{
  "cells": [
    {
      "cell_type": "code",
      "metadata": {},
      "source": [
        "#%%\n",
        "\"\"\"File 07discreteMixture.py\n",
        "\n",
        ":author: Michel Bierlaire, EPFL\n",
        ":date: Sun Sep  8 00:06:20 2019\n",
        "\n",
        " Example of a discrete mixture of logit (or latent class model)\n",
        " Three alternatives: Train, Car and Swissmetro\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.models as models\n",
        "import biogeme.messaging as msg\n",
        "from biogeme.expressions import Beta, DefineVariable, log\n",
        "\n",
        "# Read the data\n",
        "df = pd.read_csv('swissmetro.dat', '\\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",
        "PROB_CLASS1 = Beta('PROB_CLASS1', 0.5, 0, 1, 0)\n",
        "PROB_CLASS2 = 1 - PROB_CLASS1\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('TRAIN_COST_SCALED', TRAIN_COST / 100, database)\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 for latent class 1, where the\n",
        "# time coefficient is zero\n",
        "V11 = ASC_TRAIN + B_COST * TRAIN_COST_SCALED\n",
        "V12 = ASC_SM + B_COST * SM_COST_SCALED\n",
        "V13 = ASC_CAR + B_COST * CAR_CO_SCALED\n",
        "\n",
        "# Associate utility functions with the numbering of alternatives\n",
        "V1 = {1: V11,\n",
        "      2: V12,\n",
        "      3: V13}\n",
        "\n",
        "# Definition of the utility functions for latent class 2, whete the\n",
        "# time coefficient is estimated\n",
        "V21 = ASC_TRAIN + B_TIME * TRAIN_TT_SCALED + B_COST * TRAIN_COST_SCALED\n",
        "V22 = ASC_SM + B_TIME * SM_TT_SCALED + B_COST * SM_COST_SCALED\n",
        "V23 = ASC_CAR + B_TIME * CAR_TT_SCALED + B_COST * CAR_CO_SCALED\n",
        "\n",
        "# Associate utility functions with the numbering of alternatives\n",
        "V2 = {1: V21,\n",
        "      2: V22,\n",
        "      3: V23}\n",
        "\n",
        "# Associate the availability conditions with the alternatives\n",
        "av = {1: TRAIN_AV_SP,\n",
        "      2: SM_AV,\n",
        "      3: CAR_AV_SP}\n",
        "\n",
        "\n",
        "# The choice model is a discrete mixture of logit, with availability conditions\n",
        "prob1 = models.logit(V1, av, CHOICE)\n",
        "prob2 = models.logit(V2, av, CHOICE)\n",
        "prob = PROB_CLASS1 * prob1 + PROB_CLASS2 * prob2\n",
        "logprob = log(prob)\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 = '07discreteMixture'\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": 1
}