Gallery of examples¶

Assisted specification with Biogeme¶

Examples discussed in Bierlaire and Ortelli (2023) Assisted Specification with Biogeme 3.2.12

Combination of many specifications

Combination of many specifications

Base model

Investigation of several choice models

Investigation of several choice models

Catalog of nonlinear specifications

Catalog of nonlinear specifications

Catalog for alternative specific coefficients

Catalog for alternative specific coefficients

Catalog for segmented parameters

Catalog for segmented parameters

Segmentations and alternative specific specification

Segmentations and alternative specific specification

Combine many specifications: exception is raised

Combine many specifications: exception is raised

Combine many specifications: assisted specification algorithm

Combine many specifications: assisted specification algorithm

One model among many

One model among many

Re-estimation of best models

Re-estimation of best models

Example of a catalog

Example of a catalog

Biogeme examples for Bayesian inference with the Swissmetro data¶

You find here several examples of models that illustrate how to specify models to be estimated with Biogeme using Bayesian inference. To the extent possible, we have used the same examples illustrating the maximum likelihood estimation. The names of the files should correspond too.

1a. Estimation of a logit model (Bayesian)

1a. Estimation of a logit model (Bayesian)

1b. Estimation of a logit model (Bayesian)

1b. Estimation of a logit model (Bayesian)

1c. Simulation of a logit model (traditional and Bayesian)

1c. Simulation of a logit model (traditional and Bayesian)

2. Logit and sample with weights (Bayesian)

2. Logit and sample with weights (Bayesian)

3. Moneymetric and heteroscedastic specification

3. Moneymetric and heteroscedastic specification

4. Out-of-sample validation

4. Out-of-sample validation

5. Mixture of logit models: normal distribution

5. Mixture of logit models: normal distribution

6. Mixture of logit models: uniform distribution

6. Mixture of logit models: uniform distribution

7. Latent class model

7. Latent class model

8. Box-Cox transforms

8. Box-Cox transforms

9. Nested logit model

9. Nested logit model

10. Nested logit model normalized from bottom

10. Nested logit model normalized from bottom

11. Cross-nested logit

11. Cross-nested logit

12. Mixture of logit with panel data

12. Mixture of logit with panel data

15. Discrete mixture with panel data

15. Discrete mixture with panel data

16. Latent class model with panel data

16. Latent class model with panel data

17. Mixture with lognormal distribution

17. Mixture with lognormal distribution

18a. Ordinal logit model

18a. Ordinal logit model

18. Ordinal probit model

18. Ordinal probit model

19. Calculation of individual level parameters

19. Calculation of individual level parameters

23a. Binary logit model

23a. Binary logit model

23b. Binary probit model

23b. Binary probit model

25. Triangular mixture of logit

25. Triangular mixture of logit

26. Triangular mixture with panel data

26. Triangular mixture with panel data

Data preparation for Swissmetro (binary choice)

Data preparation for Swissmetro (binary choice)

Data preparation for Swissmetro

Data preparation for Swissmetro

Panel data preparation for Swissmetro

Panel data preparation for Swissmetro

Biogeme examples for hybrid choice models¶

This directory provides example implementations of MIMIC and hybrid choice models estimated with Biogeme, using both maximum likelihood and Bayesian methods. The examples range from latent-variable-only models to fully integrated hybrid choice models and are intended as reproducible references and learning material.

Choice model

Configuration

Model estimation

Model estimation

Prepare for server

Prepare for server

Latent variables

Latent variables

Likert indicators

Likert indicators

MIMIC model

Data preparation

Data preparation

1. Choice model only - maximum likelihood estimation

1. Choice model only - maximum likelihood estimation

2. MIMIC model - maximum likelihood estimation

2. MIMIC model - maximum likelihood estimation

3. Hybrid choice model - maximum likelihood estimation

3. Hybrid choice model - maximum likelihood estimation

4. Choice model only - Bayesian estimation

4. Choice model only - Bayesian estimation

5. MIMIC model - Bayesian estimation

5. MIMIC model - Bayesian estimation

6. Hybrid choice model - Bayesian estimation

6. Hybrid choice model - Bayesian estimation

Read or estimate model parameters

Read or estimate model parameters

Calculating indicators with Biogeme¶

Examples discussed in Bierlaire (2018) Calculating indicators with PandasBiogeme

Examples of mathematical expressions

Examples of mathematical expressions

Estimation and simulation of a nested logit model

Estimation and simulation of a nested logit model

Simulation of a choice model

Simulation of a choice model

Calculation of market shares

Calculation of market shares

Calculation of revenues

Calculation of revenues

Direct point elasticities

Direct point elasticities

Cross point elasticities

Cross point elasticities

Arc elasticities

Arc elasticities

Calculation of willingness to pay

Calculation of willingness to pay

Specification of a nested logit model

Specification of a nested logit model

Examples for the MDCEV model¶

sphx_glr_auto_examples_mdcev_no_outside_good_gamma_specification.py

File gamma_specification.py

sphx_glr_auto_examples_mdcev_no_outside_good_generalized_specification.py

File generalized_specification.py

sphx_glr_auto_examples_mdcev_no_outside_good_non_monotonic_specification.py

File non_monotonic_specification.py

sphx_glr_auto_examples_mdcev_no_outside_good_plot_gamma_estimation.py

File gamma_estimation.py

sphx_glr_auto_examples_mdcev_no_outside_good_plot_gamma_forecasting.py

File gamma_forecasting.py

sphx_glr_auto_examples_mdcev_no_outside_good_plot_generalized_estimation.py

File generalized_estimation.py

sphx_glr_auto_examples_mdcev_no_outside_good_plot_generalized_forecasting.py

File generalized_forecasting.py

sphx_glr_auto_examples_mdcev_no_outside_good_plot_non_monotonic_estimation.py

File non_monotonic_estimation.py

sphx_glr_auto_examples_mdcev_no_outside_good_plot_non_monotonic_forecasting.py

File non_monotonic_forecasting.py

sphx_glr_auto_examples_mdcev_no_outside_good_plot_translated_estimation.py

File translated_estimation.py

sphx_glr_auto_examples_mdcev_no_outside_good_plot_translated_forecasting.py

File translated_forecasting.py

sphx_glr_auto_examples_mdcev_no_outside_good_process_data.py

File process_data.py

Specification of the baseline utilities of a MDCEV model.

Specification of the baseline utilities of a MDCEV model.

sphx_glr_auto_examples_mdcev_no_outside_good_translated_specification.py

File translated_specification.py

Monte-Carlo integration with Biogeme¶

Example discussed in Bierlaire (2019) Monte-Carlo integration with Biogeme

Specification of the mixtures of logit

Specification of the mixtures of logit

Simple integral

Simple integral

Various integration methods

Various integration methods

Antithetic draws

Antithetic draws

Antithetic draws explicitly generated

Antithetic draws explicitly generated

Numerical integration

Numerical integration

Monte-Carlo integration

Monte-Carlo integration

Estimation of mixtures of logit

Estimation of mixtures of logit

Mixtures of logit with Monte-Carlo 10_000 draws

Mixtures of logit with Monte-Carlo 10_000 draws

Mixtures of logit with Monte-Carlo 500 draws

Mixtures of logit with Monte-Carlo 500 draws

Mixtures of logit with Monte-Carlo 10_000 antithetic draws

Mixtures of logit with Monte-Carlo 10_000 antithetic draws

Mixtures of logit with Monte-Carlo 500 antithetic draws

Mixtures of logit with Monte-Carlo 500 antithetic draws

Mixtures of logit with Monte-Carlo 10_000 Halton draws

Mixtures of logit with Monte-Carlo 10_000 Halton draws

Mixtures of logit with Monte-Carlo 500 Halton draws

Mixtures of logit with Monte-Carlo 500 Halton draws

Mixtures of logit with Monte-Carlo 10_000 MLHS draws

Mixtures of logit with Monte-Carlo 10_000 MLHS draws

Mixtures of logit with Monte-Carlo 500 MLHS draws

Mixtures of logit with Monte-Carlo 500 MLHS draws

Mixtures of logit with Monte-Carlo 10_000 antithetic MLHS draws

Mixtures of logit with Monte-Carlo 10_000 antithetic MLHS draws

Mixtures of logit with Monte-Carlo 2000 antithetic MLHS draws

Mixtures of logit with Monte-Carlo 2000 antithetic MLHS draws

Data preparation for Swissmetro

Data preparation for Swissmetro

Data preparation for Swissmetro: one observation

Data preparation for Swissmetro: one observation

Programming with Biogeme¶

Examples of the use of various Biogeme objects for programming.

biogeme.biogeme

biogeme.biogeme

biogeme.biogeme_logging

biogeme.biogeme_logging

biogeme.cnl

biogeme.database

biogeme.database

biogeme.distributions

biogeme.distributions

biogeme.draws

biogeme.expressions

biogeme.expressions

biogeme.filenames

biogeme.filenames

biogeme.loglikelihood

biogeme.loglikelihood

biogeme.models

biogeme.nests

biogeme.optimization

biogeme.optimization

biogeme.results_processing

biogeme.results_processing

biogeme.segmentation

biogeme.segmentation

biogeme.tools

biogeme.version

biogeme.version

Sampling of alternatives¶

Examples discussed in Bierlaire and Paschalidis (2023) Estimating MEV models with samples of alternatives

List of alternatives

List of alternatives

Compare parameters

Compare parameters

Logit

Nested logit

Cross-nested logit

Cross-nested logit

Model specification

Model specification

Model specification

Model specification

True parameters

True parameters

Biogeme examples for the Swissmetro data¶

You find here several examples of models that can be estimated and simulated with Biogeme.

sphx_glr_auto_examples_swissmetro_generate_jed_run.py

Generate SLURM run scripts for Biogeme experiments.

1a. Estimation of a logit model

1a. Estimation of a logit model

1b. Illustration of additional features of Biogeme

1b. Illustration of additional features of Biogeme

1c. Illustration of the quick_estimate of Biogeme

1c. Illustration of the quick_estimate of Biogeme

1d. Simulation of a logit model

1d. Simulation of a logit model

1e. Logit model with several algorithms

1e. Logit model with several algorithms

2. Estimation with weights: WESML

2. Estimation with weights: WESML

3. Moneymetric and heteroscedastic specification

3. Moneymetric and heteroscedastic specification

4. Out-of-sample validation

4. Out-of-sample validation

5a. Mixture of logit models with Monte-Carlo integration

5a. Mixture of logit models with Monte-Carlo integration

5b. Mixture of logit models with numerical integration

5b. Mixture of logit models with numerical integration

5c. Simulation of a mixture model

5c. Simulation of a mixture model

Mixture of logit

Mixture of logit

6a. Mixture of logit models with uniform distribution

6a. Mixture of logit models with uniform distribution

6b. Mixture of logit models with uniform MLHS draws

6b. Mixture of logit models with uniform MLHS draws

sphx_glr_auto_examples_swissmetro_plot_b06c_unif_mixture_integral.py

"

7. Latent class model

7. Latent class model

8. Box-Cox transforms

8. Box-Cox transforms

9. Nested logit model

9. Nested logit model

10. Nested logit model normalized from bottom

10. Nested logit model normalized from bottom

11a. Cross-nested logit

11a. Cross-nested logit

11b. Simulation of a cross-nested logit model

11b. Simulation of a cross-nested logit model

11c. Cross-nested logit with a sparse structure

11c. Cross-nested logit with a sparse structure

12. Mixture of logit with panel data

12. Mixture of logit with panel data

13. Simulation of panel model

13. Simulation of panel model

14. Nested logit with corrections for endogeneous sampling

14. Nested logit with corrections for endogeneous sampling

15a. Discrete mixture with panel data

15a. Discrete mixture with panel data

15b. Discrete mixture with panel data

15b. Discrete mixture with panel data

16. Discrete mixture with panel data

16. Discrete mixture with panel data

17a. Mixture with lognormal distribution

17a. Mixture with lognormal distribution

17b. Mixture with lognormal distribution and numerical integration

17b. Mixture with lognormal distribution and numerical integration

18a. Ordinal logit model

18a. Ordinal logit model

18b. Ordinal probit model

18b. Ordinal probit model

19. Calculation of individual level parameters

19. Calculation of individual level parameters

20. Estimation of several models

20. Estimation of several models

21a. Assisted specification

21a. Assisted specification

21b. Specification of a catalog of models

21b. Specification of a catalog of models

21c. Re-estimate the Pareto optimal models

21c. Re-estimate the Pareto optimal models

Assisted specification

Assisted specification

Specification of a catalog of models

Specification of a catalog of models

Re-estimate the Pareto optimal models

Re-estimate the Pareto optimal models

23a. Binary logit model

23a. Binary logit model

23b. Binary probit model

23b. Binary probit model

24. Mixture of logit with Halton draws

24. Mixture of logit with Halton draws

25. Triangular mixture of logit

25. Triangular mixture of logit

26. Triangular mixture with panel data

26. Triangular mixture with panel data

Data preparation for Swissmetro (binary choice)

Data preparation for Swissmetro (binary choice)

Data preparation for Swissmetro

Data preparation for Swissmetro

Panel data preparation for Swissmetro

Panel data preparation for Swissmetro

Timing function evaluation¶

We perform here the timing on some functions. The results clearly depend on the computer where it is run.

Timing of a logit model

Timing of a logit model

Timing of a cross-nested logit model

Timing of a cross-nested logit model

Timing of a logit model

Timing of a logit model

Comparison of execution times

Comparison of execution times

Data preparation for Swissmetro

Data preparation for Swissmetro

Tool for timing an expression

Tool for timing an expression

Timing of any expression

Timing of any expression

Some simple examples for beginners¶

Estimation of a binary logit model

Estimation of a binary logit model

Configuring Biogeme with parameters

Configuring Biogeme with parameters

Importing model specification

Importing model specification

Estimation results

Estimation results

Using the estimated model

Using the estimated model

Data definition for the simple tutorial

Data definition for the simple tutorial

Model specification for the simple tutorial

Model specification for the simple tutorial

Gallery generated by Sphinx-Gallery