{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import os\n",
    "import sklearn\n",
    "import sklearn.model_selection\n",
    "from sklearn import metrics, preprocessing\n",
    "import pickle\n",
    "import math\n",
    "import tensorflow as tf\n",
    "from os import path, getcwd, chdir"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create dataframes from our csv files and set indeces\n",
    "\n",
    "df = pd.read_csv('data/train.csv')\n",
    "df.set_index('PassengerId', inplace=True)\n",
    "\n",
    "testdf = pd.read_csv('data/test.csv')\n",
    "PassengerId = testdf['PassengerId']\n",
    "testdf.set_index('PassengerId', inplace=True)\n",
    "\n",
    "data = [df, testdf]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<bound method NDFrame.head of              Survived  Pclass  \\\n",
      "PassengerId                     \n",
      "1                   0       3   \n",
      "2                   1       1   \n",
      "3                   1       3   \n",
      "4                   1       1   \n",
      "5                   0       3   \n",
      "...               ...     ...   \n",
      "887                 0       2   \n",
      "888                 1       1   \n",
      "889                 0       3   \n",
      "890                 1       1   \n",
      "891                 0       3   \n",
      "\n",
      "                                                          Name  Sex  \\\n",
      "PassengerId                                                           \n",
      "1                                      Braund, Mr. Owen Harris    1   \n",
      "2            Cumings, Mrs. John Bradley (Florence Briggs Th...    0   \n",
      "3                                       Heikkinen, Miss. Laina    0   \n",
      "4                 Futrelle, Mrs. Jacques Heath (Lily May Peel)    0   \n",
      "5                                     Allen, Mr. William Henry    1   \n",
      "...                                                        ...  ...   \n",
      "887                                      Montvila, Rev. Juozas    1   \n",
      "888                               Graham, Miss. Margaret Edith    0   \n",
      "889                   Johnston, Miss. Catherine Helen \"Carrie\"    0   \n",
      "890                                      Behr, Mr. Karl Howell    1   \n",
      "891                                        Dooley, Mr. Patrick    1   \n",
      "\n",
      "                   Age  SibSp  Parch            Ticket     Fare  Cabin  \\\n",
      "PassengerId                                                              \n",
      "1            22.000000      1      0         A/5 21171   7.2500    147   \n",
      "2            38.000000      1      0          PC 17599  71.2833     81   \n",
      "3            26.000000      0      0  STON/O2. 3101282   7.9250    147   \n",
      "4            35.000000      1      0            113803  53.1000     55   \n",
      "5            35.000000      0      0            373450   8.0500    147   \n",
      "...                ...    ...    ...               ...      ...    ...   \n",
      "887          27.000000      0      0            211536  13.0000    147   \n",
      "888          19.000000      0      0            112053  30.0000     30   \n",
      "889          29.699118      1      2        W./C. 6607  23.4500    147   \n",
      "890          26.000000      0      0            111369  30.0000     60   \n",
      "891          32.000000      0      0            370376   7.7500    147   \n",
      "\n",
      "             Embarked  \n",
      "PassengerId            \n",
      "1                   2  \n",
      "2                   0  \n",
      "3                   2  \n",
      "4                   2  \n",
      "5                   2  \n",
      "...               ...  \n",
      "887                 2  \n",
      "888                 2  \n",
      "889                 2  \n",
      "890                 0  \n",
      "891                 1  \n",
      "\n",
      "[891 rows x 11 columns]>\n"
     ]
    }
   ],
   "source": [
    "# Preprocess the data by converting non numerical features into numerical categorical features \n",
    "# and applying mean imputation to deal with NaN values\n",
    "\n",
    "for dataframe in data:\n",
    "    le = preprocessing.LabelEncoder()\n",
    "    dataframe[\"Sex\"] = le.fit_transform(list(dataframe[\"Sex\"]))\n",
    "    dataframe[\"Cabin\"] = le.fit_transform(list(dataframe[\"Cabin\"]))\n",
    "    dataframe[\"Embarked\"] = le.fit_transform(list(dataframe[\"Embarked\"]))\n",
    "    dataframe.fillna(dataframe.mean(), inplace=True)\n",
    "    \n",
    "print(df.head)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<bound method NDFrame.head of              Pclass  Sex        Age  SibSp  Parch     Fare  Cabin  Embarked\n",
      "PassengerId                                                                \n",
      "1                 3    1  22.000000      1      0   7.2500    147         2\n",
      "2                 1    0  38.000000      1      0  71.2833     81         0\n",
      "3                 3    0  26.000000      0      0   7.9250    147         2\n",
      "4                 1    0  35.000000      1      0  53.1000     55         2\n",
      "5                 3    1  35.000000      0      0   8.0500    147         2\n",
      "...             ...  ...        ...    ...    ...      ...    ...       ...\n",
      "887               2    1  27.000000      0      0  13.0000    147         2\n",
      "888               1    0  19.000000      0      0  30.0000     30         2\n",
      "889               3    0  29.699118      1      2  23.4500    147         2\n",
      "890               1    1  26.000000      0      0  30.0000     60         0\n",
      "891               3    1  32.000000      0      0   7.7500    147         1\n",
      "\n",
      "[891 rows x 8 columns]>\n"
     ]
    }
   ],
   "source": [
    "# Create our input matrix, label vector, and test input matrix\n",
    "\n",
    "X = df.drop(['Name', 'Survived', 'Ticket'], axis=1)\n",
    "y = df['Survived']\n",
    "X_test = testdf.drop(['Name', 'Ticket'], axis=1)\n",
    "print(X.head)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Normalize the data\n",
    "\n",
    "X=(X-X.mean())/X.std()\n",
    "X_test=(X_test-X_test.mean())/X_test.std()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Setup our data to be fed into our model\n",
    "\n",
    "dataset = tf.data.Dataset.from_tensor_slices((X.values, y.values))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "WARNING:tensorflow:Layer sequential_2 is casting an input tensor from dtype float64 to the layer's dtype of float32, which is new behavior in TensorFlow 2.  The layer has dtype float32 because it's dtype defaults to floatx.\n",
      "\n",
      "If you intended to run this layer in float32, you can safely ignore this warning. If in doubt, this warning is likely only an issue if you are porting a TensorFlow 1.X model to TensorFlow 2.\n",
      "\n",
      "To change all layers to have dtype float64 by default, call `tf.keras.backend.set_floatx('float64')`. To change just this layer, pass dtype='float64' to the layer constructor. If you are the author of this layer, you can disable autocasting by passing autocast=False to the base Layer constructor.\n",
      "\n",
      "Epoch 1/10\n",
      "      1/Unknown - 0s 186ms/step"
     ]
    },
    {
     "ename": "ValueError",
     "evalue": "Shape mismatch: The shape of labels (received (1,)) should equal the shape of logits except for the last dimension (received (8, 2)).",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mValueError\u001b[0m                                Traceback (most recent call last)",
      "\u001b[1;32m<ipython-input-10-9ade9a378180>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[0;32m     21\u001b[0m     \u001b[0mdataset\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     22\u001b[0m     \u001b[0mepochs\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;36m10\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 23\u001b[1;33m     \u001b[0mshuffle\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mTrue\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     24\u001b[0m )\n",
      "\u001b[1;32mc:\\users\\tsb\\appdata\\local\\programs\\python\\python37\\lib\\site-packages\\tensorflow_core\\python\\keras\\engine\\training.py\u001b[0m in \u001b[0;36mfit\u001b[1;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_freq, max_queue_size, workers, use_multiprocessing, **kwargs)\u001b[0m\n\u001b[0;32m    726\u001b[0m         \u001b[0mmax_queue_size\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mmax_queue_size\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    727\u001b[0m         \u001b[0mworkers\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mworkers\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 728\u001b[1;33m         use_multiprocessing=use_multiprocessing)\n\u001b[0m\u001b[0;32m    729\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    730\u001b[0m   def evaluate(self,\n",
      "\u001b[1;32mc:\\users\\tsb\\appdata\\local\\programs\\python\\python37\\lib\\site-packages\\tensorflow_core\\python\\keras\\engine\\training_v2.py\u001b[0m in \u001b[0;36mfit\u001b[1;34m(self, model, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_freq, **kwargs)\u001b[0m\n\u001b[0;32m    322\u001b[0m                 \u001b[0mmode\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mModeKeys\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mTRAIN\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    323\u001b[0m                 \u001b[0mtraining_context\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mtraining_context\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 324\u001b[1;33m                 total_epochs=epochs)\n\u001b[0m\u001b[0;32m    325\u001b[0m             \u001b[0mcbks\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mmake_logs\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mmodel\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mepoch_logs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mtraining_result\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mModeKeys\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mTRAIN\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    326\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mc:\\users\\tsb\\appdata\\local\\programs\\python\\python37\\lib\\site-packages\\tensorflow_core\\python\\keras\\engine\\training_v2.py\u001b[0m in \u001b[0;36mrun_one_epoch\u001b[1;34m(model, iterator, execution_function, dataset_size, batch_size, strategy, steps_per_epoch, num_samples, mode, training_context, total_epochs)\u001b[0m\n\u001b[0;32m    121\u001b[0m         step=step, mode=mode, size=current_batch_size) as batch_logs:\n\u001b[0;32m    122\u001b[0m       \u001b[1;32mtry\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 123\u001b[1;33m         \u001b[0mbatch_outs\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mexecution_function\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0miterator\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    124\u001b[0m       \u001b[1;32mexcept\u001b[0m \u001b[1;33m(\u001b[0m\u001b[0mStopIteration\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0merrors\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mOutOfRangeError\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    125\u001b[0m         \u001b[1;31m# TODO(kaftan): File bug about tf function and errors.OutOfRangeError?\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mc:\\users\\tsb\\appdata\\local\\programs\\python\\python37\\lib\\site-packages\\tensorflow_core\\python\\keras\\engine\\training_v2_utils.py\u001b[0m in \u001b[0;36mexecution_function\u001b[1;34m(input_fn)\u001b[0m\n\u001b[0;32m     84\u001b[0m     \u001b[1;31m# `numpy` translates Tensors to values in Eager mode.\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     85\u001b[0m     return nest.map_structure(_non_none_constant_value,\n\u001b[1;32m---> 86\u001b[1;33m                               distributed_function(input_fn))\n\u001b[0m\u001b[0;32m     87\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     88\u001b[0m   \u001b[1;32mreturn\u001b[0m \u001b[0mexecution_function\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mc:\\users\\tsb\\appdata\\local\\programs\\python\\python37\\lib\\site-packages\\tensorflow_core\\python\\eager\\def_function.py\u001b[0m in \u001b[0;36m__call__\u001b[1;34m(self, *args, **kwds)\u001b[0m\n\u001b[0;32m    455\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    456\u001b[0m     \u001b[0mtracing_count\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_get_tracing_count\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 457\u001b[1;33m     \u001b[0mresult\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_call\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwds\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    458\u001b[0m     \u001b[1;32mif\u001b[0m \u001b[0mtracing_count\u001b[0m \u001b[1;33m==\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_get_tracing_count\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    459\u001b[0m       \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_call_counter\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mcalled_without_tracing\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mc:\\users\\tsb\\appdata\\local\\programs\\python\\python37\\lib\\site-packages\\tensorflow_core\\python\\eager\\def_function.py\u001b[0m in \u001b[0;36m_call\u001b[1;34m(self, *args, **kwds)\u001b[0m\n\u001b[0;32m    501\u001b[0m       \u001b[1;31m# This is the first call of __call__, so we have to initialize.\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    502\u001b[0m       \u001b[0minitializer_map\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mobject_identity\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mObjectIdentityDictionary\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 503\u001b[1;33m       \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_initialize\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mkwds\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0madd_initializers_to\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0minitializer_map\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    504\u001b[0m     \u001b[1;32mfinally\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    505\u001b[0m       \u001b[1;31m# At this point we know that the initialization is complete (or less\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mc:\\users\\tsb\\appdata\\local\\programs\\python\\python37\\lib\\site-packages\\tensorflow_core\\python\\eager\\def_function.py\u001b[0m in \u001b[0;36m_initialize\u001b[1;34m(self, args, kwds, add_initializers_to)\u001b[0m\n\u001b[0;32m    406\u001b[0m     self._concrete_stateful_fn = (\n\u001b[0;32m    407\u001b[0m         self._stateful_fn._get_concrete_function_internal_garbage_collected(  # pylint: disable=protected-access\n\u001b[1;32m--> 408\u001b[1;33m             *args, **kwds))\n\u001b[0m\u001b[0;32m    409\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    410\u001b[0m     \u001b[1;32mdef\u001b[0m \u001b[0minvalid_creator_scope\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m*\u001b[0m\u001b[0munused_args\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0munused_kwds\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mc:\\users\\tsb\\appdata\\local\\programs\\python\\python37\\lib\\site-packages\\tensorflow_core\\python\\eager\\function.py\u001b[0m in \u001b[0;36m_get_concrete_function_internal_garbage_collected\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m   1846\u001b[0m     \u001b[1;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0minput_signature\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1847\u001b[0m       \u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mkwargs\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1848\u001b[1;33m     \u001b[0mgraph_function\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0m_\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0m_\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_maybe_define_function\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m   1849\u001b[0m     \u001b[1;32mreturn\u001b[0m \u001b[0mgraph_function\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1850\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mc:\\users\\tsb\\appdata\\local\\programs\\python\\python37\\lib\\site-packages\\tensorflow_core\\python\\eager\\function.py\u001b[0m in \u001b[0;36m_maybe_define_function\u001b[1;34m(self, args, kwargs)\u001b[0m\n\u001b[0;32m   2148\u001b[0m         \u001b[0mgraph_function\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_function_cache\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mprimary\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mcache_key\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   2149\u001b[0m         \u001b[1;32mif\u001b[0m \u001b[0mgraph_function\u001b[0m \u001b[1;32mis\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 2150\u001b[1;33m           \u001b[0mgraph_function\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_create_graph_function\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m   2151\u001b[0m           \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_function_cache\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mprimary\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mcache_key\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mgraph_function\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   2152\u001b[0m         \u001b[1;32mreturn\u001b[0m \u001b[0mgraph_function\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mkwargs\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mc:\\users\\tsb\\appdata\\local\\programs\\python\\python37\\lib\\site-packages\\tensorflow_core\\python\\eager\\function.py\u001b[0m in \u001b[0;36m_create_graph_function\u001b[1;34m(self, args, kwargs, override_flat_arg_shapes)\u001b[0m\n\u001b[0;32m   2039\u001b[0m             \u001b[0marg_names\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0marg_names\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   2040\u001b[0m             \u001b[0moverride_flat_arg_shapes\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0moverride_flat_arg_shapes\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 2041\u001b[1;33m             capture_by_value=self._capture_by_value),\n\u001b[0m\u001b[0;32m   2042\u001b[0m         \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_function_attributes\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   2043\u001b[0m         \u001b[1;31m# Tell the ConcreteFunction to clean up its graph once it goes out of\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mc:\\users\\tsb\\appdata\\local\\programs\\python\\python37\\lib\\site-packages\\tensorflow_core\\python\\framework\\func_graph.py\u001b[0m in \u001b[0;36mfunc_graph_from_py_func\u001b[1;34m(name, python_func, args, kwargs, signature, func_graph, autograph, autograph_options, add_control_dependencies, arg_names, op_return_value, collections, capture_by_value, override_flat_arg_shapes)\u001b[0m\n\u001b[0;32m    913\u001b[0m                                           converted_func)\n\u001b[0;32m    914\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 915\u001b[1;33m       \u001b[0mfunc_outputs\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mpython_func\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m*\u001b[0m\u001b[0mfunc_args\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mfunc_kwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    916\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    917\u001b[0m       \u001b[1;31m# invariant: `func_outputs` contains only Tensors, CompositeTensors,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mc:\\users\\tsb\\appdata\\local\\programs\\python\\python37\\lib\\site-packages\\tensorflow_core\\python\\eager\\def_function.py\u001b[0m in \u001b[0;36mwrapped_fn\u001b[1;34m(*args, **kwds)\u001b[0m\n\u001b[0;32m    356\u001b[0m         \u001b[1;31m# __wrapped__ allows AutoGraph to swap in a converted function. We give\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    357\u001b[0m         \u001b[1;31m# the function a weak reference to itself to avoid a reference cycle.\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 358\u001b[1;33m         \u001b[1;32mreturn\u001b[0m \u001b[0mweak_wrapped_fn\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__wrapped__\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwds\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    359\u001b[0m     \u001b[0mweak_wrapped_fn\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mweakref\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mref\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mwrapped_fn\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    360\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mc:\\users\\tsb\\appdata\\local\\programs\\python\\python37\\lib\\site-packages\\tensorflow_core\\python\\keras\\engine\\training_v2_utils.py\u001b[0m in \u001b[0;36mdistributed_function\u001b[1;34m(input_iterator)\u001b[0m\n\u001b[0;32m     71\u001b[0m     \u001b[0mstrategy\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mdistribution_strategy_context\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_strategy\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     72\u001b[0m     outputs = strategy.experimental_run_v2(\n\u001b[1;32m---> 73\u001b[1;33m         per_replica_function, args=(model, x, y, sample_weights))\n\u001b[0m\u001b[0;32m     74\u001b[0m     \u001b[1;31m# Out of PerReplica outputs reduce or pick values to return.\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     75\u001b[0m     all_outputs = dist_utils.unwrap_output_dict(\n",
      "\u001b[1;32mc:\\users\\tsb\\appdata\\local\\programs\\python\\python37\\lib\\site-packages\\tensorflow_core\\python\\distribute\\distribute_lib.py\u001b[0m in \u001b[0;36mexperimental_run_v2\u001b[1;34m(self, fn, args, kwargs)\u001b[0m\n\u001b[0;32m    758\u001b[0m       fn = autograph.tf_convert(fn, ag_ctx.control_status_ctx(),\n\u001b[0;32m    759\u001b[0m                                 convert_by_default=False)\n\u001b[1;32m--> 760\u001b[1;33m       \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_extended\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mcall_for_each_replica\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mfn\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0margs\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mkwargs\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    761\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    762\u001b[0m   \u001b[1;32mdef\u001b[0m \u001b[0mreduce\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mreduce_op\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mvalue\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0maxis\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mc:\\users\\tsb\\appdata\\local\\programs\\python\\python37\\lib\\site-packages\\tensorflow_core\\python\\distribute\\distribute_lib.py\u001b[0m in \u001b[0;36mcall_for_each_replica\u001b[1;34m(self, fn, args, kwargs)\u001b[0m\n\u001b[0;32m   1785\u001b[0m       \u001b[0mkwargs\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;33m{\u001b[0m\u001b[1;33m}\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1786\u001b[0m     \u001b[1;32mwith\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_container_strategy\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mscope\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1787\u001b[1;33m       \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_call_for_each_replica\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mfn\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m   1788\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1789\u001b[0m   \u001b[1;32mdef\u001b[0m \u001b[0m_call_for_each_replica\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mfn\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mc:\\users\\tsb\\appdata\\local\\programs\\python\\python37\\lib\\site-packages\\tensorflow_core\\python\\distribute\\distribute_lib.py\u001b[0m in \u001b[0;36m_call_for_each_replica\u001b[1;34m(self, fn, args, kwargs)\u001b[0m\n\u001b[0;32m   2130\u001b[0m         \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_container_strategy\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   2131\u001b[0m         replica_id_in_sync_group=constant_op.constant(0, dtypes.int32)):\n\u001b[1;32m-> 2132\u001b[1;33m       \u001b[1;32mreturn\u001b[0m \u001b[0mfn\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m   2133\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   2134\u001b[0m   \u001b[1;32mdef\u001b[0m \u001b[0m_reduce_to\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mreduce_op\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mvalue\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdestinations\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mc:\\users\\tsb\\appdata\\local\\programs\\python\\python37\\lib\\site-packages\\tensorflow_core\\python\\autograph\\impl\\api.py\u001b[0m in \u001b[0;36mwrapper\u001b[1;34m(*args, **kwargs)\u001b[0m\n\u001b[0;32m    290\u001b[0m   \u001b[1;32mdef\u001b[0m \u001b[0mwrapper\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    291\u001b[0m     \u001b[1;32mwith\u001b[0m \u001b[0mag_ctx\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mControlStatusCtx\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mstatus\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mag_ctx\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mStatus\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mDISABLED\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 292\u001b[1;33m       \u001b[1;32mreturn\u001b[0m \u001b[0mfunc\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    293\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    294\u001b[0m   \u001b[1;32mif\u001b[0m \u001b[0minspect\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0misfunction\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mfunc\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;32mor\u001b[0m \u001b[0minspect\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mismethod\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mfunc\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mc:\\users\\tsb\\appdata\\local\\programs\\python\\python37\\lib\\site-packages\\tensorflow_core\\python\\keras\\engine\\training_v2_utils.py\u001b[0m in \u001b[0;36mtrain_on_batch\u001b[1;34m(model, x, y, sample_weight, class_weight, reset_metrics)\u001b[0m\n\u001b[0;32m    262\u001b[0m       \u001b[0my\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    263\u001b[0m       \u001b[0msample_weights\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0msample_weights\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 264\u001b[1;33m       output_loss_metrics=model._output_loss_metrics)\n\u001b[0m\u001b[0;32m    265\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    266\u001b[0m   \u001b[1;32mif\u001b[0m \u001b[0mreset_metrics\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mc:\\users\\tsb\\appdata\\local\\programs\\python\\python37\\lib\\site-packages\\tensorflow_core\\python\\keras\\engine\\training_eager.py\u001b[0m in \u001b[0;36mtrain_on_batch\u001b[1;34m(model, inputs, targets, sample_weights, output_loss_metrics)\u001b[0m\n\u001b[0;32m    309\u001b[0m           \u001b[0msample_weights\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0msample_weights\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    310\u001b[0m           \u001b[0mtraining\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mTrue\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 311\u001b[1;33m           output_loss_metrics=output_loss_metrics))\n\u001b[0m\u001b[0;32m    312\u001b[0m   \u001b[1;32mif\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[0misinstance\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mouts\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mlist\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    313\u001b[0m     \u001b[0mouts\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;33m[\u001b[0m\u001b[0mouts\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mc:\\users\\tsb\\appdata\\local\\programs\\python\\python37\\lib\\site-packages\\tensorflow_core\\python\\keras\\engine\\training_eager.py\u001b[0m in \u001b[0;36m_process_single_batch\u001b[1;34m(model, inputs, targets, output_loss_metrics, sample_weights, training)\u001b[0m\n\u001b[0;32m    250\u001b[0m               \u001b[0moutput_loss_metrics\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0moutput_loss_metrics\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    251\u001b[0m               \u001b[0msample_weights\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0msample_weights\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 252\u001b[1;33m               training=training))\n\u001b[0m\u001b[0;32m    253\u001b[0m       \u001b[1;32mif\u001b[0m \u001b[0mtotal_loss\u001b[0m \u001b[1;32mis\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    254\u001b[0m         raise ValueError('The model cannot be run '\n",
      "\u001b[1;32mc:\\users\\tsb\\appdata\\local\\programs\\python\\python37\\lib\\site-packages\\tensorflow_core\\python\\keras\\engine\\training_eager.py\u001b[0m in \u001b[0;36m_model_loss\u001b[1;34m(model, inputs, targets, output_loss_metrics, sample_weights, training)\u001b[0m\n\u001b[0;32m    164\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    165\u001b[0m         \u001b[1;32mif\u001b[0m \u001b[0mhasattr\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mloss_fn\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m'reduction'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 166\u001b[1;33m           \u001b[0mper_sample_losses\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mloss_fn\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mcall\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mtargets\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mi\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mouts\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mi\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    167\u001b[0m           weighted_losses = losses_utils.compute_weighted_loss(\n\u001b[0;32m    168\u001b[0m               \u001b[0mper_sample_losses\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mc:\\users\\tsb\\appdata\\local\\programs\\python\\python37\\lib\\site-packages\\tensorflow_core\\python\\keras\\losses.py\u001b[0m in \u001b[0;36mcall\u001b[1;34m(self, y_true, y_pred)\u001b[0m\n\u001b[0;32m    219\u001b[0m       y_pred, y_true = tf_losses_util.squeeze_or_expand_dimensions(\n\u001b[0;32m    220\u001b[0m           y_pred, y_true)\n\u001b[1;32m--> 221\u001b[1;33m     \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mfn\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0my_true\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0my_pred\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_fn_kwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    222\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    223\u001b[0m   \u001b[1;32mdef\u001b[0m \u001b[0mget_config\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mc:\\users\\tsb\\appdata\\local\\programs\\python\\python37\\lib\\site-packages\\tensorflow_core\\python\\keras\\losses.py\u001b[0m in \u001b[0;36msparse_categorical_crossentropy\u001b[1;34m(y_true, y_pred, from_logits, axis)\u001b[0m\n\u001b[0;32m    976\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0msparse_categorical_crossentropy\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0my_true\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0my_pred\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mfrom_logits\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mFalse\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0maxis\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;33m-\u001b[0m\u001b[1;36m1\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    977\u001b[0m   return K.sparse_categorical_crossentropy(\n\u001b[1;32m--> 978\u001b[1;33m       y_true, y_pred, from_logits=from_logits, axis=axis)\n\u001b[0m\u001b[0;32m    979\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    980\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mc:\\users\\tsb\\appdata\\local\\programs\\python\\python37\\lib\\site-packages\\tensorflow_core\\python\\keras\\backend.py\u001b[0m in \u001b[0;36msparse_categorical_crossentropy\u001b[1;34m(target, output, from_logits, axis)\u001b[0m\n\u001b[0;32m   4544\u001b[0m     \u001b[1;32mwith\u001b[0m \u001b[0mget_graph\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mas_default\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   4545\u001b[0m       res = nn.sparse_softmax_cross_entropy_with_logits_v2(\n\u001b[1;32m-> 4546\u001b[1;33m           labels=target, logits=output)\n\u001b[0m\u001b[0;32m   4547\u001b[0m   \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   4548\u001b[0m     res = nn.sparse_softmax_cross_entropy_with_logits_v2(\n",
      "\u001b[1;32mc:\\users\\tsb\\appdata\\local\\programs\\python\\python37\\lib\\site-packages\\tensorflow_core\\python\\ops\\nn_ops.py\u001b[0m in \u001b[0;36msparse_softmax_cross_entropy_with_logits_v2\u001b[1;34m(labels, logits, name)\u001b[0m\n\u001b[0;32m   3475\u001b[0m   \"\"\"\n\u001b[0;32m   3476\u001b[0m   return sparse_softmax_cross_entropy_with_logits(\n\u001b[1;32m-> 3477\u001b[1;33m       labels=labels, logits=logits, name=name)\n\u001b[0m\u001b[0;32m   3478\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   3479\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mc:\\users\\tsb\\appdata\\local\\programs\\python\\python37\\lib\\site-packages\\tensorflow_core\\python\\ops\\nn_ops.py\u001b[0m in \u001b[0;36msparse_softmax_cross_entropy_with_logits\u001b[1;34m(_sentinel, labels, logits, name)\u001b[0m\n\u001b[0;32m   3391\u001b[0m                        \u001b[1;34m\"should equal the shape of logits except for the last \"\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   3392\u001b[0m                        \"dimension (received %s).\" % (labels_static_shape,\n\u001b[1;32m-> 3393\u001b[1;33m                                                      logits.get_shape()))\n\u001b[0m\u001b[0;32m   3394\u001b[0m     \u001b[1;31m# Check if no reshapes are required.\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   3395\u001b[0m     \u001b[1;32mif\u001b[0m \u001b[0mlogits\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_shape\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mndims\u001b[0m \u001b[1;33m==\u001b[0m \u001b[1;36m2\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;31mValueError\u001b[0m: Shape mismatch: The shape of labels (received (1,)) should equal the shape of logits except for the last dimension (received (8, 2))."
     ]
    }
   ],
   "source": [
    "# Setup our model\n",
    "\n",
    "model = tf.keras.models.Sequential([\n",
    "    # Flatten out our input\n",
    "    tf.keras.layers.Flatten(),\n",
    "    \n",
    "    # Setup our first layer\n",
    "    tf.keras.layers.Dense(1024, activation=tf.nn.relu),\n",
    "    \n",
    "    # Setup output layer\n",
    "    tf.keras.layers.Dense(2, activation=tf.nn.softmax)\n",
    "])\n",
    "\n",
    "# Compile our model\n",
    "model.compile(optimizer='adam', \n",
    "              loss = 'sparse_categorical_crossentropy', \n",
    "             metrics=['accuracy'])\n",
    "\n",
    "# Fit model\n",
    "history = model.fit(\n",
    "    dataset, \n",
    "    epochs=10,\n",
    "    shuffle=True,\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 100,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<bound method NDFrame.head of      PassengerId  Survived\n",
      "0            892         0\n",
      "1            893         0\n",
      "2            894         0\n",
      "3            895         0\n",
      "4            896         0\n",
      "..           ...       ...\n",
      "413         1305         0\n",
      "414         1306         1\n",
      "415         1307         0\n",
      "416         1308         0\n",
      "417         1309         0\n",
      "\n",
      "[418 rows x 2 columns]>\n"
     ]
    }
   ],
   "source": [
    "test_pred = model.predict(X_test.values) # Note that we need to feed our model the values or our dataframe X_test\n",
    "predictions = np.c_[PassengerId, np.argmax(test_pred, axis=1)]\n",
    "submission = pd.DataFrame(predictions, columns = ['PassengerId', 'Survived'])\n",
    "print(submission.head)\n",
    "submission.to_csv(\"submissions/NNSubmission.csv\", index=False)"
   ]
  },
  {
   "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": "3.7.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}