.. DO NOT EDIT.
.. THIS FILE WAS AUTOMATICALLY GENERATED BY SPHINX-GALLERY.
.. TO MAKE CHANGES, EDIT THE SOURCE PYTHON FILE:
.. "auto_examples/eda.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_eda.py>`
        to download the full example code.

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

.. _sphx_glr_auto_examples_eda.py:


=========================
Exploratory Data Analysis
=========================

.. GENERATED FROM PYTHON SOURCE LINES 6-26

.. code-block:: Python

    import os
    import pandas as pd

    import matplotlib.pyplot as plt

    from easy_mpl import imshow
    from easy_mpl.utils import create_subplots

    from mne.viz import circular_layout
    from mne_connectivity.viz import plot_connectivity_circle

    from utils import SAVE
    from utils import LABEL_MAP
    from utils import set_rcParams
    from utils import distribution_plot
    from utils import pie_from_series
    from utils import merge_uniques
    from utils import prepare_data
    from utils import print_version_info








.. GENERATED FROM PYTHON SOURCE LINES 27-31

.. code-block:: Python


    # Print the version info of the packages being used
    print_version_info()





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

 .. code-block:: none

    python 3.12.7 (main, Nov  5 2024, 16:16:58) [GCC 11.4.0]
    os posix
    ai4water 1.07
    xgboost 2.1.3
    easy_mpl 0.21.4
    SeqMetrics 2.0.0
    torch 2.5.1+cu124
    numpy 1.26.4
    pandas 1.5.3
    matplotlib 3.8.4
    sklearn 1.3.1
    xarray 2024.3.0
    netCDF4 1.7.2
    seaborn 0.13.2
    bnlearn 0.10.2
    Script Executed on:  Wed Jan  1 06:31:55 2025
    tot_cpus 2
    avail_cpus 2
    mem_gib 7.612831115722656




.. GENERATED FROM PYTHON SOURCE LINES 32-35

.. code-block:: Python


    set_rcParams()








.. GENERATED FROM PYTHON SOURCE LINES 36-39

.. code-block:: Python

    fpath = os.path.join("../data/data.xlsx")
    df = pd.read_excel(fpath)








.. GENERATED FROM PYTHON SOURCE LINES 40-44

.. code-block:: Python


    # Display the first 5 rows of the dataset
    df.head()






.. 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>Catalyst type</th>
          <th>Surface area</th>
          <th>Pore volume</th>
          <th>BandGap (eV)</th>
          <th>Au</th>
          <th>Bi</th>
          <th>Fe</th>
          <th>O</th>
          <th>Catalyst loading (g/L)</th>
          <th>Light intensity (W)</th>
          <th>time (min)</th>
          <th>solution pH</th>
          <th>Anions</th>
          <th>Ci (mg/L)</th>
          <th>Cf (mg/L)</th>
          <th>Efficiency (%)</th>
        </tr>
      </thead>
      <tbody>
        <tr>
          <th>0</th>
          <td>no catalyst</td>
          <td>0.0</td>
          <td>0.0</td>
          <td>0.0</td>
          <td>0.0</td>
          <td>0.0</td>
          <td>0.0</td>
          <td>0.0</td>
          <td>0.0</td>
          <td>105</td>
          <td>0</td>
          <td>5.4</td>
          <td>Without Anions</td>
          <td>5</td>
          <td>5.00</td>
          <td>0.0</td>
        </tr>
        <tr>
          <th>1</th>
          <td>no catalyst</td>
          <td>0.0</td>
          <td>0.0</td>
          <td>0.0</td>
          <td>0.0</td>
          <td>0.0</td>
          <td>0.0</td>
          <td>0.0</td>
          <td>0.0</td>
          <td>105</td>
          <td>30</td>
          <td>5.4</td>
          <td>Without Anions</td>
          <td>5</td>
          <td>4.99</td>
          <td>0.2</td>
        </tr>
        <tr>
          <th>2</th>
          <td>no catalyst</td>
          <td>0.0</td>
          <td>0.0</td>
          <td>0.0</td>
          <td>0.0</td>
          <td>0.0</td>
          <td>0.0</td>
          <td>0.0</td>
          <td>0.0</td>
          <td>105</td>
          <td>60</td>
          <td>5.4</td>
          <td>Without Anions</td>
          <td>5</td>
          <td>4.96</td>
          <td>0.8</td>
        </tr>
        <tr>
          <th>3</th>
          <td>no catalyst</td>
          <td>0.0</td>
          <td>0.0</td>
          <td>0.0</td>
          <td>0.0</td>
          <td>0.0</td>
          <td>0.0</td>
          <td>0.0</td>
          <td>0.0</td>
          <td>105</td>
          <td>90</td>
          <td>5.4</td>
          <td>Without Anions</td>
          <td>5</td>
          <td>4.96</td>
          <td>0.8</td>
        </tr>
        <tr>
          <th>4</th>
          <td>no catalyst</td>
          <td>0.0</td>
          <td>0.0</td>
          <td>0.0</td>
          <td>0.0</td>
          <td>0.0</td>
          <td>0.0</td>
          <td>0.0</td>
          <td>0.0</td>
          <td>105</td>
          <td>120</td>
          <td>5.4</td>
          <td>Without Anions</td>
          <td>5</td>
          <td>4.94</td>
          <td>1.2</td>
        </tr>
      </tbody>
    </table>
    </div>
    </div>
    <br />
    <br />

.. GENERATED FROM PYTHON SOURCE LINES 45-46

Display the last 5 rows of the dataset

.. GENERATED FROM PYTHON SOURCE LINES 46-48

.. code-block:: Python

    df.tail()






.. 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>Catalyst type</th>
          <th>Surface area</th>
          <th>Pore volume</th>
          <th>BandGap (eV)</th>
          <th>Au</th>
          <th>Bi</th>
          <th>Fe</th>
          <th>O</th>
          <th>Catalyst loading (g/L)</th>
          <th>Light intensity (W)</th>
          <th>time (min)</th>
          <th>solution pH</th>
          <th>Anions</th>
          <th>Ci (mg/L)</th>
          <th>Cf (mg/L)</th>
          <th>Efficiency (%)</th>
        </tr>
      </thead>
      <tbody>
        <tr>
          <th>1039</th>
          <td>1 wt% Au-BFO</td>
          <td>21.6</td>
          <td>0.0043</td>
          <td>2.35</td>
          <td>1.0</td>
          <td>55.79</td>
          <td>13.68</td>
          <td>29.52</td>
          <td>1.5</td>
          <td>105</td>
          <td>210</td>
          <td>7.0</td>
          <td>Na2HPO4</td>
          <td>5</td>
          <td>2.14</td>
          <td>57.2</td>
        </tr>
        <tr>
          <th>1040</th>
          <td>1 wt% Au-BFO</td>
          <td>21.6</td>
          <td>0.0043</td>
          <td>2.35</td>
          <td>1.0</td>
          <td>55.79</td>
          <td>13.68</td>
          <td>29.52</td>
          <td>1.5</td>
          <td>105</td>
          <td>240</td>
          <td>7.0</td>
          <td>Na2HPO4</td>
          <td>5</td>
          <td>1.73</td>
          <td>65.4</td>
        </tr>
        <tr>
          <th>1041</th>
          <td>1 wt% Au-BFO</td>
          <td>21.6</td>
          <td>0.0043</td>
          <td>2.35</td>
          <td>1.0</td>
          <td>55.79</td>
          <td>13.68</td>
          <td>29.52</td>
          <td>1.5</td>
          <td>105</td>
          <td>270</td>
          <td>7.0</td>
          <td>Na2HPO4</td>
          <td>5</td>
          <td>1.26</td>
          <td>74.8</td>
        </tr>
        <tr>
          <th>1042</th>
          <td>1 wt% Au-BFO</td>
          <td>21.6</td>
          <td>0.0043</td>
          <td>2.35</td>
          <td>1.0</td>
          <td>55.79</td>
          <td>13.68</td>
          <td>29.52</td>
          <td>1.5</td>
          <td>105</td>
          <td>300</td>
          <td>7.0</td>
          <td>Na2HPO4</td>
          <td>5</td>
          <td>0.83</td>
          <td>83.4</td>
        </tr>
        <tr>
          <th>1043</th>
          <td>1 wt% Au-BFO</td>
          <td>21.6</td>
          <td>0.0043</td>
          <td>2.35</td>
          <td>1.0</td>
          <td>55.79</td>
          <td>13.68</td>
          <td>29.52</td>
          <td>1.5</td>
          <td>105</td>
          <td>330</td>
          <td>7.0</td>
          <td>Na2HPO4</td>
          <td>5</td>
          <td>0.35</td>
          <td>93.0</td>
        </tr>
      </tbody>
    </table>
    </div>
    </div>
    <br />
    <br />

.. GENERATED FROM PYTHON SOURCE LINES 49-50

Display the shape of the dataset

.. GENERATED FROM PYTHON SOURCE LINES 50-52

.. code-block:: Python

    df.shape





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

 .. code-block:: none


    (1044, 16)



.. GENERATED FROM PYTHON SOURCE LINES 53-54

Display the columns of the dataset

.. GENERATED FROM PYTHON SOURCE LINES 54-56

.. code-block:: Python

    df.columns





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

 .. code-block:: none


    Index(['Catalyst type', 'Surface area', 'Pore volume', 'BandGap (eV)', 'Au',
           'Bi', 'Fe', 'O', 'Catalyst loading (g/L)', 'Light intensity (W)',
           'time (min)', 'solution pH', 'Anions', 'Ci (mg/L)', 'Cf (mg/L)',
           'Efficiency (%)'],
          dtype='object')



.. GENERATED FROM PYTHON SOURCE LINES 57-58

Display the info of the dataset

.. GENERATED FROM PYTHON SOURCE LINES 58-60

.. code-block:: Python

    df.info()





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

 .. code-block:: none

    <class 'pandas.core.frame.DataFrame'>
    RangeIndex: 1044 entries, 0 to 1043
    Data columns (total 16 columns):
     #   Column                  Non-Null Count  Dtype  
    ---  ------                  --------------  -----  
     0   Catalyst type           1044 non-null   object 
     1   Surface area            1044 non-null   float64
     2   Pore volume             1044 non-null   float64
     3   BandGap (eV)            1044 non-null   float64
     4   Au                      1044 non-null   float64
     5   Bi                      1044 non-null   float64
     6   Fe                      1044 non-null   float64
     7   O                       1044 non-null   float64
     8   Catalyst loading (g/L)  1044 non-null   float64
     9   Light intensity (W)     1044 non-null   int64  
     10  time (min)              1044 non-null   int64  
     11  solution pH             1044 non-null   float64
     12  Anions                  1044 non-null   object 
     13  Ci (mg/L)               1044 non-null   int64  
     14  Cf (mg/L)               1044 non-null   float64
     15  Efficiency (%)          1044 non-null   float64
    dtypes: float64(11), int64(3), object(2)
    memory usage: 130.6+ KB




.. GENERATED FROM PYTHON SOURCE LINES 61-62

Display the summary statistics of the dataset

.. GENERATED FROM PYTHON SOURCE LINES 62-64

.. code-block:: Python

    df.describe()






.. 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>Surface area</th>
          <th>Pore volume</th>
          <th>BandGap (eV)</th>
          <th>Au</th>
          <th>Bi</th>
          <th>Fe</th>
          <th>O</th>
          <th>Catalyst loading (g/L)</th>
          <th>Light intensity (W)</th>
          <th>time (min)</th>
          <th>solution pH</th>
          <th>Ci (mg/L)</th>
          <th>Cf (mg/L)</th>
          <th>Efficiency (%)</th>
        </tr>
      </thead>
      <tbody>
        <tr>
          <th>count</th>
          <td>1044.000000</td>
          <td>1044.000000</td>
          <td>1044.000000</td>
          <td>1044.000000</td>
          <td>1044.000000</td>
          <td>1044.000000</td>
          <td>1044.000000</td>
          <td>1044.000000</td>
          <td>1044.000000</td>
          <td>1044.00000</td>
          <td>1044.000000</td>
          <td>1044.000000</td>
          <td>1044.000000</td>
          <td>1044.000000</td>
        </tr>
        <tr>
          <th>mean</th>
          <td>20.796552</td>
          <td>0.004038</td>
          <td>2.314138</td>
          <td>0.887586</td>
          <td>51.886207</td>
          <td>12.670000</td>
          <td>27.651724</td>
          <td>1.143678</td>
          <td>100.517241</td>
          <td>165.00000</td>
          <td>6.034483</td>
          <td>9.482759</td>
          <td>6.670795</td>
          <td>44.788506</td>
        </tr>
        <tr>
          <th>std</th>
          <td>6.395003</td>
          <td>0.000856</td>
          <td>0.465941</td>
          <td>0.389551</td>
          <td>14.129589</td>
          <td>3.455051</td>
          <td>7.556266</td>
          <td>0.425064</td>
          <td>16.943329</td>
          <td>103.61121</td>
          <td>1.104839</td>
          <td>14.998264</td>
          <td>14.254075</td>
          <td>34.274206</td>
        </tr>
        <tr>
          <th>min</th>
          <td>0.000000</td>
          <td>0.000000</td>
          <td>0.000000</td>
          <td>0.000000</td>
          <td>0.000000</td>
          <td>0.000000</td>
          <td>0.000000</td>
          <td>0.000000</td>
          <td>25.000000</td>
          <td>0.00000</td>
          <td>3.000000</td>
          <td>5.000000</td>
          <td>0.000000</td>
          <td>0.000000</td>
        </tr>
        <tr>
          <th>25%</th>
          <td>21.600000</td>
          <td>0.004300</td>
          <td>2.350000</td>
          <td>1.000000</td>
          <td>55.790000</td>
          <td>13.680000</td>
          <td>29.520000</td>
          <td>1.000000</td>
          <td>105.000000</td>
          <td>82.50000</td>
          <td>5.400000</td>
          <td>5.000000</td>
          <td>1.280000</td>
          <td>11.400000</td>
        </tr>
        <tr>
          <th>50%</th>
          <td>21.600000</td>
          <td>0.004300</td>
          <td>2.350000</td>
          <td>1.000000</td>
          <td>55.790000</td>
          <td>13.680000</td>
          <td>29.520000</td>
          <td>1.000000</td>
          <td>105.000000</td>
          <td>165.00000</td>
          <td>5.400000</td>
          <td>5.000000</td>
          <td>3.070000</td>
          <td>40.600000</td>
        </tr>
        <tr>
          <th>75%</th>
          <td>21.600000</td>
          <td>0.004300</td>
          <td>2.350000</td>
          <td>1.000000</td>
          <td>55.790000</td>
          <td>13.680000</td>
          <td>29.520000</td>
          <td>1.500000</td>
          <td>105.000000</td>
          <td>247.50000</td>
          <td>7.000000</td>
          <td>5.000000</td>
          <td>4.742500</td>
          <td>74.850000</td>
        </tr>
        <tr>
          <th>max</th>
          <td>45.000000</td>
          <td>0.004900</td>
          <td>3.200000</td>
          <td>1.980000</td>
          <td>55.920000</td>
          <td>13.680000</td>
          <td>31.600000</td>
          <td>2.500000</td>
          <td>105.000000</td>
          <td>330.00000</td>
          <td>9.000000</td>
          <td>80.000000</td>
          <td>80.000000</td>
          <td>100.000000</td>
        </tr>
      </tbody>
    </table>
    </div>
    </div>
    <br />
    <br />

.. GENERATED FROM PYTHON SOURCE LINES 65-66

Display the missing values of the dataset

.. GENERATED FROM PYTHON SOURCE LINES 66-68

.. code-block:: Python

    df.isnull().sum()





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

 .. code-block:: none


    Catalyst type             0
    Surface area              0
    Pore volume               0
    BandGap (eV)              0
    Au                        0
    Bi                        0
    Fe                        0
    O                         0
    Catalyst loading (g/L)    0
    Light intensity (W)       0
    time (min)                0
    solution pH               0
    Anions                    0
    Ci (mg/L)                 0
    Cf (mg/L)                 0
    Efficiency (%)            0
    dtype: int64



.. GENERATED FROM PYTHON SOURCE LINES 69-70

Display the duplicated rows of the dataset

.. GENERATED FROM PYTHON SOURCE LINES 70-72

.. code-block:: Python

    df.duplicated().sum()





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

 .. code-block:: none


    218



.. GENERATED FROM PYTHON SOURCE LINES 73-74

numerical columns

.. GENERATED FROM PYTHON SOURCE LINES 74-79

.. code-block:: Python

    num_columns = ['Surface area', 'Pore volume', 'BandGap (eV)', 'Au',
           'Bi', 'Fe', 'O', 'Catalyst loading (g/L)', 'Light intensity (W)',
           'time (min)', 'solution pH', 'Ci (mg/L)', 'Cf (mg/L)',
           'Efficiency (%)']








.. GENERATED FROM PYTHON SOURCE LINES 80-81

Display the distribution of the numerical columns

.. GENERATED FROM PYTHON SOURCE LINES 81-86

.. code-block:: Python

    for col in num_columns:
        print(f"{col}: {df[col].describe()}")


    data_num = df[num_columns].copy()




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

 .. code-block:: none

    Surface area: count    1044.000000
    mean       20.796552
    std         6.395003
    min         0.000000
    25%        21.600000
    50%        21.600000
    75%        21.600000
    max        45.000000
    Name: Surface area, dtype: float64
    Pore volume: count    1044.000000
    mean        0.004038
    std         0.000856
    min         0.000000
    25%         0.004300
    50%         0.004300
    75%         0.004300
    max         0.004900
    Name: Pore volume, dtype: float64
    BandGap (eV): count    1044.000000
    mean        2.314138
    std         0.465941
    min         0.000000
    25%         2.350000
    50%         2.350000
    75%         2.350000
    max         3.200000
    Name: BandGap (eV), dtype: float64
    Au: count    1044.000000
    mean        0.887586
    std         0.389551
    min         0.000000
    25%         1.000000
    50%         1.000000
    75%         1.000000
    max         1.980000
    Name: Au, dtype: float64
    Bi: count    1044.000000
    mean       51.886207
    std        14.129589
    min         0.000000
    25%        55.790000
    50%        55.790000
    75%        55.790000
    max        55.920000
    Name: Bi, dtype: float64
    Fe: count    1044.000000
    mean       12.670000
    std         3.455051
    min         0.000000
    25%        13.680000
    50%        13.680000
    75%        13.680000
    max        13.680000
    Name: Fe, dtype: float64
    O: count    1044.000000
    mean       27.651724
    std         7.556266
    min         0.000000
    25%        29.520000
    50%        29.520000
    75%        29.520000
    max        31.600000
    Name: O, dtype: float64
    Catalyst loading (g/L): count    1044.000000
    mean        1.143678
    std         0.425064
    min         0.000000
    25%         1.000000
    50%         1.000000
    75%         1.500000
    max         2.500000
    Name: Catalyst loading (g/L), dtype: float64
    Light intensity (W): count    1044.000000
    mean      100.517241
    std        16.943329
    min        25.000000
    25%       105.000000
    50%       105.000000
    75%       105.000000
    max       105.000000
    Name: Light intensity (W), dtype: float64
    time (min): count    1044.00000
    mean      165.00000
    std       103.61121
    min         0.00000
    25%        82.50000
    50%       165.00000
    75%       247.50000
    max       330.00000
    Name: time (min), dtype: float64
    solution pH: count    1044.000000
    mean        6.034483
    std         1.104839
    min         3.000000
    25%         5.400000
    50%         5.400000
    75%         7.000000
    max         9.000000
    Name: solution pH, dtype: float64
    Ci (mg/L): count    1044.000000
    mean        9.482759
    std        14.998264
    min         5.000000
    25%         5.000000
    50%         5.000000
    75%         5.000000
    max        80.000000
    Name: Ci (mg/L), dtype: float64
    Cf (mg/L): count    1044.000000
    mean        6.670795
    std        14.254075
    min         0.000000
    25%         1.280000
    50%         3.070000
    75%         4.742500
    max        80.000000
    Name: Cf (mg/L), dtype: float64
    Efficiency (%): count    1044.000000
    mean       44.788506
    std        34.274206
    min         0.000000
    25%        11.400000
    50%        40.600000
    75%        74.850000
    max       100.000000
    Name: Efficiency (%), dtype: float64




.. GENERATED FROM PYTHON SOURCE LINES 87-107

.. code-block:: Python


    fig, axes = create_subplots(data_num.shape[1]-2, figsize=(9, 8))
    for ax, col in zip(axes.flat, data_num.columns):
        if col in ['Cf (mg/L)', 'Efficiency (%)']:
            continue

        distribution_plot(ax=ax, data=data_num[col],
                          box_facecolor='#dcae80',
                          scatter_fc = '#1b1b1c',
                          ridge_lc='#1b1b1c',
                      
                          )
        ax.set_xlabel(xlabel=LABEL_MAP.get(col, col), weight='bold', fontsize=14)
        ax.set_yticklabels('')
    plt.tight_layout()

    # plt.savefig("../manuscript/figures/fig2.png", dpi=600,
    #             bbox_inches="tight")
    plt.show()




.. image-sg:: /auto_examples/images/sphx_glr_eda_001.png
   :alt: eda
   :srcset: /auto_examples/images/sphx_glr_eda_001.png, /auto_examples/images/sphx_glr_eda_001_2_00x.png 2.00x
   :class: sphx-glr-single-img





.. GENERATED FROM PYTHON SOURCE LINES 108-124

.. code-block:: Python


    fig, axes = create_subplots(data_num.shape[1], figsize=(9, 8))
    for ax, col in zip(axes.flat, data_num.columns):

        distribution_plot(ax=ax, data=data_num[col],
                          box_facecolor='#dcae80',
                          scatter_fc = '#1b1b1c',
                          ridge_lc='#1b1b1c',
                      
                          )
        ax.set_xlabel(xlabel=LABEL_MAP.get(col, col), weight='bold', fontsize=14)
        ax.set_yticklabels('')
    plt.tight_layout()

    plt.show()




.. image-sg:: /auto_examples/images/sphx_glr_eda_002.png
   :alt: eda
   :srcset: /auto_examples/images/sphx_glr_eda_002.png, /auto_examples/images/sphx_glr_eda_002_2_00x.png 2.00x
   :class: sphx-glr-single-img





.. GENERATED FROM PYTHON SOURCE LINES 125-127

Categorical Data
===================

.. GENERATED FROM PYTHON SOURCE LINES 129-130

categorical columns

.. GENERATED FROM PYTHON SOURCE LINES 130-132

.. code-block:: Python

    cat_columns = ['Catalyst type', 'Anions']








.. GENERATED FROM PYTHON SOURCE LINES 133-134

Display the unique values of the categorical columns

.. GENERATED FROM PYTHON SOURCE LINES 134-137

.. code-block:: Python

    for col in cat_columns:
        print(f"{col}: {df[col].unique()}")





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

 .. code-block:: none

    Catalyst type: ['no catalyst' 'pure BFO' '0.25 wt% Au-BFO' '0.5 wt% Au-BFO'
     '1 wt% Au-BFO' '2 wt% Au-BFO' 'commercial TiO2']
    Anions: ['Without Anions' 'NaCl' 'Na2SO4' 'NaCO3' 'NaHCO3' 'Na2HPO4']




.. GENERATED FROM PYTHON SOURCE LINES 138-139

Display the value counts of the categorical columns

.. GENERATED FROM PYTHON SOURCE LINES 139-146

.. code-block:: Python

    for col in cat_columns:
        print(f"{col}: {df[col].value_counts()}")


    merged_series = merge_uniques(df['Catalyst type'], 7)
    pie_from_series(merged_series, cmap="coolwarm",  show=False, leg_pos=(0.85, 0.7))




.. image-sg:: /auto_examples/images/sphx_glr_eda_003.png
   :alt: eda
   :srcset: /auto_examples/images/sphx_glr_eda_003.png, /auto_examples/images/sphx_glr_eda_003_2_00x.png 2.00x
   :class: sphx-glr-single-img


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

 .. code-block:: none

    Catalyst type: 1 wt% Au-BFO       828
    pure BFO            36
    no catalyst         36
    0.25 wt% Au-BFO     36
    0.5 wt% Au-BFO      36
    2 wt% Au-BFO        36
    commercial TiO2     36
    Name: Catalyst type, dtype: int64
    Anions: Without Anions    864
    NaCl               36
    Na2SO4             36
    NaCO3              36
    NaHCO3             36
    Na2HPO4            36
    Name: Anions, dtype: int64




.. GENERATED FROM PYTHON SOURCE LINES 147-151

.. code-block:: Python


    merged_series = merge_uniques(df['Anions'], 5)
    pie_from_series(merged_series, cmap="coolwarm",  show=False, leg_pos=(0.85, 0.7))




.. image-sg:: /auto_examples/images/sphx_glr_eda_004.png
   :alt: eda
   :srcset: /auto_examples/images/sphx_glr_eda_004.png, /auto_examples/images/sphx_glr_eda_004_2_00x.png 2.00x
   :class: sphx-glr-single-img





.. GENERATED FROM PYTHON SOURCE LINES 152-154

Correlation
===========

.. GENERATED FROM PYTHON SOURCE LINES 154-164

.. code-block:: Python


    df, cat_enc, an_enc = prepare_data(encoding="ohe", exclude_cf=False)
    df = df.rename(
        columns={f"Catalyst type_{idx}":category for idx, category in enumerate(cat_enc.categories_[0])})
    df = df.rename(
        columns={f"Anions_{idx}":category for idx, category in enumerate(an_enc.categories_[0])})
    # # %%

    corr = df.corr(method="pearson")








.. GENERATED FROM PYTHON SOURCE LINES 165-170

.. code-block:: Python


    imshow(corr, colorbar=True, show=False)
    plt.tight_layout()
    plt.show()




.. image-sg:: /auto_examples/images/sphx_glr_eda_005.png
   :alt: eda
   :srcset: /auto_examples/images/sphx_glr_eda_005.png, /auto_examples/images/sphx_glr_eda_005_2_00x.png 2.00x
   :class: sphx-glr-single-img





.. GENERATED FROM PYTHON SOURCE LINES 171-174

.. code-block:: Python


    df = df.fillna(0.0)








.. GENERATED FROM PYTHON SOURCE LINES 175-181

.. code-block:: Python


    node_angles = circular_layout(corr.columns.tolist(), corr.columns.tolist(),
                                  start_pos=90, group_boundaries=[0, len(corr.columns.tolist()) // 2])

    print(node_angles.shape)





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

 .. code-block:: none

    (27,)




.. GENERATED FROM PYTHON SOURCE LINES 182-204

.. code-block:: Python


    fig, ax = plt.subplots(figsize=(16, 16),
                           facecolor="#EFE9E6",
                           subplot_kw=dict(polar=True))
    fig, axes = plot_connectivity_circle(
        corr.values,
        node_names = corr.columns.tolist(),
        node_angles=node_angles,
        fontsize_names =14,
        fontsize_colorbar =14,
        facecolor ="#EFE9E6",
        textcolor='black',
        #n_lines = 14,
        node_edgecolor="white",
        colormap="Spectral",
        colorbar_size=0.5,
        colorbar_pos=(-0.5, 0.5),
        ax=ax)

    #fig.savefig(f"../manuscript/figures/fig3.png", dpi=600, bbox_inches="tight")
    fig.tight_layout()




.. image-sg:: /auto_examples/images/sphx_glr_eda_006.png
   :alt: eda
   :srcset: /auto_examples/images/sphx_glr_eda_006.png, /auto_examples/images/sphx_glr_eda_006_2_00x.png 2.00x
   :class: sphx-glr-single-img





.. GENERATED FROM PYTHON SOURCE LINES 205-208

.. code-block:: Python


    df, _, _ = prepare_data(encoding="le", exclude_cf=False)








.. GENERATED FROM PYTHON SOURCE LINES 209-212

.. code-block:: Python


    corr = df.corr(method="pearson")








.. GENERATED FROM PYTHON SOURCE LINES 213-218

.. code-block:: Python


    imshow(corr, colorbar=True, show=False)
    plt.tight_layout()
    plt.show()




.. image-sg:: /auto_examples/images/sphx_glr_eda_007.png
   :alt: eda
   :srcset: /auto_examples/images/sphx_glr_eda_007.png, /auto_examples/images/sphx_glr_eda_007_2_00x.png 2.00x
   :class: sphx-glr-single-img





.. GENERATED FROM PYTHON SOURCE LINES 219-222

.. code-block:: Python


    df = df.fillna(0.0)








.. GENERATED FROM PYTHON SOURCE LINES 223-229

.. code-block:: Python


    node_angles = circular_layout(corr.columns.tolist(), corr.columns.tolist(),
                                  start_pos=90, group_boundaries=[0, len(corr.columns.tolist()) // 2])

    print(node_angles.shape)





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

 .. code-block:: none

    (16,)




.. GENERATED FROM PYTHON SOURCE LINES 230-252

.. code-block:: Python


    fig, ax = plt.subplots(figsize=(16, 16),
                           facecolor="#EFE9E6",
                           subplot_kw=dict(polar=True))
    fig, axes = plot_connectivity_circle(
        corr.values,
        node_names = corr.columns.tolist(),
        node_angles=node_angles,
        fontsize_names =14,
        fontsize_colorbar =14,
        facecolor ="#EFE9E6",
        textcolor='black',
        #n_lines = 14,
        node_edgecolor="white",
        colormap="Spectral",
        colorbar_size=0.5,
        colorbar_pos=(-0.5, 0.5),
        ax=ax)

    # fig.savefig(f"figures/chord_large_le", dpi=600, bbox_inches="tight")
    fig.tight_layout()




.. image-sg:: /auto_examples/images/sphx_glr_eda_008.png
   :alt: eda
   :srcset: /auto_examples/images/sphx_glr_eda_008.png, /auto_examples/images/sphx_glr_eda_008_2_00x.png 2.00x
   :class: sphx-glr-single-img





.. GENERATED FROM PYTHON SOURCE LINES 253-265

.. code-block:: Python


    df_org = pd.read_excel(fpath)
    print(df_org.shape)

    df_org = df_org.drop(columns=['Catalyst type', 'Anions'])

    corr = df_org.corr(method="pearson")

    imshow(corr, colorbar=True, show=False)
    plt.tight_layout()
    plt.show()




.. image-sg:: /auto_examples/images/sphx_glr_eda_009.png
   :alt: eda
   :srcset: /auto_examples/images/sphx_glr_eda_009.png, /auto_examples/images/sphx_glr_eda_009_2_00x.png 2.00x
   :class: sphx-glr-single-img


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

 .. code-block:: none

    (1044, 16)




.. GENERATED FROM PYTHON SOURCE LINES 266-269

.. code-block:: Python


    df_org = df_org.fillna(0.0)








.. GENERATED FROM PYTHON SOURCE LINES 270-276

.. code-block:: Python


    node_angles = circular_layout(corr.columns.tolist(), corr.columns.tolist(),
                                  start_pos=90, group_boundaries=[0, len(corr.columns.tolist()) // 2])

    print(node_angles.shape)





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

 .. code-block:: none

    (14,)




.. GENERATED FROM PYTHON SOURCE LINES 277-299

.. code-block:: Python


    fig, ax = plt.subplots(figsize=(16, 16),
                           facecolor="#EFE9E6",
                           subplot_kw=dict(polar=True))
    fig, axes = plot_connectivity_circle(
        corr.values,
        node_names = corr.columns.tolist(),
        node_angles=node_angles,
        fontsize_names =14,
        fontsize_colorbar =14,
        facecolor ="#EFE9E6",
        textcolor='black',
        #n_lines = 14,conda 
        node_edgecolor="white",
        colormap="Spectral",
        colorbar_size=0.5,
        colorbar_pos=(-0.5, 0.5),
        ax=ax)

    if SAVE:
        fig.savefig(f"figures/chord_large_org", dpi=600, bbox_inches="tight")
    fig.tight_layout()



.. image-sg:: /auto_examples/images/sphx_glr_eda_010.png
   :alt: eda
   :srcset: /auto_examples/images/sphx_glr_eda_010.png, /auto_examples/images/sphx_glr_eda_010_2_00x.png 2.00x
   :class: sphx-glr-single-img






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

   **Total running time of the script:** (0 minutes 11.910 seconds)


.. _sphx_glr_download_auto_examples_eda.py:

.. only:: html

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

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

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

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

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

    .. container:: sphx-glr-download sphx-glr-download-zip

      :download:`Download zipped: eda.zip <eda.zip>`


.. only:: html

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

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