{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "id": "xwFyEsosINqT"
   },
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "id": "pKewSQysItJ-"
   },
   "outputs": [],
   "source": [
    "# https://www.statsmodels.org/stable/index.html\n",
    "import statsmodels.api as sm"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "id": "Lz-DyAtNWsJR"
   },
   "outputs": [],
   "source": [
    "# Download Dataset from https://www.dropbox.com/scl/fi/zt2vtwhpz8ndblsxqdqx1/Salary_MIS.xlsx?rlkey=2uk6m7m9w90isv6zsynhhhpyv&st=gxumjns5&dl=1\n",
    "# and add it to colab"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "id": "6rRHygNBIpgA"
   },
   "outputs": [],
   "source": [
    "sallaryMisDf = pd.read_excel(\"https://www.dropbox.com/scl/fi/zt2vtwhpz8ndblsxqdqx1/Salary_MIS.xlsx?rlkey=2uk6m7m9w90isv6zsynhhhpyv&st=gxumjns5&dl=1\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "id": "0zM8FGMJXJ70"
   },
   "outputs": [],
   "source": [
    "# sallaryMisDf = pd.read_excel(\"./Salary_MIS.xlsx\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "id": "wsIgDGYcXT_z"
   },
   "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>Salary</th>\n",
       "      <th>GPA</th>\n",
       "      <th>MIS</th>\n",
       "      <th>Statistics</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>72</td>\n",
       "      <td>3.53</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>66</td>\n",
       "      <td>2.86</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>72</td>\n",
       "      <td>3.69</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>63</td>\n",
       "      <td>3.24</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>65</td>\n",
       "      <td>3.21</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>115</th>\n",
       "      <td>66</td>\n",
       "      <td>3.27</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>116</th>\n",
       "      <td>63</td>\n",
       "      <td>2.86</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>117</th>\n",
       "      <td>78</td>\n",
       "      <td>3.04</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>118</th>\n",
       "      <td>64</td>\n",
       "      <td>2.99</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>119</th>\n",
       "      <td>66</td>\n",
       "      <td>3.65</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>120 rows × 4 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     Salary   GPA  MIS  Statistics\n",
       "0        72  3.53    1           0\n",
       "1        66  2.86    1           0\n",
       "2        72  3.69    0           0\n",
       "3        63  3.24    0           0\n",
       "4        65  3.21    0           0\n",
       "..      ...   ...  ...         ...\n",
       "115      66  3.27    0           0\n",
       "116      63  2.86    1           0\n",
       "117      78  3.04    1           1\n",
       "118      64  2.99    0           0\n",
       "119      66  3.65    0           0\n",
       "\n",
       "[120 rows x 4 columns]"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sallaryMisDf"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "id": "nw2BHv7PmpVU"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(120, 4)"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sallaryMisDf.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "id": "mWaKOoGvmrE8"
   },
   "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>Salary</th>\n",
       "      <th>GPA</th>\n",
       "      <th>MIS</th>\n",
       "      <th>Statistics</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>120.000000</td>\n",
       "      <td>120.000000</td>\n",
       "      <td>120.000000</td>\n",
       "      <td>120.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>69.875000</td>\n",
       "      <td>3.242750</td>\n",
       "      <td>0.316667</td>\n",
       "      <td>0.341667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>6.594577</td>\n",
       "      <td>0.493834</td>\n",
       "      <td>0.467127</td>\n",
       "      <td>0.476257</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>53.000000</td>\n",
       "      <td>2.410000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>65.750000</td>\n",
       "      <td>2.805000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>70.000000</td>\n",
       "      <td>3.280000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>73.250000</td>\n",
       "      <td>3.692500</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>88.000000</td>\n",
       "      <td>3.980000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           Salary         GPA         MIS  Statistics\n",
       "count  120.000000  120.000000  120.000000  120.000000\n",
       "mean    69.875000    3.242750    0.316667    0.341667\n",
       "std      6.594577    0.493834    0.467127    0.476257\n",
       "min     53.000000    2.410000    0.000000    0.000000\n",
       "25%     65.750000    2.805000    0.000000    0.000000\n",
       "50%     70.000000    3.280000    0.000000    0.000000\n",
       "75%     73.250000    3.692500    1.000000    1.000000\n",
       "max     88.000000    3.980000    1.000000    1.000000"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sallaryMisDf.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "id": "w-fAHOgMmyH5"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(120, 4)"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sallaryMisDf.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "id": "MDlD1b-aY4Yc"
   },
   "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>const</th>\n",
       "      <th>GPA</th>\n",
       "      <th>MIS</th>\n",
       "      <th>Statistics</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1.0</td>\n",
       "      <td>3.53</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1.0</td>\n",
       "      <td>2.86</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1.0</td>\n",
       "      <td>3.69</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1.0</td>\n",
       "      <td>3.24</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1.0</td>\n",
       "      <td>3.21</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>115</th>\n",
       "      <td>1.0</td>\n",
       "      <td>3.27</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>116</th>\n",
       "      <td>1.0</td>\n",
       "      <td>2.86</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>117</th>\n",
       "      <td>1.0</td>\n",
       "      <td>3.04</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>118</th>\n",
       "      <td>1.0</td>\n",
       "      <td>2.99</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>119</th>\n",
       "      <td>1.0</td>\n",
       "      <td>3.65</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>120 rows × 4 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     const   GPA  MIS  Statistics\n",
       "0      1.0  3.53    1           0\n",
       "1      1.0  2.86    1           0\n",
       "2      1.0  3.69    0           0\n",
       "3      1.0  3.24    0           0\n",
       "4      1.0  3.21    0           0\n",
       "..     ...   ...  ...         ...\n",
       "115    1.0  3.27    0           0\n",
       "116    1.0  2.86    1           0\n",
       "117    1.0  3.04    1           1\n",
       "118    1.0  2.99    0           0\n",
       "119    1.0  3.65    0           0\n",
       "\n",
       "[120 rows x 4 columns]"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sm.add_constant(sallaryMisDf[[\"GPA\", \"MIS\", \"Statistics\"]])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "id": "MjFUWOq2m6P3"
   },
   "outputs": [],
   "source": [
    "salaryBasedOnGpaMisStatistics = sm.OLS(\n",
    "  sallaryMisDf[\"Salary\"],\n",
    "  sm.add_constant(sallaryMisDf[[\"GPA\", \"MIS\", \"Statistics\"]])\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "id": "3yteijRmnabA"
   },
   "outputs": [],
   "source": [
    "salaryBasedOnGpaMisStatisticsFit = salaryBasedOnGpaMisStatistics.fit()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<statsmodels.regression.linear_model.RegressionResultsWrapper at 0x3473b7020>"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from functions.exportModel import exportModel\n",
    "exportModel({\n",
    "    \"modelName\": \"salaryBasedOnGpaMisStatisticsFit\",\n",
    "    \"model\": salaryBasedOnGpaMisStatisticsFit,\n",
    "    \"description\": \"Predict Salary based on GPA MIS Statistics for sallaryMisDf\",\n",
    "    \"modelType\": \"sm.OLS\",\n",
    "    \"baseRelativePath\": \"..\",\n",
    "    \"inputs\": [\n",
    "        {\n",
    "            \"name\": \"const\",\n",
    "            \"type\": \"int\"\n",
    "        },\n",
    "        {\n",
    "            \"name\": \"GPA\",\n",
    "            \"type\": \"float\"\n",
    "        },\n",
    "        {\n",
    "            \"name\": \"MIS\",\n",
    "            \"type\": \"binary\"\n",
    "        },\n",
    "        {\n",
    "            \"name\": \"Statistics\",\n",
    "            \"type\": \"binary\"\n",
    "        }\n",
    "    ],\n",
    "    \"output\": {\n",
    "        \"name\": \"Salary\",\n",
    "        \"type\": \"int\"\n",
    "    }\n",
    "})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "id": "adXMPcPPndd1"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                            OLS Regression Results                            \n",
      "==============================================================================\n",
      "Dep. Variable:                 Salary   R-squared:                       0.795\n",
      "Model:                            OLS   Adj. R-squared:                  0.790\n",
      "Method:                 Least Squares   F-statistic:                     150.3\n",
      "Date:                Sun, 09 Jun 2024   Prob (F-statistic):           8.35e-40\n",
      "Time:                        01:24:53   Log-Likelihood:                -300.92\n",
      "No. Observations:                 120   AIC:                             609.8\n",
      "Df Residuals:                     116   BIC:                             621.0\n",
      "Df Model:                           3                                         \n",
      "Covariance Type:            nonrobust                                         \n",
      "==============================================================================\n",
      "                 coef    std err          t      P>|t|      [0.025      0.975]\n",
      "------------------------------------------------------------------------------\n",
      "const         44.0072      1.860     23.662      0.000      40.324      47.691\n",
      "GPA            6.6227      0.569     11.649      0.000       5.497       7.749\n",
      "MIS            6.6071      0.595     11.098      0.000       5.428       7.786\n",
      "Statistics     6.7309      0.591     11.391      0.000       5.561       7.901\n",
      "==============================================================================\n",
      "Omnibus:                        1.144   Durbin-Watson:                   2.164\n",
      "Prob(Omnibus):                  0.564   Jarque-Bera (JB):                0.758\n",
      "Skew:                          -0.172   Prob(JB):                        0.685\n",
      "Kurtosis:                       3.182   Cond. No.                         24.4\n",
      "==============================================================================\n",
      "\n",
      "Notes:\n",
      "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n"
     ]
    }
   ],
   "source": [
    "print(salaryBasedOnGpaMisStatisticsFit.summary())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "id": "H5PP4w6epEwm"
   },
   "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>Salary</th>\n",
       "      <th>GPA</th>\n",
       "      <th>MIS</th>\n",
       "      <th>Statistics</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>72</td>\n",
       "      <td>3.53</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>66</td>\n",
       "      <td>2.86</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>72</td>\n",
       "      <td>3.69</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>63</td>\n",
       "      <td>3.24</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>65</td>\n",
       "      <td>3.21</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>115</th>\n",
       "      <td>66</td>\n",
       "      <td>3.27</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>116</th>\n",
       "      <td>63</td>\n",
       "      <td>2.86</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>117</th>\n",
       "      <td>78</td>\n",
       "      <td>3.04</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>118</th>\n",
       "      <td>64</td>\n",
       "      <td>2.99</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>119</th>\n",
       "      <td>66</td>\n",
       "      <td>3.65</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>120 rows × 4 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     Salary   GPA  MIS  Statistics\n",
       "0        72  3.53    1           0\n",
       "1        66  2.86    1           0\n",
       "2        72  3.69    0           0\n",
       "3        63  3.24    0           0\n",
       "4        65  3.21    0           0\n",
       "..      ...   ...  ...         ...\n",
       "115      66  3.27    0           0\n",
       "116      63  2.86    1           0\n",
       "117      78  3.04    1           1\n",
       "118      64  2.99    0           0\n",
       "119      66  3.65    0           0\n",
       "\n",
       "[120 rows x 4 columns]"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sallaryMisDf"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "id": "jgXOZuY4ocyq"
   },
   "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>Salary</th>\n",
       "      <th>GPA</th>\n",
       "      <th>MIS</th>\n",
       "      <th>Statistics</th>\n",
       "      <th>misXStatistics</th>\n",
       "      <th>misXStatistics1</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>72</td>\n",
       "      <td>3.53</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>66</td>\n",
       "      <td>2.86</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>72</td>\n",
       "      <td>3.69</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>63</td>\n",
       "      <td>3.24</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>65</td>\n",
       "      <td>3.21</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>115</th>\n",
       "      <td>66</td>\n",
       "      <td>3.27</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>116</th>\n",
       "      <td>63</td>\n",
       "      <td>2.86</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>117</th>\n",
       "      <td>78</td>\n",
       "      <td>3.04</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>118</th>\n",
       "      <td>64</td>\n",
       "      <td>2.99</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>119</th>\n",
       "      <td>66</td>\n",
       "      <td>3.65</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>120 rows × 6 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     Salary   GPA  MIS  Statistics  misXStatistics  misXStatistics1\n",
       "0        72  3.53    1           0               0              0.0\n",
       "1        66  2.86    1           0               0              0.0\n",
       "2        72  3.69    0           0               0              0.0\n",
       "3        63  3.24    0           0               0              0.0\n",
       "4        65  3.21    0           0               0              0.0\n",
       "..      ...   ...  ...         ...             ...              ...\n",
       "115      66  3.27    0           0               0              0.0\n",
       "116      63  2.86    1           0               0              0.0\n",
       "117      78  3.04    1           1               1              1.0\n",
       "118      64  2.99    0           0               0              0.0\n",
       "119      66  3.65    0           0               0              0.0\n",
       "\n",
       "[120 rows x 6 columns]"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from functions.transformers import transformersDict\n",
    "sallaryMisDf[\"misXStatistics\"] = sallaryMisDf[\"MIS\"] * sallaryMisDf[\"Statistics\"]\n",
    "# sallaryMisDf['misXStatistics1'] = sallaryMisDf.apply(lambda row: row['MIS'] * row['Statistics'], axis=1)\n",
    "sallaryMisDf['misXStatistics1'] = sallaryMisDf.apply(transformersDict.get('MIS_X_Statistics'), axis=1)\n",
    "\n",
    "sallaryMisDf"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "id": "FwXG9Q54pbne"
   },
   "outputs": [],
   "source": [
    "salaryBasedOnGpaMisStatistics_Transfoms_misXStatistics = sm.OLS(\n",
    "  sallaryMisDf[\"Salary\"],\n",
    "  sm.add_constant(\n",
    "      sallaryMisDf[[\n",
    "          \"GPA\",\n",
    "          \"MIS\",\n",
    "          \"Statistics\",\n",
    "          \"misXStatistics1\"\n",
    "      ]]\n",
    "  )\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "id": "w7hob-54phqv"
   },
   "outputs": [],
   "source": [
    "salaryBasedOnGpaMisStatistics_Transfoms_misXStatisticsFit = salaryBasedOnGpaMisStatistics_Transfoms_misXStatistics.fit()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<statsmodels.regression.linear_model.RegressionResultsWrapper at 0x3473d1e20>"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from functions.exportModel import exportModel\n",
    "exportModel({\n",
    "    \"modelName\": \"salaryBasedOnGpaMisStatistics_Transfoms_misXStatisticsFit\",\n",
    "    \"model\": salaryBasedOnGpaMisStatistics_Transfoms_misXStatisticsFit,\n",
    "    \"description\": \"Predict Salary based on GPA MIS Statistics and interaction MIS * Statistics for sallaryMisDf\",\n",
    "    \"modelType\": \"sm.OLS\",\n",
    "    \"baseRelativePath\": \"..\",\n",
    "    \"inputs\": [\n",
    "        {\n",
    "            \"name\": \"const\",\n",
    "            \"type\": \"int\"\n",
    "        },\n",
    "        {\n",
    "            \"name\": \"GPA\",\n",
    "            \"type\": \"float\"\n",
    "        },\n",
    "        {\n",
    "            \"name\": \"MIS\",\n",
    "            \"type\": \"binary\"\n",
    "        },\n",
    "        {\n",
    "            \"name\": \"Statistics\",\n",
    "            \"type\": \"binary\"\n",
    "        }\n",
    "    ],\n",
    "    \"transformers\":[\n",
    "        {\n",
    "            \"name\": \"misXStatistics\",\n",
    "            \"transformer\": \"MIS_X_Statistics\"\n",
    "        }\n",
    "    ],\n",
    "    \"output\": {\n",
    "        \"name\": \"Salary\",\n",
    "        \"type\": \"int\"\n",
    "    }\n",
    "})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "id": "NMNYYAespkAn"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                            OLS Regression Results                            \n",
      "==============================================================================\n",
      "Dep. Variable:                 Salary   R-squared:                       0.810\n",
      "Model:                            OLS   Adj. R-squared:                  0.803\n",
      "Method:                 Least Squares   F-statistic:                     122.2\n",
      "Date:                Sun, 09 Jun 2024   Prob (F-statistic):           1.87e-40\n",
      "Time:                        01:24:53   Log-Likelihood:                -296.63\n",
      "No. Observations:                 120   AIC:                             603.3\n",
      "Df Residuals:                     115   BIC:                             617.2\n",
      "Df Model:                           4                                         \n",
      "Covariance Type:            nonrobust                                         \n",
      "===================================================================================\n",
      "                      coef    std err          t      P>|t|      [0.025      0.975]\n",
      "-----------------------------------------------------------------------------------\n",
      "const              44.0993      1.803     24.464      0.000      40.529      47.670\n",
      "GPA                 6.7109      0.552     12.162      0.000       5.618       7.804\n",
      "MIS                 5.3250      0.725      7.343      0.000       3.889       6.761\n",
      "Statistics          5.5350      0.704      7.861      0.000       4.140       6.930\n",
      "misXStatistics1     3.4915      1.196      2.918      0.004       1.122       5.861\n",
      "==============================================================================\n",
      "Omnibus:                        0.396   Durbin-Watson:                   2.073\n",
      "Prob(Omnibus):                  0.820   Jarque-Bera (JB):                0.109\n",
      "Skew:                          -0.013   Prob(JB):                        0.947\n",
      "Kurtosis:                       3.146   Cond. No.                         24.4\n",
      "==============================================================================\n",
      "\n",
      "Notes:\n",
      "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n"
     ]
    }
   ],
   "source": [
    "print(salaryBasedOnGpaMisStatistics_Transfoms_misXStatisticsFit.summary())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "id": "ZnQnXfdRv7dP"
   },
   "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>Salary</th>\n",
       "      <th>GPA</th>\n",
       "      <th>MIS</th>\n",
       "      <th>Statistics</th>\n",
       "      <th>misXStatistics</th>\n",
       "      <th>misXStatistics1</th>\n",
       "      <th>misXGpa</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>72</td>\n",
       "      <td>3.53</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3.53</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>66</td>\n",
       "      <td>2.86</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.86</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>72</td>\n",
       "      <td>3.69</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>63</td>\n",
       "      <td>3.24</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>65</td>\n",
       "      <td>3.21</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>115</th>\n",
       "      <td>66</td>\n",
       "      <td>3.27</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>116</th>\n",
       "      <td>63</td>\n",
       "      <td>2.86</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.86</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>117</th>\n",
       "      <td>78</td>\n",
       "      <td>3.04</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>3.04</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>118</th>\n",
       "      <td>64</td>\n",
       "      <td>2.99</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>119</th>\n",
       "      <td>66</td>\n",
       "      <td>3.65</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>120 rows × 7 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     Salary   GPA  MIS  Statistics  misXStatistics  misXStatistics1  misXGpa\n",
       "0        72  3.53    1           0               0              0.0     3.53\n",
       "1        66  2.86    1           0               0              0.0     2.86\n",
       "2        72  3.69    0           0               0              0.0     0.00\n",
       "3        63  3.24    0           0               0              0.0     0.00\n",
       "4        65  3.21    0           0               0              0.0     0.00\n",
       "..      ...   ...  ...         ...             ...              ...      ...\n",
       "115      66  3.27    0           0               0              0.0     0.00\n",
       "116      63  2.86    1           0               0              0.0     2.86\n",
       "117      78  3.04    1           1               1              1.0     3.04\n",
       "118      64  2.99    0           0               0              0.0     0.00\n",
       "119      66  3.65    0           0               0              0.0     0.00\n",
       "\n",
       "[120 rows x 7 columns]"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# sallaryMisDf['misXGpa'] = sallaryMisDf.apply(lambda row: row['MIS'] * row['GPA'], axis=1)\n",
    "sallaryMisDf['misXGpa'] = sallaryMisDf.apply(transformersDict.get('MIS_X_GPA'), axis=1)\n",
    "\n",
    "sallaryMisDf"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {
    "id": "6CjgMmDAwEPw"
   },
   "outputs": [],
   "source": [
    "salaryBasedOnGpaMisStatistics_Transfoms_misXGpa = sm.OLS(\n",
    "  sallaryMisDf[\"Salary\"],\n",
    "  sm.add_constant(\n",
    "      sallaryMisDf[[\n",
    "          \"GPA\",\n",
    "          \"MIS\",\n",
    "          \"Statistics\",\n",
    "          \"misXGpa\"\n",
    "      ]]\n",
    "  )\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {
    "id": "VmYH7tHmwMzm"
   },
   "outputs": [],
   "source": [
    "salaryBasedOnGpaMisStatistics_Transfoms_misXGpaFit = salaryBasedOnGpaMisStatistics_Transfoms_misXGpa.fit()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<statsmodels.regression.linear_model.RegressionResultsWrapper at 0x3473f2a20>"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from functions.exportModel import exportModel\n",
    "exportModel({\n",
    "    \"modelName\": \"salaryBasedOnGpaMisStatistics_Transfoms_misXGpaFit\",\n",
    "    \"model\": salaryBasedOnGpaMisStatistics_Transfoms_misXGpaFit,\n",
    "    \"description\": \"Predict Salary based on GPA MIS Statistics and interaction misXGpa for sallaryMisDf\",\n",
    "    \"modelType\": \"sm.OLS\",\n",
    "    \"baseRelativePath\": \"..\",\n",
    "    \"inputs\": [\n",
    "        {\n",
    "            \"name\": \"const\",\n",
    "            \"type\": \"int\"\n",
    "        },\n",
    "        {\n",
    "            \"name\": \"GPA\",\n",
    "            \"type\": \"float\"\n",
    "        },\n",
    "        {\n",
    "            \"name\": \"MIS\",\n",
    "            \"type\": \"binary\"\n",
    "        },\n",
    "        {\n",
    "            \"name\": \"Statistics\",\n",
    "            \"type\": \"binary\"\n",
    "        }\n",
    "    ],\n",
    "    \"transformers\":[\n",
    "        {\n",
    "            \"name\": \"misXGpa\",\n",
    "            \"transformer\": \"MIS_X_GPA\"\n",
    "        }\n",
    "    ],\n",
    "    \"output\": {\n",
    "        \"name\": \"Salary\",\n",
    "        \"type\": \"int\"\n",
    "    }\n",
    "})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {
    "id": "rL8pX5dTwP8H"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                            OLS Regression Results                            \n",
      "==============================================================================\n",
      "Dep. Variable:                 Salary   R-squared:                       0.795\n",
      "Model:                            OLS   Adj. R-squared:                  0.788\n",
      "Method:                 Least Squares   F-statistic:                     111.8\n",
      "Date:                Sun, 09 Jun 2024   Prob (F-statistic):           1.11e-38\n",
      "Time:                        01:24:53   Log-Likelihood:                -300.91\n",
      "No. Observations:                 120   AIC:                             611.8\n",
      "Df Residuals:                     115   BIC:                             625.8\n",
      "Df Model:                           4                                         \n",
      "Covariance Type:            nonrobust                                         \n",
      "==============================================================================\n",
      "                 coef    std err          t      P>|t|      [0.025      0.975]\n",
      "------------------------------------------------------------------------------\n",
      "const         44.1653      2.307     19.142      0.000      39.595      48.736\n",
      "GPA            6.5737      0.709      9.278      0.000       5.170       7.977\n",
      "MIS            6.1605      3.873      1.591      0.114      -1.511      13.832\n",
      "Statistics     6.7350      0.594     11.330      0.000       5.558       7.912\n",
      "misXGpa        0.1381      1.184      0.117      0.907      -2.206       2.483\n",
      "==============================================================================\n",
      "Omnibus:                        1.114   Durbin-Watson:                   2.167\n",
      "Prob(Omnibus):                  0.573   Jarque-Bera (JB):                0.727\n",
      "Skew:                          -0.167   Prob(JB):                        0.695\n",
      "Kurtosis:                       3.185   Cond. No.                         57.3\n",
      "==============================================================================\n",
      "\n",
      "Notes:\n",
      "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n"
     ]
    }
   ],
   "source": [
    "print(salaryBasedOnGpaMisStatistics_Transfoms_misXGpaFit.summary())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {
    "id": "z-idrSTJwi90"
   },
   "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>Salary</th>\n",
       "      <th>GPA</th>\n",
       "      <th>MIS</th>\n",
       "      <th>Statistics</th>\n",
       "      <th>misXStatistics</th>\n",
       "      <th>misXStatistics1</th>\n",
       "      <th>misXGpa</th>\n",
       "      <th>statisticsXGpa</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>72</td>\n",
       "      <td>3.53</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3.53</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>66</td>\n",
       "      <td>2.86</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.86</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>72</td>\n",
       "      <td>3.69</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>63</td>\n",
       "      <td>3.24</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>65</td>\n",
       "      <td>3.21</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>115</th>\n",
       "      <td>66</td>\n",
       "      <td>3.27</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>116</th>\n",
       "      <td>63</td>\n",
       "      <td>2.86</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.86</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>117</th>\n",
       "      <td>78</td>\n",
       "      <td>3.04</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>3.04</td>\n",
       "      <td>3.04</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>118</th>\n",
       "      <td>64</td>\n",
       "      <td>2.99</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>119</th>\n",
       "      <td>66</td>\n",
       "      <td>3.65</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>120 rows × 8 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     Salary   GPA  MIS  Statistics  misXStatistics  misXStatistics1  misXGpa  \\\n",
       "0        72  3.53    1           0               0              0.0     3.53   \n",
       "1        66  2.86    1           0               0              0.0     2.86   \n",
       "2        72  3.69    0           0               0              0.0     0.00   \n",
       "3        63  3.24    0           0               0              0.0     0.00   \n",
       "4        65  3.21    0           0               0              0.0     0.00   \n",
       "..      ...   ...  ...         ...             ...              ...      ...   \n",
       "115      66  3.27    0           0               0              0.0     0.00   \n",
       "116      63  2.86    1           0               0              0.0     2.86   \n",
       "117      78  3.04    1           1               1              1.0     3.04   \n",
       "118      64  2.99    0           0               0              0.0     0.00   \n",
       "119      66  3.65    0           0               0              0.0     0.00   \n",
       "\n",
       "     statisticsXGpa  \n",
       "0              0.00  \n",
       "1              0.00  \n",
       "2              0.00  \n",
       "3              0.00  \n",
       "4              0.00  \n",
       "..              ...  \n",
       "115            0.00  \n",
       "116            0.00  \n",
       "117            3.04  \n",
       "118            0.00  \n",
       "119            0.00  \n",
       "\n",
       "[120 rows x 8 columns]"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# sallaryMisDf['statisticsXGpa'] = sallaryMisDf.apply(lambda row: row['Statistics'] * row['GPA'], axis=1)\n",
    "sallaryMisDf['statisticsXGpa'] = sallaryMisDf.apply(transformersDict.get('GPA_X_Statistics'), axis=1)\n",
    "\n",
    "sallaryMisDf"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {
    "id": "im61d1RUwpQJ"
   },
   "outputs": [],
   "source": [
    "salaryBasedOnGpaMisStatistics_Transfoms_statisticsXGpa = sm.OLS(\n",
    "  sallaryMisDf[\"Salary\"],\n",
    "  sm.add_constant(\n",
    "      sallaryMisDf[[\n",
    "          \"GPA\",\n",
    "          \"MIS\",\n",
    "          \"Statistics\",\n",
    "          \"statisticsXGpa\"\n",
    "      ]]\n",
    "  )\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {
    "id": "WZ9eNcnMwvB3"
   },
   "outputs": [],
   "source": [
    "salaryBasedOnGpaMisStatistics_Transfoms_statisticsXGpaFit = salaryBasedOnGpaMisStatistics_Transfoms_statisticsXGpa.fit()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<statsmodels.regression.linear_model.RegressionResultsWrapper at 0x3473f1040>"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from functions.exportModel import exportModel\n",
    "exportModel({\n",
    "    \"modelName\": \"salaryBasedOnGpaMisStatistics_Transfoms_statisticsXGpaFit\",\n",
    "    \"model\": salaryBasedOnGpaMisStatistics_Transfoms_statisticsXGpaFit,\n",
    "    \"description\": \"Predict Salary based on GPA MIS Statistics and interaction misXGpa for statisticsXGpa\",\n",
    "    \"modelType\": \"sm.OLS\",\n",
    "    \"baseRelativePath\": \"..\",\n",
    "    \"inputs\": [\n",
    "        {\n",
    "            \"name\": \"const\",\n",
    "            \"type\": \"int\"\n",
    "        },\n",
    "        {\n",
    "            \"name\": \"GPA\",\n",
    "            \"type\": \"float\"\n",
    "        },\n",
    "        {\n",
    "            \"name\": \"MIS\",\n",
    "            \"type\": \"binary\"\n",
    "        },\n",
    "        {\n",
    "            \"name\": \"Statistics\",\n",
    "            \"type\": \"binary\"\n",
    "        }\n",
    "    ],\n",
    "    \"transformers\":[\n",
    "        {\n",
    "            \"name\": \"statisticsXGpa\",\n",
    "            \"transformer\": \"GPA_X_Statistics\"\n",
    "        }\n",
    "    ],\n",
    "    \"output\": {\n",
    "        \"name\": \"Salary\",\n",
    "        \"type\": \"int\"\n",
    "    }\n",
    "})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {
    "id": "P5MFMA4NwzcE"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                            OLS Regression Results                            \n",
      "==============================================================================\n",
      "Dep. Variable:                 Salary   R-squared:                       0.803\n",
      "Model:                            OLS   Adj. R-squared:                  0.796\n",
      "Method:                 Least Squares   F-statistic:                     116.9\n",
      "Date:                Sun, 09 Jun 2024   Prob (F-statistic):           1.44e-39\n",
      "Time:                        01:24:53   Log-Likelihood:                -298.78\n",
      "No. Observations:                 120   AIC:                             607.6\n",
      "Df Residuals:                     115   BIC:                             621.5\n",
      "Df Model:                           4                                         \n",
      "Covariance Type:            nonrobust                                         \n",
      "==================================================================================\n",
      "                     coef    std err          t      P>|t|      [0.025      0.975]\n",
      "----------------------------------------------------------------------------------\n",
      "const             41.2856      2.267     18.215      0.000      36.796      45.775\n",
      "GPA                7.4828      0.701     10.674      0.000       6.094       8.871\n",
      "MIS                6.5400      0.588     11.118      0.000       5.375       7.705\n",
      "Statistics        14.5988      3.891      3.752      0.000       6.892      22.306\n",
      "statisticsXGpa    -2.3890      1.168     -2.045      0.043      -4.703      -0.075\n",
      "==============================================================================\n",
      "Omnibus:                        0.348   Durbin-Watson:                   2.118\n",
      "Prob(Omnibus):                  0.840   Jarque-Bera (JB):                0.149\n",
      "Skew:                          -0.079   Prob(JB):                        0.928\n",
      "Kurtosis:                       3.068   Cond. No.                         59.1\n",
      "==============================================================================\n",
      "\n",
      "Notes:\n",
      "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n"
     ]
    }
   ],
   "source": [
    "print(salaryBasedOnGpaMisStatistics_Transfoms_statisticsXGpaFit.summary())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {
    "id": "gJGNzwfdw-mg"
   },
   "outputs": [],
   "source": [
    "salaryBasedOnGpaMisStatistics_Transfoms_misXStatistics_misXGpa_statisticsXGpa = sm.OLS(\n",
    "  sallaryMisDf[\"Salary\"],\n",
    "  sm.add_constant(\n",
    "      sallaryMisDf[[\n",
    "          \"GPA\",\n",
    "          \"MIS\",\n",
    "          \"Statistics\",\n",
    "          \"misXStatistics\",\n",
    "          \"misXGpa\",\n",
    "          \"statisticsXGpa\"\n",
    "      ]]\n",
    "  )\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {
    "id": "NPGVE5cFxW-q"
   },
   "outputs": [],
   "source": [
    "salaryBasedOnGpaMisStatistics_Transfoms_misXStatistics_misXGpa_statisticsXGpaFit = salaryBasedOnGpaMisStatistics_Transfoms_misXStatistics_misXGpa_statisticsXGpa.fit()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<statsmodels.regression.linear_model.RegressionResultsWrapper at 0x34741ec30>"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from functions.exportModel import exportModel\n",
    "exportModel({\n",
    "    \"modelName\": \"salaryBasedOnGpaMisStatistics_Transfoms_misXStatistics_misXGpa_statisticsXGpaFit\",\n",
    "    \"model\": salaryBasedOnGpaMisStatistics_Transfoms_misXStatistics_misXGpa_statisticsXGpaFit,\n",
    "    \"description\": \"Predict Salary based on GPA MIS Statistics and interaction misXStatistics, misXGpa, statisticsXGpa\",\n",
    "    \"modelType\": \"sm.OLS\",\n",
    "    \"baseRelativePath\": \"..\",\n",
    "    \"inputs\": [\n",
    "        {\n",
    "            \"name\": \"const\",\n",
    "            \"type\": \"int\"\n",
    "        },\n",
    "        {\n",
    "            \"name\": \"GPA\",\n",
    "            \"type\": \"float\"\n",
    "        },\n",
    "        {\n",
    "            \"name\": \"MIS\",\n",
    "            \"type\": \"binary\"\n",
    "        },\n",
    "        {\n",
    "            \"name\": \"Statistics\",\n",
    "            \"type\": \"binary\"\n",
    "        }\n",
    "    ],\n",
    "    \"transformers\":[\n",
    "        {\n",
    "            \"name\": \"misXStatistics\",\n",
    "            \"transformer\": \"MIS_X_Statistics\"\n",
    "        },\n",
    "        {\n",
    "            \"name\": \"misXGpa\",\n",
    "            \"transformer\": \"MIS_X_GPA\"\n",
    "        },\n",
    "        {\n",
    "            \"name\": \"statisticsXGpa\",\n",
    "            \"transformer\": \"GPA_X_Statistics\"\n",
    "        }\n",
    "    ],\n",
    "    \"output\": {\n",
    "        \"name\": \"Salary\",\n",
    "        \"type\": \"int\"\n",
    "    }\n",
    "})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {
    "id": "qRpqQP9LxaO-"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                            OLS Regression Results                            \n",
      "==============================================================================\n",
      "Dep. Variable:                 Salary   R-squared:                       0.815\n",
      "Model:                            OLS   Adj. R-squared:                  0.805\n",
      "Method:                 Least Squares   F-statistic:                     83.09\n",
      "Date:                Sun, 09 Jun 2024   Prob (F-statistic):           4.15e-39\n",
      "Time:                        01:24:53   Log-Likelihood:                -294.81\n",
      "No. Observations:                 120   AIC:                             603.6\n",
      "Df Residuals:                     113   BIC:                             623.1\n",
      "Df Model:                           6                                         \n",
      "Covariance Type:            nonrobust                                         \n",
      "==================================================================================\n",
      "                     coef    std err          t      P>|t|      [0.025      0.975]\n",
      "----------------------------------------------------------------------------------\n",
      "const             41.7092      2.481     16.809      0.000      36.793      46.625\n",
      "GPA                7.4604      0.769      9.708      0.000       5.938       8.983\n",
      "MIS                5.1669      3.757      1.375      0.172      -2.276      12.610\n",
      "Statistics        12.6641      3.923      3.229      0.002       4.893      20.435\n",
      "misXStatistics     3.3076      1.204      2.747      0.007       0.922       5.693\n",
      "misXGpa            0.0512      1.158      0.044      0.965      -2.243       2.345\n",
      "statisticsXGpa    -2.1451      1.158     -1.853      0.066      -4.439       0.148\n",
      "==============================================================================\n",
      "Omnibus:                        0.398   Durbin-Watson:                   2.028\n",
      "Prob(Omnibus):                  0.820   Jarque-Bera (JB):                0.148\n",
      "Skew:                           0.067   Prob(JB):                        0.928\n",
      "Kurtosis:                       3.108   Cond. No.                         63.5\n",
      "==============================================================================\n",
      "\n",
      "Notes:\n",
      "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n"
     ]
    }
   ],
   "source": [
    "print(salaryBasedOnGpaMisStatistics_Transfoms_misXStatistics_misXGpa_statisticsXGpaFit.summary())"
   ]
  },
  {
   "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": "3.12.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}