measurement-scripts/calc_gps_map_csv.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 geopandas as gpd
import contextily as cx
import matplotlib.pyplot as plt


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["datetime"] = pd.to_datetime(tmp_df["datetime"])
        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("--time_offset", default=None, type=int, help="Minutes added to GPS datetime.")
    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
    )

    # load dataframe an put it into geopandas
    df = pd.read_csv(args.gps_file)
    df["kmh"] = df["speed (knots)"].apply(lambda x: x * 1.852)
    if args.time_offset is not None:
        if args.time_offset > 0:
            df["datetime"] = pd.to_datetime(df["datetime"]) + pd.Timedelta(minutes=abs(args.time_offset))
        else:
            df["datetime"] = pd.to_datetime(df["datetime"]) - pd.Timedelta(minutes=abs(args.time_offset))
    else:
        df["datetime"] = pd.to_datetime(df["datetime"])
    df = df.set_index("datetime")
    df.index = pd.to_datetime(df.index)

    gdf = gpd.GeoDataFrame(
        df,
        geometry=gpd.points_from_xy(df["longitude"], df["latitude"]),
        crs="EPSG:4326",
    )
    gdf = pd.merge_asof(
        gdf,
        transmission_df,
        tolerance=pd.Timedelta("10s"),
        right_index=True,
        left_index=True,
    )

    # 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["datetime"] = pd.to_datetime(serial_df["datetime"])
    serial_df = serial_df.set_index("datetime")
    serial_df.index = pd.to_datetime(serial_df.index)

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

    # format to needed format and add basemap as background
    df_wm = gdf.to_crs(epsg=3857)
    #df_wm.to_csv("debug-data.csv")
    # ax2 = df_wm.plot(figsize=(10, 10), alpha=0.5, edgecolor='k')

    df_wm.to_csv("{}gps_plot.csv".format(args.save))
    print("Saved calculations to: {}gps_plot.csv".format(args.save))