{
  "cells": [
    {
      "cell_type": "code",
      "metadata": {},
      "source": [
        "#%%\n",
        "\"\"\"File 10nestedBottom.py\n",
        "\n",
        ":author: Michel Bierlaire, EPFL\n",
        ":date: Sun Sep  8 00:36:04 2019\n",
        "\n",
        " Example of a nested logit model where the normalization is done at\n",
        " the bottom level.  Three alternatives: Train, Car and Swissmetro\n",
        " Train and car are in the same nest.  SP data\n",
        "\n",
        "\"\"\"\n",
        "\n",
        "import pandas as pd\n",
        "import biogeme.database as db\n",
        "import biogeme.biogeme as bio\n",
        "from biogeme import models\n",
        "import biogeme.messaging as msg\n",
        "from biogeme.expressions import Beta, DefineVariable\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\n",
        "exclude = ((PURPOSE != 1) * (PURPOSE != 3) + (CHOICE == 0)) > 0\n",
        "database.remove(exclude)\n",
        "\n",
        "# Parameters to be estimated\n",
        "ASC_CAR = Beta('ASC_CAR', 0, None, None, 0)\n",
        "ASC_TRAIN = Beta('ASC_TRAIN', 0, None, None, 0)\n",
        "ASC_SM = Beta('ASC_SM', 0, None, None, 1)\n",
        "B_TIME = Beta('B_TIME', 0, None, None, 0)\n",
        "B_COST = Beta('B_COST', 0, None, None, 0)\n",
        "\n",
        "# If the lower bound is set to zero, the model cannot be evaluated.\n",
        "# Therefore, we set the lower bound to a small number, strictly larger\n",
        "# than zero.\n",
        "MU = Beta('MU', 0.5, 0.000001, 1.0, 0)\n",
        "\n",
        "# Definition of new variables\n",
        "SM_COST = SM_CO * (GA == 0)\n",
        "TRAIN_COST = TRAIN_CO * (GA == 0)\n",
        "\n",
        "# Definition of new variables: adding columns to the database\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",
        "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",
        "SM_TT_SCALED = DefineVariable('SM_TT_SCALED', SM_TT / 100.0, database)\n",
        "SM_COST_SCALED = DefineVariable('SM_COST_SCALED', SM_COST / 100, database)\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",
        "V1 = ASC_TRAIN + B_TIME * TRAIN_TT_SCALED + B_COST * TRAIN_COST_SCALED\n",
        "V2 = ASC_SM + B_TIME * SM_TT_SCALED + B_COST * SM_COST_SCALED\n",
        "V3 = ASC_CAR + B_TIME * CAR_TT_SCALED + B_COST * CAR_CO_SCALED\n",
        "\n",
        "# Associate utility functions with the numbering of alternatives\n",
        "V = {1: V1, 2: V2, 3: V3}\n",
        "\n",
        "# Associate the availability conditions with the alternatives\n",
        "av = {1: TRAIN_AV_SP, 2: SM_AV, 3: CAR_AV_SP}\n",
        "\n",
        "# Definition of nests:\n",
        "# 1: nests parameter\n",
        "# 2: list of alternatives\n",
        "existing = 1.0, [1, 3]\n",
        "future = 1.0, [2]\n",
        "nests = existing, future\n",
        "\n",
        "# Definition of the model. This is the contribution of each\n",
        "# observation to the log likelihood function.\n",
        "# The choice model is a nested logit, with availability conditions,\n",
        "# where the scale parameter mu is explicitly involved.\n",
        "logprob = models.lognestedMevMu(V, av, nests, CHOICE, MU)\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 = '10nestedBottom'\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
}