      "Epoch 20/100\n",
      "4750/4750 [==============================] - 0s 44us/sample - loss: 0.1525 - val_loss: 0.1508\n",
      "Epoch 21/100\n",
      "4750/4750 [==============================] - 0s 42us/sample - loss: 0.1529 - val_loss: 0.1519\n",
      "Epoch 22/100\n",
      "4750/4750 [==============================] - 0s 46us/sample - loss: 0.1523 - val_loss: 0.1499\n",
      "Epoch 23/100\n",
      "4750/4750 [==============================] - 0s 44us/sample - loss: 0.1518 - val_loss: 0.1528\n",
      "Epoch 24/100\n",
      "4750/4750 [==============================] - 0s 43us/sample - loss: 0.1520 - val_loss: 0.1524\n",
      "Epoch 25/100\n",
      "4750/4750 [==============================] - 0s 46us/sample - loss: 0.1515 - val_loss: 0.1502\n",
      "Epoch 26/100\n",
      "4750/4750 [==============================] - 0s 42us/sample - loss: 0.1517 - val_loss: 0.1509\n",
      "Epoch 27/100\n",
      "4750/4750 [==============================] - 0s 45us/sample - loss: 0.1512 - val_loss: 0.1511\n"
     ]
    }
   ],
   "source": [
    "es_cb=EarlyStopping(monitor='val_loss',patience=5)\n",
    "\n",
    "model=get_model()\n",
    "preds_on_untrained=model.predict(x_test)\n",
    "\n",
    "history=model.fit(\n",
    "    x_train,y_train,\n",
    "    validation_data=(x_test,y_test),\n",
    "    epochs=100,\n",
    "    callbacks=[es_cb]\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 6.2: Plot Training and Validation Loss\n",
    "\n",
    "Let's use the `plot_loss` helper function to take a look training and validation loss."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAfUAAAHjCAYAAAA6x4aXAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDMuMC4zLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvnQurowAAIABJREFUeJzt3XuUXFWd9//Pt+59qUogfclVEgkqCQkBIuMlKPMgyE2CyANkDSgg4h0dBx6i4zDID2f5U3+IOOiICjM6AsPogOiAiMg8yDACCSQBEjExBNIkJJ1r37vrsn9/VFWn0qlbd7q66lS/X2vVqqpTp07vrjR8au/zPXubc04AAMD7fNVuAAAAGB+EOgAAdYJQBwCgThDqAADUCUIdAIA6QagDAFAnCHUAAOoEoQ4AQJ0g1AEAqBOBajdgtFpaWtzcuXOr3QwAACbE6tWrdznnWsvZ13OhPnfuXK1atarazQAAYEKY2avl7svwOwAAdYJQBwCgThDqAADUCc+dUwcAFBePx9XR0aGBgYFqNwWjEIlENHv2bAWDwTEfg1AHgDrT0dGhaDSquXPnysyq3RyUwTmn3bt3q6OjQ/PmzRvzcRh+B4A6MzAwoGnTphHoHmJmmjZt2mGPrhDqAFCHCHTvGY9/M0IdAIA6QagDAMbVqaeeqkceeeSgbbfeeqs+9alPFX1fc3OzJGnbtm268MILCx671ARkt956q/r6+oafn3322dq3b185TS/qxhtv1De/+c3DPk4lEeoAgHG1YsUK3XvvvQdtu/fee7VixYqy3j9z5kz97Gc/G/PPHxnqDz30kKZOnTrm43kJ1e8AUMe+8suXtH5b17gec8HMmP7+AwsLvn7hhRfqy1/+sgYHBxUOh7VlyxZt27ZNy5YtU09Pj5YvX669e/cqHo/r5ptv1vLlyw96/5YtW3TuuefqxRdfVH9/v6644gqtX79exx57rPr7+4f3++QnP6lnn31W/f39uvDCC/WVr3xFt912m7Zt26a//Mu/VEtLix5//PHh6cVbWlp0yy236M4775QkXXXVVfr85z+vLVu26KyzztKyZcv01FNPadasWfrFL36hhoaGsj6PfMfs7e3VRRddpI6ODiWTSf3d3/2dLr74Yq1cuVIPPvigAoGAzjjjjHHv+RPqAIBxNW3aNJ188sn69a9/reXLl+vee+/VxRdfLDNTJBLR/fffr1gspl27dukd73iHzjvvvIJFYt/73vfU2NiodevWad26dTrxxBOHX/vqV7+qI488UslkUqeddprWrVuna665Rrfccosef/xxtbS0HHSs1atX66677tLTTz8t55z+4i/+Qu9973t1xBFHaOPGjbrnnnv0gx/8QBdddJF+/vOf69JLLy35uxY65ubNmzVz5kz953/+pyRp//792rNnj+6//3798Y9/lJmNyymBkQh1AKhjxXrUlZQdgs+GerYn65zTl770JT3xxBPy+Xx6/fXXtWPHDk2fPj3vcZ544gldc801kqTFixdr8eLFw6/dd999uuOOO5RIJLR9+3atX7/+oNdHevLJJ/XBD35QTU1NkqQLLrhAv//973Xeeedp3rx5WrJkiSTppJNO0pYtW8r6PQsd88wzz9S1116r66+/Xueee65OOeUUJRIJRSIRXXXVVTrnnHN07rnnlvUzRoNz6gCAcXf++efrscce03PPPaf+/v7hHvZPf/pTdXZ2avXq1VqzZo3a29tLXpudrxf/yiuv6Jvf/KYee+wxrVu3Tuecc07J4zjnCr4WDoeHH/v9fiUSiaLHKnXMt7zlLVq9erUWLVqkL37xi7rpppsUCAT0zDPP6EMf+pAeeOABnXnmmWX9jNEg1AEA4665uVmnnnqqrrzyyoMK5Pbv36+2tjYFg0E9/vjjevXV4quKvuc979FPf/pTSdKLL76odevWSZK6urrU1NSkKVOmaMeOHXr44YeH3xONRtXd3Z33WA888ID6+vrU29ur+++/X6eccsph/Z6Fjrlt2zY1Njbq0ksv1bXXXqvnnntOPT092r9/v84++2zdeuutWrNmzWH97HwYfgcAVMSKFSt0wQUXHFQJ/1d/9Vf6wAc+oKVLl2rJkiV629veVvQYn/zkJ3XFFVdo8eLFWrJkiU4++WRJ0vHHH68TTjhBCxcu1Jvf/Ga9+93vHn7P1VdfrbPOOkszZszQ448/Prz9xBNP1OWXXz58jKuuukonnHBC2UPtknTzzTfr1ltvHX7e0dGR95iPPPKIrrvuOvl8PgWDQX3ve99Td3e3li9froGBATnn9K1vfavsn1suKzYcUYuWLl3qSl2jWLZkQhrskiJTJR+DFgDqw4YNG3TsscdWuxkYg3z/dma22jm3tJz3T+4ke/4n0tfnST1vVLslAAActskd6uFo+n6wp7rtAABgHEzyUI+l7wcPLagAAMBrJnmop+cZ1uD4zrYEAEA1TPJQzwy/DzH8DgDwvskd6qFsT53hdwCA903uUB8+p05PHQDGy+7du7VkyRItWbJE06dP16xZs4afDw0NlXWMK664Qi+//HLRfW6//fbhiWkO17JlyyoyGcxEm9yTz3BOHQDG3bRp04YD8sYbb1Rzc7Ouvfbag/Zxzsk5J1+BOULuuuuukj/n05/+9OE3ts5M7lAPhCV/iOF3APXr4ZXSGy+M7zGnL5LO+tqo37Zp0yadf/75WrZsmZ5++mn96le/0le+8pXh+eEvvvhi3XDDDZLSPed//Md/1HHHHaeWlhZ94hOf0MMPP6zGxkb94he/UFtbm7785S+rpaVFn//857Vs2TItW7ZMv/vd77R//37dddddete73qXe3l59+MMf1qZNm7RgwQJt3LhRP/zhD4cXbymmv79fn/jEJ/Tcc88pGAzq1ltv1Xve8x698MILuvLKKxWPx5VKpfTAAw+otbVVF110kbZt26ZkMqkbb7xRF1544ag/o8M1uYffpXSxHIVyADAh1q9fr49+9KN6/vnnNWvWLH3ta1/TqlWrtHbtWj366KNav379Ie/Zv3+/3vve92rt2rV65zvfObzi20jOOT3zzDP6xje+oZtuukmS9J3vfEfTp0/X2rVrtXLlSj3//PNlt/W2225TKBTSCy+8oJ/85Ce67LLLNDQ0pO9+97u69tprtWbNGj377LOaOXOmHnroIc2dO1dr167Viy++qNNPP31sH9Bhmtw9dSldLEdPHUC9GkOPupKOPvpovf3tbx9+fs899+hHP/qREomEtm3bpvXr12vBggUHvaehoUFnnXWWpPSyqL///e/zHvuCCy4Y3ic7n/uTTz6p66+/XlJ6vviFC8tfivbJJ5/UddddJ0lauHChZs6cqU2bNuld73qXbr75Zr366qu64IILNH/+fC1evFgrV67UypUr9YEPfOCguegnEj31cIxCOQCYINl1xyVp48aN+va3v63f/e53Wrdunc4888y8y6eGQqHhx8WWRc0un5q7z+Gsb1LovZdddpnuv/9+hcNhnX766XriiSd07LHHatWqVVq4cKGuu+46/cM//MOYf+7hINTDUQrlAKAKurq6FI1GFYvFtH37dj3yyCPj/jOWLVum++67T5L0wgsv5B3eLyR32dcNGzZo+/btmj9/vjZv3qz58+frc5/7nM455xytW7dOr7/+upqbm3XZZZfpC1/4gp577rlx/13KwfB7uFnq2VntVgDApHPiiSdqwYIFOu644w5ZPnW8fPazn9WHP/xhLV68WCeeeKKOO+44TZkyJe++73//+xUMBiVJp5xyiu688059/OMf16JFixQMBvXjH/9YoVBId999t+655x4Fg0HNnDlTN998s5566imtXLlSPp9PoVBI//RP/zTuv0s5JvfSq5L0syul7Wulz64ev2MCQBWx9OoBiURCiURCkUhEGzdu1BlnnKGNGzcqEKjNPu3hLr1am7/VRKJQDgDqVk9Pj0477TQlEgk55/T973+/ZgN9PNTvb1aucJRCOQCoU1OnTtXq1ZNnJJZCuXBMivdKqWS1WwIA48Zrp1YxPv9mhHqYRV0A1JdIJKLdu3cT7B7inNPu3bsViUQO6zgMv+cuv9owtbptAYBxMHv2bHV0dKizs7PaTcEoRCIRzZ49+7COQaiz/CqAOhMMBjVv3rxqNwNVwPA7y68CAOoEoZ4dfmdWOQCAxxHqFMoBAOoEoZ5bKAcAgIcR6hTKAQDqBKE+fE6dnjoAwNsqGupmdqaZvWxmm8xsZZ7X32Rmj5vZ82a2zszOrmR78vIHpUADhXIAAM+rWKibmV/S7ZLOkrRA0gozWzBity9Lus85d4KkSyR9t1LtKSrMoi4AAO+rZE/9ZEmbnHObnXNDku6VtHzEPk5S5kJxTZG0rYLtKSwcpVAOAOB5lZxRbpakrTnPOyT9xYh9bpT0GzP7rKQmSe+rYHsKY/lVAEAdqGRP3fJsG7m6wApJ/+ycmy3pbEk/MbND2mRmV5vZKjNbVZG5jMMxCuUAAJ5XyVDvkDQn5/lsHTq8/lFJ90mSc+5/JEUktYw8kHPuDufcUufc0tbW1vFvaThKoRwAwPMqGerPSjrGzOaZWUjpQrgHR+zzmqTTJMnMjlU61Cd+WSEK5QAAdaBioe6cS0j6jKRHJG1Qusr9JTO7yczOy+z2N5I+ZmZrJd0j6XJXjQWAKZQDANSBii696px7SNJDI7bdkPN4vaR3V7INZaFQDgBQB5hRTkoXyiUGpGS82i0BAGDMCHUpZ6pYeusAAO8i1CWWXwUA1AVCXWL5VQBAXSDUJZZfBQDUBUJdShfKScwqBwDwNEJdyimUY1Y5AIB3EeoShXIAgLpAqEsUygEA6gKhLlEoBwCoC4S6JPn8UrCJUAcAeBqhnsVKbQAAjyPUs8JRQh0A4GmEehbLrwIAPI5Qz2L5VQCAxxHqWeEYM8oBADyNUM8KNzOjHADA0wj1LArlAAAeR6hnUSgHAPA4Qj0r1Cwlh6TEYLVbAgDAmBDqWSy/CgDwOEI9a3ilNorlAADeRKhnsVIbAMDjCPWsbKhTAQ8A8ChCPStEqAMAvI1Qz6KnDgDwOEI9a7hQjlAHAHgToZ5FoRwAwOMI9axgkySjpw4A8CxCPcvnY/lVAICnEeq5WNQFAOBhhHquMD11AIB3Eeq5WKkNAOBhhHouht8BAB5GqOeiUA4A4GGEeq5wjKVXAQCeRajnCjez9CoAwLMI9VzZQjnnqt0SAABGjVDPFY5KqYSUGKh2SwAAGDVCPVeIRV0AAN5FqOcKx9L3hDoAwIMI9VwsvwoA8DBCPRfLrwIAPIxQz5UNdXrqAAAPItRzhQh1AIB3Eeq56KkDADyMUM9FoRwAwMMI9VzBRsl8FMoBADypoqFuZmea2ctmtsnMVuZ5/VtmtiZz+5OZ7atke0oyY/lVAIBnBSp1YDPzS7pd0umSOiQ9a2YPOufWZ/dxzv11zv6flXRCpdpTthChDgDwpkr21E+WtMk5t9k5NyTpXknLi+y/QtI9FWxPeeipAwA8qpKhPkvS1pznHZlthzCzoyTNk/S7Aq9fbWarzGxVZ2fnuDf0IOFmQh0A4EmVDHXLs63QmqaXSPqZcy6Z70Xn3B3OuaXOuaWtra3j1sC8ssuvAgDgMZUM9Q5Jc3Kez5a0rcC+l6gWht4lht8BAJ5VyVB/VtIxZjbPzEJKB/eDI3cys7dKOkLS/1SwLeWjUA4A4FEVC3XnXELSZyQ9ImmDpPuccy+Z2U1mdl7Orisk3eucKzQ0P7HCUWmQ4XcAgPdU7JI2SXLOPSTpoRHbbhjx/MZKtmHUws3SULfkXPq6dQAAPIIZ5UYKRyWXkuJ91W4JAACjQqiPxKIuAACPItRHYvlVAIBHEeoj0VMHAHgUoT4Sy68CADyKUB8p21NnVjkAgMcQ6iMx/A4A8ChCfSQK5QAAHkWoj0RPHQDgUYT6SIGw5AsQ6gAAzyHURzJj+VUAgCcR6vmw/CoAwIMI9XxYfhUA4EGEej701AEAHkSo5xNuJtQBAJ5DqOdDoRwAwIMI9XwYfgcAeBChng+FcgAADyLU88kOv6dS1W4JAABlI9TzyS6/ynl1AICHEOr5sPwqAMCDCPV8WNQFAOBBhHo+w8uv0lMHAHgHoZ7PcE+9q7rtAABgFAj1fLKFcgy/AwA8hFDPh0I5AIAHEer5hGPpe3rqAAAPIdTzCTH8DgDwHkI9n0BI8ocJdQCApxDqhbD8KgDAYwj1Qlh+FQDgMYR6ISy/CgDwGEK9EJZfBQB4DKFeCD11AIDHEOqFUCgHAPAYQr0QCuUAAB5DqBcSoqcOAPAWQr2QcEyK90mpZLVbAgBAWQj1QoaXX6W3DgDwBkK9EJZfBQB4DKFeCMuvAgA8hlAvJMTwOwDAWwj1QjinDgDwGEK9EEIdAOAxhHohFMoBADyGUC+EQjkAgMcQ6oVQKAcA8JiKhrqZnWlmL5vZJjNbWWCfi8xsvZm9ZGZ3V7I9o+IPSIEGQh0A4BmBSh3YzPySbpd0uqQOSc+a2YPOufU5+xwj6YuS3u2c22tmbZVqz5iw/CoAwEMq2VM/WdIm59xm59yQpHslLR+xz8ck3e6c2ytJzrmdFWzP6LH8KgDAQyoZ6rMkbc153pHZlustkt5iZv9tZn8wszPzHcjMrjazVWa2qrOzs0LNzYPlVwEAHlLJULc829yI5wFJx0g6VdIKST80s6mHvMm5O5xzS51zS1tbW8e9oQWFGH4HAHhHJUO9Q9KcnOezJW3Ls88vnHNx59wrkl5WOuRrA+fUAQAeUslQf1bSMWY2z8xCki6R9OCIfR6Q9JeSZGYtSg/Hb65gm0aHUAcAeEjFQt05l5D0GUmPSNog6T7n3EtmdpOZnZfZ7RFJu81svaTHJV3nnNtdqTaNGoVyAAAPqdglbZLknHtI0kMjtt2Q89hJ+kLmVnsolAMAeAgzyhUTikqJASkZr3ZLAAAoiVAvhpXaAAAeQqgXQ6gDADyEUC+G5VcBAB5CqBfD8qsAAA8h1Ith+VUAgIcQ6sVwTh0A4CGEejGEOgDAQwj1YiiUAwB4CKFeTCgT6hTKAQA8gFAvxueXgk301AEAnkCol8JKbQAAjyDUSyHUAQAeQaiXwvKrAACPINRLYflVAIBHEOqlhBh+BwB4A6FeCufUAQAeQaiXQqgDADyCUC+FQjkAgEcQ6qWEo1IqLiUGq90SAACKItRLYflVAIBHEOqlsFIbAMAjCPVSCHUAgEcQ6qWEWakNAOANhHop9NQBAB5BqJdCoRwAwCMI9VLoqQMAPIJQL4VQBwB4BKFeSqhJklEoBwCoeYR6KWbM/w4A8ARCvRyhZmmwq9qtAACgKEK9HOGoNMjwOwCgthHq5WD4HQDgAYR6OcLNFMoBAGoeoV4OeuoAAA8g1MsRItQBALWPUC8HPXUAgAcQ6uXIhrpz1W4JAAAFEerlCDdLLiklBqrdEgAACiLUy8H87wAADyDUy8HyqwAADygr1M3saDMLZx6fambXmNnUyjathtBTBwB4QLk99Z9LSprZfEk/kjRP0t0Va1WtIdQBAB5QbqinnHMJSR+UdKtz7q8lzahcs2pMuDl9z6xyAIAaVm6ox81shaSPSPpVZluwMk2qQeFY+p6eOgCghpUb6ldIeqekrzrnXjGzeZL+tXLNqjGhTE+d5VcBADUsUM5Ozrn1kq6RJDM7QlLUOfe1SjaspgyfU2f4HQBQu8qtfv8vM4uZ2ZGS1kq6y8xuKeN9Z5rZy2a2ycxW5nn9cjPrNLM1mdtVo/8VJkCwQTI/w+8AgJpW7vD7FOdcl6QLJN3lnDtJ0vuKvcHM/JJul3SWpAWSVpjZgjy7/ptzbknm9sNRtH3imLH8KgCg5pUb6gEzmyHpIh0olCvlZEmbnHObnXNDku6VtHwMbawN4Rg9dQBATSs31G+S9IikPzvnnjWzN0vaWOI9syRtzXnekdk20ofMbJ2Z/czM5uQ7kJldbWarzGxVZ2dnmU0eZ6FmCuUAADWtrFB3zv27c26xc+6TmeebnXMfKvE2y3eoEc9/KWmuc26xpN9K+pcCP/8O59xS59zS1tbWcpo8/sJRCuUAADWt3EK52WZ2v5ntNLMdZvZzM5td4m0dknJ73rMlbcvdwTm32zk3mHn6A0knldvwCcea6gCAGlfu8Ptdkh6UNFPpIfRfZrYV86ykY8xsnpmFJF2SOcawzHn6rPMkbSizPROPQjkAQI0rN9RbnXN3OecSmds/Syo6Dp6ZVvYzSp+L3yDpPufcS2Z2k5mdl9ntGjN7yczWKn0d/OVj+i0mAj11AECNK2vyGUm7zOxSSfdknq+QtLvUm5xzD0l6aMS2G3Ief1HSF8tsQ3WFCHUAQG0rt6d+pdKXs70habukC5WeOnbyyPbU3chaPwAAakO51e+vOefOc861OufanHPnKz0RzeQRbpbkpKHearcEAIC8yu2p5/OFcWtFlQwlUtq6p0+pVBm97+z87xTLAQBq1OGEer7r0D3lvlVbdcrXH1dnz2DpnVl+FQBQ4w4n1D1/crk9FpEk7egaKL0zy68CAGpc0ep3M+tW/vA2SQ0VadEEao+FJUk7usrpqbP8KgCgthUNdedcdKIaUg2j6qmHsz11ht8BALXpcIbfPW9aU0hm0s6yQp1COQBAbZvUoR7w+9TSHNbObgrlAADeN6lDXUqfV6dQDgBQDwj1aKS8QrlAWPIFKZQDANSsSR/qbbGIdnaX0VM3SxfLMfwOAKhRkz7U22Nh7eoZUjyZKr1zOEqhHACgZhHqmcvaOsstlqOnDgCoUYT68AQ0ZRbLUSgHAKhRkz7U26LZCWjKnFWOQjkAQI0i1DM99c5yiuUolAMA1LBJH+rTmsLy+6z8njqFcgCAGjXpQ93vM7U2lzkBDYVyAIAaNulDXcrMKldO9XuoOd1TT5Vx+RsAABOMUFdmAhoWdQEAeByhrlHM/87yqwCAGkaoKz3/+96+uAYTyeI70lMHANQwQl0HLmvbWaoCnuVXAQA1jFBX+py6pNLrqrP8KgCghhHqSg+/SypdLJcdfmdWOQBADSLUNYr53ymUAwDUMEJd0hGNIQX9Vvpa9ew5dQrlAAA1iFCX5POZ2qKR0j11zqkDAGoYoZ7RFguXrn4PhCR/mHPqAICaRKhntJfTU5cyy69yTh0AUHsI9Yy20cwqR6gDAGoQoZ7RHouoayChgXgZs8pRKAcAqEGEekZbdBSzytFTBwDUIEI9oz0zq9yO7jIq4Al1AEANItQzhkO9nFnlCHUAQA0i1DMOzCpXavidnjoAoDYR6hlTGoIKBXzlzf9OoRwAoAYR6hlmpvZyLmsLx6R4n5RMTEzDAAAoE6GeIz1VbJnLr9JbBwDUGEI9R3ssrJ2lqt+Hl1/lvDoAoLYQ6jnaopEyrlNn+VUAQG0i1HO0xyLqHkyod7DI+fJsT53hdwBAjSHUc2Qva9tZbF317JrqLL8KAKgxhHqOsiagGV5TnZ46AKC2EOo5DkxAUyTUKZQDANQoQj1HW6anXrRYjkI5AECNqmiom9mZZvaymW0ys5VF9rvQzJyZLa1ke0qJhgOKBH0lht8plAMA1KaKhbqZ+SXdLuksSQskrTCzBXn2i0q6RtLTlWpLudKzykWKF8r5A1KwkUI5AEDNqWRP/WRJm5xzm51zQ5LulbQ8z37/j6SvSyox68vEaI9GSk8VG2qmUA4AUHMqGeqzJG3Ned6R2TbMzE6QNMc596tiBzKzq81slZmt6uzsHP+W5miLhYv31CWWXwUA1KRKhrrl2eaGXzTzSfqWpL8pdSDn3B3OuaXOuaWtra3j2MRDtcfSPXXnXOGdWH4VAFCDKhnqHZLm5DyfLWlbzvOopOMk/ZeZbZH0DkkPVrtYrj0WVt9QUj1FZ5WLUSgHAKg5lQz1ZyUdY2bzzCwk6RJJD2ZfdM7td861OOfmOufmSvqDpPOcc6sq2KaSDkxAU+yytiiFcgCAmlOxUHfOJSR9RtIjkjZIus8595KZ3WRm51Xq5x6utmj2WvUSs8pRKAcAqDGBSh7cOfeQpIdGbLuhwL6nVrIt5WrLzipXbAlWCuUAADWIGeVGaC93VjlCHQBQYwj1EZrDATWF/KXPqScHpcTQxDUMAIASCPU82mOREsPvmeVXqYAHANQQQj2Ptli4dKGcxBA8AKCmEOp5pCegKTH8LhHqAICaQqjnUXJWOZZfBQDUIEI9j7ZoWIOJlLr6C8wqxzl1AEANItTzaMvOKleoWG54+J1Z5QAAtYNQz6M9mp6ApuC16sOFcvTUAQC1g1DP48D876V66pxTBwDUDkI9j5JTxXJJGwCgBhHqeTSGAopGAoWH332+dLBTKAcAqCGEegHZy9oKYvlVAECNIdQLaI+Fi4c6y68CAGoMoV5Ae7SMWeU4pw4AqCGEegGtsbA6uweLzypHqAMAagihXkB7NKKhZEr7+uL5dwjHKJQDANQUQr2A9nJmlaNQDgBQQwj1Atqz16oXm1WOQjkAQA0h1Asoa1a5wW6p0Dl3AAAmGKFeQOvw/O+FQr1ZSsWlRJEKeQAAJhChXkAk6NfUxmDh4XeWXwUA1BhCvYj0teosvwoA8AZCvYi2WFg7ull+FQDgDYR6EW3RiDpZfhUA4BGEehHtsbB2dg8qlcpT4R5m+VUAQG0h1Itoj0WUSDnt6Rs69EUK5QAANYZQL+LABDR5huCHz6lTKAcAqA2EehFtmQlodua7rG34nDo9dQBAbSDUiyg6q1yoSZJxTh0AUDMI9SJam4vM/26W7q1zTh0AUCMI9SJCAZ+ObAqxUhsAwBMI9RLaouH859SlzEptDL8DAGoDoV5CeyyinYV66pEpUt+eiW0QAAAFEOoltMfChed/b32rtHM9y68CAGoCoV5Ceyyizu5BJfPNKjfjeKlvt9S1beIbBgDACIR6CW2xiFJO2t2T57z69EXp+zdemNhGAQCQB6FeQnu0yGVt7cdJMumNdRPbKAAA8iDUSyg6AU24WZp2tLR97QS3CgCAQxHqJbRl538vVAE/fTE9dQBATSDUS2hpDsuswPzvUvq8+r7XpP59E9swAABGINRLCPp9mtYULnyt+ozF6XuK5QAAVUaolyF9rXqhnvrx6XuG4AF4u1NUAAAauElEQVQAVUaol6E9Fik8AU1zqxSdIW0n1AEA1UWol6FoT12iWA4AUBMI9TK0RSPa3TuoeDKVf4fpi6TOl6V4gd48AAATgFAvQ3ssIuekXflmlZPSxXIumZ4HHgCAKqloqJvZmWb2spltMrOVeV7/hJm9YGZrzOxJM1tQyfaMVXusyKxyUnr4XWIIHgBQVRULdTPzS7pd0lmSFkhakSe073bOLXLOLZH0dUm3VKo9h6Mtmp5VbmehYrkj5krhGMVyAICqqmRP/WRJm5xzm51zQ5LulbQ8dwfnXFfO0yZJNbmG6XBPvbtAT90sfV6dnjoAoIoqGeqzJG3Ned6R2XYQM/u0mf1Z6Z76NRVsz5hNaw7LZ0V66lJ6CH7HS1IqOXENAwAgRyVD3fJsO6Qn7py73Tl3tKTrJX0574HMrjazVWa2qrOzc5ybWZrfZ2qNhgtfqy6li+XifdLuP09cwwAAyFHJUO+QNCfn+WxJ24rsf6+k8/O94Jy7wzm31Dm3tLW1dRybWL70BDQlrlWXGIIHAFRNJUP9WUnHmNk8MwtJukTSg7k7mNkxOU/PkbSxgu05LG3RIrPKSVLrWyV/iGVYAQBVE6jUgZ1zCTP7jKRHJPkl3emce8nMbpK0yjn3oKTPmNn7JMUl7ZX0kUq153C1x8J67rW9hXfwB6W2Y1nYBQBQNRULdUlyzj0k6aER227Iefy5Sv788dQei2hP75CGEimFAgUGOKYvll5+SHIuXREPAMAEYka5MrVF05e1dRaaVU6SZhwv9e2WuoqVDgAAUBmEepnaY+kJaIqeV6dYDgBQRYR6mdoyE9AUvVa9faEkY2Y5AEBVEOplOtBTLzL8Hm6Wph1NTx0AUBWEepmObAwp4LPiw+8Sa6sDAKqGUC+Tz2dqi4aL99Sl9Mxy+16T+otc/gYAQAUQ6qPQFotoZ3cZPXWJ69UBABOOUB+F9liJ+d8lQh0AUDWE+ii0RSPaWWj51azmVik6gwp4AMCEI9RHoT0W1r6+uAbiJZZXpVgOAFAFhPootGUua+ss1VufsVjqfFmK909AqwAASCPUR6GsWeUkafoiySWlnesnoFUAAKQR6qPQnplVruRlbRTLAQCqgFAfhfZomT31I+ZK4SkUywEAJhShPgpTG4MK+X3aUepadbP0EDzFcgCACUSoj4KZqS0W1s5Sw+9Sulhux0tSqkSlPAAA44RQH6W2aLj0rHJSuqce75N2b6p8owAAEKE+au2xSOlCOYliOQDAhCPURykd6mX01FvfKvnD0va1lW8UAAAi1EetLRZW90BCfUOJ4jv6g1LbsRTLAQAmDKE+StnL2soqlpu+KH1Zm3MVbhUAAIT6qJU9q5wkzThe6t8jdW2rcKsAACDUR214VrlS879LOcVyDMEDACqPUB+l7KIuO8vpqbcvlGTMLAcAmBCE+ijFIgGFA77S66pLUrhZmjafnjoAYEIQ6qNkZuVf1iYdKJYDAKDCCPUxaI+Fyw/1GYul/a9J/Xsr2ygAwKRHqI9BWyxS3iVtEjPLAQAmDKE+Bu3R0Qy/Z0KdIXgAQIUR6mPQHgurdyipnsESs8pJUnOrFJ1BsRwAoOII9TEY1QQ0Urq3Tk8dAFBhhPoYtGUnoBlNsdyuP0nx/gq2CgAw2RHqY9CWmf+9s5xr1aV0T90lpZ3rK9gqAMBkR6iPQftYeuoSQ/AAgIoi1MegORxQY8ivHeVe1jb1KCk8hWI5AEBFEepjMOpZ5czSM8txrToAoIII9TFqi4bLn4BGSg/B73hJSiUr1ygAwKRGqI9ReyyiHd1l9tSldLFcvE/avalyjQIATGqE+hhl5393zpX3humL0vcUywEAKoRQH6P2WEQD8ZS6BsqYVU6SWt8q+cPSG2sr2zAAwKRFqI9RazR9WVtnuUPw/qDUdizFcgCAiiHUx+jAVLGjLJbbvk4qd8geAIBRINTHaNTzv0vpYrn+PVLX6xVqFQBgMiPUx6gtmp1VbhQ9dZZhBQBUEKE+Rk3hgKLhwOh66u0LJRnn1QEAFUGoH4a2WFgde0ex8lq4WZo2n+liAQAVQagfhnfPb9FvN+zQL9duK/9NM1hbHQBQGYT6Yfjbc47VyXOP1N/8+1qt2rKnvDdNXyTtf03qK3N/AADKVNFQN7MzzexlM9tkZivzvP4FM1tvZuvM7DEzO6qS7Rlv4YBf37/sJM2a2qCP/XiVtuzqLf2mbLEc59UBAOOsYqFuZn5Jt0s6S9ICSSvMbMGI3Z6XtNQ5t1jSzyR9vVLtqZQjmkK66/K3S5Ku/Odntbd3qPgbZhyfvifUAQDjrJI99ZMlbXLObXbODUm6V9Ly3B2cc4875/oyT/8gaXYF21Mxc1ua9IMPL1XHvn59/CerNZgoshJbU4sUnUmxHABg3FUy1GdJ2przvCOzrZCPSno43wtmdrWZrTKzVZ2dnePYxPGzdO6R+ub/Pl7PbNmj//OzdcUXeqFYDgBQAZUMdcuzLW/SmdmlkpZK+ka+151zdzjnljrnlra2to5jE8fXecfP1HXvf6t+sWabvvXbjYV3nL5I2vUnKT6Ky+EAACihkqHeIWlOzvPZkg659svM3ifpbyWd55wbxfRstelTpx6ti5fO0W2PbdTPVnfk32n6YsklpR3rJ7ZxAIC6VslQf1bSMWY2z8xCki6R9GDuDmZ2gqTvKx3oOyvYlgljZrr5g8dp2fwWffE/1umpP+86dKcZ2Qp4huABAOOnYqHunEtI+oykRyRtkHSfc+4lM7vJzM7L7PYNSc2S/t3M1pjZgwUO5ylBv0/fvfREzZ3WpI//ZLU27ew+eIepR0nhKYQ6AGBcWdGCrhq0dOlSt2rVqmo3oywde/t0/u1PKRL06f5PvXt4DXZJ0l3nSIkB6WOPVa+BAICaZ2arnXNLy9mXGeUqaPYRjfrRR5ZqV8+gPvbjVRqI51zqNmOxtOMlKVXk8jcAAEaBUK+w4+dM1bcvOUFrO/bpr/9tjVKpzMjI9MVSol/aVaRKHgCAUSDUJ8D7F07X3559rB5+8Q197dd/TG+c/XZJJt1zsfTS/ZLHToMAAGoPoT5BPrpsnj78zqN0xxOb9a9/eFVqmS9d+nMp2Cj9++XSj86QXnu62s0EAHgYoT5BzEw3nLtA/+ttbfr7B1/Sf728U5p/mvSJJ6XzviPte0268wzp3y6Tdv+52s0FAHgQoT6BAn6fvrPiBL1telSf/ulzWr+tS/L5pRM/LF3znHTql6RNj0m3nyw9fL3Uu7vaTQYAeAihPsGawgH96CNvVzQS1JX//Kz+c9129QwmpFCTdOr16XA/4VLpmTuk206Q/vvbUnyg2s0GAHgA16lXyfptXbr8rme0s3tQIb9P7zh6mk5f0K73HdumGVMapJ0bpEdvkDb+RpryJum0G6TjPiT5+B4GAJPJaK5TJ9SrKJFM6bnX9unR9W/o0fU7tGV3ehXaRbOmZAK+Xcf2Pyd79Mvp9ddnniCdcbM0d1mVWw4AmCiEugc55/Tnzh79Zv0O/Xb9Dj2/dZ+ck2ZNbdAZx7ZqRcMfdMyLt8i6tklvPVt631ek1rdUu9kAgAoj1OvAzu4B/W7DTv12ww79fuMuDSZSaomkdEPL/9VZ++5WIDkgO+5D0pveIc1cIrUtlIKRajcbADDOCPU60zeU0JMbd+nR9Tv0uz/ulOvdpc8H/0MXBJ5Ss+uRJKUsoIEjjpFv5gkKv+lE2cwTpPaFUrChyq0HABwOQr2OJVNOz7+2V4+u36HVW/YosXeLpvf+SYt8m7XIXtFxvld0pKWDPimfdjXMU/cRC5WavkSNR52olmOWKtIYrfJvAQAoF6E+yQzEk+rY26fX9vTp1V292rfjFYV2rNMR+9dr9sDLWqBX1GJdkqSkM23xzVZH+C1KTp2rqe1v0ozZczV91lxZdIbU1JK+dh4AUBMIdQxzzqmze0BvdGxW35bVsu1rFd37kqb3vawjU3sO2T8lv+INLfJPmaFAbIYUbZeiM6TmzH32eVMr4Q8AE2A0oR6odGNQXWamtliD2hYslBYsPOi15NCAXnl1s17Z/Ge98foW7d/ZIevZrtbufWrr2ac5Ozeozf5H0eS+/AcPRaXwyFuzFI7l2T5iW6hJCjWn7wMNXH8PAOOAUJ/E/KGI5h+zQPOPWTC8rWcwoXUd+7Rm6z7d/do+Pb91n/b19qpF+zUrsF9Lpw1o8ZRBzY30KJzsVSCRvgXjPQr071UgvlWBRI+C8V4FEj0ylTcSlAg0KuVvUDLYpFSwUalAo1z2PtQkF2xKfwEINkqhJkWaompojMrCzVKwSQo1Dr+Wvm9Mbw+EKvXxAUDNIdRxkOZwQO86ukXvOrpFUnr4ftv+Aa15bZ/WbN2r1Vv36a7N+zWYSJVxNKcGDapZ/Ypav5rVr2brV1R9atKAGm1QjRpQkw2qITGoJg2owdL3jRpQo3Wn7zWoRhtQkwbVaIOj+n2cLyAXbJSFmmXZ4A82SOZPnz4w34H7Q7b5R9xntvvDUiCcPk4gnB5pCISlQCR9WWEgfRu0kLoTAXXFfdoX92vvoF9dSZ8i4YiaGyOKNoQVbWxQtCGkWENIkSCnM+rBYCKpl9/o1guv79cLHfu1s3tQx82aopOOOkInvGmqYpFgtZuIOkaooygz06ypDZo1tUHnLJ4hSYonU9q6p0+pPJ1wszzb8hw35aSUc0qmDtwSKaeUc0ok0/c9KaeuzPYD+yXlhnrV09Wlru4u9fbsV39vlwZ7uzXU36PEQI9CLv1FoCHzZaBxaFBNfYOaGogr5h9Ss39QfnMKKKWAOfktJb9S8svJZ+l7v1LyKSWfS6bvlZK5lHxKSsm4fIkB+VPFv2CEM7eWMj7nIedXv/xKWrolKfPLmV/OF5Tz+SVfQOYLyAJBBUINCoYiCkUa5QtkvmBkb/7c5xHJH8p8yQgdeJ69BbKPw5I/mNmWfTximy9w8D+uc5lbqsQtZ5/M75H+mcFDj+lBuQH+4uv7ta5jv/60o1vxZPo/jikNQbVGw/qvl3cq5dK/7lvbozrxqCN00puO0ElHHaGjpjXKPP45oHYQ6hi1oN+nN7c2V7sZeTnn1NWfUGfPoHZlb92D2to7pOd7BtXZPaR9fUMaTKQ0EE9qIJHUQDylwXhSA4mUhsoagRj+aQorrmkRp/YGqaXBqTWS0rSQ05GRlKYGU5oaSmpKMKmoP6loIKGIxRUfimtwaFCDQ0MaGhrSUHxI8XhcifigEvGEEokhJRMJJRNxpRJDSsUTSiUTMpdQSAmFFVfI9iusXWryJ9XkTyhiCYUtrpCLy++G5EsOytxofpfiUjIl5ZPJyZe5jQfnS39xMH8m7H3BzJeJzBeK3C8Bzklyo7hXzvMMM0mW+aZpI7bl3uvAY/NJwUYlw1O0P9WgN4Yi2toX0OYevzbt92tvqkFdrlEuPEVHT2/Xae+cqbfOmaFFs6dqzpENMjN1D8S1dut+rX51r1a/tle/XLNNdz/9miRpWmNQbz8qqqVzojpxVpMWtEUU8aW/PCoZl1JxKZWUXFJKpTL3SSmVOPDYpXL2yb6W82Vq+LMd8TmP/JJV6LH5yvoCNpRIaWf3gHZ0DWhn16CSzingMwV8Pvn9Nvw4kO+x35e5N/l9prDfr2gkIJ+PLzyjQfU7kCOVcsOBXyj4IwGfjmwKaWpjSFMbgwr6J6bIbyCeVGf3oLbu7VPHnn5t3dunrXv6tHVvv7bu6dPO7oNHDhoCTvOmBDR3akBvmuLXrGZTfGhQ+7t71NXbp+7ePvX29am/v19BxRVUQkElFLL0l4dYMKUjwtKUsNPUoFNDwCnpTAlnSqR00H08pZzH6e1DmW1xZ4onnRLJpEJKKKBk+mdZ+j6gpJoDKTUHnJoCKTUGnBr9SUX8KTX4Ugr7kgopqXRUW+aWHu1xMqUkOXfg3in9JSSVyfWUy6nsOCj4c57nfhnI2W6ZEYnUUK+C8S5F1aeYehWxePF/LPNJkSnpAtFQUzpkk0OZoB6SS8blEkNyySH5XeLw/zgmgPMF5MyvlAWUkk8JCyjhfIpnboMpn4ZSPiXkU1J+JTKLgPpyvgiaUjnPUzlfElPymTvouUlKKPPzfAHJF5TzBWT+oMwflC8Qkj8QlD8YUjAYUiAYUigUViAYks8fTH8JyRlRci4pl0oplUoplUoqlUrJuZRSyfRrqVRKLnNLudSB39UXkLNA+rH5lfJlH6efJ+3Q5wo2asn5nx+3z57qd2CMfD5TQ8ivhlDtnd+OBP2ac2Sj5hzZKB196Ovp+Qr6M6F/IOxf29un/97Wr/39cflMammeorZYm1qPDKvtqIjmx8Jqi4bVGo2oNZp9HB73c/zxZEp7+4a0p3dIe3qGtCfzeHfPkLb2Zp73ZF7vG9Le3iEl8p3jGaWg32Rm8pnkM5Mpfa/s85ztlnme3Sf72tzpjTpu1hQtnjVVi2ZN0ZyYTzbYLQ3sz9z2SYNdOc/3SwOZ5/G+nJ5vuvdr/pAsd0TCH1RvwqetXUm9um9Ir+wZ0ua9cQ0kfYpnTgYlM7eU0sGZkk9J55M/EFAwEFAgEFAwEJQ/EFQoFFQg4JffH9DQ0KD6+gc1MDCggcEBKZlQ0BIKKKGgDnyxCiqpBl9SzSEpGnSKBp0CSqhvcEgDg0NSIpE+ZZWOWgWUVFNQas7cGoNSY0Bq9qe/AEZ8KZllY9yGIzyVeZzKPnaWGQnKbHfp7cmUUyI+pER8SMnE0PDIlYunRzB86jmo7QEl07+TJRWypEwaPv7IY2e/HKZ0cPtyX8v+jsHs72sHHmd/bvbmt4P/TrvUJI1jqI8GoQ7UiUjQr/ltzZrflv/USO9gQpGgX/4qDWcG/T61RSNqi5a3RkH2VMru3sHMF5L0sGzu0K0/Z7g2dyjXn/N65X6hiNTcOm6Ha5L0tsxNSg9lr9/epZ6BhCJBnyLB9JfNhmD6Fgn6FQ74RjU87ZzTQDylff1D2tcX176+uPZnH/fHtb8/ve21zLaUc2qPRTQ9FknfT4moPRZWeyz97xgKVOdSVOec+oaS2tObbufOvvRptT29Q9rbF898IUwp6PcN30J+Uyhw4Hkw4FPY71MwYDn7+BQK+Ib/hg76Mjji3pd5Lf0l0MnnEvK7ZPpeKcWq8skQ6sCk0RT21n/uZqYpjUFNaZyc1eKhgE9L5kwd12OaZUeiGjRjinfXhTAzNYUDagoHNOfIaremtjDjBwAAdYJQBwCgThDqAADUCUIdAIA6QagDAFAnCHUAAOoEoQ4AQJ0g1AEAqBOEOgAAdYJQBwCgThDqAADUCUIdAIA6QagDAFAnCHUAAOoEoQ4AQJ0g1AEAqBOEOgAAdYJQBwCgTphzrtptGBUz65T06jgeskXSrnE83mTB5zY2fG5jw+c2dnx2Y1NLn9tRzrnWcnb0XKiPNzNb5ZxbWu12eA2f29jwuY0Nn9vY8dmNjVc/N4bfAQCoE4Q6AAB1glCX7qh2AzyKz21s+NzGhs9t7PjsxsaTn9ukP6cOAEC9oKcOAECdINQBAKgTkzrUzexMM3vZzDaZ2cpqt8crzGyLmb1gZmvMbFW121OrzOxOM9tpZi/mbDvSzB41s42Z+yOq2cZaVOBzu9HMXs/8za0xs7Or2cZaZGZzzOxxM9tgZi+Z2ecy2/mbK6LI5+bJv7lJe07dzPyS/iTpdEkdkp6VtMI5t76qDfMAM9siaalzrlYmZqhJZvYeST2SfuycOy6z7euS9jjnvpb5InmEc+76araz1hT43G6U1OOc+2Y121bLzGyGpBnOuefMLCpptaTzJV0u/uYKKvK5XSQP/s1N5p76yZI2Oec2O+eGJN0raXmV24Q64px7QtKeEZuXS/qXzON/Ufp/HshR4HNDCc657c655zKPuyVtkDRL/M0VVeRz86TJHOqzJG3Ned4hD/9DTjAn6TdmttrMrq52Yzym3Tm3XUr/z0RSW5Xb4yWfMbN1meF5hpCLMLO5kk6Q9LT4myvbiM9N8uDf3GQOdcuzbXKeixi9dzvnTpR0lqRPZ4ZLgUr6nqSjJS2RtF3S/1fd5tQuM2uW9HNJn3fOdVW7PV6R53Pz5N/cZA71Dklzcp7PlrStSm3xFOfctsz9Tkn3K30qA+XZkTmHlz2Xt7PK7fEE59wO51zSOZeS9APxN5eXmQWVDqafOuf+I7OZv7kS8n1uXv2bm8yh/qykY8xsnpmFJF0i6cEqt6nmmVlTpphEZtYk6QxJLxZ/F3I8KOkjmccfkfSLKrbFM7KhlPFB8Td3CDMzST+StME5d0vOS/zNFVHoc/Pq39ykrX6XpMwlCrdK8ku60zn31So3qeaZ2ZuV7p1LUkDS3Xxu+ZnZPZJOVXoJxx2S/l7SA5Luk/QmSa9J+t/OOYrCchT43E5VehjUSdoi6ePZ88RIM7Nlkn4v6QVJqczmLyl9fpi/uQKKfG4r5MG/uUkd6gAA1JPJPPwOAEBdIdQBAKgThDoAAHWCUAcAoE4Q6gAA1AlCHZgEzCyZs9rUmvFcldDM5uauqAagegLVbgCACdHvnFtS7UYAqCx66sAkZmZbzOz/NbNnMrf5me1HmdljmcUsHjOzN2W2t5vZ/Wa2NnN7V+ZQfjP7QWY96t+YWUNm/2vMbH3mOPdW6dcEJg1CHZgcGkYMv1+c81qXc+5kSf+o9AyLyjz+sXNusaSfSrots/02Sf/XOXe8pBMlvZTZfoyk251zCyXtk/ShzPaVkk7IHOcTlfrlAKQxoxwwCZhZj3OuOc/2LZL+l3Nuc2ZRizecc9PMbJekGc65eGb7dudci5l1SprtnBvMOcZcSY86547JPL9eUtA5d7OZ/VpSj9LT4z7gnOup8K8KTGr01AG4Ao8L7ZPPYM7jpA7U65wj6XZJJ0labWbU8QAVRKgDuDjn/n8yj59SeuVCSforSU9mHj8m6ZOSZGZ+M4sVOqiZ+STNcc49Lun/SJoq6ZDRAgDjh2/NwOTQYGZrcp7/2jmXvawtbGZPK/0lf0Vm2zWS7jSz6yR1Srois/1zku4ws48q3SP/pKRCK1f5Jf2rmU2RZJK+5ZzbN26/EYBDcE4dmMQy59SXOud2VbstAA4fw+8AANQJeuoAANQJeuoAANQJQh0AgDpBqAMAUCcIdQAA6gShDgBAnfj/AWb/aLkEgZnBAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<Figure size 576x576 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plot_loss(history)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Task 7: Predictions"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 7.1: Plot Raw Predictions\n",
    "\n",
    "Let's use the `compare_predictions` helper function to compare predictions from the model when it was untrained and when it was trained."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x576 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "preds_on_trained=model.predict(x_test)\n",
    "compare_predictions(preds_on_untrained,preds_on_trained,y_test)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 7.2: Plot Price Predictions\n",
    "\n",
    "The plot for price predictions and raw predictions will look the same with just one difference: The x and y axis scale is changed."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x576 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "price_untrained=[convert_label_value(y) for y in preds_on_untrained]\n",
    "price_trained=[convert_label_value(y) for y in preds_on_trained]\n",
    "price_test=[convert_label_value(y) for y in y_test]\n",
    "\n",
    "compare_predictions(price_untrained, price_trained, price_test)"
   ]
  },
  {
   "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
}