{
  "cells": [
    {
      "cell_type": "code",
      "metadata": {},
      "source": [
        "#%%\n",
        "\"\"\"File 21probit.py\n",
        "\n",
        ":author: Michel Bierlaire, EPFL\n",
        ":date: Mon Sep  9 10:14:57 2019\n",
        "\n",
        " Example of a binary probit model.\n",
        " Two alternatives: Train and Car\n",
        " SP data\n",
        "\"\"\"\n",
        "\n",
        "import pandas as pd\n",
        "import biogeme.database as db\n",
        "import biogeme.biogeme as bio\n",
        "import biogeme.messaging as msg\n",
        "from biogeme.expressions import Beta, DefineVariable, bioNormalCdf, Elem, log\n",
        "\n",
        "# Read the data\n",
        "df = pd.read_csv('swissmetro.dat', sep='\\t')\n",
        "database = db.Database('swissmetro', df)\n",
        "\n",
        "# The Pandas data structure is available as database.data. Use all the\n",
        "# Pandas functions to invesigate the database\n",
        "# print(database.data.describe())\n",
        "\n",
        "# The following statement allows you to use the names of the variable\n",
        "# as Python variable.\n",
        "globals().update(database.variables)\n",
        "\n",
        "# Removing some observations can be done directly using pandas.\n",
        "# remove = (((database.data.PURPOSE != 1) &\n",
        "#           (database.data.PURPOSE != 3)) |\n",
        "#          (database.data.CHOICE == 0))\n",
        "# database.data.drop(database.data[remove].index,inplace=True)\n",
        "\n",
        "# Here we use the \"biogeme\" way for backward compatibility. As we\n",
        "# estimate a binary model, we remove observations where Swissmetro was\n",
        "# chosen (CHOICE == 2). We also remove observations where one of the\n",
        "# two alternatives is not available.\n",
        "\n",
        "CAR_AV_SP = DefineVariable('CAR_AV_SP', CAR_AV * (SP != 0), database)\n",
        "TRAIN_AV_SP = DefineVariable('TRAIN_AV_SP', TRAIN_AV * (SP != 0), database)\n",
        "exclude = (TRAIN_AV_SP == 0) + (CAR_AV_SP == 0) + (CHOICE == 2) + (\n",
        "    (PURPOSE != 1) * (PURPOSE != 3) + (CHOICE == 0)\n",
        ") > 0\n",
        "database.remove(exclude)\n",
        "\n",
        "# Parameters to be estimated\n",
        "ASC_CAR = Beta('ASC_CAR', 0, None, None, 0)\n",
        "B_TIME = Beta('B_TIME', 0, None, None, 0)\n",
        "B_COST = Beta('B_COST', 0, None, None, 0)\n",
        "\n",
        "# Definition of new variables\n",
        "TRAIN_COST = TRAIN_CO * (GA == 0)\n",
        "\n",
        "# Definition of new variables by adding columns to the database.\n",
        "# This is recommended for estimation. And not recommended for simulation.\n",
        "TRAIN_TT_SCALED = DefineVariable('TRAIN_TT_SCALED', TRAIN_TT / 100.0, database)\n",
        "TRAIN_COST_SCALED = DefineVariable(\n",
        "    'TRAIN_COST_SCALED', TRAIN_COST / 100, database\n",
        ")\n",
        "CAR_TT_SCALED = DefineVariable('CAR_TT_SCALED', CAR_TT / 100, database)\n",
        "CAR_CO_SCALED = DefineVariable('CAR_CO_SCALED', CAR_CO / 100, database)\n",
        "\n",
        "# Definition of the utility functions\n",
        "# We estimate a binary probit model. There are only two alternatives.\n",
        "V1 = B_TIME * TRAIN_TT_SCALED + B_COST * TRAIN_COST_SCALED\n",
        "V3 = ASC_CAR + B_TIME * CAR_TT_SCALED + B_COST * CAR_CO_SCALED\n",
        "\n",
        "# Associate choice probability with the numbering of alternatives\n",
        "P = {1: bioNormalCdf(V1 - V3), 3: bioNormalCdf(V3 - V1)}\n",
        "\n",
        "# Definition of the model. This is the contribution of each\n",
        "# observation to the log likelihood function.\n",
        "logprob = log(Elem(P, CHOICE))\n",
        "\n",
        "# Define level of verbosity\n",
        "logger = msg.bioMessage()\n",
        "logger.setSilent()\n",
        "# logger.setWarning()\n",
        "# logger.setGeneral()\n",
        "# logger.setDetailed()\n",
        "\n",
        "# Create the Biogeme object\n",
        "biogeme = bio.BIOGEME(database, logprob)\n",
        "biogeme.modelName = '21probit'\n",
        "\n",
        "# Estimate the parameters\n",
        "results = biogeme.estimate()\n",
        "pandasResults = results.getEstimatedParameters()\n",
        "print(pandasResults)\n"
      ],
      "outputs": [],
      "execution_count": null
    }
  ],
  "metadata": {
    "anaconda-cloud": {},
    "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": "3.6.1"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 4
}