measurement-scripts/plot_transmission_timeline.py

#!/usr/bin/env python3
import multiprocessing
import os
from argparse import ArgumentParser
from math import ceil
from time import sleep

import pandas as pd
import matplotlib.pyplot as plt
from mpl_toolkits import axisartist
from mpl_toolkits.axes_grid1 import host_subplot



def csv_to_dataframe(csv_list, dummy):

    global n
    global frame_list

    transmission_df = None

    for csv in csv_list:
        tmp_df = pd.read_csv(
            "{}{}".format(args.pcap_csv_folder, csv),
            dtype=dict(is_retranmission=bool, is_dup_ack=bool),
        )
        tmp_df["datetime"] = pd.to_datetime(tmp_df["datetime"]) - pd.Timedelta(hours=1)
        tmp_df = tmp_df.set_index("datetime")
        tmp_df.index = pd.to_datetime(tmp_df.index)
        if transmission_df is None:
            transmission_df = tmp_df
        else:
            transmission_df = pd.concat([transmission_df, tmp_df])

        n.value += 1

    frame_list.append(transmission_df)


from itertools import islice

def chunk(it, size):
    it = iter(it)
    return iter(lambda: tuple(islice(it, size)), ())


if __name__ == "__main__":
    parser = ArgumentParser()
    parser.add_argument("-f", "--gps_file", required=True, help="GPS csv file.")
    parser.add_argument("-s", "--serial_file", required=True, help="Serial csv file.")
    parser.add_argument("-p", "--pcap_csv_folder", required=True, help="PCAP csv folder.")
    parser.add_argument("--save", default=None, help="Location to save pdf file.")
    parser.add_argument(
        "--show_providerinfo",
        default=False,
        help="Show providerinfo for map tiles an zoom levels.",
    )
    parser.add_argument(
        "-c",
        "--cores",
        default=1,
        type=int,
        help="Number of cores for multiprocessing.",
    )
    parser.add_argument(
        "-i",
        "--interval",
        default=10,
        type=int,
        help="Time interval for rolling window.",
    )

    args = parser.parse_args()
    manager = multiprocessing.Manager()
    n = manager.Value("i", 0)
    frame_list = manager.list()
    jobs = []

    # load all pcap csv into one dataframe
    pcap_csv_list = list()
    for filename in os.listdir(args.pcap_csv_folder):
        if filename.endswith(".csv") and "tcp" in filename:
            pcap_csv_list.append(filename)

    parts = chunk(pcap_csv_list, ceil(len(pcap_csv_list) / args.cores))
    print("Start processing with {} jobs.".format(args.cores))
    for p in parts:
        process = multiprocessing.Process(target=csv_to_dataframe, args=(p, "dummy"))
        jobs.append(process)

    for j in jobs:
        j.start()

    print("Started all jobs.")
    # Ensure all of the processes have finished
    finished_job_counter = 0
    working = ["|", "/", "-", "\\", "|", "/", "-", "\\"]
    w = 0
    while len(jobs) != finished_job_counter:
        sleep(1)
        print(
            "\r\t{}{}{}\t Running {} jobs ({} finished). Processed {} out of {} pcap csv files.    ({}%)    ".format(
                working[w],
                working[w],
                working[w],
                len(jobs),
                finished_job_counter,
                n.value,
                len(pcap_csv_list),
                round((n.value / len(pcap_csv_list)) * 100, 2),
            ),
            end="",
        )
        finished_job_counter = 0
        for j in jobs:
            if not j.is_alive():
                finished_job_counter += 1
        if (w + 1) % len(working) == 0:
            w = 0
        else:
            w += 1
    print("\r\nSorting table...")

    transmission_df = pd.concat(frame_list)
    frame_list = None
    transmission_df = transmission_df.sort_index()

    print("Calculate goodput...")
    transmission_df["goodput"] = transmission_df["payload_size"].rolling("{}s".format(args.interval)).sum()
    transmission_df["goodput"] = transmission_df["goodput"].apply(
        lambda x: ((x * 8) / args.interval) / 10**6
    )

    # remove all not needed columns
    transmission_df = transmission_df.filter(["goodput", "datetime"])

    # read serial csv
    serial_df = pd.read_csv(args.serial_file)
    serial_df["datetime"] = pd.to_datetime(serial_df["datetime"]) - pd.Timedelta(hours=1)
    serial_df = serial_df.set_index("datetime")
    serial_df.index = pd.to_datetime(serial_df.index)

    transmission_df = pd.merge_asof(
        transmission_df,
        serial_df,
        tolerance=pd.Timedelta("1s"),
        right_index=True,
        left_index=True,
    )

    scaley = 1.5
    scalex = 1.0
    plt.figure(figsize=[6.4 * scaley, 4.8 * scalex])

    host = host_subplot(111, axes_class=axisartist.Axes)
    plt.subplots_adjust()

    # additional y axes
    par11 = host.twinx()
    par12 = host.twinx()
    # par13 = host.twinx()

    # axes offset
    par12.axis["right"] = par12.new_fixed_axis(loc="right", offset=(60, 0))
    # par13.axis["right"] = par13.new_fixed_axis(loc="right", offset=(120, 0))

    par11.axis["right"].toggle(all=True)
    par12.axis["right"].toggle(all=True)
    # par13.axis["right"].toggle(all=True)

    host.plot(transmission_df["goodput"], "-", color="blue", label="goodput" )
    host.set_xlabel("datetime")
    host.set_ylabel("goodput [Mbps]")
    #host.set_ylim([0, 13])
    #host.set_yscale("log")
    #host.set_yscale("log")
    #host.set_yscale("log")
    #host.set_yscale("log")

    par11.plot(transmission_df["downlink_cqi"], "--", color="green", label="CQI")
    par11.set_ylabel("CQI")
    par11.set_ylim([0, 15])

    par12.plot()

    if args.save:
        plt.savefig("{}timeline_plot.pdf".format(args.save))
    else:
        plt.show()

    plt.clf()

    # Get the frequency, PDF and CDF for each value in the series

    # Frequency
    stats_df = transmission_df \
        .groupby("goodput") \
        ["goodput"] \
        .agg("count") \
        .pipe(pd.DataFrame) \
        .rename(columns={"goodput": 'frequency'})

    # PDF
    stats_df['pdf'] = stats_df['frequency'] / sum(stats_df['frequency'])

    # CDF
    stats_df['cdf'] = stats_df['pdf'].cumsum()
    stats_df = stats_df.reset_index()

    stats_df.plot(x="goodput", y=["cdf"], grid=True)

    if args.save:
        plt.savefig("{}cdf_plot.pdf".format(args.save))
    else:
        plt.show()