{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's import some libraries first..."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas\n",
    "from pandas.plotting import scatter_matrix\n",
    "\n",
    "from sklearn import datasets\n",
    "from sklearn import model_selection\n",
    "from sklearn import linear_model\n",
    "\n",
    "# models\n",
    "from sklearn.ensemble import RandomForestRegressor\n",
    "from sklearn.neighbors import KNeighborsRegressor\n",
    "from sklearn.preprocessing import StandardScaler, PolynomialFeatures\n",
    "from sklearn.linear_model import LinearRegression, Ridge\n",
    "from sklearn.tree import DecisionTreeRegressor\n",
    "from sklearn.metrics import mean_squared_error, r2_score\n",
    "\n",
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Load and examine dataset..."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "   period   npbt  avg_gross_loan_book  net_lending  revenue\n",
      "0  1HFY14  -2830              27424.5        17511     7000\n",
      "1  2HFY14   -692              49041.0        31619    12104\n",
      "2  1HFY15   2907              67541.0        16220    16603\n",
      "3  2HFY15  -1400              85802.0        34800    19223\n",
      "4  1HFY16   2053             110302.0        31900    26204\n",
      "5  2HFY16   6100             127976.5        23200    26214\n",
      "6  1HFY17   4513             145476.5        30391    29735\n",
      "7  2HFY17  13083             158238.0        15793    36639\n",
      "8  1HFY18   8292             166238.0        24394    37566\n",
      "9  2HFY18  14736             177548.0        28011    41770\n"
     ]
    }
   ],
   "source": [
    "dataset = pandas.read_csv(\"data/ccp-consumer-lending-half-year.csv\")\n",
    "print (dataset)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Period 1HFY14 to 1HFY15:  p = 0.140936039634br + -0.064399199089l + -5567.40604369\n",
      "Period 2HFY14 to 2HFY15:  p = 0.000873579448887br + -0.232666977089l + 6621.85593883\n",
      "Period 1HFY15 to 1HFY16:  p = 0.101672186835br + -0.331734973293l + 1420.70009581\n",
      "Period 2HFY15 to 2HFY16:  p = 0.113066609345br + -0.235471748635l + -2906.92436252\n",
      "Period 1HFY16 to 1HFY17:  p = 0.0547529021572br + -0.353939061014l + 7304.3014326\n",
      "Period 2HFY16 to 2HFY17:  p = 0.110760929767br + -0.490240059925l + 3298.77326195\n",
      "Period 1HFY17 to 1HFY18:  p = 0.0166480875203br + -0.572513045014l + 19490.3384469\n",
      "Period 2HFY17 to 2HFY18:  p = 1.0645668191br + -1.54720783081l + -130936.871049\n"
     ]
    }
   ],
   "source": [
    "array = dataset.values\n",
    "num_data_points = 3\n",
    "\n",
    "for i in range(0, len(array) - (num_data_points - 1)):\n",
    "    begin = i\n",
    "    end = i + (num_data_points - 1)\n",
    "    \n",
    "    X = array[begin:end+1,2:4]   # data = avg_gross_loan_book, net_lending\n",
    "    Y = array[begin:end+1,1]     # result = NPAT\n",
    "\n",
    "    model = LinearRegression()\n",
    "    model.fit(X, Y) # train model\n",
    "    \n",
    "    print(\"Period %s to %s: \" % (array[begin,0], array[end,0]), end =\" \")\n",
    "    print(\"p = %sbr + %sl + %s\" % (model.coef_[0], model.coef_[1], model.intercept_))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Where\n",
    "```\n",
    "p = Net profit before tax (NPBT).\n",
    "r = Reporting period. Full year = 2, half year = 1.\n",
    "b = Average gross loan book.\n",
    "l = Net lending for the period.\n",
    "```"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## FY19 Predictions\n",
    "\n",
    "Assumptions:\n",
    "\n",
    "* Average gross loan book will be $196m.\n",
    "\n",
    "* Net lending will be $50m, on the upper range of the forecast. Quoting a high number here will actually reduce EBIT.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "EBIT = 209012.930498\n",
      "NPAT = 146309.051349\n"
     ]
    }
   ],
   "source": [
    "b = 196000\n",
    "l = 50000\n",
    "r = 2\n",
    "\n",
    "p = model.coef_[0] * b * r + model.coef_[1] * l + model.intercept_\n",
    "\n",
    "print(\"EBIT = %s\" % p)\n",
    "print(\"NPAT = %s\" % (p * 0.7))"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}