.. DO NOT EDIT.
.. THIS FILE WAS AUTOMATICALLY GENERATED BY SPHINX-GALLERY.
.. TO MAKE CHANGES, EDIT THE SOURCE PYTHON FILE:
.. "auto_examples/sampling/plot_b01logit.py"
.. LINE NUMBERS ARE GIVEN BELOW.

.. only:: html

    .. note::
        :class: sphx-glr-download-link-note

        :ref:`Go to the end <sphx_glr_download_auto_examples_sampling_plot_b01logit.py>`
        to download the full example code

.. rst-class:: sphx-glr-example-title

.. _sphx_glr_auto_examples_sampling_plot_b01logit.py:


Logit
=====

Estimation of a logit model using sampling of alternatives.

:author: Michel Bierlaire
:date: Wed Nov  1 17:39:47 2023

.. GENERATED FROM PYTHON SOURCE LINES 11-29

.. code-block:: default


    import pandas as pd
    from biogeme.sampling_of_alternatives import (
        SamplingContext,
        ChoiceSetsGeneration,
        GenerateModel,
        generate_segment_size,
    )
    import biogeme.biogeme_logging as blog
    import biogeme.biogeme as bio
    from compare import compare
    from specification import V, combined_variables
    from alternatives import (
        alternatives,
        ID_COLUMN,
        partitions,
    )





.. rst-class:: sphx-glr-script-out

 .. code-block:: none

    Number of asian restaurants: 33




.. GENERATED FROM PYTHON SOURCE LINES 30-32

.. code-block:: default

    logger = blog.get_screen_logger(level=blog.INFO)








.. GENERATED FROM PYTHON SOURCE LINES 33-35

The data file contains several columns associated with synthetic
choices. Here we arbitrarily select `logit_4`.

.. GENERATED FROM PYTHON SOURCE LINES 35-37

.. code-block:: default

    CHOICE_COLUMN = 'logit_4'








.. GENERATED FROM PYTHON SOURCE LINES 38-44

.. code-block:: default

    SAMPLE_SIZE = 10
    PARTITION = 'asian'
    MODEL_NAME = f'logit_{PARTITION}_{SAMPLE_SIZE}_alt'
    FILE_NAME = f'{MODEL_NAME}.dat'
    OBS_FILE = 'obs_choice.dat'








.. GENERATED FROM PYTHON SOURCE LINES 45-49

.. code-block:: default

    the_partition = partitions.get(PARTITION)
    if the_partition is None:
        raise ValueError(f'Unknown partition: {PARTITION}')








.. GENERATED FROM PYTHON SOURCE LINES 50-52

.. code-block:: default

    segment_sizes = generate_segment_size(SAMPLE_SIZE, the_partition.number_of_segments())








.. GENERATED FROM PYTHON SOURCE LINES 53-55

.. code-block:: default

    observations = pd.read_csv(OBS_FILE)








.. GENERATED FROM PYTHON SOURCE LINES 56-68

.. code-block:: default

    context = SamplingContext(
        the_partition=the_partition,
        sample_sizes=segment_sizes,
        individuals=observations,
        choice_column=CHOICE_COLUMN,
        alternatives=alternatives,
        id_column=ID_COLUMN,
        biogeme_file_name=FILE_NAME,
        utility_function=V,
        combined_variables=combined_variables,
    )








.. GENERATED FROM PYTHON SOURCE LINES 69-71

.. code-block:: default

    logger.info(context.reporting())





.. rst-class:: sphx-glr-script-out

 .. code-block:: none

    Size of the choice set: 100
    Main partition: 2 segment(s) of size 33, 67
    Main sample: 10: 5/33, 5/67
 




.. GENERATED FROM PYTHON SOURCE LINES 72-74

.. code-block:: default

    the_data_generation = ChoiceSetsGeneration(context=context)








.. GENERATED FROM PYTHON SOURCE LINES 75-77

.. code-block:: default

    the_model_generation = GenerateModel(context=context)








.. GENERATED FROM PYTHON SOURCE LINES 78-80

.. code-block:: default

    biogeme_database = the_data_generation.sample_and_merge(recycle=False)





.. rst-class:: sphx-glr-script-out

 .. code-block:: none

    Generating 10 alternatives for 10000 observations 

      0%|          | 0/10000 [00:00<?, ?it/s]
      1%|          | 77/10000 [00:00<00:12, 768.19it/s]
      2%|▏         | 154/10000 [00:00<00:13, 749.42it/s]
      2%|▏         | 229/10000 [00:00<00:13, 735.04it/s]
      3%|▎         | 303/10000 [00:00<00:13, 729.89it/s]
      4%|▍         | 385/10000 [00:00<00:12, 759.12it/s]
      5%|▍         | 470/10000 [00:00<00:12, 789.23it/s]
      5%|▌         | 549/10000 [00:00<00:12, 767.74it/s]
      6%|▋         | 626/10000 [00:00<00:12, 756.75it/s]
      7%|▋         | 712/10000 [00:00<00:11, 787.32it/s]
      8%|▊         | 794/10000 [00:01<00:11, 795.66it/s]
      9%|▊         | 874/10000 [00:01<00:11, 779.76it/s]
     10%|▉         | 953/10000 [00:01<00:11, 768.28it/s]
     10%|█         | 1032/10000 [00:01<00:11, 774.31it/s]
     11%|█         | 1117/10000 [00:01<00:11, 795.44it/s]
     12%|█▏        | 1198/10000 [00:01<00:11, 798.44it/s]
     13%|█▎        | 1278/10000 [00:01<00:11, 787.08it/s]
     14%|█▎        | 1357/10000 [00:01<00:11, 762.93it/s]
     14%|█▍        | 1434/10000 [00:01<00:11, 748.33it/s]
     15%|█▌        | 1510/10000 [00:01<00:11, 748.53it/s]
     16%|█▌        | 1585/10000 [00:02<00:11, 733.15it/s]
     17%|█▋        | 1659/10000 [00:02<00:11, 726.96it/s]
     17%|█▋        | 1732/10000 [00:02<00:11, 721.21it/s]
     18%|█▊        | 1807/10000 [00:02<00:11, 728.32it/s]
     19%|█▉        | 1896/10000 [00:02<00:10, 773.43it/s]
     20%|█▉        | 1974/10000 [00:02<00:10, 757.47it/s]
     20%|██        | 2050/10000 [00:02<00:10, 739.83it/s]
     21%|██▏       | 2132/10000 [00:02<00:10, 762.45it/s]
     22%|██▏       | 2209/10000 [00:02<00:10, 749.80it/s]
     23%|██▎       | 2297/10000 [00:03<00:09, 784.74it/s]
     24%|██▍       | 2379/10000 [00:03<00:09, 794.96it/s]
     25%|██▍       | 2459/10000 [00:03<00:09, 762.82it/s]
     25%|██▌       | 2536/10000 [00:03<00:09, 760.76it/s]
     26%|██▌       | 2620/10000 [00:03<00:09, 781.79it/s]
     27%|██▋       | 2699/10000 [00:03<00:09, 767.27it/s]
     28%|██▊       | 2776/10000 [00:03<00:09, 762.11it/s]
     29%|██▊       | 2853/10000 [00:03<00:09, 754.02it/s]
     29%|██▉       | 2929/10000 [00:03<00:09, 753.36it/s]
     30%|███       | 3006/10000 [00:03<00:09, 758.22it/s]
     31%|███       | 3082/10000 [00:04<00:09, 741.74it/s]
     32%|███▏      | 3157/10000 [00:04<00:09, 737.00it/s]
     32%|███▏      | 3231/10000 [00:04<00:09, 732.87it/s]
     33%|███▎      | 3307/10000 [00:04<00:09, 740.03it/s]
     34%|███▍      | 3388/10000 [00:04<00:08, 759.61it/s]
     35%|███▍      | 3465/10000 [00:04<00:08, 754.25it/s]
     35%|███▌      | 3541/10000 [00:04<00:08, 753.29it/s]
     36%|███▌      | 3617/10000 [00:04<00:08, 747.23it/s]
     37%|███▋      | 3692/10000 [00:04<00:08, 742.36it/s]
     38%|███▊      | 3771/10000 [00:04<00:08, 755.80it/s]
     39%|███▊      | 3856/10000 [00:05<00:07, 783.21it/s]
     39%|███▉      | 3935/10000 [00:05<00:07, 770.56it/s]
     40%|████      | 4013/10000 [00:05<00:07, 765.32it/s]
     41%|████      | 4090/10000 [00:05<00:07, 757.94it/s]
     42%|████▏     | 4175/10000 [00:05<00:07, 783.39it/s]
     43%|████▎     | 4254/10000 [00:05<00:07, 774.80it/s]
     43%|████▎     | 4332/10000 [00:05<00:07, 748.24it/s]
     44%|████▍     | 4408/10000 [00:05<00:07, 740.02it/s]
     45%|████▍     | 4485/10000 [00:05<00:07, 747.57it/s]
     46%|████▌     | 4572/10000 [00:06<00:06, 782.36it/s]
     47%|████▋     | 4651/10000 [00:06<00:06, 782.30it/s]
     47%|████▋     | 4730/10000 [00:06<00:06, 783.70it/s]
     48%|████▊     | 4827/10000 [00:06<00:06, 836.16it/s]
     49%|████▉     | 4911/10000 [00:06<00:06, 824.42it/s]
     50%|█████     | 5007/10000 [00:06<00:05, 861.97it/s]
     51%|█████     | 5094/10000 [00:06<00:05, 854.64it/s]
     52%|█████▏    | 5202/10000 [00:06<00:05, 918.73it/s]
     53%|█████▎    | 5307/10000 [00:06<00:04, 954.44it/s]
     54%|█████▍    | 5403/10000 [00:06<00:04, 931.00it/s]
     55%|█████▍    | 5497/10000 [00:07<00:04, 905.93it/s]
     56%|█████▌    | 5588/10000 [00:07<00:04, 902.71it/s]
     57%|█████▋    | 5684/10000 [00:07<00:04, 918.30it/s]
     58%|█████▊    | 5776/10000 [00:07<00:04, 895.85it/s]
     59%|█████▉    | 5875/10000 [00:07<00:04, 922.85it/s]
     60%|█████▉    | 5968/10000 [00:07<00:04, 898.42it/s]
     61%|██████    | 6059/10000 [00:07<00:04, 861.87it/s]
     61%|██████▏   | 6146/10000 [00:07<00:04, 859.69it/s]
     62%|██████▏   | 6233/10000 [00:07<00:04, 840.06it/s]
     63%|██████▎   | 6319/10000 [00:07<00:04, 845.42it/s]
     64%|██████▍   | 6406/10000 [00:08<00:04, 849.68it/s]
     65%|██████▍   | 6492/10000 [00:08<00:04, 835.57it/s]
     66%|██████▌   | 6576/10000 [00:08<00:04, 826.30it/s]
     67%|██████▋   | 6659/10000 [00:08<00:04, 826.40it/s]
     68%|██████▊   | 6751/10000 [00:08<00:03, 852.65it/s]
     68%|██████▊   | 6837/10000 [00:08<00:03, 853.99it/s]
     69%|██████▉   | 6923/10000 [00:08<00:03, 836.16it/s]
     70%|███████   | 7014/10000 [00:08<00:03, 854.97it/s]
     71%|███████   | 7100/10000 [00:08<00:03, 855.61it/s]
     72%|███████▏  | 7192/10000 [00:09<00:03, 872.73it/s]
     73%|███████▎  | 7281/10000 [00:09<00:03, 874.97it/s]
     74%|███████▎  | 7369/10000 [00:09<00:03, 871.66it/s]
     75%|███████▍  | 7460/10000 [00:09<00:02, 881.51it/s]
     76%|███████▌  | 7554/10000 [00:09<00:02, 896.59it/s]
     76%|███████▋  | 7649/10000 [00:09<00:02, 912.32it/s]
     77%|███████▋  | 7741/10000 [00:09<00:02, 893.66it/s]
     78%|███████▊  | 7831/10000 [00:09<00:02, 888.19it/s]
     79%|███████▉  | 7920/10000 [00:09<00:02, 883.60it/s]
     80%|████████  | 8009/10000 [00:09<00:02, 871.79it/s]
     81%|████████  | 8108/10000 [00:10<00:02, 905.32it/s]
     82%|████████▏ | 8199/10000 [00:10<00:02, 870.72it/s]
     83%|████████▎ | 8331/10000 [00:10<00:01, 998.58it/s]
     84%|████████▍ | 8432/10000 [00:10<00:01, 892.53it/s]
     85%|████████▌ | 8539/10000 [00:10<00:01, 935.87it/s]
     86%|████████▋ | 8635/10000 [00:10<00:01, 913.63it/s]
     87%|████████▋ | 8728/10000 [00:10<00:01, 858.82it/s]
     89%|████████▊ | 8861/10000 [00:10<00:01, 984.83it/s]
     90%|████████▉ | 8962/10000 [00:10<00:01, 942.82it/s]
     91%|█████████ | 9059/10000 [00:11<00:01, 935.75it/s]
     92%|█████████▏| 9154/10000 [00:11<00:00, 897.79it/s]
     92%|█████████▏| 9245/10000 [00:11<00:00, 892.81it/s]
     93%|█████████▎| 9335/10000 [00:11<00:00, 822.33it/s]
     94%|█████████▍| 9419/10000 [00:11<00:00, 805.43it/s]
     95%|█████████▌| 9501/10000 [00:11<00:00, 800.46it/s]
     96%|█████████▌| 9582/10000 [00:11<00:00, 786.48it/s]
     97%|█████████▋| 9661/10000 [00:11<00:00, 782.33it/s]
     97%|█████████▋| 9740/10000 [00:11<00:00, 775.33it/s]
     98%|█████████▊| 9822/10000 [00:12<00:00, 786.60it/s]
     99%|█████████▉| 9901/10000 [00:12<00:00, 782.60it/s]
    100%|█████████▉| 9980/10000 [00:12<00:00, 765.56it/s]
    100%|██████████| 10000/10000 [00:12<00:00, 792.30it/s]
    Define new variables 

    Defining new variables...:   0%|          | 0/10 [00:00<?, ?it/s]
    Defining new variables...:  20%|██        | 2/10 [00:00<00:00, 10.09it/s]
    Defining new variables...:  40%|████      | 4/10 [00:00<00:00,  9.89it/s]
    Defining new variables...:  60%|██████    | 6/10 [00:00<00:00, 10.24it/s]
    Defining new variables...:  80%|████████  | 8/10 [00:00<00:00,  9.85it/s]
    Defining new variables...:  90%|█████████ | 9/10 [00:00<00:00,  9.68it/s]
    Defining new variables...: 100%|██████████| 10/10 [00:01<00:00,  9.57it/s]
    Defining new variables...: 100%|██████████| 10/10 [00:01<00:00,  9.77it/s]
    File logit_asian_10_alt.dat has been created. 




.. GENERATED FROM PYTHON SOURCE LINES 81-83

.. code-block:: default

    logprob = the_model_generation.get_logit()








.. GENERATED FROM PYTHON SOURCE LINES 84-87

.. code-block:: default

    the_biogeme = bio.BIOGEME(biogeme_database, logprob)
    the_biogeme.modelName = MODEL_NAME





.. rst-class:: sphx-glr-script-out

 .. code-block:: none

    File biogeme.toml has been parsed. 




.. GENERATED FROM PYTHON SOURCE LINES 88-89

Calculate the null log likelihood for reporting.

.. GENERATED FROM PYTHON SOURCE LINES 89-91

.. code-block:: default

    the_biogeme.calculateNullLoglikelihood({i: 1 for i in range(SAMPLE_SIZE)})





.. rst-class:: sphx-glr-script-out

 .. code-block:: none


    -23025.850929942502



.. GENERATED FROM PYTHON SOURCE LINES 92-93

Estimate the parameters

.. GENERATED FROM PYTHON SOURCE LINES 93-95

.. code-block:: default

    results = the_biogeme.estimate(recycle=False)





.. rst-class:: sphx-glr-script-out

 .. code-block:: none

    *** Initial values of the parameters are obtained from the file __logit_asian_10_alt.iter 
    Parameter values restored from __logit_asian_10_alt.iter 
    Optimization algorithm: hybrid Newton/BFGS with simple bounds [simple_bounds] 
    ** Optimization: Newton with trust region for simple bounds 
    Iter.    beta_chinese  beta_ethiopian     beta_french     beta_indian   beta_japanese     beta_korean   beta_lebanese   beta_log_dist    beta_mexican      beta_price     beta_rating     Function    Relgrad   Radius      Rho      
        0            0.62            0.44            0.64            0.93             1.2            0.73            0.71            -0.6             1.2           -0.41            0.76      1.8e+04    1.9e-05       10        1   ++ 
        1            0.62            0.44            0.64            0.93             1.2            0.73            0.71            -0.6             1.2           -0.41            0.76      1.8e+04    1.5e-09       10        1   ++ 
    Results saved in file logit_asian_10_alt~00.html 
    Results saved in file logit_asian_10_alt~00.pickle 




.. GENERATED FROM PYTHON SOURCE LINES 96-98

.. code-block:: default

    print(results.short_summary())





.. rst-class:: sphx-glr-script-out

 .. code-block:: none

    Results for model logit_asian_10_alt
    Nbr of parameters:              11
    Sample size:                    10000
    Excluded data:                  0
    Null log likelihood:            -23025.85
    Final log likelihood:           -18419.15
    Likelihood ratio test (null):           9213.409
    Rho square (null):                      0.2
    Rho bar square (null):                  0.2
    Akaike Information Criterion:   36860.29
    Bayesian Information Criterion: 36939.61





.. GENERATED FROM PYTHON SOURCE LINES 99-102

.. code-block:: default

    estimated_parameters = results.getEstimatedParameters()
    estimated_parameters






.. raw:: html

    <div class="output_subarea output_html rendered_html output_result">
    <div>
    <style scoped>
        .dataframe tbody tr th:only-of-type {
            vertical-align: middle;
        }

        .dataframe tbody tr th {
            vertical-align: top;
        }

        .dataframe thead th {
            text-align: right;
        }
    </style>
    <table border="1" class="dataframe">
      <thead>
        <tr style="text-align: right;">
          <th></th>
          <th>Value</th>
          <th>Rob. Std err</th>
          <th>Rob. t-test</th>
          <th>Rob. p-value</th>
        </tr>
      </thead>
      <tbody>
        <tr>
          <th>beta_chinese</th>
          <td>0.624533</td>
          <td>0.050571</td>
          <td>12.349548</td>
          <td>0.0</td>
        </tr>
        <tr>
          <th>beta_ethiopian</th>
          <td>0.441458</td>
          <td>0.050674</td>
          <td>8.711710</td>
          <td>0.0</td>
        </tr>
        <tr>
          <th>beta_french</th>
          <td>0.641939</td>
          <td>0.062615</td>
          <td>10.252160</td>
          <td>0.0</td>
        </tr>
        <tr>
          <th>beta_indian</th>
          <td>0.927575</td>
          <td>0.042896</td>
          <td>21.623899</td>
          <td>0.0</td>
        </tr>
        <tr>
          <th>beta_japanese</th>
          <td>1.191176</td>
          <td>0.046636</td>
          <td>25.541986</td>
          <td>0.0</td>
        </tr>
        <tr>
          <th>beta_korean</th>
          <td>0.726871</td>
          <td>0.042680</td>
          <td>17.030570</td>
          <td>0.0</td>
        </tr>
        <tr>
          <th>beta_lebanese</th>
          <td>0.708292</td>
          <td>0.062616</td>
          <td>11.311743</td>
          <td>0.0</td>
        </tr>
        <tr>
          <th>beta_log_dist</th>
          <td>-0.595134</td>
          <td>0.015042</td>
          <td>-39.564050</td>
          <td>0.0</td>
        </tr>
        <tr>
          <th>beta_mexican</th>
          <td>1.216204</td>
          <td>0.036573</td>
          <td>33.254283</td>
          <td>0.0</td>
        </tr>
        <tr>
          <th>beta_price</th>
          <td>-0.405947</td>
          <td>0.012733</td>
          <td>-31.882617</td>
          <td>0.0</td>
        </tr>
        <tr>
          <th>beta_rating</th>
          <td>0.759850</td>
          <td>0.015470</td>
          <td>49.116968</td>
          <td>0.0</td>
        </tr>
      </tbody>
    </table>
    </div>
    </div>
    <br />
    <br />

.. GENERATED FROM PYTHON SOURCE LINES 103-105

.. code-block:: default

    df, msg = compare(estimated_parameters)








.. GENERATED FROM PYTHON SOURCE LINES 106-108

.. code-block:: default

    print(df)





.. rst-class:: sphx-glr-script-out

 .. code-block:: none

                  Name  True Value  Estimated Value    T-Test
    0      beta_rating        0.75         0.759850 -0.636700
    1       beta_price       -0.40        -0.405947  0.467069
    2     beta_chinese        0.75         0.624533  2.480988
    3    beta_japanese        1.25         1.191176  1.261347
    4      beta_korean        0.75         0.726871  0.541905
    5      beta_indian        1.00         0.927575  1.688384
    6      beta_french        0.75         0.641939  1.725793
    7     beta_mexican        1.25         1.216204  0.924075
    8    beta_lebanese        0.75         0.708292  0.666092
    9   beta_ethiopian        0.50         0.441458  1.155270
    10   beta_log_dist       -0.60        -0.595134 -0.323468




.. GENERATED FROM PYTHON SOURCE LINES 109-110

.. code-block:: default

    print(msg)




.. rst-class:: sphx-glr-script-out

 .. code-block:: none

    Parameters not estimated: ['mu_asian', 'mu_downtown']





.. rst-class:: sphx-glr-timing

   **Total running time of the script:** (0 minutes 16.782 seconds)


.. _sphx_glr_download_auto_examples_sampling_plot_b01logit.py:

.. only:: html

  .. container:: sphx-glr-footer sphx-glr-footer-example




    .. container:: sphx-glr-download sphx-glr-download-python

      :download:`Download Python source code: plot_b01logit.py <plot_b01logit.py>`

    .. container:: sphx-glr-download sphx-glr-download-jupyter

      :download:`Download Jupyter notebook: plot_b01logit.ipynb <plot_b01logit.ipynb>`


.. only:: html

 .. rst-class:: sphx-glr-signature

    `Gallery generated by Sphinx-Gallery <https://sphinx-gallery.github.io>`_