measurement-scripts/cdf_compare.py

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

import matplotlib
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, folder, dummy):

    global n
    global frame_list

    transmission_df = None

    for csv in csv_list:
        tmp_df = pd.read_csv(
            "{}{}".format(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)), ())


def plot_cdf(dataframe, column_name, axis=None):
    stats_df = dataframe \
        .groupby(column_name) \
        [column_name] \
        .agg("count") \
        .pipe(pd.DataFrame) \
        .rename(columns={column_name: "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()

    if axis:
        stats_df.plot(x=column_name, y=["CDF"], grid=True, ax=axis)
    else:
        stats_df.plot(x=column_name, y=["CDF"], grid=True)
    return axis


if __name__ == "__main__":
    parser = ArgumentParser()
    parser.add_argument("--serial1", required=True, help="Serial csv file1.")
    parser.add_argument("--serial2", required=True, help="Serial csv file2.")
    parser.add_argument("--folder1", required=True, help="PCAP csv folder1.")
    parser.add_argument("--folder2", required=True, help="PCAP csv folder2.")
    parser.add_argument("--save", default=None, help="Location to save pdf file.")
    parser.add_argument(
        "-c",
        "--cores",
        default=1,
        type=int,
        help="Number of cores for multiprocessing.",
    )
    parser.add_argument(
        "-i",
        "--interval",
        default=2,
        type=int,
        help="Time interval for rolling window.",
    )

    args = parser.parse_args()

    transmission_df_list = list()
    for f in [args.folder1, args.folder2]:
        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(f):
            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, f, "dummy"))
            jobs.append(process)

        for j in jobs:
            j.start()

        print("Started all jobs.")
        # Ensure all 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["srtt"] = transmission_df["srtt"].apply(lambda x: x / 10 ** 6)

        # key for columns and level for index
        transmission_df["goodput"] = transmission_df["payload_size"].groupby(pd.Grouper(level="datetime", freq="{}s".format(args.interval))).transform("sum")
        transmission_df["goodput"] = transmission_df["goodput"].apply(
            lambda x: ((x * 8) / args.interval) / 10**6
        )

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

        # set meta values
        cc_algo = transmission_df["congestion_control"].iloc[0]
        cc_algo = cc_algo.upper()
        transmission_direction = transmission_df["direction"].iloc[0]

        # 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)
        #serial_df.sort_index()

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

        transmission_df_list.append(dict(
            df=transmission_df,
            cc_algo=cc_algo,
            transmission_direction=transmission_direction
        ))

    # Plot sRTT CDF
    ax = plot_cdf(transmission_df_list[0]["df"], "srtt")
    plot_cdf(transmission_df_list[1]["df"], "srtt", axis=ax)
    plt.xscale("log")
    plt.xlabel("sRTT [s]")
    plt.ylabel("CDF")
    plt.legend([transmission_df_list[0]["cc_algo"], transmission_df_list[1]["cc_algo"]])
    plt.title("{}".format(transmission_direction))
    plt.savefig("{}{}_cdf_compare_plot.pdf".format(args.save, "srtt"))

    plt.clf()

    # Plot goodput CDF
    ax = plot_cdf(transmission_df_list[0]["df"], "goodput")
    plot_cdf(transmission_df_list[1]["df"], "goodput", axis=ax)
    plt.xlabel("goodput [mbps]")
    plt.ylabel("CDF")
    plt.legend([transmission_df_list[0]["cc_algo"], transmission_df_list[1]["cc_algo"]])
    plt.title("{}".format(transmission_direction))
    plt.savefig("{}{}_cdf_compare_plot.pdf".format(args.save, "goodput"))