def avg_plots()

in src/analyze.py [0:0]

• 55 lines of code
• 8 McCabe index (conditional complexity)

def avg_plots(df: pd.DataFrame, metric: str, plot_rank: bool = True):
    """
    For each {dataset, seed, oversampler, classifier} keep only the results of the HP configuration that
    yield the best score according to opt_metric. Then, calculate average and rank for the scores in
    output_metrics

    Parameters
    ----------
    df : pandas.DataFrame
        Filtered and summarized dataframe, produced by filter_optimal_hps
    metric : str
        metric to present
    plot_rank : bool
        Whether to plot rank or not

    Returns
    -------
    None
    """
    score_mean = []
    score_std = []
    rank_mean = []
    rank_std = []
    model_names = []
    major_ticks = []
    classifiers = list(np.unique(df.reset_index()["learner"]))
    oversamplers = list(np.unique(df.reset_index()["oversampler"]))
    for classifier in classifiers:
        for oversampler in oversamplers:
            idx = (classifier, oversampler)
            score_mean.append(df.loc[idx][(metric, "mean")])
            score_std.append(df.loc[idx][(metric, "std")])
            rank_mean.append(df.loc[idx][(f"{metric}.rank", "mean")])
            rank_std.append(df.loc[idx][(f"{metric}.rank", "std")])
            model_name = CLASSIFIERS[classifier]
            if oversampler != "none":
                model_name += "+" + OVERSAMPLERS[oversampler]
            model_names.append(model_name)
        # Add an empty row between classifiers
        score_mean.append(np.nan)
        score_std.append(np.nan)
        rank_mean.append(np.nan)
        rank_std.append(np.nan)
        model_names.append(" " * len(model_names))
        major_ticks.append(len(score_mean) - 1)

    # Delete the last empty row
    score_mean = score_mean[:-1]
    score_std = score_std[:-1]
    model_names = model_names[:-1]
    major_ticks = major_ticks[:-1]
    rank_mean = rank_mean[:-1]
    rank_std = rank_std[:-1]

    fig_height = 9 / (4 * 8) * (len(classifiers) * (len(oversamplers) + 1))
    plt.figure(figsize=(5, fig_height), dpi=320)
    ax = plt.axes()
    if plot_rank:
        ax2 = ax.twiny()
        ax2.errorbar(x=rank_mean, y=range(len(score_mean)), xerr=rank_std, fmt="r^")
        ax2.set_xlabel("Rank")
        ax2.xaxis.label.set_color("red")
        for t in ax2.xaxis.get_ticklabels():
            t.set_color("red")
    ax.errorbar(x=score_mean, y=range(len(score_mean)), xerr=score_std, fmt="bo")
    ax.xaxis.grid(True)
    ax.set_yticks(major_ticks, minor=False)
    ax.set_yticklabels("" * len(major_ticks), minor=False)
    ax.set_yticks(range(len(model_names)), minor=True)
    ax.set_yticklabels(model_names, minor=True)
    ax.yaxis.grid(True, which="major")
    ax.set_xlabel(METRICS[metric.split(".")[1]])
    if plot_rank:
        ax.xaxis.label.set_color("blue")
        for t in ax.xaxis.get_ticklabels():
            t.set_color("blue")
    plt.show()