Function heatmap

missingno/missingno.py:381–464

Presents a `seaborn` heatmap visualization of nullity correlation in the given DataFrame. Note that this visualization has no special support for large datasets. For those, try the dendrogram instead. :param df: The DataFrame whose completeness is being heatmapped. :param

(df, inline=True,
            filter=None, n=0, p=0, sort=None,
            figsize=(20, 12), fontsize=16, labels=True, cmap='RdBu'
            )

def heatmap(df, inline=True,
            filter=None, n=0, p=0, sort=None,
            figsize=(20, 12), fontsize=16, labels=True, cmap='RdBu'
            ):
    """
    Presents a `seaborn` heatmap visualization of nullity correlation in the given DataFrame.
    
    Note that this visualization has no special support for large datasets. For those, try the dendrogram instead.
    

    :param df: The DataFrame whose completeness is being heatmapped.
    :param filter: The filter to apply to the heatmap. Should be one of "top", "bottom", or None (default). See
    `nullity_filter()` for more information.
    :param n: The cap on the number of columns to include in the filtered DataFrame. See  `nullity_filter()` for
    more information.
    :param p: The cap on the percentage fill of the columns in the filtered DataFrame. See  `nullity_filter()` for
    more information.
    :param sort: The sort to apply to the heatmap. Should be one of "ascending", "descending", or None. See
    `nullity_sort()` for more information.
    :param figsize: The size of the figure to display. This is a `matplotlib` parameter which defaults to (20, 12).
    :param fontsize: The figure's font size.
    :param labels: Whether or not to label each matrix entry with its correlation (default is True).
    :param cmap: What `matplotlib` colormap to use. Defaults to `RdBu`.
    :param inline: Whether or not the figure is inline. If it's not then instead of getting plotted, this method will
    return its figure.
    :return: If `inline` is True, the underlying `matplotlib.figure` object. Else, nothing.
    """
    # Apply filters and sorts.
    df = nullity_filter(df, filter=filter, n=n, p=p)
    df = nullity_sort(df, sort=sort)

    # Set up the figure.
    fig = plt.figure(figsize=figsize)
    gs = gridspec.GridSpec(1, 1)
    ax0 = plt.subplot(gs[0])

    # Pre-processing: remove completely filled or completely empty variables.
    df = df[[i for i, n in enumerate(np.var(df.isnull(), axis='rows')) if n > 0]]

    # Create and mask the correlation matrix.
    corr_mat = df.isnull().corr()
    # corr_mat = corr_mat.replace(np.nan, 1)
    # corr_mat[np.isnan(corr_mat)] = 0
    mask = np.zeros_like(corr_mat)
    mask[np.triu_indices_from(mask)] = True

    # Set fontsize.
    # fontsize = _set_font_size(fig, df, fontsize)

    # Construct the base heatmap.
    if labels:
        sns.heatmap(corr_mat, mask=mask, cmap=cmap, ax=ax0, cbar=False,
                    annot=True, annot_kws={"size": fontsize - 2})
    else:
        sns.heatmap(corr_mat, mask=mask, cmap=cmap, ax=ax0, cbar=False)

    # Apply visual corrections and modifications.
    ax0.set_xticklabels(ax0.xaxis.get_majorticklabels(), rotation=45, ha='left', fontsize=fontsize)