obesity_prediction.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd \n",
    "import sklearn \n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.metrics import precision_recall_fscore_support\n",
    "from sklearn.metrics import accuracy_score\n",
    "from sklearn.metrics import mean_squared_error\n",
    "from sklearn import metrics\n",
    "import matplotlib.pyplot as plt \n",
    "import seaborn as sns\n",
    "import numpy as np\n",
    "from sklearn.metrics import classification_report\n",
    "from tensorflow import keras\n",
    "from keras.models import Sequential\n",
    "from keras.layers import Dense\n",
    "from sklearn.model_selection import StratifiedKFold\n",
    "\n",
    "\n",
    "pd.options.mode.chained_assignment = None  # default='warn'\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "sns.set(context='talk', style='white', rc={'figure.facecolor':'white'}, font_scale=1)\n",
    "sns.set_style('ticks')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# read in data "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "data based on the UCI diabetes set \n",
    "https://archive.ics.uci.edu/ml/datasets/Estimation+of+obesity+levels+based+on+eating+habits+and+physical+condition+"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "full data attributes described here: \n",
    "https://www.sciencedirect.com/science/article/pii/S2352340919306985?via%3Dihub"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "obesity = pd.read_csv(\"obesity.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "# make outcome binary for this exercise \n",
    "obesity[\"overweight\"] = np.where(obesity.NObeyesdad.str.contains(\"Obesity\") |\n",
    "                                 obesity.NObeyesdad.str.contains(\"Overweight\"), \n",
    "                                 1, 0) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "obesity = obesity.drop(\"NObeyesdad\", axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "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>Gender</th>\n",
       "      <th>Age</th>\n",
       "      <th>Height</th>\n",
       "      <th>Weight</th>\n",
       "      <th>family_history_with_overweight</th>\n",
       "      <th>FAVC</th>\n",
       "      <th>FCVC</th>\n",
       "      <th>NCP</th>\n",
       "      <th>CAEC</th>\n",
       "      <th>SMOKE</th>\n",
       "      <th>CH2O</th>\n",
       "      <th>SCC</th>\n",
       "      <th>FAF</th>\n",
       "      <th>TUE</th>\n",
       "      <th>CALC</th>\n",
       "      <th>MTRANS</th>\n",
       "      <th>overweight</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Female</td>\n",
       "      <td>21.0</td>\n",
       "      <td>1.62</td>\n",
       "      <td>64.0</td>\n",
       "      <td>yes</td>\n",
       "      <td>no</td>\n",
       "      <td>2.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>Sometimes</td>\n",
       "      <td>no</td>\n",
       "      <td>2.0</td>\n",
       "      <td>no</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>no</td>\n",
       "      <td>Public_Transportation</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Female</td>\n",
       "      <td>21.0</td>\n",
       "      <td>1.52</td>\n",
       "      <td>56.0</td>\n",
       "      <td>yes</td>\n",
       "      <td>no</td>\n",
       "      <td>3.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>Sometimes</td>\n",
       "      <td>yes</td>\n",
       "      <td>3.0</td>\n",
       "      <td>yes</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Sometimes</td>\n",
       "      <td>Public_Transportation</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Male</td>\n",
       "      <td>23.0</td>\n",
       "      <td>1.80</td>\n",
       "      <td>77.0</td>\n",
       "      <td>yes</td>\n",
       "      <td>no</td>\n",
       "      <td>2.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>Sometimes</td>\n",
       "      <td>no</td>\n",
       "      <td>2.0</td>\n",
       "      <td>no</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>Frequently</td>\n",
       "      <td>Public_Transportation</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Male</td>\n",
       "      <td>27.0</td>\n",
       "      <td>1.80</td>\n",
       "      <td>87.0</td>\n",
       "      <td>no</td>\n",
       "      <td>no</td>\n",
       "      <td>3.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>Sometimes</td>\n",
       "      <td>no</td>\n",
       "      <td>2.0</td>\n",
       "      <td>no</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Frequently</td>\n",
       "      <td>Walking</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Male</td>\n",
       "      <td>22.0</td>\n",
       "      <td>1.78</td>\n",
       "      <td>89.8</td>\n",
       "      <td>no</td>\n",
       "      <td>no</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>Sometimes</td>\n",
       "      <td>no</td>\n",
       "      <td>2.0</td>\n",
       "      <td>no</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Sometimes</td>\n",
       "      <td>Public_Transportation</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Gender   Age  Height  Weight family_history_with_overweight FAVC  FCVC  \\\n",
       "0  Female  21.0    1.62    64.0                            yes   no   2.0   \n",
       "1  Female  21.0    1.52    56.0                            yes   no   3.0   \n",
       "2    Male  23.0    1.80    77.0                            yes   no   2.0   \n",
       "3    Male  27.0    1.80    87.0                             no   no   3.0   \n",
       "4    Male  22.0    1.78    89.8                             no   no   2.0   \n",
       "\n",
       "   NCP       CAEC SMOKE  CH2O  SCC  FAF  TUE        CALC  \\\n",
       "0  3.0  Sometimes    no   2.0   no  0.0  1.0          no   \n",
       "1  3.0  Sometimes   yes   3.0  yes  3.0  0.0   Sometimes   \n",
       "2  3.0  Sometimes    no   2.0   no  2.0  1.0  Frequently   \n",
       "3  3.0  Sometimes    no   2.0   no  2.0  0.0  Frequently   \n",
       "4  1.0  Sometimes    no   2.0   no  0.0  0.0   Sometimes   \n",
       "\n",
       "                  MTRANS  overweight  \n",
       "0  Public_Transportation           0  \n",
       "1  Public_Transportation           0  \n",
       "2  Public_Transportation           0  \n",
       "3                Walking           1  \n",
       "4  Public_Transportation           1  "
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "obesity.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# data properties\n",
    "make some plots to explore the data attributes and their underlying properties "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.histplot(x=\"Age\", data=obesity, color=\"green\")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# statistics "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# data preparation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "def make_boolean(column): \n",
    "    return column.replace({\"yes\":1, \"no\":0})    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "def make_scale(column): \n",
    "    return column.replace({\"no\":0, \"Sometimes\":1, \"Frequently\":2, \"Always\":3})    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [],
   "source": [
    "# numerical data is best for a ML algorithm. We can start by making the yes/no columns boolean \n",
    "\n",
    "obesity[\"family_history_with_overweight\"] = make_boolean(obesity[\"family_history_with_overweight\"])\n",
    "obesity[\"FAVC\"] = make_boolean(obesity[\"FAVC\"])\n",
    "obesity[\"SMOKE\"] = make_boolean(obesity[\"SMOKE\"])\n",
    "obesity[\"SCC\"] = make_boolean(obesity[\"SCC\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [],
   "source": [
    "# recode sex as boolean too \n",
    "\n",
    "obesity[\"Gender\"] = obesity[\"Gender\"].replace({\"Female\":1, \"Male\":0})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [],
   "source": [
    "# we also have categorical data, that is a scale - \"no\" on one end of the spectrum, \n",
    "# \"always\" on the other end. this data could be coded a few ways, but here I chose \n",
    "# numerically, with \"no\" being 0, and \"always\" being 4 \n",
    "\n",
    "obesity[\"CALC\"] = make_scale(obesity[\"CALC\"])\n",
    "obesity[\"CAEC\"] = make_scale(obesity[\"CAEC\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [],
   "source": [
    "# lastly, we have strictly categorical data. there is no inherent numbering between the methods \n",
    "# of transportation column- \"Public_transportation\" isn't necessarily higher than \"walking\". \n",
    "# so instead, we one hot encode these. This transforms them into numbers that work with the \n",
    "# algorithm, but keeps the inherent lack of relationship between the variables \n",
    "\n",
    "transport = pd.get_dummies(obesity[\"MTRANS\"])\n",
    "obesity = obesity.drop(\"MTRANS\", axis = 1)\n",
    "obesity = obesity.join(transport)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "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>Gender</th>\n",
       "      <th>Age</th>\n",
       "      <th>Height</th>\n",
       "      <th>Weight</th>\n",
       "      <th>family_history_with_overweight</th>\n",
       "      <th>FAVC</th>\n",
       "      <th>FCVC</th>\n",
       "      <th>NCP</th>\n",
       "      <th>CAEC</th>\n",
       "      <th>SMOKE</th>\n",
       "      <th>...</th>\n",
       "      <th>SCC</th>\n",
       "      <th>FAF</th>\n",
       "      <th>TUE</th>\n",
       "      <th>CALC</th>\n",
       "      <th>overweight</th>\n",
       "      <th>Automobile</th>\n",
       "      <th>Bike</th>\n",
       "      <th>Motorbike</th>\n",
       "      <th>Public_Transportation</th>\n",
       "      <th>Walking</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>21.0</td>\n",
       "      <td>1.62</td>\n",
       "      <td>64.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>21.0</td>\n",
       "      <td>1.52</td>\n",
       "      <td>56.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "      <td>23.0</td>\n",
       "      <td>1.80</td>\n",
       "      <td>77.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0</td>\n",
       "      <td>27.0</td>\n",
       "      <td>1.80</td>\n",
       "      <td>87.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>22.0</td>\n",
       "      <td>1.78</td>\n",
       "      <td>89.8</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 21 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   Gender   Age  Height  Weight  family_history_with_overweight  FAVC  FCVC  \\\n",
       "0       1  21.0    1.62    64.0                               1     0   2.0   \n",
       "1       1  21.0    1.52    56.0                               1     0   3.0   \n",
       "2       0  23.0    1.80    77.0                               1     0   2.0   \n",
       "3       0  27.0    1.80    87.0                               0     0   3.0   \n",
       "4       0  22.0    1.78    89.8                               0     0   2.0   \n",
       "\n",
       "   NCP  CAEC  SMOKE  ...  SCC  FAF  TUE  CALC  overweight  Automobile  Bike  \\\n",
       "0  3.0     1      0  ...    0  0.0  1.0     0           0           0     0   \n",
       "1  3.0     1      1  ...    1  3.0  0.0     1           0           0     0   \n",
       "2  3.0     1      0  ...    0  2.0  1.0     2           0           0     0   \n",
       "3  3.0     1      0  ...    0  2.0  0.0     2           1           0     0   \n",
       "4  1.0     1      0  ...    0  0.0  0.0     1           1           0     0   \n",
       "\n",
       "   Motorbike  Public_Transportation  Walking  \n",
       "0          0                      1        0  \n",
       "1          0                      1        0  \n",
       "2          0                      1        0  \n",
       "3          0                      0        1  \n",
       "4          0                      1        0  \n",
       "\n",
       "[5 rows x 21 columns]"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "obesity.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# logistic regression\n",
    "use a logistic regression model to use whatever combination of attributes you'd like to predict whether the individual is overweight (use \"overweight\" column as output) "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### test/train split "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### define model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### fit model "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### test model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### evaluate model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# neural network "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "metadata": {},
   "outputs": [],
   "source": [
    "# here we are separating our data into outcome and input variables \n",
    "\n",
    "Y = obesity[[\"overweight\"]].values\n",
    "X = obesity.drop(\"overweight\", axis=1).values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "metadata": {},
   "outputs": [],
   "source": [
    "x_train, x_test, y_train, y_test = train_test_split(X, Y, test_size=0.25)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 78,
   "metadata": {},
   "outputs": [],
   "source": [
    "# create a simple neural network with 2 8-node layers (\"dense\" means a \"normal\" NN layer)\n",
    "# and one output layer, that gives our one dimensional output. \n",
    "# the \"sigmoid\" function gives us an output that is between 0/1, which is consistent with \n",
    "# our binary classification task \n",
    "\n",
    "model = Sequential()\n",
    "model.add(Dense(8, input_dim=x_train.shape[1], activation='relu'))\n",
    "model.add(Dense(8, activation='relu'))\n",
    "model.add(Dense(1, activation='sigmoid'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 79,
   "metadata": {},
   "outputs": [],
   "source": [
    "# this defines more parameters about how the model is trained. \n",
    "# we ust a binary cross entropy loss function because we have a binary classification task \n",
    "\n",
    "model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### model training "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 80,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/10\n",
      "127/127 [==============================] - 2s 9ms/step - loss: 2.3135 - accuracy: 0.7313 - val_loss: 0.4972 - val_accuracy: 0.7098\n",
      "Epoch 2/10\n",
      "127/127 [==============================] - 0s 3ms/step - loss: 0.4334 - accuracy: 0.7506 - val_loss: 0.3802 - val_accuracy: 0.8233\n",
      "Epoch 3/10\n",
      "127/127 [==============================] - 1s 4ms/step - loss: 0.3696 - accuracy: 0.8101 - val_loss: 0.3617 - val_accuracy: 0.8328\n",
      "Epoch 4/10\n",
      "127/127 [==============================] - 0s 2ms/step - loss: 0.3283 - accuracy: 0.8497 - val_loss: 0.2947 - val_accuracy: 0.8959\n",
      "Epoch 5/10\n",
      "127/127 [==============================] - 0s 1ms/step - loss: 0.2720 - accuracy: 0.9018 - val_loss: 0.2470 - val_accuracy: 0.9117\n",
      "Epoch 6/10\n",
      "127/127 [==============================] - 0s 2ms/step - loss: 0.2189 - accuracy: 0.9300 - val_loss: 0.2220 - val_accuracy: 0.9211\n",
      "Epoch 7/10\n",
      "127/127 [==============================] - 0s 2ms/step - loss: 0.2109 - accuracy: 0.9133 - val_loss: 0.2052 - val_accuracy: 0.9338\n",
      "Epoch 8/10\n",
      "127/127 [==============================] - 0s 2ms/step - loss: 0.1794 - accuracy: 0.9383 - val_loss: 0.1935 - val_accuracy: 0.9338\n",
      "Epoch 9/10\n",
      "127/127 [==============================] - 0s 2ms/step - loss: 0.1806 - accuracy: 0.9313 - val_loss: 0.1844 - val_accuracy: 0.9369\n",
      "Epoch 10/10\n",
      "127/127 [==============================] - 0s 2ms/step - loss: 0.1609 - accuracy: 0.9386 - val_loss: 0.1776 - val_accuracy: 0.9306\n"
     ]
    }
   ],
   "source": [
    "# we train the data in \"epochs\"- the more epochs, the more the data is run though the NN \n",
    "# for something simple like this, 15 epochs is fine, but in the future we might want to fit more \n",
    "\n",
    "history = model.fit(x_train, y_train, epochs=10,  validation_split=0.2, batch_size=10, verbose=1)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### assessing model training"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 81,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# we can assess how well the model /training/ step is doing (so not testing yet) by looking at how \n",
    "# accurate the model is on our training set. The ideal is for this to be as close to one as possible\n",
    "# if it's not at one, we might want more layers, more epochs, or to revisit how our model is defined\n",
    "\n",
    "plt.plot(history.history[\"accuracy\"], label=\"train\")\n",
    "plt.plot(history.history[\"val_accuracy\"], label=\"validation\")\n",
    "plt.title(\"model accuracy\")\n",
    "plt.ylabel(\"accuracy\")\n",
    "plt.xlabel(\"epoch\")\n",
    "plt.legend([\"train\", \"validation\"], loc='upper left')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 85,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# here we are also evaluating the training, looking at the loss function. a NN tries to minimize \n",
    "# the loss, so we want this number to be as close to 0 as possible \n",
    "\n",
    "plt.plot(history.history[\"loss\"], label=\"train\")\n",
    "plt.plot(history.history[\"val_loss\"], label=\"validation\")\n",
    "plt.title(\"model loss\")\n",
    "plt.ylabel(\"loss\")\n",
    "plt.xlabel(\"epoch\")\n",
    "plt.legend([\"train\"], loc='upper left')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### evaluating the model "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 86,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[0.1684906929731369, 0.935606062412262]"
      ]
     },
     "execution_count": 86,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# here we are finally seeing how well the model does on our test set in terms of \n",
    "# average loss (first number) and average accuracy (second number)\n",
    "score = model.evaluate(x_test, y_test, verbose=0)\n",
    "score"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 87,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[1. ],\n",
       "       [1. ],\n",
       "       [0.1],\n",
       "       [0.6],\n",
       "       [0.9],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.1],\n",
       "       [1. ],\n",
       "       [0.6],\n",
       "       [0.8],\n",
       "       [1. ],\n",
       "       [0.2],\n",
       "       [0.9],\n",
       "       [0. ],\n",
       "       [1. ],\n",
       "       [0.1],\n",
       "       [0.1],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.2],\n",
       "       [0.8],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.2],\n",
       "       [0.9],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.5],\n",
       "       [1. ],\n",
       "       [0.9],\n",
       "       [0.2],\n",
       "       [0.9],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.8],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.1],\n",
       "       [0.7],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.2],\n",
       "       [0.9],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.1],\n",
       "       [1. ],\n",
       "       [0.9],\n",
       "       [0.7],\n",
       "       [0.1],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.2],\n",
       "       [1. ],\n",
       "       [0.9],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.9],\n",
       "       [1. ],\n",
       "       [0.1],\n",
       "       [0.1],\n",
       "       [0.1],\n",
       "       [0.9],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.2],\n",
       "       [0.2],\n",
       "       [0.9],\n",
       "       [0.9],\n",
       "       [0.2],\n",
       "       [1. ],\n",
       "       [0.9],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.7],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.5],\n",
       "       [0. ],\n",
       "       [0.3],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.1],\n",
       "       [1. ],\n",
       "       [0.9],\n",
       "       [1. ],\n",
       "       [0.9],\n",
       "       [0.9],\n",
       "       [0.4],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.2],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.8],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.6],\n",
       "       [0.5],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.9],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.9],\n",
       "       [0.2],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.8],\n",
       "       [0.5],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.9],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0. ],\n",
       "       [0.9],\n",
       "       [0.1],\n",
       "       [0.3],\n",
       "       [0.9],\n",
       "       [1. ],\n",
       "       [0.1],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.8],\n",
       "       [0.9],\n",
       "       [0.8],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.7],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.9],\n",
       "       [1. ],\n",
       "       [0.9],\n",
       "       [0.9],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.1],\n",
       "       [0.5],\n",
       "       [1. ],\n",
       "       [0. ],\n",
       "       [1. ],\n",
       "       [0. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.4],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.9],\n",
       "       [0.9],\n",
       "       [1. ],\n",
       "       [0. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0. ],\n",
       "       [0.7],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.8],\n",
       "       [0.9],\n",
       "       [0.9],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.1],\n",
       "       [0.3],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0. ],\n",
       "       [0.1],\n",
       "       [0.8],\n",
       "       [1. ],\n",
       "       [0.1],\n",
       "       [1. ],\n",
       "       [0.7],\n",
       "       [0.8],\n",
       "       [0.9],\n",
       "       [1. ],\n",
       "       [0. ],\n",
       "       [0.9],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.1],\n",
       "       [0.6],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.7],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.1],\n",
       "       [1. ],\n",
       "       [0.5],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.1],\n",
       "       [1. ],\n",
       "       [0.9],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.2],\n",
       "       [0.9],\n",
       "       [0.1],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.7],\n",
       "       [1. ],\n",
       "       [0.7],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.9],\n",
       "       [0.9],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.8],\n",
       "       [0.9],\n",
       "       [1. ],\n",
       "       [0.9],\n",
       "       [0.1],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.9],\n",
       "       [0. ],\n",
       "       [1. ],\n",
       "       [0.1],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.9],\n",
       "       [0.9],\n",
       "       [0.1],\n",
       "       [0. ],\n",
       "       [0.1],\n",
       "       [0.9],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.1],\n",
       "       [1. ],\n",
       "       [0.9],\n",
       "       [0.9],\n",
       "       [0. ],\n",
       "       [1. ],\n",
       "       [0.9],\n",
       "       [0.2],\n",
       "       [0.5],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.9],\n",
       "       [0. ],\n",
       "       [0.6],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.4],\n",
       "       [0.2],\n",
       "       [0.9],\n",
       "       [0. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0. ],\n",
       "       [1. ],\n",
       "       [0.5],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.9],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.1],\n",
       "       [1. ],\n",
       "       [0.7],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.1],\n",
       "       [1. ],\n",
       "       [0.5],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.4],\n",
       "       [1. ],\n",
       "       [0.2],\n",
       "       [0.1],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.9],\n",
       "       [1. ],\n",
       "       [0.8],\n",
       "       [0.9],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.7],\n",
       "       [1. ],\n",
       "       [0.3],\n",
       "       [0.7],\n",
       "       [0.9],\n",
       "       [0.2],\n",
       "       [0.3],\n",
       "       [0.2],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0. ],\n",
       "       [0.9],\n",
       "       [0.1],\n",
       "       [0.9],\n",
       "       [1. ],\n",
       "       [0.9],\n",
       "       [0.1],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.7],\n",
       "       [1. ],\n",
       "       [0.7],\n",
       "       [1. ],\n",
       "       [0.4],\n",
       "       [1. ],\n",
       "       [0. ],\n",
       "       [0.8],\n",
       "       [1. ],\n",
       "       [0.6],\n",
       "       [1. ],\n",
       "       [0.4],\n",
       "       [0.2],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0. ],\n",
       "       [0. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.1],\n",
       "       [0.5],\n",
       "       [1. ],\n",
       "       [0.1],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.9],\n",
       "       [1. ],\n",
       "       [0.2],\n",
       "       [0. ],\n",
       "       [1. ],\n",
       "       [0.9],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.6],\n",
       "       [1. ],\n",
       "       [0. ],\n",
       "       [1. ],\n",
       "       [0.1],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.9],\n",
       "       [1. ],\n",
       "       [0.9],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0. ],\n",
       "       [0.8],\n",
       "       [0. ],\n",
       "       [1. ],\n",
       "       [0.2],\n",
       "       [0.3],\n",
       "       [0.1],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0. ],\n",
       "       [0.9],\n",
       "       [0. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.3],\n",
       "       [1. ],\n",
       "       [0. ],\n",
       "       [1. ],\n",
       "       [0.9],\n",
       "       [0.3],\n",
       "       [1. ],\n",
       "       [0.1],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.2],\n",
       "       [0.7],\n",
       "       [1. ],\n",
       "       [0.8],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0. ],\n",
       "       [1. ],\n",
       "       [0. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.1],\n",
       "       [1. ],\n",
       "       [0.6],\n",
       "       [1. ],\n",
       "       [0.9],\n",
       "       [1. ],\n",
       "       [0. ],\n",
       "       [0.9],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.7],\n",
       "       [0.5],\n",
       "       [1. ],\n",
       "       [0.1],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.2],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.5],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.1],\n",
       "       [1. ],\n",
       "       [0.5],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.1],\n",
       "       [0.9],\n",
       "       [0. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.7],\n",
       "       [0.7],\n",
       "       [0.1],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.9],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.4],\n",
       "       [0.1],\n",
       "       [0.1],\n",
       "       [0.8],\n",
       "       [0. ],\n",
       "       [0. ],\n",
       "       [0.9],\n",
       "       [0.1],\n",
       "       [0.6],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.7],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.1],\n",
       "       [0.9],\n",
       "       [1. ],\n",
       "       [0.4],\n",
       "       [0.4],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.8],\n",
       "       [1. ],\n",
       "       [1. ],\n",
       "       [0.5],\n",
       "       [1. ]], dtype=float32)"
      ]
     },
     "execution_count": 87,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# here we can see the predictions \n",
    "# the predictions are probabilities that an individual is overeight or not \n",
    "# less than 0.5 is not overweight, greater or equal is overweight \n",
    "predictions = model.predict(x_test)\n",
    "predictions.round(1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 171,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [1.]], dtype=float32)"
      ]
     },
     "execution_count": 171,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# this numpy function makes everything the classic 0/1 that we expect \n",
    "np.rint(predictions)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 89,
   "metadata": {},
   "outputs": [],
   "source": [
    "# a confusion matrix can help us visualize where the model is misclassifying individuals \n",
    "confusion_matrix = sklearn.metrics.confusion_matrix(y_test, np.rint(predictions))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 90,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.heatmap(confusion_matrix, annot=True, cmap=\"YlGnBu\")\n",
    "plt.xlabel(\"model prediction\")\n",
    "plt.ylabel(\"truth\")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# neural network cross validation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 91,
   "metadata": {},
   "outputs": [],
   "source": [
    "# here we are separating our data into outcome and input variables \n",
    "\n",
    "Y = obesity[[\"overweight\"]].values\n",
    "X = obesity.drop(\"overweight\", axis=1).values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 92,
   "metadata": {},
   "outputs": [],
   "source": [
    "input_dim = X.shape[-1]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 93,
   "metadata": {},
   "outputs": [],
   "source": [
    "kfold = StratifiedKFold(n_splits=10, shuffle=True, random_state=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 94,
   "metadata": {},
   "outputs": [
    {
     "ename": "KeyboardInterrupt",
     "evalue": "",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
      "\u001b[0;32m/var/folders/4x/lcz5fxn94d55vvrj7fv94vs40000gn/T/ipykernel_71198/3253227511.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m     11\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     12\u001b[0m     \u001b[0;31m# Fit the model\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 13\u001b[0;31m     \u001b[0mmodel\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfit\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mX\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mtrain\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mY\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mtrain\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mepochs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m150\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mbatch_size\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m10\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mverbose\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     14\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     15\u001b[0m     \u001b[0;31m# evaluate the model\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/miniconda3/envs/ml/lib/python3.9/site-packages/tensorflow/python/keras/engine/training.py\u001b[0m in \u001b[0;36mfit\u001b[0;34m(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_batch_size, validation_freq, max_queue_size, workers, use_multiprocessing)\u001b[0m\n\u001b[1;32m   1093\u001b[0m                 _r=1):\n\u001b[1;32m   1094\u001b[0m               \u001b[0mcallbacks\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mon_train_batch_begin\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mstep\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1095\u001b[0;31m               \u001b[0mtmp_logs\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtrain_function\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0miterator\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1096\u001b[0m               \u001b[0;32mif\u001b[0m \u001b[0mdata_handler\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mshould_sync\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1097\u001b[0m                 \u001b[0mcontext\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0masync_wait\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/miniconda3/envs/ml/lib/python3.9/site-packages/tensorflow/python/eager/def_function.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, *args, **kwds)\u001b[0m\n\u001b[1;32m    826\u001b[0m     \u001b[0mtracing_count\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mexperimental_get_tracing_count\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    827\u001b[0m     \u001b[0;32mwith\u001b[0m \u001b[0mtrace\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mTrace\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_name\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mtm\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 828\u001b[0;31m       \u001b[0mresult\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_call\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwds\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    829\u001b[0m       \u001b[0mcompiler\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m\"xla\"\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_experimental_compile\u001b[0m \u001b[0;32melse\u001b[0m \u001b[0;34m\"nonXla\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    830\u001b[0m       \u001b[0mnew_tracing_count\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mexperimental_get_tracing_count\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/miniconda3/envs/ml/lib/python3.9/site-packages/tensorflow/python/eager/def_function.py\u001b[0m in \u001b[0;36m_call\u001b[0;34m(self, *args, **kwds)\u001b[0m\n\u001b[1;32m    853\u001b[0m       \u001b[0;31m# In this case we have created variables on the first call, so we run the\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    854\u001b[0m       \u001b[0;31m# defunned version which is guaranteed to never create variables.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 855\u001b[0;31m       \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_stateless_fn\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwds\u001b[0m\u001b[0;34m)\u001b[0m  \u001b[0;31m# pylint: disable=not-callable\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    856\u001b[0m     \u001b[0;32melif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_stateful_fn\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    857\u001b[0m       \u001b[0;31m# Release the lock early so that multiple threads can perform the call\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/miniconda3/envs/ml/lib/python3.9/site-packages/tensorflow/python/eager/function.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   2940\u001b[0m       (graph_function,\n\u001b[1;32m   2941\u001b[0m        filtered_flat_args) = self._maybe_define_function(args, kwargs)\n\u001b[0;32m-> 2942\u001b[0;31m     return graph_function._call_flat(\n\u001b[0m\u001b[1;32m   2943\u001b[0m         filtered_flat_args, captured_inputs=graph_function.captured_inputs)  # pylint: disable=protected-access\n\u001b[1;32m   2944\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/miniconda3/envs/ml/lib/python3.9/site-packages/tensorflow/python/eager/function.py\u001b[0m in \u001b[0;36m_call_flat\u001b[0;34m(self, args, captured_inputs, cancellation_manager)\u001b[0m\n\u001b[1;32m   1916\u001b[0m         and executing_eagerly):\n\u001b[1;32m   1917\u001b[0m       \u001b[0;31m# No tape is watching; skip to running the function.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1918\u001b[0;31m       return self._build_call_outputs(self._inference_function.call(\n\u001b[0m\u001b[1;32m   1919\u001b[0m           ctx, args, cancellation_manager=cancellation_manager))\n\u001b[1;32m   1920\u001b[0m     forward_backward = self._select_forward_and_backward_functions(\n",
      "\u001b[0;32m~/miniconda3/envs/ml/lib/python3.9/site-packages/tensorflow/python/eager/function.py\u001b[0m in \u001b[0;36mcall\u001b[0;34m(self, ctx, args, cancellation_manager)\u001b[0m\n\u001b[1;32m    553\u001b[0m       \u001b[0;32mwith\u001b[0m \u001b[0m_InterpolateFunctionError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    554\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mcancellation_manager\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 555\u001b[0;31m           outputs = execute.execute(\n\u001b[0m\u001b[1;32m    556\u001b[0m               \u001b[0mstr\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msignature\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mname\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    557\u001b[0m               \u001b[0mnum_outputs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_num_outputs\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/miniconda3/envs/ml/lib/python3.9/site-packages/tensorflow/python/eager/execute.py\u001b[0m in \u001b[0;36mquick_execute\u001b[0;34m(op_name, num_outputs, inputs, attrs, ctx, name)\u001b[0m\n\u001b[1;32m     57\u001b[0m   \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     58\u001b[0m     \u001b[0mctx\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mensure_initialized\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 59\u001b[0;31m     tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name,\n\u001b[0m\u001b[1;32m     60\u001b[0m                                         inputs, attrs, num_outputs)\n\u001b[1;32m     61\u001b[0m   \u001b[0;32mexcept\u001b[0m \u001b[0mcore\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_NotOkStatusException\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
     ]
    }
   ],
   "source": [
    "cvscores = []\n",
    "for train, test in kfold.split(X, Y):\n",
    "    # create model\n",
    "    model = Sequential()\n",
    "    model.add(Dense(8, input_dim=input_dim, activation='relu'))\n",
    "    model.add(Dense(8, activation='relu'))\n",
    "    model.add(Dense(1, activation='sigmoid'))\n",
    "    \n",
    "    # Compile model\n",
    "    model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])\n",
    "    \n",
    "    # Fit the model\n",
    "    model.fit(X[train], Y[train], epochs=150, batch_size=10, verbose=0)\n",
    "    \n",
    "    # evaluate the model\n",
    "    scores = model.evaluate(X[test], Y[test], verbose=0)\n",
    "    cvscores.append(scores[1] * 100)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "96.44720256328583"
      ]
     },
     "execution_count": 57,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.array(cvscores).mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.9.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}