def plot_chunk_histogram()

in demo-python/code/data-chunking/lib/common.py [0:0]

• 23 lines of code
• 6 McCabe index (conditional complexity)

def plot_chunk_histogram(chunks, length_fn, title, xlabel, ylabel="Chunk Count"):
    def round_to_lowest_multiple(number, multiple):
        return (number // multiple) * multiple

    def round_to_highest_multiple(number, multiple):
        return math.ceil(number / multiple) * multiple

    ys = [length_fn(chunk) for chunk in chunks]
    min_y = min(ys)
    max_y = max(ys)
    bins=25
    n, _, _ = plt.hist(ys, edgecolor="black", bins=bins) 
    # Set y-axis limits to remove the gap at the top
    max_freq = max(n)
    plt.ylim(0, max_freq)

    # Spacing for ticks on x-axis and x-axis limits to remove gaps
    tick_step = max(int(round_to_lowest_multiple((max_y-min_y)/5, 100)), 100)
    max_xtick = round_to_highest_multiple(max_y, tick_step)
    xticks = list(np.arange(start=round_to_lowest_multiple(min_y, tick_step), stop=round_to_highest_multiple(max_xtick, tick_step), step=tick_step))
    if max_xtick and xticks[-1] != max_xtick:
        xticks.append(max_xtick)
    plt.xticks(xticks)
    plt.xlim(round_to_lowest_multiple(min_y, tick_step), max_xtick)

    plt.xlabel(xlabel)
    plt.ylabel(ylabel)
    plt.title(title)
    plt.show()