klib.describe.dist_plot()

Complexity

Conditions

9

Size

Total Lines	123
Code Lines	62

Duplication

Lines	0
Ratio	0 %

Importance

Changes

0

'''
def dist_plot(data, mean_color='orange', figsize=(14, 2), fill_range=(0.025, 0.975), hist=False, bins=None,
              showall=False, kde_kws=None, rug_kws=None, fill_kws=None, font_kws=None):
    '''
    Two-dimensional visualization of the distribution of numerical features.

    Parameters
    ----------
    data: 2D dataset that can be coerced into Pandas DataFrame. If a Pandas DataFrame is provided, the index/column \
    information is used to label the plots.

    mean_color: any valid color, default 'orange'
        Color of the vertical line indicating the mean of the data.

    figsize: tuple, default (14, 2)
        Use to control the figure size.

    fill_range: tuple, default (0.025, 0.975)
        Use to control set the quantiles for shading. Default spans 95% of the data, which is about two std. deviations\
        above and below the mean.

    hist: bool, default False
        Set to True to display histogram bars in the plot.

    bins: integer, default None
        Specification of the number of hist bins. Requires hist = True

    showall: bool, default False
        Set to True to remove the output limit of 20 plots.

    kdw_kws: dict, default None
        Keyword arguments for kdeplot().

    rug_kws: dict, default None
        Keyword arguments for rugplot().

    fill_kws: dict, default None
        Keyword arguments to control the fill.

    font_kws: dict, default None
        Keyword arguments to control the font.

    Returns
    -------
    ax: matplotlib Axes
        Returns the Axes object with the plot for further tweaking.
    '''

    # Validate Inputs
    _validate_input_bool(hist, 'hist')
    _validate_input_bool(showall, 'showall')

    # Handle dictionary defaults
    kde_kws = {} if kde_kws is None else kde_kws.copy()
    rug_kws = {} if rug_kws is None else rug_kws.copy()
    fill_kws = {} if fill_kws is None else fill_kws.copy()
    font_kws = {} if font_kws is None else font_kws.copy()

    data = pd.DataFrame(data).copy()
    cols = list(data.select_dtypes(include=['number']).columns)  # numeric cols

    if len(cols) == 0:
        print('No columns with numeric data were detected.')
    elif len(cols) >= 20 and showall is False:
        print(
            f'Note: The number of numerical features is very large ({len(cols)}), please consider splitting the data.\
            Showing plots for the first 20 numerical features. Override this by setting showall=True.')
        cols = cols[:20]

    # Default settings
    kde_kws = {'color': 'k', 'alpha': 0.7, 'linewidth': 1, **kde_kws}
    rug_kws = {'color': 'brown', 'alpha': 0.5, 'linewidth': 2, 'height': 0.04, **rug_kws}
    fill_kws = {'color': 'brown', 'alpha': 0.1, **fill_kws}
    font_kws = {'color':  '#111111', 'weight': 'normal', 'size': 11, **font_kws}

    ax = []
    for col in cols:
        _, ax = plt.subplots(figsize=figsize)
        ax = sns.distplot(data[col], bins=bins, hist=hist, rug=True, kde_kws=kde_kws,
                          rug_kws=rug_kws, hist_kws={'alpha': 0.5, 'histtype': 'step'})

        # Vertical lines and fill
        line = ax.lines[0]
        x = line.get_xydata()[:, 0]
        y = line.get_xydata()[:, 1]
        ax.fill_between(x, y,
                        where=(
                            (x >= np.quantile(data[col], fill_range[0])) &
                            (x <= np.quantile(data[col], fill_range[1]))),
                        label=f'{fill_range[0]*100:.0f}% - {fill_range[1]*100:.0f}%',
                        **fill_kws)

        ax.vlines(x=np.mean(data[col]),
                  ymin=0,
                  ymax=np.interp(np.mean(data[col]), x, y),
                  ls='dotted', color=mean_color, lw=2, label='mean')
        ax.vlines(x=np.median(data[col]),
                  ymin=0,
                  ymax=np.interp(np.median(data[col]), x, y),
                  ls=':', color='.3', label='median')
        ax.vlines(x=np.quantile(data[col], 0.25),
                  ymin=0,
                  ymax=np.interp(np.quantile(data[col], 0.25), x, y), ls=':', color='.5', label='25%')
        ax.vlines(x=np.quantile(data[col], 0.75),
                  ymin=0,
                  ymax=np.interp(np.quantile(data[col], 0.75), x, y), ls=':', color='.5', label='75%')

        ax.set_ylim(0,)
        ax.set_xlim(ax.get_xlim()[0]*1.1, ax.get_xlim()[1]*1.1)

        # Annotations and legend
        ax.text(0.01, 0.85, f'Mean: {np.round(np.mean(data[col]),2)}',
                fontdict=font_kws, transform=ax.transAxes)
        ax.text(0.01, 0.7, f'Std. dev: {np.round(scipy.stats.tstd(data[col]),2)}',
                fontdict=font_kws, transform=ax.transAxes)
        ax.text(0.01, 0.55, f'Skew: {np.round(scipy.stats.skew(data[col]),2)}',
                fontdict=font_kws, transform=ax.transAxes)
        ax.text(0.01, 0.4, f'Kurtosis: {np.round(scipy.stats.kurtosis(data[col]),2)}',  # Excess Kurtosis
                fontdict=font_kws, transform=ax.transAxes)
        ax.text(0.01, 0.25, f'Count: {np.round(len(data[col]))}',
                fontdict=font_kws, transform=ax.transAxes)
        ax.legend(loc='upper right')

    return ax