{
 "cells": [
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {
    "_cell_guid": "b1076dfc-b9ad-4769-8c92-a6c4dae69d19",
    "_uuid": "8f2839f25d086af736a60e9eeb907d3b93b6e0e5",
    "execution": {
     "iopub.execute_input": "2022-12-08T13:51:01.372378Z",
     "iopub.status.busy": "2022-12-08T13:51:01.371165Z",
     "iopub.status.idle": "2022-12-08T13:51:01.40242Z",
     "shell.execute_reply": "2022-12-08T13:51:01.399538Z",
     "shell.execute_reply.started": "2022-12-08T13:51:01.372248Z"
    },
    "id": "XuycFYxcK5ue"
   },
   "source": [
    "## <center> Predicting Listing Gains in the Indian IPO Market Using TensorFlow\n",
    "\n",
    "I develop a deep learning classification model to predict listing gains for Initial Public Offerings (IPO) in the Indian market. This model can be useful to make investment decisions in the IPO market."
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Preliminary data exploration\n",
    "The dataset is available under the file name `data.csv` (https://github.com/magorshunov/predicting_ipo_gains/blob/main/data.csv). Listing gains are the percentage increase in the share price of a company from its IPO issue price on the day of listing.\n",
    "The data consists of following columns:\n",
    "- `Date`: date when the IPO was listed\n",
    "- `IPOName`: name of the IPO\n",
    "- `Issue_Size`: size of the IPO issue, in INR Crores\n",
    "- `Subscription_QIB`: number of times the IPO was subscribed by the QIB (Qualified Institutional Buyer) investor category\n",
    "- `Subscription_HNI`: number of times the IPO was subscribed by the HNI (High Networth Individual) investor category\n",
    "- `Subscription_RII`: number of times the IPO was subscribed by the RII (Retail Individual Investors) investor category\n",
    "- `Subscription_Total`: total number of times the IPO was subscribed overall\n",
    "- `Issue_Price`: the price in INR at which the IPO was issued\n",
    "- `Listing_Gains_Percent`: is the percentage gain in the listing price over the issue price"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-12-27T18:32:02.368665Z",
     "iopub.status.busy": "2022-12-27T18:32:02.368168Z",
     "iopub.status.idle": "2022-12-27T18:32:09.766150Z",
     "shell.execute_reply": "2022-12-27T18:32:09.764954Z",
     "shell.execute_reply.started": "2022-12-27T18:32:02.368525Z"
    },
    "id": "f022OaJIK5ul"
   },
   "outputs": [],
   "source": [
    "import numpy as np \n",
    "import pandas as pd \n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt\n",
    "import tensorflow as tf\n",
    "from tensorflow import keras\n",
    "from tensorflow.keras import layers\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.metrics import mean_squared_error\n",
    "from math import sqrt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 224
    },
    "execution": {
     "iopub.execute_input": "2022-12-27T18:32:09.769839Z",
     "iopub.status.busy": "2022-12-27T18:32:09.768871Z",
     "iopub.status.idle": "2022-12-27T18:32:09.824190Z",
     "shell.execute_reply": "2022-12-27T18:32:09.823214Z",
     "shell.execute_reply.started": "2022-12-27T18:32:09.769801Z"
    },
    "id": "ZAw9a566K5um",
    "outputId": "cfab95d0-5609-4362-e535-d6a1615f066b"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(319, 9)\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Date</th>\n",
       "      <th>IPOName</th>\n",
       "      <th>Issue_Size</th>\n",
       "      <th>Subscription_QIB</th>\n",
       "      <th>Subscription_HNI</th>\n",
       "      <th>Subscription_RII</th>\n",
       "      <th>Subscription_Total</th>\n",
       "      <th>Issue_Price</th>\n",
       "      <th>Listing_Gains_Percent</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>03/02/10</td>\n",
       "      <td>Infinite Comp</td>\n",
       "      <td>189.80</td>\n",
       "      <td>48.44</td>\n",
       "      <td>106.02</td>\n",
       "      <td>11.08</td>\n",
       "      <td>43.22</td>\n",
       "      <td>165</td>\n",
       "      <td>11.82</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>08/02/10</td>\n",
       "      <td>Jubilant Food</td>\n",
       "      <td>328.70</td>\n",
       "      <td>59.39</td>\n",
       "      <td>51.95</td>\n",
       "      <td>3.79</td>\n",
       "      <td>31.11</td>\n",
       "      <td>145</td>\n",
       "      <td>-84.21</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>15/02/10</td>\n",
       "      <td>Syncom Health</td>\n",
       "      <td>56.25</td>\n",
       "      <td>0.99</td>\n",
       "      <td>16.60</td>\n",
       "      <td>6.25</td>\n",
       "      <td>5.17</td>\n",
       "      <td>75</td>\n",
       "      <td>17.13</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>15/02/10</td>\n",
       "      <td>Vascon Engineer</td>\n",
       "      <td>199.80</td>\n",
       "      <td>1.12</td>\n",
       "      <td>3.65</td>\n",
       "      <td>0.62</td>\n",
       "      <td>1.22</td>\n",
       "      <td>165</td>\n",
       "      <td>-11.28</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>19/02/10</td>\n",
       "      <td>Thangamayil</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.52</td>\n",
       "      <td>1.52</td>\n",
       "      <td>2.26</td>\n",
       "      <td>1.12</td>\n",
       "      <td>75</td>\n",
       "      <td>-5.20</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      Date           IPOName  Issue_Size  Subscription_QIB  Subscription_HNI   \n",
       "0  03/02/10    Infinite Comp      189.80             48.44            106.02  \\\n",
       "1  08/02/10    Jubilant Food      328.70             59.39             51.95   \n",
       "2  15/02/10    Syncom Health       56.25              0.99             16.60   \n",
       "3  15/02/10  Vascon Engineer      199.80              1.12              3.65   \n",
       "4  19/02/10      Thangamayil        0.00              0.52              1.52   \n",
       "\n",
       "   Subscription_RII  Subscription_Total  Issue_Price  Listing_Gains_Percent  \n",
       "0             11.08               43.22          165                  11.82  \n",
       "1              3.79               31.11          145                 -84.21  \n",
       "2              6.25                5.17           75                  17.13  \n",
       "3              0.62                1.22          165                 -11.28  \n",
       "4              2.26                1.12           75                  -5.20  "
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.read_csv('data.csv')\n",
    "print(df.shape)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 394
    },
    "execution": {
     "iopub.execute_input": "2022-12-27T18:32:09.835454Z",
     "iopub.status.busy": "2022-12-27T18:32:09.834527Z",
     "iopub.status.idle": "2022-12-27T18:32:09.888708Z",
     "shell.execute_reply": "2022-12-27T18:32:09.887449Z",
     "shell.execute_reply.started": "2022-12-27T18:32:09.835412Z"
    },
    "id": "d8VNWtLDK5un",
    "outputId": "31bede43-e79f-4bad-ab8c-223a91296f8b"
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Date</th>\n",
       "      <th>IPOName</th>\n",
       "      <th>Issue_Size</th>\n",
       "      <th>Subscription_QIB</th>\n",
       "      <th>Subscription_HNI</th>\n",
       "      <th>Subscription_RII</th>\n",
       "      <th>Subscription_Total</th>\n",
       "      <th>Issue_Price</th>\n",
       "      <th>Listing_Gains_Percent</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>319</td>\n",
       "      <td>319</td>\n",
       "      <td>319.000000</td>\n",
       "      <td>319.000000</td>\n",
       "      <td>319.000000</td>\n",
       "      <td>319.000000</td>\n",
       "      <td>319.000000</td>\n",
       "      <td>319.000000</td>\n",
       "      <td>319.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>unique</th>\n",
       "      <td>287</td>\n",
       "      <td>319</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>top</th>\n",
       "      <td>16/08/21</td>\n",
       "      <td>Infinite Comp</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>freq</th>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1192.859969</td>\n",
       "      <td>25.684138</td>\n",
       "      <td>70.091379</td>\n",
       "      <td>8.561599</td>\n",
       "      <td>27.447147</td>\n",
       "      <td>375.128527</td>\n",
       "      <td>4.742696</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2384.643786</td>\n",
       "      <td>40.716782</td>\n",
       "      <td>142.454416</td>\n",
       "      <td>14.508670</td>\n",
       "      <td>48.772203</td>\n",
       "      <td>353.897614</td>\n",
       "      <td>47.650946</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>-97.150000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>169.005000</td>\n",
       "      <td>1.150000</td>\n",
       "      <td>1.255000</td>\n",
       "      <td>1.275000</td>\n",
       "      <td>1.645000</td>\n",
       "      <td>119.000000</td>\n",
       "      <td>-11.555000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>496.250000</td>\n",
       "      <td>4.940000</td>\n",
       "      <td>5.070000</td>\n",
       "      <td>3.420000</td>\n",
       "      <td>4.930000</td>\n",
       "      <td>250.000000</td>\n",
       "      <td>1.810000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1100.000000</td>\n",
       "      <td>34.635000</td>\n",
       "      <td>62.095000</td>\n",
       "      <td>8.605000</td>\n",
       "      <td>33.395000</td>\n",
       "      <td>536.000000</td>\n",
       "      <td>25.310000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>21000.000000</td>\n",
       "      <td>215.450000</td>\n",
       "      <td>958.070000</td>\n",
       "      <td>119.440000</td>\n",
       "      <td>326.490000</td>\n",
       "      <td>2150.000000</td>\n",
       "      <td>270.400000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           Date         IPOName    Issue_Size  Subscription_QIB   \n",
       "count        319            319    319.000000        319.000000  \\\n",
       "unique       287            319           NaN               NaN   \n",
       "top     16/08/21  Infinite Comp           NaN               NaN   \n",
       "freq           4              1           NaN               NaN   \n",
       "mean         NaN            NaN   1192.859969         25.684138   \n",
       "std          NaN            NaN   2384.643786         40.716782   \n",
       "min          NaN            NaN      0.000000          0.000000   \n",
       "25%          NaN            NaN    169.005000          1.150000   \n",
       "50%          NaN            NaN    496.250000          4.940000   \n",
       "75%          NaN            NaN   1100.000000         34.635000   \n",
       "max          NaN            NaN  21000.000000        215.450000   \n",
       "\n",
       "        Subscription_HNI  Subscription_RII  Subscription_Total  Issue_Price   \n",
       "count         319.000000        319.000000          319.000000   319.000000  \\\n",
       "unique               NaN               NaN                 NaN          NaN   \n",
       "top                  NaN               NaN                 NaN          NaN   \n",
       "freq                 NaN               NaN                 NaN          NaN   \n",
       "mean           70.091379          8.561599           27.447147   375.128527   \n",
       "std           142.454416         14.508670           48.772203   353.897614   \n",
       "min             0.000000          0.000000            0.000000     0.000000   \n",
       "25%             1.255000          1.275000            1.645000   119.000000   \n",
       "50%             5.070000          3.420000            4.930000   250.000000   \n",
       "75%            62.095000          8.605000           33.395000   536.000000   \n",
       "max           958.070000        119.440000          326.490000  2150.000000   \n",
       "\n",
       "        Listing_Gains_Percent  \n",
       "count              319.000000  \n",
       "unique                    NaN  \n",
       "top                       NaN  \n",
       "freq                      NaN  \n",
       "mean                 4.742696  \n",
       "std                 47.650946  \n",
       "min                -97.150000  \n",
       "25%                -11.555000  \n",
       "50%                  1.810000  \n",
       "75%                 25.310000  \n",
       "max                270.400000  "
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.describe(include='all')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "execution": {
     "iopub.execute_input": "2022-12-27T18:32:09.893105Z",
     "iopub.status.busy": "2022-12-27T18:32:09.892679Z",
     "iopub.status.idle": "2022-12-27T18:32:09.903968Z",
     "shell.execute_reply": "2022-12-27T18:32:09.902838Z",
     "shell.execute_reply.started": "2022-12-27T18:32:09.893072Z"
    },
    "id": "quX0LdyMK5uo",
    "outputId": "1262653e-07aa-40cf-c0ee-bce542137be3"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "count    319.000000\n",
       "mean       4.742696\n",
       "std       47.650946\n",
       "min      -97.150000\n",
       "25%      -11.555000\n",
       "50%        1.810000\n",
       "75%       25.310000\n",
       "max      270.400000\n",
       "Name: Listing_Gains_Percent, dtype: float64"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['Listing_Gains_Percent'].describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Date                     0\n",
       "IPOName                  0\n",
       "Issue_Size               0\n",
       "Subscription_QIB         0\n",
       "Subscription_HNI         0\n",
       "Subscription_RII         0\n",
       "Subscription_Total       0\n",
       "Issue_Price              0\n",
       "Listing_Gains_Percent    0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.isnull().sum()"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {
    "id": "KwApVwu4K5uo"
   },
   "source": [
    "## Exploring the Data\n",
    "The `Listing_Gains_Percent` target variable is continous. Therfore, I will need to convert it into a categorical variable before I proceed. Approximately 55% of the IPOs listed in profit, and the data is fairly balanced. I have also dropped some of the variables that might not have predictive power. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-12-27T18:32:09.922352Z",
     "iopub.status.busy": "2022-12-27T18:32:09.921602Z",
     "iopub.status.idle": "2022-12-27T18:32:09.930727Z",
     "shell.execute_reply": "2022-12-27T18:32:09.929560Z",
     "shell.execute_reply.started": "2022-12-27T18:32:09.922304Z"
    },
    "id": "QqkYBOUNK5up"
   },
   "outputs": [],
   "source": [
    "df['Listing_Gains_Profit'] = df['Listing_Gains_Percent'].apply(lambda x: 1 if x > 0 else 0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "execution": {
     "iopub.execute_input": "2022-12-27T18:32:09.932506Z",
     "iopub.status.busy": "2022-12-27T18:32:09.932169Z",
     "iopub.status.idle": "2022-12-27T18:32:09.946096Z",
     "shell.execute_reply": "2022-12-27T18:32:09.944849Z",
     "shell.execute_reply.started": "2022-12-27T18:32:09.932469Z"
    },
    "id": "FyUnzaeYK5up",
    "outputId": "46fab12a-dbfe-4130-b484-60062cc9d161"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "count    319.000000\n",
       "mean       0.545455\n",
       "std        0.498712\n",
       "min        0.000000\n",
       "25%        0.000000\n",
       "50%        1.000000\n",
       "75%        1.000000\n",
       "max        1.000000\n",
       "Name: Listing_Gains_Profit, dtype: float64"
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['Listing_Gains_Profit'].describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "execution": {
     "iopub.execute_input": "2022-12-27T18:32:09.948100Z",
     "iopub.status.busy": "2022-12-27T18:32:09.947749Z",
     "iopub.status.idle": "2022-12-27T18:32:09.957636Z",
     "shell.execute_reply": "2022-12-27T18:32:09.956803Z",
     "shell.execute_reply.started": "2022-12-27T18:32:09.948070Z"
    },
    "id": "tusoDA3PK5up",
    "outputId": "c50fed56-638e-42b4-f28e-700dfa1caaae"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Listing_Gains_Profit\n",
       "1    0.545455\n",
       "0    0.454545\n",
       "Name: proportion, dtype: float64"
      ]
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['Listing_Gains_Profit'].value_counts(normalize=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "execution": {
     "iopub.execute_input": "2022-12-27T18:32:09.959345Z",
     "iopub.status.busy": "2022-12-27T18:32:09.958997Z",
     "iopub.status.idle": "2022-12-27T18:32:09.982144Z",
     "shell.execute_reply": "2022-12-27T18:32:09.980694Z",
     "shell.execute_reply.started": "2022-12-27T18:32:09.959314Z"
    },
    "id": "M8LYT3OdK5uq",
    "outputId": "3ac1f945-2e95-4a17-f5e9-d24b4d6d6a5e"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 319 entries, 0 to 318\n",
      "Data columns (total 7 columns):\n",
      " #   Column                Non-Null Count  Dtype  \n",
      "---  ------                --------------  -----  \n",
      " 0   Issue_Size            319 non-null    float64\n",
      " 1   Subscription_QIB      319 non-null    float64\n",
      " 2   Subscription_HNI      319 non-null    float64\n",
      " 3   Subscription_RII      319 non-null    float64\n",
      " 4   Subscription_Total    319 non-null    float64\n",
      " 5   Issue_Price           319 non-null    int64  \n",
      " 6   Listing_Gains_Profit  319 non-null    int64  \n",
      "dtypes: float64(5), int64(2)\n",
      "memory usage: 17.6 KB\n"
     ]
    }
   ],
   "source": [
    "df.drop(['Date ', 'IPOName', 'Listing_Gains_Percent'], axis=1, inplace=True)\n",
    "df.info()"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {
    "id": "Rqly_22nK5uq"
   },
   "source": [
    "## Data Visualization \n",
    "I will check for the distribution of predictors with respect to the target variable, since they could be informative for modeling. To do that, I will: \n",
    "- Created a countplot to visualize the distribution of the target variable, and give the plot a proper title.\n",
    "- Used plots to check for the presence of outliers in each of the continuous variables of the dataset.\n",
    "- Used visualizations to check the relationship between your selected predictor variables and the target variable. Check if segmenting the plots with the distribution of the outcome classes provides any meaningful insight.\n",
    "- Used visualizations to check if there are correlations between predictor variables.\n",
    "\n",
    "Here are some of the findings:\n",
    "\n",
    "1. The histogram and the boxplots show that outliers are present in the data and might need outlier treatment. \n",
    "\n",
    "2. The boxplot of `Issue_Price`, with respect to `Listing_Gains_Profit`, shows that there are more outliers for IPOs that listed a loss than there are outliers for IPOs that listed a profit. \n",
    "\n",
    "3. The scatterplot shows a correlation between Retail and Total IPO Subscription via a scatterplot."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 295
    },
    "execution": {
     "iopub.execute_input": "2022-12-27T18:32:09.984476Z",
     "iopub.status.busy": "2022-12-27T18:32:09.983979Z",
     "iopub.status.idle": "2022-12-27T18:32:10.215080Z",
     "shell.execute_reply": "2022-12-27T18:32:10.214284Z",
     "shell.execute_reply.started": "2022-12-27T18:32:09.984433Z"
    },
    "id": "MGFC-ZSNK5ur",
    "outputId": "3811b1fe-a766-4131-ae9c-2540fd0187ce"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# visualizing the target variable\n",
    "sns.countplot(x='Listing_Gains_Profit', data=df)\n",
    "plt.title('Distribution of IPO Listing Profit Category')\n",
    "plt.xlabel('Listing Profit (No=0, Yes=1)')\n",
    "plt.ylabel('Frequency')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 351
    },
    "execution": {
     "iopub.execute_input": "2022-12-27T18:32:10.216760Z",
     "iopub.status.busy": "2022-12-27T18:32:10.216291Z",
     "iopub.status.idle": "2022-12-27T18:32:10.518091Z",
     "shell.execute_reply": "2022-12-27T18:32:10.516968Z",
     "shell.execute_reply.started": "2022-12-27T18:32:10.216731Z"
    },
    "id": "u8zD7oyCK5ur",
    "outputId": "e5a8a747-b65c-4021-bd87-bc00276d06d5"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 800x500 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=[8,5])\n",
    "sns.histplot(data=df, x='Issue_Price', bins=50).set(title='Distribution of Issue_Price', ylabel='Count')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 351
    },
    "execution": {
     "iopub.execute_input": "2022-12-27T18:32:10.520447Z",
     "iopub.status.busy": "2022-12-27T18:32:10.520140Z",
     "iopub.status.idle": "2022-12-27T18:32:10.822114Z",
     "shell.execute_reply": "2022-12-27T18:32:10.820900Z",
     "shell.execute_reply.started": "2022-12-27T18:32:10.520419Z"
    },
    "id": "62lZ4aQTK5ur",
    "outputId": "2099c778-fce5-4837-8819-9749ddf89d36"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 800x500 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=[8,5])\n",
    "sns.histplot(data=df, x='Issue_Size', bins=50).set(title='Distribution of Issue_Size', ylabel='Count')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 268
    },
    "execution": {
     "iopub.execute_input": "2022-12-27T18:32:10.828097Z",
     "iopub.status.busy": "2022-12-27T18:32:10.827747Z",
     "iopub.status.idle": "2022-12-27T18:32:10.998452Z",
     "shell.execute_reply": "2022-12-27T18:32:10.997110Z",
     "shell.execute_reply.started": "2022-12-27T18:32:10.828067Z"
    },
    "id": "WrkZRIztK5ur",
    "outputId": "5e348e9e-9a2f-470d-b685-cb152052f7bf"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.boxplot(data=df, y='Issue_Size')\n",
    "plt.title('Boxplot of Issue_Size')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 295
    },
    "execution": {
     "iopub.execute_input": "2022-12-27T18:32:11.000271Z",
     "iopub.status.busy": "2022-12-27T18:32:10.999879Z",
     "iopub.status.idle": "2022-12-27T18:32:11.198774Z",
     "shell.execute_reply": "2022-12-27T18:32:11.197900Z",
     "shell.execute_reply.started": "2022-12-27T18:32:11.000237Z"
    },
    "id": "UEK5vEBYK5us",
    "outputId": "e7938243-822e-4beb-fd1d-ca27ee676b74"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.boxplot(data=df, x='Listing_Gains_Profit', y='Issue_Price')\n",
    "plt.title('Boxplot of Issue_Price with respect to Listing Gains Type')\n",
    "plt.xlabel('Listing Profit (No=0, Yes=1)')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "execution": {
     "iopub.execute_input": "2022-12-27T18:32:11.200947Z",
     "iopub.status.busy": "2022-12-27T18:32:11.200319Z",
     "iopub.status.idle": "2022-12-27T18:32:11.207924Z",
     "shell.execute_reply": "2022-12-27T18:32:11.207051Z",
     "shell.execute_reply.started": "2022-12-27T18:32:11.200912Z"
    },
    "id": "5Tas_DpEK5us",
    "outputId": "ab488bb0-5fad-452c-8ea0-84e480a780f1"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Issue_Size              4.853402\n",
      "Subscription_QIB        2.143705\n",
      "Subscription_HNI        3.078445\n",
      "Subscription_RII        3.708274\n",
      "Subscription_Total      2.911907\n",
      "Issue_Price             1.696881\n",
      "Listing_Gains_Profit   -0.183438\n",
      "dtype: float64\n"
     ]
    }
   ],
   "source": [
    "print(df.skew())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 268
    },
    "execution": {
     "iopub.execute_input": "2022-12-27T18:32:11.209644Z",
     "iopub.status.busy": "2022-12-27T18:32:11.209282Z",
     "iopub.status.idle": "2022-12-27T18:32:11.386354Z",
     "shell.execute_reply": "2022-12-27T18:32:11.385216Z",
     "shell.execute_reply.started": "2022-12-27T18:32:11.209599Z"
    },
    "id": "9OclMZRSK5us",
    "outputId": "baa862bb-349c-40f2-d9dc-b11c948f6bd9"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.boxplot(data=df, y='Subscription_QIB')\n",
    "plt.title('Boxplot of Subscription_QIB')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 296
    },
    "execution": {
     "iopub.execute_input": "2022-12-27T18:32:11.388794Z",
     "iopub.status.busy": "2022-12-27T18:32:11.388041Z",
     "iopub.status.idle": "2022-12-27T18:32:11.623059Z",
     "shell.execute_reply": "2022-12-27T18:32:11.621912Z",
     "shell.execute_reply.started": "2022-12-27T18:32:11.388733Z"
    },
    "id": "xFoR7F-lK5us",
    "outputId": "9bc27b47-0862-4735-e301-21330ef1b8e1"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.scatterplot(data=df, x='Subscription_RII', y='Subscription_Total')\n",
    "plt.title('Scatterplot between Retail and Total IPO Subscription')\n",
    "plt.show()"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {
    "id": "T-PN0gKiK5ut"
   },
   "source": [
    "## Outlier Treatment\n",
    "Apart from performing a visual inspection, outliers can also be identified with the skewness or the interquartile range (IQR) value. There are different approaches to outlier treatment, but the one I've used here is outlier identification using the interquartile menthod. Once I identified the outliers, I clipped the variable values between the upper and lower bounds."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "execution": {
     "iopub.execute_input": "2022-12-27T18:32:11.797659Z",
     "iopub.status.busy": "2022-12-27T18:32:11.797316Z",
     "iopub.status.idle": "2022-12-27T18:32:11.808432Z",
     "shell.execute_reply": "2022-12-27T18:32:11.807238Z",
     "shell.execute_reply.started": "2022-12-27T18:32:11.797626Z"
    },
    "id": "VXcqCGqCK5ut",
    "outputId": "3347b3ee-6a34-4f2d-c8f4-39af7d394616"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "IQR = 930.995\n",
      "lower = -1227.4875000000002\n",
      "upper = 2496.4925000000003\n"
     ]
    }
   ],
   "source": [
    "q1 = df['Issue_Size'].quantile(q=0.25)\n",
    "q3 = df['Issue_Size'].quantile(q=0.75)  \n",
    "iqr = q3 - q1   \n",
    "lower = (q1 - 1.5 * iqr) \n",
    "upper = (q3 + 1.5 * iqr) \n",
    "print('IQR = ', iqr, '\\nlower = ', lower, '\\nupper = ', upper, sep='')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "execution": {
     "iopub.execute_input": "2022-12-27T18:32:11.809845Z",
     "iopub.status.busy": "2022-12-27T18:32:11.809529Z",
     "iopub.status.idle": "2022-12-27T18:32:11.829979Z",
     "shell.execute_reply": "2022-12-27T18:32:11.828506Z",
     "shell.execute_reply.started": "2022-12-27T18:32:11.809817Z"
    },
    "id": "MyxUXuWCK5ut",
    "outputId": "ec2114dc-1139-4fc4-a173-7b75c18ea6ec"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "count     319.000000\n",
       "mean      763.561238\n",
       "std       769.689122\n",
       "min         0.000000\n",
       "25%       169.005000\n",
       "50%       496.250000\n",
       "75%      1100.000000\n",
       "max      2496.492500\n",
       "Name: Issue_Size, dtype: float64"
      ]
     },
     "execution_count": 50,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['Issue_Size'] = df['Issue_Size'].clip(lower, upper)\n",
    "df['Issue_Size'].describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "execution": {
     "iopub.execute_input": "2022-12-27T18:32:11.831412Z",
     "iopub.status.busy": "2022-12-27T18:32:11.831071Z",
     "iopub.status.idle": "2022-12-27T18:32:11.842221Z",
     "shell.execute_reply": "2022-12-27T18:32:11.840980Z",
     "shell.execute_reply.started": "2022-12-27T18:32:11.831377Z"
    },
    "id": "2no3iuXXK5ut",
    "outputId": "d7c63024-5830-4c17-b6f8-1eb659dcc223"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "IQR = 33.48500000000001\n",
      "lower = -49.07750000000001\n",
      "upper = 84.86250000000001\n"
     ]
    }
   ],
   "source": [
    "q1 = df['Subscription_QIB'].quantile(q=0.25)\n",
    "q3 = df['Subscription_QIB'].quantile(q=0.75)  \n",
    "iqr = q3 - q1   \n",
    "lower = (q1 - 1.5 * iqr) \n",
    "upper = (q3 + 1.5 * iqr) \n",
    "print('IQR = ', iqr, '\\nlower = ', lower, '\\nupper = ', upper, sep='')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "execution": {
     "iopub.execute_input": "2022-12-27T18:32:11.844442Z",
     "iopub.status.busy": "2022-12-27T18:32:11.843981Z",
     "iopub.status.idle": "2022-12-27T18:32:11.860042Z",
     "shell.execute_reply": "2022-12-27T18:32:11.858761Z",
     "shell.execute_reply.started": "2022-12-27T18:32:11.844398Z"
    },
    "id": "KTRUl5bdK5ut",
    "outputId": "a6d98c3b-4113-4244-fd0b-a697ca16e139"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "count    319.000000\n",
       "mean      21.521183\n",
       "std       29.104549\n",
       "min        0.000000\n",
       "25%        1.150000\n",
       "50%        4.940000\n",
       "75%       34.635000\n",
       "max       84.862500\n",
       "Name: Subscription_QIB, dtype: float64"
      ]
     },
     "execution_count": 52,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['Subscription_QIB'] = df['Subscription_QIB'].clip(lower, upper)\n",
    "df['Subscription_QIB'].describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "execution": {
     "iopub.execute_input": "2022-12-27T18:32:11.862921Z",
     "iopub.status.busy": "2022-12-27T18:32:11.861528Z",
     "iopub.status.idle": "2022-12-27T18:32:11.871911Z",
     "shell.execute_reply": "2022-12-27T18:32:11.870729Z",
     "shell.execute_reply.started": "2022-12-27T18:32:11.862883Z"
    },
    "id": "RCU2kxX-K5uu",
    "outputId": "b0b6bcd6-de91-42d3-d45d-0912f6f3e198"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "IQR = 60.839999999999996\n",
      "lower = -90.005\n",
      "upper = 153.355\n"
     ]
    }
   ],
   "source": [
    "q1 = df['Subscription_HNI'].quantile(q=0.25)\n",
    "q3 = df['Subscription_HNI'].quantile(q=0.75)  \n",
    "iqr = q3 - q1   \n",
    "lower = (q1 - 1.5 * iqr) \n",
    "upper = (q3 + 1.5 * iqr) \n",
    "print('IQR = ', iqr, '\\nlower = ', lower, '\\nupper = ', upper, sep='')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "execution": {
     "iopub.execute_input": "2022-12-27T18:32:11.874563Z",
     "iopub.status.busy": "2022-12-27T18:32:11.873563Z",
     "iopub.status.idle": "2022-12-27T18:32:11.889349Z",
     "shell.execute_reply": "2022-12-27T18:32:11.888085Z",
     "shell.execute_reply.started": "2022-12-27T18:32:11.874517Z"
    },
    "id": "7Bi4KyUOK5uu",
    "outputId": "189f296a-a9b6-4c07-cdf3-d5c7cd94e147"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "count    319.000000\n",
       "mean      40.356426\n",
       "std       57.427921\n",
       "min        0.000000\n",
       "25%        1.255000\n",
       "50%        5.070000\n",
       "75%       62.095000\n",
       "max      153.355000\n",
       "Name: Subscription_HNI, dtype: float64"
      ]
     },
     "execution_count": 54,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['Subscription_HNI'] = df['Subscription_HNI'].clip(lower, upper)\n",
    "df['Subscription_HNI'].describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "execution": {
     "iopub.execute_input": "2022-12-27T18:32:11.891309Z",
     "iopub.status.busy": "2022-12-27T18:32:11.890841Z",
     "iopub.status.idle": "2022-12-27T18:32:11.903508Z",
     "shell.execute_reply": "2022-12-27T18:32:11.902206Z",
     "shell.execute_reply.started": "2022-12-27T18:32:11.891254Z"
    },
    "id": "ynAHmlw4K5uu",
    "outputId": "32547e3f-effb-4be6-b31f-d94e5ca8fc15"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "IQR = 7.33\n",
      "lower = -9.72\n",
      "upper = 19.6\n"
     ]
    }
   ],
   "source": [
    "q1 = df['Subscription_RII'].quantile(q=0.25)\n",
    "q3 = df['Subscription_RII'].quantile(q=0.75)  \n",
    "iqr = q3 - q1   \n",
    "lower = (q1 - 1.5 * iqr) \n",
    "upper = (q3 + 1.5 * iqr) \n",
    "print('IQR = ', iqr, '\\nlower = ', lower, '\\nupper = ', upper, sep='')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "execution": {
     "iopub.execute_input": "2022-12-27T18:32:11.905291Z",
     "iopub.status.busy": "2022-12-27T18:32:11.904829Z",
     "iopub.status.idle": "2022-12-27T18:32:11.920193Z",
     "shell.execute_reply": "2022-12-27T18:32:11.919398Z",
     "shell.execute_reply.started": "2022-12-27T18:32:11.905250Z"
    },
    "id": "IjQZoL6KK5uu",
    "outputId": "30c6be06-c313-4ea4-a481-03e0c34b3452"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "count    319.000000\n",
       "mean       6.060940\n",
       "std        6.176882\n",
       "min        0.000000\n",
       "25%        1.275000\n",
       "50%        3.420000\n",
       "75%        8.605000\n",
       "max       19.600000\n",
       "Name: Subscription_RII, dtype: float64"
      ]
     },
     "execution_count": 56,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['Subscription_RII'] = df['Subscription_RII'].clip(lower, upper)\n",
    "df['Subscription_RII'].describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "execution": {
     "iopub.execute_input": "2022-12-27T18:32:11.921919Z",
     "iopub.status.busy": "2022-12-27T18:32:11.921276Z",
     "iopub.status.idle": "2022-12-27T18:32:11.935310Z",
     "shell.execute_reply": "2022-12-27T18:32:11.934484Z",
     "shell.execute_reply.started": "2022-12-27T18:32:11.921885Z"
    },
    "id": "jDf0sDipK5uu",
    "outputId": "a2f3cd7c-2456-4217-df5c-1b4f019af4fc"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "IQR = 31.749999999999996\n",
      "lower = -45.97999999999999\n",
      "upper = 81.01999999999998\n"
     ]
    }
   ],
   "source": [
    "q1 = df['Subscription_Total'].quantile(q=0.25)\n",
    "q3 = df['Subscription_Total'].quantile(q=0.75)  \n",
    "iqr = q3 - q1   \n",
    "lower = (q1 - 1.5 * iqr) \n",
    "upper = (q3 + 1.5 * iqr) \n",
    "print('IQR = ', iqr, '\\nlower = ', lower, '\\nupper = ', upper, sep='')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "execution": {
     "iopub.execute_input": "2022-12-27T18:32:11.937247Z",
     "iopub.status.busy": "2022-12-27T18:32:11.936404Z",
     "iopub.status.idle": "2022-12-27T18:32:11.952110Z",
     "shell.execute_reply": "2022-12-27T18:32:11.951342Z",
     "shell.execute_reply.started": "2022-12-27T18:32:11.937211Z"
    },
    "id": "nrK_ia3IK5uu",
    "outputId": "329220ea-eb96-4a7e-c206-479a8a735e36"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "count    319.000000\n",
       "mean      20.456646\n",
       "std       27.217740\n",
       "min        0.000000\n",
       "25%        1.645000\n",
       "50%        4.930000\n",
       "75%       33.395000\n",
       "max       81.020000\n",
       "Name: Subscription_Total, dtype: float64"
      ]
     },
     "execution_count": 58,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['Subscription_Total'] = df['Subscription_Total'].clip(lower, upper)\n",
    "df['Subscription_Total'].describe()"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {
    "id": "0FdzVKR3K5uv"
   },
   "source": [
    "## Setting the Target and Predictor Variables\n",
    "Before moving on to modelling, I will:\n",
    "- Create an array of the target variable (dependent variable).\n",
    "- Create an array of the predictor variables (independent variables).\n",
    "- Perform normalization on the predictor variables to scale their values to between 0 and 1."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 300
    },
    "execution": {
     "iopub.execute_input": "2022-12-27T18:32:11.953327Z",
     "iopub.status.busy": "2022-12-27T18:32:11.953000Z",
     "iopub.status.idle": "2022-12-27T18:32:11.996296Z",
     "shell.execute_reply": "2022-12-27T18:32:11.995087Z",
     "shell.execute_reply.started": "2022-12-27T18:32:11.953297Z"
    },
    "id": "lnCJqqTzK5uv",
    "outputId": "d8a74d8b-72c1-4c15-8231-9c793f9733bf"
   },
   "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>Issue_Size</th>\n",
       "      <th>Subscription_QIB</th>\n",
       "      <th>Subscription_HNI</th>\n",
       "      <th>Subscription_RII</th>\n",
       "      <th>Subscription_Total</th>\n",
       "      <th>Issue_Price</th>\n",
       "      <th>Listing_Gains_Profit</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>319.000000</td>\n",
       "      <td>319.000000</td>\n",
       "      <td>319.000000</td>\n",
       "      <td>319.000000</td>\n",
       "      <td>319.000000</td>\n",
       "      <td>319.000000</td>\n",
       "      <td>319.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>0.305854</td>\n",
       "      <td>0.253601</td>\n",
       "      <td>0.263157</td>\n",
       "      <td>0.309232</td>\n",
       "      <td>0.252489</td>\n",
       "      <td>0.174478</td>\n",
       "      <td>0.545455</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>0.308308</td>\n",
       "      <td>0.342961</td>\n",
       "      <td>0.374477</td>\n",
       "      <td>0.315147</td>\n",
       "      <td>0.335939</td>\n",
       "      <td>0.164604</td>\n",
       "      <td>0.498712</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>0.067697</td>\n",
       "      <td>0.013551</td>\n",
       "      <td>0.008184</td>\n",
       "      <td>0.065051</td>\n",
       "      <td>0.020304</td>\n",
       "      <td>0.055349</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>0.198779</td>\n",
       "      <td>0.058212</td>\n",
       "      <td>0.033061</td>\n",
       "      <td>0.174490</td>\n",
       "      <td>0.060849</td>\n",
       "      <td>0.116279</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>0.440618</td>\n",
       "      <td>0.408131</td>\n",
       "      <td>0.404910</td>\n",
       "      <td>0.439031</td>\n",
       "      <td>0.412182</td>\n",
       "      <td>0.249302</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       Issue_Size  Subscription_QIB  Subscription_HNI  Subscription_RII   \n",
       "count  319.000000        319.000000        319.000000        319.000000  \\\n",
       "mean     0.305854          0.253601          0.263157          0.309232   \n",
       "std      0.308308          0.342961          0.374477          0.315147   \n",
       "min      0.000000          0.000000          0.000000          0.000000   \n",
       "25%      0.067697          0.013551          0.008184          0.065051   \n",
       "50%      0.198779          0.058212          0.033061          0.174490   \n",
       "75%      0.440618          0.408131          0.404910          0.439031   \n",
       "max      1.000000          1.000000          1.000000          1.000000   \n",
       "\n",
       "       Subscription_Total  Issue_Price  Listing_Gains_Profit  \n",
       "count          319.000000   319.000000            319.000000  \n",
       "mean             0.252489     0.174478              0.545455  \n",
       "std              0.335939     0.164604              0.498712  \n",
       "min              0.000000     0.000000              0.000000  \n",
       "25%              0.020304     0.055349              0.000000  \n",
       "50%              0.060849     0.116279              1.000000  \n",
       "75%              0.412182     0.249302              1.000000  \n",
       "max              1.000000     1.000000              1.000000  "
      ]
     },
     "execution_count": 59,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "target_variable = ['Listing_Gains_Profit'] \n",
    "predictors = list(set(list(df.columns)) - set(target_variable))\n",
    "df[predictors] = df[predictors]/df[predictors].max()\n",
    "df.describe()"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {
    "id": "Re0qt2A7K5uv"
   },
   "source": [
    "## Creating the Holdout Validation Approach\n",
    "I will use the hold out validation approach to model evaluation. In this approach, I will divide the data in the 70:30 ratio, where I will use 70% of the data for training the model, while I will use the other 30% of the data to test the model."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "execution": {
     "iopub.execute_input": "2022-12-27T18:32:11.997760Z",
     "iopub.status.busy": "2022-12-27T18:32:11.997459Z",
     "iopub.status.idle": "2022-12-27T18:32:12.007201Z",
     "shell.execute_reply": "2022-12-27T18:32:12.006116Z",
     "shell.execute_reply.started": "2022-12-27T18:32:11.997732Z"
    },
    "id": "79ia8fAdK5uv",
    "outputId": "831e6c4e-fd28-4311-f1c1-db69f0d196e9"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(223, 6)\n",
      "(96, 6)\n"
     ]
    }
   ],
   "source": [
    "X = df[predictors].values\n",
    "y = df[target_variable].values\n",
    "\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.30, random_state=100)\n",
    "print(X_train.shape); print(X_test.shape)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {
    "id": "hbdwpVyOK5uv"
   },
   "source": [
    "## Define the Deep Learning Classification Model\n",
    "In this step, I've defined the model by instantiating the sequential model class in TensorFlow's Keras. The model architecture is comprised of four hidden layers with `relu` as the activation function. The output layer uses a `sigmoid` activation function, which is a good choice for a binary classification model."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-12-27T18:32:12.009002Z",
     "iopub.status.busy": "2022-12-27T18:32:12.008652Z",
     "iopub.status.idle": "2022-12-27T18:32:12.162585Z",
     "shell.execute_reply": "2022-12-27T18:32:12.161353Z",
     "shell.execute_reply.started": "2022-12-27T18:32:12.008972Z"
    },
    "id": "5fE0bP4rK5uv"
   },
   "outputs": [],
   "source": [
    "# define model\n",
    "tf.random.set_seed(100)\n",
    "model = tf.keras.Sequential()\n",
    "model.add(tf.keras.layers.Dense(32, input_shape = (X_train.shape[1],), activation = 'relu'))\n",
    "model.add(tf.keras.layers.Dense(16, activation= 'relu'))\n",
    "model.add(tf.keras.layers.Dense(8, activation= 'relu'))\n",
    "model.add(tf.keras.layers.Dense(4, activation= 'relu'))\n",
    "model.add(tf.keras.layers.Dense(1, activation='sigmoid'))    "
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {
    "id": "_8zUg4DyK5uw"
   },
   "source": [
    "## Compile and Train the Model\n",
    "Once I have defined the model, the next steps are to compile and train it. Compiling a model requires specification of the following:\n",
    "- An optimizer\n",
    "- A loss function\n",
    "- An evaluation metric\n",
    "\n",
    "After compiling the model, I fitted it on the training set. The accuracy improved over epochs. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "execution": {
     "iopub.execute_input": "2022-12-27T18:35:30.988666Z",
     "iopub.status.busy": "2022-12-27T18:35:30.987862Z",
     "iopub.status.idle": "2022-12-27T18:35:30.995402Z",
     "shell.execute_reply": "2022-12-27T18:35:30.994354Z",
     "shell.execute_reply.started": "2022-12-27T18:35:30.988624Z"
    },
    "id": "IPz2XmGoK5uw",
    "outputId": "3c333a63-86a1-43d7-cfc1-b6787f6ee1a0"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model: \"sequential\"\n",
      "_________________________________________________________________\n",
      " Layer (type)                Output Shape              Param #   \n",
      "=================================================================\n",
      " dense (Dense)               (None, 32)                224       \n",
      "                                                                 \n",
      " dense_1 (Dense)             (None, 16)                528       \n",
      "                                                                 \n",
      " dense_2 (Dense)             (None, 8)                 136       \n",
      "                                                                 \n",
      " dense_3 (Dense)             (None, 4)                 36        \n",
      "                                                                 \n",
      " dense_4 (Dense)             (None, 1)                 5         \n",
      "                                                                 \n",
      "=================================================================\n",
      "Total params: 929\n",
      "Trainable params: 929\n",
      "Non-trainable params: 0\n",
      "_________________________________________________________________\n",
      "None\n"
     ]
    }
   ],
   "source": [
    "model.compile(optimizer=tf.keras.optimizers.Adam(0.001), loss=tf.keras.losses.BinaryCrossentropy(), metrics=['accuracy'])\n",
    "print(model.summary())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "execution": {
     "iopub.execute_input": "2022-12-27T18:47:17.359902Z",
     "iopub.status.busy": "2022-12-27T18:47:17.359424Z",
     "iopub.status.idle": "2022-12-27T18:47:23.418354Z",
     "shell.execute_reply": "2022-12-27T18:47:23.417193Z",
     "shell.execute_reply.started": "2022-12-27T18:47:17.359866Z"
    },
    "id": "2hFSDV0oK5uw",
    "outputId": "15f1297b-d73d-4764-d75a-4b873e8a424c"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/250\n",
      "7/7 [==============================] - 1s 3ms/step - loss: 0.6899 - accuracy: 0.5874\n",
      "Epoch 2/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.6859 - accuracy: 0.5650\n",
      "Epoch 3/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.6826 - accuracy: 0.5516\n",
      "Epoch 4/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.6771 - accuracy: 0.5561\n",
      "Epoch 5/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.6729 - accuracy: 0.5561\n",
      "Epoch 6/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.6680 - accuracy: 0.5561\n",
      "Epoch 7/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.6629 - accuracy: 0.5561\n",
      "Epoch 8/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.6586 - accuracy: 0.5561\n",
      "Epoch 9/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.6536 - accuracy: 0.5561\n",
      "Epoch 10/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.6493 - accuracy: 0.5561\n",
      "Epoch 11/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.6454 - accuracy: 0.5561\n",
      "Epoch 12/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.6416 - accuracy: 0.5561\n",
      "Epoch 13/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.6383 - accuracy: 0.5516\n",
      "Epoch 14/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.6351 - accuracy: 0.5919\n",
      "Epoch 15/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.6330 - accuracy: 0.6368\n",
      "Epoch 16/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.6303 - accuracy: 0.6502\n",
      "Epoch 17/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.6275 - accuracy: 0.6771\n",
      "Epoch 18/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.6262 - accuracy: 0.6726\n",
      "Epoch 19/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.6249 - accuracy: 0.6592\n",
      "Epoch 20/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.6232 - accuracy: 0.6816\n",
      "Epoch 21/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.6214 - accuracy: 0.6771\n",
      "Epoch 22/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.6206 - accuracy: 0.6682\n",
      "Epoch 23/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.6190 - accuracy: 0.6726\n",
      "Epoch 24/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.6182 - accuracy: 0.6726\n",
      "Epoch 25/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.6167 - accuracy: 0.6682\n",
      "Epoch 26/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.6164 - accuracy: 0.6771\n",
      "Epoch 27/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.6159 - accuracy: 0.6592\n",
      "Epoch 28/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.6138 - accuracy: 0.6637\n",
      "Epoch 29/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.6127 - accuracy: 0.6592\n",
      "Epoch 30/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.6119 - accuracy: 0.6682\n",
      "Epoch 31/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.6103 - accuracy: 0.6726\n",
      "Epoch 32/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.6101 - accuracy: 0.6816\n",
      "Epoch 33/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.6082 - accuracy: 0.6726\n",
      "Epoch 34/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.6069 - accuracy: 0.6771\n",
      "Epoch 35/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.6055 - accuracy: 0.6816\n",
      "Epoch 36/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.6051 - accuracy: 0.6861\n",
      "Epoch 37/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.6036 - accuracy: 0.6861\n",
      "Epoch 38/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.6027 - accuracy: 0.6816\n",
      "Epoch 39/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.6022 - accuracy: 0.6816\n",
      "Epoch 40/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.6014 - accuracy: 0.6816\n",
      "Epoch 41/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.5998 - accuracy: 0.6861\n",
      "Epoch 42/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5992 - accuracy: 0.6816\n",
      "Epoch 43/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.5980 - accuracy: 0.6861\n",
      "Epoch 44/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.5977 - accuracy: 0.6861\n",
      "Epoch 45/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5966 - accuracy: 0.6906\n",
      "Epoch 46/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.5967 - accuracy: 0.6861\n",
      "Epoch 47/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.5951 - accuracy: 0.6816\n",
      "Epoch 48/250\n",
      "7/7 [==============================] - 0s 6ms/step - loss: 0.5938 - accuracy: 0.6771\n",
      "Epoch 49/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5927 - accuracy: 0.6771\n",
      "Epoch 50/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5919 - accuracy: 0.6861\n",
      "Epoch 51/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.5924 - accuracy: 0.6816\n",
      "Epoch 52/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5903 - accuracy: 0.6771\n",
      "Epoch 53/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5900 - accuracy: 0.6816\n",
      "Epoch 54/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5895 - accuracy: 0.6816\n",
      "Epoch 55/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.5878 - accuracy: 0.6906\n",
      "Epoch 56/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.5878 - accuracy: 0.6816\n",
      "Epoch 57/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5881 - accuracy: 0.6906\n",
      "Epoch 58/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5854 - accuracy: 0.6816\n",
      "Epoch 59/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5848 - accuracy: 0.6771\n",
      "Epoch 60/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5844 - accuracy: 0.6861\n",
      "Epoch 61/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.5825 - accuracy: 0.6861\n",
      "Epoch 62/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.5820 - accuracy: 0.6816\n",
      "Epoch 63/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5837 - accuracy: 0.6816\n",
      "Epoch 64/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5818 - accuracy: 0.6861\n",
      "Epoch 65/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5806 - accuracy: 0.6906\n",
      "Epoch 66/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5800 - accuracy: 0.6861\n",
      "Epoch 67/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5794 - accuracy: 0.6906\n",
      "Epoch 68/250\n",
      "7/7 [==============================] - 0s 3ms/step - loss: 0.5784 - accuracy: 0.6861\n",
      "Epoch 69/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.5789 - accuracy: 0.6771\n",
      "Epoch 70/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5769 - accuracy: 0.6816\n",
      "Epoch 71/250\n",
      "7/7 [==============================] - 0s 3ms/step - loss: 0.5761 - accuracy: 0.6906\n",
      "Epoch 72/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5760 - accuracy: 0.6906\n",
      "Epoch 73/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5773 - accuracy: 0.6906\n",
      "Epoch 74/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5762 - accuracy: 0.6726\n",
      "Epoch 75/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.5742 - accuracy: 0.6951\n",
      "Epoch 76/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5727 - accuracy: 0.6951\n",
      "Epoch 77/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5726 - accuracy: 0.6861\n",
      "Epoch 78/250\n",
      "7/7 [==============================] - 0s 3ms/step - loss: 0.5727 - accuracy: 0.6726\n",
      "Epoch 79/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5728 - accuracy: 0.6951\n",
      "Epoch 80/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5730 - accuracy: 0.6906\n",
      "Epoch 81/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5706 - accuracy: 0.6771\n",
      "Epoch 82/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5703 - accuracy: 0.6951\n",
      "Epoch 83/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5696 - accuracy: 0.6906\n",
      "Epoch 84/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5693 - accuracy: 0.6816\n",
      "Epoch 85/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5677 - accuracy: 0.6906\n",
      "Epoch 86/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.5702 - accuracy: 0.6996\n",
      "Epoch 87/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.5673 - accuracy: 0.7040\n",
      "Epoch 88/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5664 - accuracy: 0.6951\n",
      "Epoch 89/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5679 - accuracy: 0.6951\n",
      "Epoch 90/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5656 - accuracy: 0.6951\n",
      "Epoch 91/250\n",
      "7/7 [==============================] - 0s 5ms/step - loss: 0.5664 - accuracy: 0.6951\n",
      "Epoch 92/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5664 - accuracy: 0.6816\n",
      "Epoch 93/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5645 - accuracy: 0.6996\n",
      "Epoch 94/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5646 - accuracy: 0.6996\n",
      "Epoch 95/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5644 - accuracy: 0.6906\n",
      "Epoch 96/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5642 - accuracy: 0.6906\n",
      "Epoch 97/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5621 - accuracy: 0.6906\n",
      "Epoch 98/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.5634 - accuracy: 0.6951\n",
      "Epoch 99/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5623 - accuracy: 0.6996\n",
      "Epoch 100/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5616 - accuracy: 0.6996\n",
      "Epoch 101/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5607 - accuracy: 0.6951\n",
      "Epoch 102/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5606 - accuracy: 0.6951\n",
      "Epoch 103/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5603 - accuracy: 0.6951\n",
      "Epoch 104/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5594 - accuracy: 0.6996\n",
      "Epoch 105/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5590 - accuracy: 0.6951\n",
      "Epoch 106/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.5603 - accuracy: 0.6906\n",
      "Epoch 107/250\n",
      "7/7 [==============================] - 0s 3ms/step - loss: 0.5582 - accuracy: 0.6951\n",
      "Epoch 108/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5595 - accuracy: 0.6951\n",
      "Epoch 109/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5593 - accuracy: 0.6906\n",
      "Epoch 110/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.5569 - accuracy: 0.6996\n",
      "Epoch 111/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.5602 - accuracy: 0.6996\n",
      "Epoch 112/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.5588 - accuracy: 0.6906\n",
      "Epoch 113/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5573 - accuracy: 0.6951\n",
      "Epoch 114/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.5553 - accuracy: 0.6996\n",
      "Epoch 115/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5563 - accuracy: 0.6906\n",
      "Epoch 116/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5556 - accuracy: 0.6951\n",
      "Epoch 117/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5558 - accuracy: 0.6996\n",
      "Epoch 118/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5546 - accuracy: 0.6951\n",
      "Epoch 119/250\n",
      "7/7 [==============================] - 0s 7ms/step - loss: 0.5539 - accuracy: 0.6996\n",
      "Epoch 120/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5586 - accuracy: 0.6951\n",
      "Epoch 121/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.5563 - accuracy: 0.6996\n",
      "Epoch 122/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5536 - accuracy: 0.6996\n",
      "Epoch 123/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5539 - accuracy: 0.6951\n",
      "Epoch 124/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5539 - accuracy: 0.6951\n",
      "Epoch 125/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5524 - accuracy: 0.6996\n",
      "Epoch 126/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5523 - accuracy: 0.7040\n",
      "Epoch 127/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5521 - accuracy: 0.6996\n",
      "Epoch 128/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5560 - accuracy: 0.6906\n",
      "Epoch 129/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5521 - accuracy: 0.6951\n",
      "Epoch 130/250\n",
      "7/7 [==============================] - 0s 3ms/step - loss: 0.5582 - accuracy: 0.6951\n",
      "Epoch 131/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5535 - accuracy: 0.7085\n",
      "Epoch 132/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5535 - accuracy: 0.6906\n",
      "Epoch 133/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5521 - accuracy: 0.7040\n",
      "Epoch 134/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.5500 - accuracy: 0.7085\n",
      "Epoch 135/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.5489 - accuracy: 0.6996\n",
      "Epoch 136/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.5491 - accuracy: 0.6996\n",
      "Epoch 137/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5497 - accuracy: 0.7040\n",
      "Epoch 138/250\n",
      "7/7 [==============================] - 0s 3ms/step - loss: 0.5479 - accuracy: 0.6951\n",
      "Epoch 139/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.5522 - accuracy: 0.7040\n",
      "Epoch 140/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.5480 - accuracy: 0.6951\n",
      "Epoch 141/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5484 - accuracy: 0.6906\n",
      "Epoch 142/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5467 - accuracy: 0.7040\n",
      "Epoch 143/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5458 - accuracy: 0.6996\n",
      "Epoch 144/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5461 - accuracy: 0.7085\n",
      "Epoch 145/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5451 - accuracy: 0.7040\n",
      "Epoch 146/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5463 - accuracy: 0.6951\n",
      "Epoch 147/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5465 - accuracy: 0.6996\n",
      "Epoch 148/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5471 - accuracy: 0.6951\n",
      "Epoch 149/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5441 - accuracy: 0.7040\n",
      "Epoch 150/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.5447 - accuracy: 0.6996\n",
      "Epoch 151/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.5437 - accuracy: 0.6951\n",
      "Epoch 152/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.5430 - accuracy: 0.7040\n",
      "Epoch 153/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.5430 - accuracy: 0.6996\n",
      "Epoch 154/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5433 - accuracy: 0.7040\n",
      "Epoch 155/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5457 - accuracy: 0.6951\n",
      "Epoch 156/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5419 - accuracy: 0.6996\n",
      "Epoch 157/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5410 - accuracy: 0.6996\n",
      "Epoch 158/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5424 - accuracy: 0.6996\n",
      "Epoch 159/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5405 - accuracy: 0.6996\n",
      "Epoch 160/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5420 - accuracy: 0.6996\n",
      "Epoch 161/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.5403 - accuracy: 0.7040\n",
      "Epoch 162/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5420 - accuracy: 0.7040\n",
      "Epoch 163/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.5400 - accuracy: 0.6996\n",
      "Epoch 164/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.5402 - accuracy: 0.6996\n",
      "Epoch 165/250\n",
      "7/7 [==============================] - 0s 7ms/step - loss: 0.5392 - accuracy: 0.7040\n",
      "Epoch 166/250\n",
      "7/7 [==============================] - 0s 3ms/step - loss: 0.5383 - accuracy: 0.7040\n",
      "Epoch 167/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5407 - accuracy: 0.6996\n",
      "Epoch 168/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5399 - accuracy: 0.6996\n",
      "Epoch 169/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5378 - accuracy: 0.6996\n",
      "Epoch 170/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5429 - accuracy: 0.6951\n",
      "Epoch 171/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.5371 - accuracy: 0.6996\n",
      "Epoch 172/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5412 - accuracy: 0.7040\n",
      "Epoch 173/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5403 - accuracy: 0.6996\n",
      "Epoch 174/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5384 - accuracy: 0.7085\n",
      "Epoch 175/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5375 - accuracy: 0.6996\n",
      "Epoch 176/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5390 - accuracy: 0.6996\n",
      "Epoch 177/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5371 - accuracy: 0.7040\n",
      "Epoch 178/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5365 - accuracy: 0.7085\n",
      "Epoch 179/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5341 - accuracy: 0.6996\n",
      "Epoch 180/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5339 - accuracy: 0.7085\n",
      "Epoch 181/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5345 - accuracy: 0.7085\n",
      "Epoch 182/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5340 - accuracy: 0.6996\n",
      "Epoch 183/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5338 - accuracy: 0.7085\n",
      "Epoch 184/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5344 - accuracy: 0.7130\n",
      "Epoch 185/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5323 - accuracy: 0.7040\n",
      "Epoch 186/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5335 - accuracy: 0.7040\n",
      "Epoch 187/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.5329 - accuracy: 0.7040\n",
      "Epoch 188/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.5317 - accuracy: 0.7040\n",
      "Epoch 189/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5309 - accuracy: 0.7040\n",
      "Epoch 190/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.5312 - accuracy: 0.7130\n",
      "Epoch 191/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.5297 - accuracy: 0.7085\n",
      "Epoch 192/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5434 - accuracy: 0.6906\n",
      "Epoch 193/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.5351 - accuracy: 0.7220\n",
      "Epoch 194/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5352 - accuracy: 0.7130\n",
      "Epoch 195/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5300 - accuracy: 0.7040\n",
      "Epoch 196/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5301 - accuracy: 0.7085\n",
      "Epoch 197/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.5288 - accuracy: 0.7130\n",
      "Epoch 198/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5309 - accuracy: 0.7085\n",
      "Epoch 199/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.5329 - accuracy: 0.7040\n",
      "Epoch 200/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5289 - accuracy: 0.7175\n",
      "Epoch 201/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.5306 - accuracy: 0.7130\n",
      "Epoch 202/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.5285 - accuracy: 0.7130\n",
      "Epoch 203/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.5285 - accuracy: 0.7175\n",
      "Epoch 204/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5302 - accuracy: 0.7175\n",
      "Epoch 205/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5253 - accuracy: 0.7085\n",
      "Epoch 206/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5283 - accuracy: 0.7175\n",
      "Epoch 207/250\n",
      "7/7 [==============================] - 0s 3ms/step - loss: 0.5265 - accuracy: 0.7220\n",
      "Epoch 208/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5279 - accuracy: 0.7175\n",
      "Epoch 209/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.5293 - accuracy: 0.7130\n",
      "Epoch 210/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5273 - accuracy: 0.7175\n",
      "Epoch 211/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5259 - accuracy: 0.7130\n",
      "Epoch 212/250\n",
      "7/7 [==============================] - 0s 8ms/step - loss: 0.5260 - accuracy: 0.7175\n",
      "Epoch 213/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5232 - accuracy: 0.7220\n",
      "Epoch 214/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5235 - accuracy: 0.7130\n",
      "Epoch 215/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5220 - accuracy: 0.7130\n",
      "Epoch 216/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5216 - accuracy: 0.7085\n",
      "Epoch 217/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5231 - accuracy: 0.7130\n",
      "Epoch 218/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.5244 - accuracy: 0.7130\n",
      "Epoch 219/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.5222 - accuracy: 0.7085\n",
      "Epoch 220/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.5197 - accuracy: 0.7130\n",
      "Epoch 221/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5198 - accuracy: 0.7175\n",
      "Epoch 222/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5199 - accuracy: 0.7130\n",
      "Epoch 223/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5191 - accuracy: 0.7130\n",
      "Epoch 224/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5181 - accuracy: 0.7175\n",
      "Epoch 225/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.5191 - accuracy: 0.7220\n",
      "Epoch 226/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5186 - accuracy: 0.7309\n",
      "Epoch 227/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5196 - accuracy: 0.7309\n",
      "Epoch 228/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5208 - accuracy: 0.7085\n",
      "Epoch 229/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5169 - accuracy: 0.7220\n",
      "Epoch 230/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5179 - accuracy: 0.7220\n",
      "Epoch 231/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5168 - accuracy: 0.7220\n",
      "Epoch 232/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5157 - accuracy: 0.7354\n",
      "Epoch 233/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5149 - accuracy: 0.7309\n",
      "Epoch 234/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5158 - accuracy: 0.7309\n",
      "Epoch 235/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.5143 - accuracy: 0.7444\n",
      "Epoch 236/250\n",
      "7/7 [==============================] - 0s 7ms/step - loss: 0.5188 - accuracy: 0.7265\n",
      "Epoch 237/250\n",
      "7/7 [==============================] - 0s 3ms/step - loss: 0.5144 - accuracy: 0.7399\n",
      "Epoch 238/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5142 - accuracy: 0.7354\n",
      "Epoch 239/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5154 - accuracy: 0.7399\n",
      "Epoch 240/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5136 - accuracy: 0.7220\n",
      "Epoch 241/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.5148 - accuracy: 0.7354\n",
      "Epoch 242/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.5123 - accuracy: 0.7354\n",
      "Epoch 243/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5125 - accuracy: 0.7309\n",
      "Epoch 244/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.5116 - accuracy: 0.7265\n",
      "Epoch 245/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5112 - accuracy: 0.7354\n",
      "Epoch 246/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5116 - accuracy: 0.7220\n",
      "Epoch 247/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5117 - accuracy: 0.7220\n",
      "Epoch 248/250\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5118 - accuracy: 0.7399\n",
      "Epoch 249/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.5132 - accuracy: 0.7444\n",
      "Epoch 250/250\n",
      "7/7 [==============================] - 0s 1ms/step - loss: 0.5092 - accuracy: 0.7354\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<keras.callbacks.History at 0x290a4944cd0>"
      ]
     },
     "execution_count": 63,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.fit(X_train, y_train, epochs=250)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {
    "id": "w6VAo-ZNK5uw"
   },
   "source": [
    "## Model Evaluation\n",
    "The model evaluation output shows the performance of the model on both training and test data. The accuracy was approximately 75% on the training data and 74% on the test data. It's noteworthy that the training and test set accuracies are close to each other, which shows that there is consistency, and that the accuracy doesn't drop too much when I test the model on unseen data. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "execution": {
     "iopub.execute_input": "2022-12-27T18:49:59.562231Z",
     "iopub.status.busy": "2022-12-27T18:49:59.561787Z",
     "iopub.status.idle": "2022-12-27T18:49:59.828505Z",
     "shell.execute_reply": "2022-12-27T18:49:59.827266Z",
     "shell.execute_reply.started": "2022-12-27T18:49:59.562197Z"
    },
    "id": "k2GEaWbtK5ux",
    "outputId": "90ff685a-f1bb-467f-97fe-9f03d1c0b6ea"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "7/7 [==============================] - 0s 2ms/step - loss: 0.5101 - accuracy: 0.7354\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "[0.5101242661476135, 0.7354260087013245]"
      ]
     },
     "execution_count": 64,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.evaluate(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "execution": {
     "iopub.execute_input": "2022-12-27T18:50:03.037461Z",
     "iopub.status.busy": "2022-12-27T18:50:03.036767Z",
     "iopub.status.idle": "2022-12-27T18:50:03.252629Z",
     "shell.execute_reply": "2022-12-27T18:50:03.251550Z",
     "shell.execute_reply.started": "2022-12-27T18:50:03.037425Z"
    },
    "id": "Rv1vr_EdK5ux",
    "outputId": "ffc7f898-ff5d-4cf6-96e2-36f27d5ae678"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "3/3 [==============================] - 0s 1ms/step - loss: 0.6855 - accuracy: 0.7083\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "[0.6855059266090393, 0.7083333134651184]"
      ]
     },
     "execution_count": 65,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.evaluate(X_test, y_test)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {
    "id": "M_sIj5bVK5ux"
   },
   "source": [
    "## Conclusion\n",
    "\n",
    "I have built a deep learning classification model using the deep learning framework, Keras, in TensorFlow. I used a IPO dataset and built a classifier algorithm to predict whether an IPO will list at profit or not. I used the Sequential API to build the model, which is achieving a decent accuracy of 75% and 74% on training and test data, respectively. I see that the accuracy is consistent across the training and test datasets, which is a promising sign. This model can be useful to make investment decisions in the IPO market.\n"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# PS: Alternative Approach via Functional API"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model: \"model_2\"\n",
      "_________________________________________________________________\n",
      " Layer (type)                Output Shape              Param #   \n",
      "=================================================================\n",
      " input_3 (InputLayer)        [(None, 6)]               0         \n",
      "                                                                 \n",
      " dense_17 (Dense)            (None, 128)               896       \n",
      "                                                                 \n",
      " dropout_4 (Dropout)         (None, 128)               0         \n",
      "                                                                 \n",
      " dense_18 (Dense)            (None, 64)                8256      \n",
      "                                                                 \n",
      " dropout_5 (Dropout)         (None, 64)                0         \n",
      "                                                                 \n",
      " dense_19 (Dense)            (None, 16)                1040      \n",
      "                                                                 \n",
      " dense_20 (Dense)            (None, 8)                 136       \n",
      "                                                                 \n",
      " dense_21 (Dense)            (None, 4)                 36        \n",
      "                                                                 \n",
      " dense_22 (Dense)            (None, 1)                 5         \n",
      "                                                                 \n",
      "=================================================================\n",
      "Total params: 10,369\n",
      "Trainable params: 10,369\n",
      "Non-trainable params: 0\n",
      "_________________________________________________________________\n",
      "None\n",
      "7/7 [==============================] - 0s 2ms/step - loss: 0.4684 - accuracy: 0.7668\n",
      "[0.4683583080768585, 0.7668161392211914]\n",
      "3/3 [==============================] - 0s 3ms/step - loss: 0.6766 - accuracy: 0.6875\n",
      "[0.6766266822814941, 0.6875]\n"
     ]
    }
   ],
   "source": [
    "input_layer = tf.keras.Input(shape=(X_train.shape[1],))\n",
    "hidden_layer1 = tf.keras.layers.Dense(128, activation='relu')(input_layer)\n",
    "drop1 = tf.keras.layers.Dropout(rate=0.40)(hidden_layer1)\n",
    "hidden_layer2 = tf.keras.layers.Dense(64, activation='relu')(drop1)\n",
    "drop2 =tf.keras.layers.Dropout(rate=0.20)(hidden_layer2)\n",
    "hidden_layer3 = tf.keras.layers.Dense(16, activation='relu')(drop2)\n",
    "hidden_layer4 = tf.keras.layers.Dense(8, activation='relu')(hidden_layer3)\n",
    "hidden_layer5 = tf.keras.layers.Dense(4, activation='relu')(hidden_layer4)\n",
    "output_layer = tf.keras.layers.Dense(1, activation='sigmoid')(hidden_layer5)\n",
    "model = tf.keras.Model(inputs=input_layer, outputs=output_layer)\n",
    "print(model.summary())\n",
    "\n",
    "optimizer = tf.keras.optimizers.Adam(0.001)\n",
    "\n",
    "loss = tf.keras.losses.BinaryCrossentropy()\n",
    "\n",
    "metrics = ['accuracy']\n",
    "\n",
    "model.compile(optimizer=optimizer, loss=loss, metrics=metrics)\n",
    "model.fit(X_train, y_train, epochs=250, verbose=0)\n",
    "print(model.evaluate(X_train, y_train))\n",
    "print(model.evaluate(X_test, y_test))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "colab": {
   "provenance": []
  },
  "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": "3.11.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}