klib.describe.corr_plot()

Complexity

Conditions

3

Size

Total Lines	136
Code Lines	43

Duplication

Lines	0
Ratio	0 %

Importance

Changes

0

"""
def corr_plot(
    data: pd.DataFrame,
    split: Optional[str] = None,
    threshold: float = 0,
    target: Optional[Union[pd.Series, str]] = None,
    method: str = "pearson",
    cmap: str = "BrBG",
    figsize: Tuple = (12, 10),
    annot: bool = True,
    dev: bool = False,
    **kwargs,
):
    """ Two-dimensional visualization of the correlation between feature-columns, excluding NA values.

    Parameters
    ----------
    data : pd.DataFrame
        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
    split : Optional[str], optional
        Type of split to be performed {None, 'pos', 'neg', 'high', 'low'}, by default None
            * None: visualize all correlations between the feature-columns
            * pos: visualize all positive correlations between the feature-columns above the threshold
            * neg: visualize all negative correlations between the feature-columns below the threshold
            * high: visualize all correlations between the feature-columns for which abs(corr) > threshold is True
            * low: visualize all correlations between the feature-columns for which abs(corr) < threshold is True

    threshold : float, optional
        Value between 0 <= threshold <= 1, by default 0
    target : Optional[Union[pd.Series, str]], optional
        Specify target for correlation. E.g. label column to generate only the correlations between each feature \
        and the label, by default None
    method : str, optional
        method: {'pearson', 'spearman', 'kendall'}, by default "pearson"
            * pearson: measures linear relationships and requires normally distributed and homoscedastic data.
            * spearman: ranked/ordinal correlation, measures monotonic relationships.
            * kendall: ranked/ordinal correlation, measures monotonic relationships. Computationally more expensive \
            but more robust in smaller dataets than 'spearman'.

    cmap : str, optional
        The mapping from data values to color space, matplotlib colormap name or object, or list of colors, by default \
        "BrBG"
    figsize : Tuple, optional
        Use to control the figure size, by default (12, 10)
    annot : bool, optional
        Use to show or hide annotations, by default True
    dev : bool, optional
        Display figure settings in the plot by setting dev = True. If False, the settings are not displayed, by \
        default False

    Keyword Arguments : optional
        Additional elements to control the visualization of the plot, e.g.:

            * mask: bool, default True
                If set to False the entire correlation matrix, including the upper triangle is shown. Set dev = False \
                in this case to avoid overlap.
            * vmax: float, default is calculated from the given correlation coefficients.
                Value between -1 or vmin <= vmax <= 1, limits the range of the colorbar.
            * vmin: float, default is calculated from the given correlation coefficients.
                Value between -1 <= vmin <= 1 or vmax, limits the range of the colorbar.
            * linewidths: float, default 0.5
                Controls the line-width inbetween the squares.
            * annot_kws: dict, default {'size' : 10}
                Controls the font size of the annotations. Only available when annot = True.
            * cbar_kws: dict, default {'shrink': .95, 'aspect': 30}
                Controls the size of the colorbar.
            * Many more kwargs are available, i.e. 'alpha' to control blending, or options to adjust labels, ticks ...

        Kwargs can be supplied through a dictionary of key-value pairs (see above).

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

    # Validate Inputs
    _validate_input_range(threshold, "threshold", -1, 1)
    _validate_input_bool(annot, "annot")
    _validate_input_bool(dev, "dev")

    data = pd.DataFrame(data)

    corr = corr_mat(data, split=split, threshold=threshold, target=target, method=method, colored=False)

    mask = np.zeros_like(corr, dtype=np.bool)

    if target is None:
        mask = np.triu(np.ones_like(corr, dtype=np.bool))

    vmax = np.round(np.nanmax(corr.where(~mask)) - 0.05, 2)
    vmin = np.round(np.nanmin(corr.where(~mask)) + 0.05, 2)

    fig, ax = plt.subplots(figsize=figsize)

    # Specify kwargs for the heatmap
    kwargs = {
        "mask": mask,
        "cmap": cmap,
        "annot": annot,
        "vmax": vmax,
        "vmin": vmin,
        "linewidths": 0.5,
        "annot_kws": {"size": 10},
        "cbar_kws": {"shrink": 0.95, "aspect": 30},
        **kwargs,
    }

    # Draw heatmap with mask and default settings
    sns.heatmap(corr, center=0, fmt=".2f", **kwargs)

    ax.set_title(f"Feature-correlation ({method})", fontdict={"fontsize": 18})

    # Settings
    if dev:
        fig.suptitle(
            f"\
            Settings (dev-mode): \n\
            - split-mode: {split} \n\
            - threshold: {threshold} \n\
            - method: {method} \n\
            - annotations: {annot} \n\
            - cbar: \n\
                - vmax: {vmax} \n\
                - vmin: {vmin} \n\
            - linewidths: {kwargs['linewidths']} \n\
            - annot_kws: {kwargs['annot_kws']} \n\
            - cbar_kws: {kwargs['cbar_kws']}",
            fontsize=12,
            color="gray",
            x=0.35,
            y=0.85,
            ha="left",
        )

    return ax