#%%
"""File 05latentChoiceFull_mc.py
Choice model with the latent variable.
Mixture of logit.
Measurement equation for the indicators.
Maximum likelihood (full information) estimation.
:author: Michel Bierlaire, EPFL
:date: Sat May 30 18:21:50 2020
"""
import sys
import pandas as pd
import biogeme.database as db
import biogeme.biogeme as bio
from biogeme import models
import biogeme.optimization as opt
import biogeme.results as res
import biogeme.messaging as msg
from biogeme.expressions import (
Beta,
DefineVariable,
log,
bioDraws,
MonteCarlo,
Elem,
bioNormalCdf,
exp,
)
# Read the data
df = pd.read_csv('optima.dat', sep='\t')
database = db.Database('optima', df)
# The following statement allows you to use the names of the variable
# as Python variable.
globals().update(database.variables)
# Exclude observations such that the chosen alternative is -1
database.remove(Choice == -1.0)
# Read the estimates from the structural equation estimation
try:
structResults = res.bioResults(pickleFile='02oneLatentOrdered.pickle')
except FileNotFoundError:
print(
'Run first the script 02oneLatentOrdered.py in order to generate the '
'file 02oneLatentOrdered.pickle.'
)
sys.exit()
structBetas = structResults.getBetaValues()
### Variables
# Piecewise linear definition of income
ScaledIncome = DefineVariable(
'ScaledIncome', CalculatedIncome / 1000, database
)
thresholds = [None, 4, 6, 8, 10, None]
formulaIncome = models.piecewiseFormula(
ScaledIncome,
thresholds,
[
structBetas['beta_ScaledIncome_lessthan_4'],
structBetas['beta_ScaledIncome_4_6'],
structBetas['beta_ScaledIncome_6_8'],
structBetas['beta_ScaledIncome_8_10'],
structBetas['beta_ScaledIncome_10_more'],
],
)
# Definition of other variables
age_65_more = DefineVariable('age_65_more', age >= 65, database)
moreThanOneCar = DefineVariable('moreThanOneCar', NbCar > 1, database)
moreThanOneBike = DefineVariable('moreThanOneBike', NbBicy > 1, database)
individualHouse = DefineVariable('individualHouse', HouseType == 1, database)
male = DefineVariable('male', Gender == 1, database)
haveChildren = DefineVariable(
'haveChildren', ((FamilSitu == 3) + (FamilSitu == 4)) > 0, database
)
haveGA = DefineVariable('haveGA', GenAbST == 1, database)
highEducation = DefineVariable('highEducation', Education >= 6, database)
### Coefficients
coef_intercept = Beta(
'coef_intercept', structBetas['coef_intercept'], None, None, 0
)
coef_age_65_more = Beta(
'coef_age_65_more', structBetas['coef_age_65_more'], None, None, 0
)
coef_haveGA = Beta('coef_haveGA', structBetas['coef_haveGA'], None, None, 0)
coef_moreThanOneCar = Beta(
'coef_moreThanOneCar', structBetas['coef_moreThanOneCar'], None, None, 0
)
coef_moreThanOneBike = Beta(
'coef_moreThanOneBike', structBetas['coef_moreThanOneBike'], None, None, 0
)
coef_individualHouse = Beta(
'coef_individualHouse', structBetas['coef_individualHouse'], None, None, 0
)
coef_male = Beta('coef_male', structBetas['coef_male'], None, None, 0)
coef_haveChildren = Beta(
'coef_haveChildren', structBetas['coef_haveChildren'], None, None, 0
)
coef_highEducation = Beta(
'coef_highEducation', structBetas['coef_highEducation'], None, None, 0
)
### Latent variable: structural equation
# Define a random parameter, normally distributed, designed to be used
# for numerical integration
sigma_s = Beta('sigma_s', 1, None, None, 0)
CARLOVERS = (
coef_intercept
+ coef_age_65_more * age_65_more
+ formulaIncome
+ coef_moreThanOneCar * moreThanOneCar
+ coef_moreThanOneBike * moreThanOneBike
+ coef_individualHouse * individualHouse
+ coef_male * male
+ coef_haveChildren * haveChildren
+ coef_haveGA * haveGA
+ coef_highEducation * highEducation
+ sigma_s * bioDraws('EC', 'NORMAL_MLHS')
)
### Measurement equations
INTER_Envir01 = Beta('INTER_Envir01', 0, None, None, 1)
INTER_Envir02 = Beta('INTER_Envir02', 0, None, None, 0)
INTER_Envir03 = Beta('INTER_Envir03', 0, None, None, 0)
INTER_Mobil11 = Beta('INTER_Mobil11', 0, None, None, 0)
INTER_Mobil14 = Beta('INTER_Mobil14', 0, None, None, 0)
INTER_Mobil16 = Beta('INTER_Mobil16', 0, None, None, 0)
INTER_Mobil17 = Beta('INTER_Mobil17', 0, None, None, 0)
B_Envir01_F1 = Beta('B_Envir01_F1', -1, None, None, 1)
B_Envir02_F1 = Beta('B_Envir02_F1', -1, None, None, 0)
B_Envir03_F1 = Beta('B_Envir03_F1', 1, None, None, 0)
B_Mobil11_F1 = Beta('B_Mobil11_F1', 1, None, None, 0)
B_Mobil14_F1 = Beta('B_Mobil14_F1', 1, None, None, 0)
B_Mobil16_F1 = Beta('B_Mobil16_F1', 1, None, None, 0)
B_Mobil17_F1 = Beta('B_Mobil17_F1', 1, None, None, 0)
MODEL_Envir01 = INTER_Envir01 + B_Envir01_F1 * CARLOVERS
MODEL_Envir02 = INTER_Envir02 + B_Envir02_F1 * CARLOVERS
MODEL_Envir03 = INTER_Envir03 + B_Envir03_F1 * CARLOVERS
MODEL_Mobil11 = INTER_Mobil11 + B_Mobil11_F1 * CARLOVERS
MODEL_Mobil14 = INTER_Mobil14 + B_Mobil14_F1 * CARLOVERS
MODEL_Mobil16 = INTER_Mobil16 + B_Mobil16_F1 * CARLOVERS
MODEL_Mobil17 = INTER_Mobil17 + B_Mobil17_F1 * CARLOVERS
SIGMA_STAR_Envir01 = Beta('SIGMA_STAR_Envir01', 1, 1.0e-5, None, 1)
SIGMA_STAR_Envir02 = Beta('SIGMA_STAR_Envir02', 1, 1.0e-5, None, 0)
SIGMA_STAR_Envir03 = Beta('SIGMA_STAR_Envir03', 1, 1.0e-5, None, 0)
SIGMA_STAR_Mobil11 = Beta('SIGMA_STAR_Mobil11', 1, 1.0e-5, None, 0)
SIGMA_STAR_Mobil14 = Beta('SIGMA_STAR_Mobil14', 1, 1.0e-5, None, 0)
SIGMA_STAR_Mobil16 = Beta('SIGMA_STAR_Mobil16', 1, 1.0e-5, None, 0)
SIGMA_STAR_Mobil17 = Beta('SIGMA_STAR_Mobil17', 1, 1.0e-5, None, 0)
delta_1 = Beta('delta_1', 0.1, 1.0e-5, None, 0)
delta_2 = Beta('delta_2', 0.2, 1.0e-5, None, 0)
tau_1 = -delta_1 - delta_2
tau_2 = -delta_1
tau_3 = delta_1
tau_4 = delta_1 + delta_2
Envir01_tau_1 = (tau_1 - MODEL_Envir01) / SIGMA_STAR_Envir01
Envir01_tau_2 = (tau_2 - MODEL_Envir01) / SIGMA_STAR_Envir01
Envir01_tau_3 = (tau_3 - MODEL_Envir01) / SIGMA_STAR_Envir01
Envir01_tau_4 = (tau_4 - MODEL_Envir01) / SIGMA_STAR_Envir01
IndEnvir01 = {
1: bioNormalCdf(Envir01_tau_1),
2: bioNormalCdf(Envir01_tau_2) - bioNormalCdf(Envir01_tau_1),
3: bioNormalCdf(Envir01_tau_3) - bioNormalCdf(Envir01_tau_2),
4: bioNormalCdf(Envir01_tau_4) - bioNormalCdf(Envir01_tau_3),
5: 1 - bioNormalCdf(Envir01_tau_4),
6: 1.0,
-1: 1.0,
-2: 1.0,
}
P_Envir01 = Elem(IndEnvir01, Envir01)
Envir02_tau_1 = (tau_1 - MODEL_Envir02) / SIGMA_STAR_Envir02
Envir02_tau_2 = (tau_2 - MODEL_Envir02) / SIGMA_STAR_Envir02
Envir02_tau_3 = (tau_3 - MODEL_Envir02) / SIGMA_STAR_Envir02
Envir02_tau_4 = (tau_4 - MODEL_Envir02) / SIGMA_STAR_Envir02
IndEnvir02 = {
1: bioNormalCdf(Envir02_tau_1),
2: bioNormalCdf(Envir02_tau_2) - bioNormalCdf(Envir02_tau_1),
3: bioNormalCdf(Envir02_tau_3) - bioNormalCdf(Envir02_tau_2),
4: bioNormalCdf(Envir02_tau_4) - bioNormalCdf(Envir02_tau_3),
5: 1 - bioNormalCdf(Envir02_tau_4),
6: 1.0,
-1: 1.0,
-2: 1.0,
}
P_Envir02 = Elem(IndEnvir02, Envir02)
Envir03_tau_1 = (tau_1 - MODEL_Envir03) / SIGMA_STAR_Envir03
Envir03_tau_2 = (tau_2 - MODEL_Envir03) / SIGMA_STAR_Envir03
Envir03_tau_3 = (tau_3 - MODEL_Envir03) / SIGMA_STAR_Envir03
Envir03_tau_4 = (tau_4 - MODEL_Envir03) / SIGMA_STAR_Envir03
IndEnvir03 = {
1: bioNormalCdf(Envir03_tau_1),
2: bioNormalCdf(Envir03_tau_2) - bioNormalCdf(Envir03_tau_1),
3: bioNormalCdf(Envir03_tau_3) - bioNormalCdf(Envir03_tau_2),
4: bioNormalCdf(Envir03_tau_4) - bioNormalCdf(Envir03_tau_3),
5: 1 - bioNormalCdf(Envir03_tau_4),
6: 1.0,
-1: 1.0,
-2: 1.0,
}
P_Envir03 = Elem(IndEnvir03, Envir03)
Mobil11_tau_1 = (tau_1 - MODEL_Mobil11) / SIGMA_STAR_Mobil11
Mobil11_tau_2 = (tau_2 - MODEL_Mobil11) / SIGMA_STAR_Mobil11
Mobil11_tau_3 = (tau_3 - MODEL_Mobil11) / SIGMA_STAR_Mobil11
Mobil11_tau_4 = (tau_4 - MODEL_Mobil11) / SIGMA_STAR_Mobil11
IndMobil11 = {
1: bioNormalCdf(Mobil11_tau_1),
2: bioNormalCdf(Mobil11_tau_2) - bioNormalCdf(Mobil11_tau_1),
3: bioNormalCdf(Mobil11_tau_3) - bioNormalCdf(Mobil11_tau_2),
4: bioNormalCdf(Mobil11_tau_4) - bioNormalCdf(Mobil11_tau_3),
5: 1 - bioNormalCdf(Mobil11_tau_4),
6: 1.0,
-1: 1.0,
-2: 1.0,
}
P_Mobil11 = Elem(IndMobil11, Mobil11)
Mobil14_tau_1 = (tau_1 - MODEL_Mobil14) / SIGMA_STAR_Mobil14
Mobil14_tau_2 = (tau_2 - MODEL_Mobil14) / SIGMA_STAR_Mobil14
Mobil14_tau_3 = (tau_3 - MODEL_Mobil14) / SIGMA_STAR_Mobil14
Mobil14_tau_4 = (tau_4 - MODEL_Mobil14) / SIGMA_STAR_Mobil14
IndMobil14 = {
1: bioNormalCdf(Mobil14_tau_1),
2: bioNormalCdf(Mobil14_tau_2) - bioNormalCdf(Mobil14_tau_1),
3: bioNormalCdf(Mobil14_tau_3) - bioNormalCdf(Mobil14_tau_2),
4: bioNormalCdf(Mobil14_tau_4) - bioNormalCdf(Mobil14_tau_3),
5: 1 - bioNormalCdf(Mobil14_tau_4),
6: 1.0,
-1: 1.0,
-2: 1.0,
}
P_Mobil14 = Elem(IndMobil14, Mobil14)
Mobil16_tau_1 = (tau_1 - MODEL_Mobil16) / SIGMA_STAR_Mobil16
Mobil16_tau_2 = (tau_2 - MODEL_Mobil16) / SIGMA_STAR_Mobil16
Mobil16_tau_3 = (tau_3 - MODEL_Mobil16) / SIGMA_STAR_Mobil16
Mobil16_tau_4 = (tau_4 - MODEL_Mobil16) / SIGMA_STAR_Mobil16
IndMobil16 = {
1: bioNormalCdf(Mobil16_tau_1),
2: bioNormalCdf(Mobil16_tau_2) - bioNormalCdf(Mobil16_tau_1),
3: bioNormalCdf(Mobil16_tau_3) - bioNormalCdf(Mobil16_tau_2),
4: bioNormalCdf(Mobil16_tau_4) - bioNormalCdf(Mobil16_tau_3),
5: 1 - bioNormalCdf(Mobil16_tau_4),
6: 1.0,
-1: 1.0,
-2: 1.0,
}
P_Mobil16 = Elem(IndMobil16, Mobil16)
Mobil17_tau_1 = (tau_1 - MODEL_Mobil17) / SIGMA_STAR_Mobil17
Mobil17_tau_2 = (tau_2 - MODEL_Mobil17) / SIGMA_STAR_Mobil17
Mobil17_tau_3 = (tau_3 - MODEL_Mobil17) / SIGMA_STAR_Mobil17
Mobil17_tau_4 = (tau_4 - MODEL_Mobil17) / SIGMA_STAR_Mobil17
IndMobil17 = {
1: bioNormalCdf(Mobil17_tau_1),
2: bioNormalCdf(Mobil17_tau_2) - bioNormalCdf(Mobil17_tau_1),
3: bioNormalCdf(Mobil17_tau_3) - bioNormalCdf(Mobil17_tau_2),
4: bioNormalCdf(Mobil17_tau_4) - bioNormalCdf(Mobil17_tau_3),
5: 1 - bioNormalCdf(Mobil17_tau_4),
6: 1.0,
-1: 1.0,
-2: 1.0,
}
P_Mobil17 = Elem(IndMobil17, Mobil17)
# Choice model
# Read the estimates from the sequential estimation, and use
# them as starting values
try:
choiceResults = res.bioResults(pickleFile='04latentChoiceSeq.pickle')
except FileNotFoundError:
print(
'Run first the script 04latentChoiceSeq.py in order to generate the '
'file 04latentChoiceSeq.pickle.'
)
sys.exit()
choiceBetas = choiceResults.getBetaValues()
ASC_CAR = Beta('ASC_CAR', choiceBetas['ASC_CAR'], None, None, 0)
ASC_PT = Beta('ASC_PT', 0, None, None, 1)
ASC_SM = Beta('ASC_SM', choiceBetas['ASC_SM'], None, None, 0)
BETA_COST_HWH = Beta(
'BETA_COST_HWH', choiceBetas['BETA_COST_HWH'], None, None, 0
)
BETA_COST_OTHER = Beta(
'BETA_COST_OTHER', choiceBetas['BETA_COST_OTHER'], None, None, 0
)
BETA_DIST = Beta('BETA_DIST', choiceBetas['BETA_DIST'], None, None, 0)
BETA_TIME_CAR_REF = Beta(
'BETA_TIME_CAR_REF', choiceBetas['BETA_TIME_CAR_REF'], None, 0, 0
)
BETA_TIME_CAR_CL = Beta(
'BETA_TIME_CAR_CL', choiceBetas['BETA_TIME_CAR_CL'], None, None, 0
)
BETA_TIME_PT_REF = Beta(
'BETA_TIME_PT_REF', choiceBetas['BETA_TIME_PT_REF'], None, 0, 0
)
BETA_TIME_PT_CL = Beta(
'BETA_TIME_PT_CL', choiceBetas['BETA_TIME_PT_CL'], None, None, 0
)
BETA_WAITING_TIME = Beta(
'BETA_WAITING_TIME', choiceBetas['BETA_WAITING_TIME'], None, None, 0
)
TimePT_scaled = DefineVariable('TimePT_scaled', TimePT / 200, database)
TimeCar_scaled = DefineVariable('TimeCar_scaled', TimeCar / 200, database)
MarginalCostPT_scaled = DefineVariable(
'MarginalCostPT_scaled', MarginalCostPT / 10, database
)
CostCarCHF_scaled = DefineVariable(
'CostCarCHF_scaled', CostCarCHF / 10, database
)
distance_km_scaled = DefineVariable(
'distance_km_scaled', distance_km / 5, database
)
PurpHWH = DefineVariable('PurpHWH', TripPurpose == 1, database)
PurpOther = DefineVariable('PurpOther', TripPurpose != 1, database)
### Definition of utility functions:
BETA_TIME_PT = BETA_TIME_PT_REF * exp(BETA_TIME_PT_CL * CARLOVERS)
V0 = (
ASC_PT
+ BETA_TIME_PT * TimePT_scaled
+ BETA_WAITING_TIME * WaitingTimePT
+ BETA_COST_HWH * MarginalCostPT_scaled * PurpHWH
+ BETA_COST_OTHER * MarginalCostPT_scaled * PurpOther
)
BETA_TIME_CAR = BETA_TIME_CAR_REF * exp(BETA_TIME_CAR_CL * CARLOVERS)
V1 = (
ASC_CAR
+ BETA_TIME_CAR * TimeCar_scaled
+ BETA_COST_HWH * CostCarCHF_scaled * PurpHWH
+ BETA_COST_OTHER * CostCarCHF_scaled * PurpOther
)
V2 = ASC_SM + BETA_DIST * distance_km_scaled
# Associate utility functions with the numbering of alternatives
V = {0: V0, 1: V1, 2: V2}
# Conditional to omega, we have a logit model (called the kernel) for
# the choice
condprob = models.logit(V, None, Choice)
# Conditional to omega, we have the product of ordered probit for the
# indicators.
condlike = (
P_Envir01
* P_Envir02
* P_Envir03
* P_Mobil11
* P_Mobil14
* P_Mobil16
* P_Mobil17
* condprob
)
# We integrate over omega using numerical integration
loglike = log(MonteCarlo(condlike))
# Define level of verbosity
logger = msg.bioMessage()
# logger.setSilent()
# logger.setWarning()
logger.setGeneral()
# logger.setDetailed()
# Create the Biogeme object
biogeme = bio.BIOGEME(database, loglike, numberOfDraws=10000)
biogeme.modelName = '05latentChoiceFull_mc'
# Estimate the parameters
results = biogeme.estimate(algorithm=opt.bioBfgs)
print(f'Estimated betas: {len(results.data.betaValues)}')
print(f'Final log likelihood: {results.data.logLike:.3f}')
print(f'Output file: {results.data.htmlFileName}')
results.writeLaTeX()
print(f'LaTeX file: {results.data.latexFileName}')