def plot_frequency_of_gc_intervals()

in src/graphing/plotting.py [0:0]

• 30 lines of code
• 14 McCabe index (conditional complexity)

def plot_frequency_of_gc_intervals(
    gc_event_dataframes,
    group_by=None,
    filter_by=None,
    labels=None,
    colors=None,
    plot=None,
    column="GCIndex", # Used to determine uniqueness of GC events
    interval_duration = 0,
    column_timing = None
    ):
    if not interval_duration:
        print("No interval length provided. Abort.")
        return
    timestamp_groups, datapoint_groups, labels, colors, _ = filter_and_group(
        gc_event_dataframes, group_by, filter_by, labels, column, colors, column_timing)
    # # if no plot is passed in, create a new plot
    if not plot:
        f, plot = plt.subplots()
    number_of_buckets, min_time_duration, _ = get_buckets_and_range(timestamp_groups, interval_duration)
    
    # Determine the spacing along the X axis for the data
    x_alignment = [idx * interval_duration + min_time_duration for idx in range(number_of_buckets)]
    if len(timestamp_groups) > len(labels):
        print("Not enough labels to plot")
    if len(datapoint_groups) > len(colors):
        print("Not enough colors to plot")
    # Create a list of frequencies, one for each group, and plot that line
    for index, (timestamps, dataset) in enumerate(zip(timestamp_groups, datapoint_groups)):
        # First, group into buckets based on time interverals.
        buckets = group_into_buckets([time - min_time_duration for time in timestamps], dataset, number_of_buckets, interval_duration)
        # Calculate the frequency of gc events per bucket time interval. Then plot
        frequency = [len(set(bucket)) for bucket in buckets] # Based on frequency of UNIQUE VALUES
        plot.plot(x_alignment, frequency, label = labels[index], color = colors[index])
    
    # Add styling to the plot. Add legend, and correct x-axis labels
    plot.legend(bbox_to_anchor=(1.05, 1), loc="upper left")
    return plot