.. DO NOT EDIT. .. THIS FILE WAS AUTOMATICALLY GENERATED BY SPHINX-GALLERY. .. TO MAKE CHANGES, EDIT THE SOURCE PYTHON FILE: .. "auto_examples/swissmetro/plot_b12_panel_bis.py" .. LINE NUMBERS ARE GIVEN BELOW. .. only:: html .. note:: :class: sphx-glr-download-link-note :ref:`Go to the end ` to download the full example code. .. rst-class:: sphx-glr-example-title .. _sphx_glr_auto_examples_swissmetro_plot_b12_panel_bis.py: 12bis. Mixture of logit with panel data and segmented ASC ========================================================= Variant of the panel mixed logit example where one ASC is segmented using the socio-economic variable MALE. This can be used to reproduce the panel renaming issue if shared Variable objects are renamed multiple times. Michel Bierlaire, EPFL .. GENERATED FROM PYTHON SOURCE LINES 12-15 .. code-block:: Python from IPython.core.display_functions import display .. GENERATED FROM PYTHON SOURCE LINES 16-17 See the data processing script: :ref:`swissmetro_panel`. .. GENERATED FROM PYTHON SOURCE LINES 17-44 .. code-block:: Python from swissmetro_panel import ( CAR_AV_SP, CAR_CO_SCALED, CAR_TT_SCALED, CHOICE, MALE, SM_AV, SM_COST_SCALED, SM_TT_SCALED, TRAIN_AV_SP, TRAIN_COST_SCALED, TRAIN_TT_SCALED, database, ) import biogeme.biogeme_logging as blog from biogeme.biogeme import BIOGEME from biogeme.expressions import Beta, Draws, MonteCarlo, PanelLikelihoodTrajectory, log from biogeme.models import logit from biogeme.results_processing import ( EstimationResults, get_pandas_estimated_parameters, ) logger = blog.get_screen_logger(level=blog.INFO) logger.info("Example b12_panel_segmented_male.py") .. rst-class:: sphx-glr-script-out .. code-block:: none Example b12_panel_segmented_male.py .. GENERATED FROM PYTHON SOURCE LINES 45-46 Parameters to be estimated. .. GENERATED FROM PYTHON SOURCE LINES 46-48 .. code-block:: Python b_cost = Beta("b_cost", 0, None, 0, 0) .. GENERATED FROM PYTHON SOURCE LINES 49-51 Define a random parameter, normally distributed across individuals, designed to be used for Monte-Carlo simulation. .. GENERATED FROM PYTHON SOURCE LINES 51-53 .. code-block:: Python b_time = Beta("b_time", 0, None, 0, 0) .. GENERATED FROM PYTHON SOURCE LINES 54-55 It is advised not to use 0 as starting value for the following parameter. .. GENERATED FROM PYTHON SOURCE LINES 55-58 .. code-block:: Python b_time_s = Beta("b_time_s", 1, 1.0e-5, None, 0) b_time_rnd = b_time + b_time_s * Draws("b_time_rnd", "NORMAL_ANTI") .. GENERATED FROM PYTHON SOURCE LINES 59-60 Random ASCs to address serial correlation. .. GENERATED FROM PYTHON SOURCE LINES 60-72 .. code-block:: Python asc_car = Beta("asc_car", 0, None, None, 0) asc_car_s = Beta("asc_car_s", 1, 1.0e-5, None, 0) asc_car_rnd = asc_car + asc_car_s * Draws("asc_car_rnd", "NORMAL_ANTI") asc_train = Beta("asc_train", 0, None, None, 0) asc_train_s = Beta("asc_train_s", 1, 1.0e-5, None, 0) asc_train_rnd = asc_train + asc_train_s * Draws("asc_train_rnd", "NORMAL_ANTI") asc_sm = Beta("asc_sm", 0, None, None, 0) asc_sm_s = Beta("asc_sm_s", 1, 1.0e-5, None, 0) asc_sm_rnd_base = asc_sm + asc_sm_s * Draws("asc_sm_rnd", "NORMAL_ANTI") .. GENERATED FROM PYTHON SOURCE LINES 73-76 Segmentation of one ASC by the socioeconomic variable MALE. This is intentionally written in a way that reuses the same variable in a comparison expression, to reproduce the original issue. .. GENERATED FROM PYTHON SOURCE LINES 76-103 .. code-block:: Python asc_sm_male = Beta("asc_sm_male", 0, None, None, 0) asc_sm_rnd = asc_sm_rnd_base + asc_sm_male * (MALE == 1) asc_train_male = Beta("asc_train_male", 0, None, None, 0) asc_sm_male = Beta("asc_sm_male", 0, None, None, 0) asc_car_male = Beta("asc_car_male", 0, None, None, 0) v_train = ( asc_train_rnd + asc_train_male * (MALE == 1) + b_time_rnd * TRAIN_TT_SCALED + b_cost * TRAIN_COST_SCALED ) v_swissmetro = ( asc_sm_rnd_base + asc_sm_male * (MALE == 1) + b_time_rnd * SM_TT_SCALED + b_cost * SM_COST_SCALED ) v_car = ( asc_car_rnd + asc_car_male * (MALE == 1) + b_time_rnd * CAR_TT_SCALED + b_cost * CAR_CO_SCALED ) .. GENERATED FROM PYTHON SOURCE LINES 104-105 Associate utility functions with the numbering of alternatives. .. GENERATED FROM PYTHON SOURCE LINES 105-107 .. code-block:: Python v = {1: v_train, 2: v_swissmetro, 3: v_car} .. GENERATED FROM PYTHON SOURCE LINES 108-109 Associate the availability conditions with the alternatives. .. GENERATED FROM PYTHON SOURCE LINES 109-111 .. code-block:: Python av = {1: TRAIN_AV_SP, 2: SM_AV, 3: CAR_AV_SP} .. GENERATED FROM PYTHON SOURCE LINES 112-114 Conditional on the random parameters, the likelihood of one observation is given by the logit model (called the kernel). .. GENERATED FROM PYTHON SOURCE LINES 114-116 .. code-block:: Python choice_probability_one_observation = logit(v, av, CHOICE) .. GENERATED FROM PYTHON SOURCE LINES 117-120 Conditional on the random parameters, the likelihood of all observations for one individual (the trajectory) is the product of the likelihood of each observation. .. GENERATED FROM PYTHON SOURCE LINES 120-124 .. code-block:: Python conditional_trajectory_probability = PanelLikelihoodTrajectory( choice_probability_one_observation ) .. GENERATED FROM PYTHON SOURCE LINES 125-126 We integrate over the random parameters using Monte-Carlo. .. GENERATED FROM PYTHON SOURCE LINES 126-128 .. code-block:: Python log_probability = log(MonteCarlo(conditional_trajectory_probability)) .. GENERATED FROM PYTHON SOURCE LINES 129-138 .. code-block:: Python the_biogeme = BIOGEME( database, log_probability, number_of_draws=5_000, seed=1223, calculating_second_derivatives="never", ) the_biogeme.model_name = "b12_panel_segmented_male" .. rst-class:: sphx-glr-script-out .. code-block:: none Biogeme parameters read from biogeme.toml. .. GENERATED FROM PYTHON SOURCE LINES 139-140 Estimate the parameters. .. GENERATED FROM PYTHON SOURCE LINES 140-147 .. code-block:: Python try: results = EstimationResults.from_yaml_file( filename=f"saved_results/{the_biogeme.model_name}.yaml" ) except FileNotFoundError: results = the_biogeme.estimate() .. GENERATED FROM PYTHON SOURCE LINES 148-150 .. code-block:: Python print(results.short_summary()) .. rst-class:: sphx-glr-script-out .. code-block:: none Results for model b12_panel_segmented_male Nbr of parameters: 12 Sample size: 752 Observations: 6768 Excluded data: 0 Final log likelihood: -3543.843 Akaike Information Criterion: 7111.686 Bayesian Information Criterion: 7167.159 .. GENERATED FROM PYTHON SOURCE LINES 151-154 .. code-block:: Python pandas_results = get_pandas_estimated_parameters(estimation_results=results) display(pandas_results) .. rst-class:: sphx-glr-script-out .. code-block:: none {'Estimated parameters': Name Value ... BHHH p-value Active bound 0 asc_train 1.233454 ... 1.461649e-06 False 1 asc_train_s 2.521465 ... 0.000000e+00 False 2 asc_train_male -2.132275 ... 2.626788e-13 False 3 b_time -6.026511 ... 0.000000e+00 False 4 b_time_s 3.502407 ... 0.000000e+00 False 5 b_cost -3.523512 ... 0.000000e+00 False 6 asc_sm 0.029208 ... 8.770092e-01 False 7 asc_sm_s 0.000010 ... 9.999874e-01 True 8 asc_sm_male 0.178862 ... 3.960256e-01 False 9 asc_car -1.145479 ... 4.813668e-04 False 10 asc_car_s 3.925120 ... 0.000000e+00 False 11 asc_car_male 1.998629 ... 3.694476e-08 False [12 rows x 6 columns]} .. GENERATED FROM PYTHON SOURCE LINES 155-156 List of columns of the flat database generated by Biogeme. .. GENERATED FROM PYTHON SOURCE LINES 156-159 .. code-block:: Python for col in the_biogeme.model_elements.database.dataframe.columns: print(col) .. rst-class:: sphx-glr-script-out .. code-block:: none GROUP SURVEY SP ID PURPOSE FIRST TICKET WHO LUGGAGE AGE MALE INCOME GA ORIGIN DEST TRAIN_AV CAR_AV SM_AV TRAIN_TT TRAIN_CO TRAIN_HE SM_TT SM_CO SM_HE SM_SEATS CAR_TT CAR_CO CHOICE SM_COST TRAIN_COST CAR_AV_SP TRAIN_AV_SP TRAIN_TT_SCALED TRAIN_COST_SCALED SM_TT_SCALED SM_COST_SCALED CAR_TT_SCALED CAR_CO_SCALED .. GENERATED FROM PYTHON SOURCE LINES 160-161 List of variables that have been renamed in the model specification. .. GENERATED FROM PYTHON SOURCE LINES 161-163 .. code-block:: Python for var in the_biogeme.model_elements.expressions_registry.variables: print(var) .. rst-class:: sphx-glr-script-out .. code-block:: none GROUP SURVEY SP ID PURPOSE FIRST TICKET WHO LUGGAGE AGE MALE INCOME GA ORIGIN DEST TRAIN_AV CAR_AV SM_AV TRAIN_TT TRAIN_CO TRAIN_HE SM_TT SM_CO SM_HE SM_SEATS CAR_TT CAR_CO CHOICE SM_COST TRAIN_COST CAR_AV_SP TRAIN_AV_SP TRAIN_TT_SCALED TRAIN_COST_SCALED SM_TT_SCALED SM_COST_SCALED CAR_TT_SCALED CAR_CO_SCALED .. rst-class:: sphx-glr-timing **Total running time of the script:** (0 minutes 0.114 seconds) .. _sphx_glr_download_auto_examples_swissmetro_plot_b12_panel_bis.py: .. only:: html .. container:: sphx-glr-footer sphx-glr-footer-example .. container:: sphx-glr-download sphx-glr-download-jupyter :download:`Download Jupyter notebook: plot_b12_panel_bis.ipynb ` .. container:: sphx-glr-download sphx-glr-download-python :download:`Download Python source code: plot_b12_panel_bis.py ` .. container:: sphx-glr-download sphx-glr-download-zip :download:`Download zipped: plot_b12_panel_bis.zip ` .. only:: html .. rst-class:: sphx-glr-signature `Gallery generated by Sphinx-Gallery `_