.. DO NOT EDIT.
.. THIS FILE WAS AUTOMATICALLY GENERATED BY SPHINX-GALLERY.
.. TO MAKE CHANGES, EDIT THE SOURCE PYTHON FILE:
.. "_examples/matplotlib/plot_main07_c_2dbin_fake.py"
.. LINE NUMBERS ARE GIVEN BELOW.

.. only:: html

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

        Click :ref:`here <sphx_glr_download__examples_matplotlib_plot_main07_c_2dbin_fake.py>`
        to download the full example code

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

.. _sphx_glr__examples_matplotlib_plot_main07_c_2dbin_fake.py:


07.c ``stats.2dbin`` with fake data
-----------------------------------

Use binned_statistic_2d and display using heatmap.

.. GENERATED FROM PYTHON SOURCE LINES 8-175



.. image-sg:: /_examples/matplotlib/images/sphx_glr_plot_main07_c_2dbin_fake_001.png
   :alt: C-Reactive Protein, count, median
   :srcset: /_examples/matplotlib/images/sphx_glr_plot_main07_c_2dbin_fake_001.png
   :class: sphx-glr-single-img


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

 Out:

 .. code-block:: none

    [1 1 1 1 2 2 2 3]
    [1 1 2 2 3 3 4 1]
    [1 1 5 6 7 8 7 7]

    Scipy:
    [0.5 1.5 2.5 3.5 4.5 5.5 6.5]
    [1.         1.03030303 1.06060606 1.09090909 1.12121212 1.15151515
     1.18181818 1.21212121 1.24242424 1.27272727 1.3030303  1.33333333
     1.36363636 1.39393939 1.42424242 1.45454545 1.48484848 1.51515152
     1.54545455 1.57575758 1.60606061 1.63636364 1.66666667 1.6969697
     1.72727273 1.75757576 1.78787879 1.81818182 1.84848485 1.87878788
     1.90909091 1.93939394 1.96969697 2.         2.03030303 2.06060606
     2.09090909 2.12121212 2.15151515 2.18181818 2.21212121 2.24242424
     2.27272727 2.3030303  2.33333333 2.36363636 2.39393939 2.42424242
     2.45454545 2.48484848 2.51515152 2.54545455 2.57575758 2.60606061
     2.63636364 2.66666667 2.6969697  2.72727273 2.75757576 2.78787879
     2.81818182 2.84848485 2.87878788 2.90909091 2.93939394 2.96969697
     3.         3.03030303 3.06060606 3.09090909 3.12121212 3.15151515
     3.18181818 3.21212121 3.24242424 3.27272727 3.3030303  3.33333333
     3.36363636 3.39393939 3.42424242 3.45454545 3.48484848 3.51515152
     3.54545455 3.57575758 3.60606061 3.63636364 3.66666667 3.6969697
     3.72727273 3.75757576 3.78787879 3.81818182 3.84848485 3.87878788
     3.90909091 3.93939394 3.96969697 4.        ]
    [[2. 0. 1. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [2. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 2. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 0. 0. 0. 0. 0.]
     [0. 1. 0. 0. 0. 0.]]
    [1.01515152 1.04545455 1.07575758 1.10606061 1.13636364 1.16666667
     1.1969697  1.22727273 1.25757576 1.28787879 1.31818182 1.34848485
     1.37878788 1.40909091 1.43939394 1.46969697 1.5        1.53030303
     1.56060606 1.59090909 1.62121212 1.65151515 1.68181818 1.71212121
     1.74242424 1.77272727 1.8030303  1.83333333 1.86363636 1.89393939
     1.92424242 1.95454545 1.98484848 2.01515152 2.04545455 2.07575758
     2.10606061 2.13636364 2.16666667 2.1969697  2.22727273 2.25757576
     2.28787879 2.31818182 2.34848485 2.37878788 2.40909091 2.43939394
     2.46969697 2.5        2.53030303 2.56060606 2.59090909 2.62121212
     2.65151515 2.68181818 2.71212121 2.74242424 2.77272727 2.8030303
     2.83333333 2.86363636 2.89393939 2.92424242 2.95454545 2.98484848
     3.01515152 3.04545455 3.07575758 3.10606061 3.13636364 3.16666667
     3.1969697  3.22727273 3.25757576 3.28787879 3.31818182 3.34848485
     3.37878788 3.40909091 3.43939394 3.46969697 3.5        3.53030303
     3.56060606 3.59090909 3.62121212 3.65151515 3.68181818 3.71212121
     3.74242424 3.77272727 3.8030303  3.83333333 3.86363636 3.89393939
     3.92424242 3.95454545 3.98484848]
    [1. 2. 3. 4. 5. 6.]

    '\nimport sys\nsys.exit()\n# Compute bin statistic (count and median)\n\n# Plot\nplt.figure()\nsns.violinplot(data=data, x="timestep", y="shap_values", inner="box")\nplt.figure()\nplt.tight_layout()\nsns.violinplot(data=data, x="timestep", y="feature_values", inner="box")\nplt.figure()\nsns.histplot(data=data, x="timestep", shrink=.8)\n\n\n# Plot hist\nf1 = plt.hist2d(data.timestep, data.feature_values, bins=30, cmap=\'Reds\')\ncb = plt.colorbar()\ncb.set_label(\'counts in bin\')\nplt.title(\'Counts (square bin)\')\nplt.show()\n'





|

.. code-block:: default
   :lineno-start: 9


    # Libraries
    import seaborn as sns
    import pandas as pd
    import numpy as np
    import matplotlib.pyplot as plt

    from scipy import stats
    from matplotlib.colors import LogNorm

    def data_shap():
        data = pd.read_csv('../../datasets/shap/shap.csv')
        return data.timestep, \
               data.shap_values, \
               data.feature_values, \
               data

    def data_manual():
        """"""
        # Create random values
        x = np.array([1, 1, 1, 1, 2, 2, 2, 3])
        y = np.array([1, 1, 2, 2, 3, 3, 4, 1])
        z = np.array([1, 1, 5, 6, 7, 8, 7, 7])
        return x, y, z, None

    # Create data
    x, y, z, data = data_manual()

    print(x)
    print(y)
    print(z)

    """
    # With pandas
    v = z
    vals, bins = np.histogram(v)
    a = pd.Series(v).groupby(pd.cut(v, bins)).median()
    print("\nPandas:")
    print(bins)
    print(vals)
    print(a)
    """







    vmin = z.min()
    vmax = z.max()



    # Compute binned statistic (median)
    binx = np.linspace(0, 3, 4) + 0.5
    biny = np.linspace(0, 4, 5) + 0.5
    binx = np.linspace(0, 6, 7) + 0.5
    biny = np.linspace(y.min(), y.max(), 100)
    r1 = stats.binned_statistic_2d(x=y, y=x, values=z,
        statistic='count', bins=[biny, binx],
        expand_binnumbers=False)

    r2 = stats.binned_statistic_2d(x=y, y=x, values=z,
        statistic='median', bins=[biny, binx],
        expand_binnumbers=False)

    # Compute centres
    x_center = (r1.x_edge[:-1] + r1.x_edge[1:]) / 2
    y_center = (r1.y_edge[:-1] + r1.y_edge[1:]) / 2

    # Show
    print("\nScipy:")
    print(binx)
    print(biny)
    print(r1.statistic)
    print(x_center)
    print(y_center)

    # Convert the computed matrix to an stacked dataframe?

    flip1 = np.flip(r1.statistic, 0)
    flip2 = np.flip(r2.statistic, 0)
    #flip1 = r1.statistic
    #flip2 = r2.statistic



    # Display
    fig, axs = plt.subplots(nrows=1, ncols=2,
        sharey=False, sharex=False, figsize=(8, 7))

    sns.heatmap(flip1, annot=False, linewidth=0.5,
        xticklabels=y_center.astype(int),
        yticklabels=x_center.round(2)[::-1], # Because of flip
        cmap='Blues', ax=axs[0],
        norm=LogNorm())

    sns.heatmap(flip2, annot=False, linewidth=0.5,
        xticklabels=y_center.astype(int),
        yticklabels=x_center.round(2)[::-1], # Because of flip
        cmap='coolwarm', ax=axs[1], zorder=1,
        vmin=None, vmax=None, center=None, robust=True)

    # If robust=True and vmin or vmax are absent, the colormap range
    # is computed with robust quantiles instead of the extreme values.
    """
    sns.violinplot(x=x, y=y,
        saturation=0.5, fliersize=0.1, linewidth=0.5,
        color='green', ax=axs[2], zorder=3,
        width=0.5)
    """


    # Configure ax0
    axs[0].set_title('count')
    axs[0].set_xlabel('timestep')
    axs[0].set_ylabel('shap')
    axs[0].locator_params(axis='y', nbins=10)
    #axs[0].set_aspect('equal', 'box'

    # Configure ax1
    axs[1].set_title('median')
    axs[1].set_xlabel('timestep')
    axs[1].set_ylabel('shap')
    axs[1].locator_params(axis='y', nbins=10)
    #axs[1].set_aspect('equal', 'box')
    #axs[1].invert_yaxis()

    # Generic
    plt.suptitle('C-Reactive Protein')

    """
    # Set axes manually
    #plt.set_xticks()
    #plt.setp(axs[1].get_yticklabels()[::1], visible=False)
    #plt.setp(axs[1].get_yticklabels()[::5], visible=True)
    from matplotlib import ticker
    axs[1].xaxis.set_major_locator(ticker.MultipleLocator(1.00))
    axs[1].xaxis.set_minor_locator(ticker.MultipleLocator(0.25))
    """

    plt.tight_layout()
    plt.show()


    """
    import sys
    sys.exit()
    # Compute bin statistic (count and median)

    # Plot
    plt.figure()
    sns.violinplot(data=data, x="timestep", y="shap_values", inner="box")
    plt.figure()
    plt.tight_layout()
    sns.violinplot(data=data, x="timestep", y="feature_values", inner="box")
    plt.figure()
    sns.histplot(data=data, x="timestep", shrink=.8)


    # Plot hist
    f1 = plt.hist2d(data.timestep, data.feature_values, bins=30, cmap='Reds')
    cb = plt.colorbar()
    cb.set_label('counts in bin')
    plt.title('Counts (square bin)')
    plt.show()
    """

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

   **Total running time of the script:** ( 0 minutes  0.853 seconds)


.. _sphx_glr_download__examples_matplotlib_plot_main07_c_2dbin_fake.py:


.. only :: html

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



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

     :download:`Download Python source code: plot_main07_c_2dbin_fake.py <plot_main07_c_2dbin_fake.py>`



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

     :download:`Download Jupyter notebook: plot_main07_c_2dbin_fake.ipynb <plot_main07_c_2dbin_fake.ipynb>`


.. only:: html

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

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