Refactor and adds ne script (WIP) for plotting single transmissions

plot_single_transmission_timeline.py

@@ -0,0 +1,273 @@
+#!/usr/bin/env python3
+import multiprocessing
+import os
+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, 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)), ())
+
+
+def plot_cdf(dataframe, column_name):
+    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()
+
+    stats_df.plot(x=column_name, y=["CDF"], grid=True)
+
+
+if __name__ == "__main__":
+    parser = ArgumentParser()
+    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(
+        "-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 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...")
+
+    #print(transmission_df)
+
+    # 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 and remove all not needed columns
+    cc_algo = transmission_df["congestion_control"].iloc[0]
+    cc_algo = cc_algo.upper()
+    transmission_direction = transmission_df["direction"].iloc[0]
+
+    transmission_df = transmission_df.filter(["goodput", "datetime", "ack_rtt", "goodput_rolling"])
+
+    # 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,
+    )
+
+    # transmission timeline
+
+    scaley = 1.5
+    scalex = 1.0
+    fig, ax = plt.subplots(figsize=[6.4 * scaley, 4.8 * scalex])
+    plt.title("{} with {}".format(transmission_direction, cc_algo))
+    fig.subplots_adjust(right=0.75)
+
+    twin1 = ax.twinx()
+    twin2 = ax.twinx()
+    # Offset the right spine of twin2.  The ticks and label have already been
+    # placed on the right by twinx above.
+    twin2.spines.right.set_position(("axes", 1.2))
+
+
+    # create list fo color indices
+    transmission_df["index"] = transmission_df.index
+    color_dict = dict()
+    color_list = list()
+    i = 0
+    for cell_id in transmission_df["cellID"]:
+        if cell_id not in color_dict:
+            color_dict[cell_id] = i
+            i += 1
+        color_list.append(color_dict[cell_id])
+
+    transmission_df["cell_color"] = color_list
+    color_dict = None
+    color_list = None
+
+    cmap = matplotlib.cm.get_cmap("Set3")
+    for c in transmission_df["cell_color"].unique():
+        bounds = transmission_df[["index", "cell_color"]].groupby("cell_color").agg(["min", "max"]).loc[c]
+        ax.axvspan(bounds.min(), bounds.max(), alpha=0.3, color=cmap.colors[c])
+
+    p1, = ax.plot(transmission_df["goodput_rolling"], "-", color="blue", label="goodput")
+    p2, = twin1.plot(transmission_df["downlink_cqi"], "--", color="green", label="CQI")
+    p3, = twin2.plot(transmission_df["ack_rtt"], "-.", color="red", label="ACK RTT")
+
+    ax.set_xlim(transmission_df["index"].min(), transmission_df["index"].max())
+    ax.set_ylim(0, 500)
+    twin1.set_ylim(0, 15)
+    twin2.set_ylim(0, 1)
+
+    ax.set_xlabel("Time")
+    ax.set_ylabel("Goodput")
+    twin1.set_ylabel("CQI")
+    twin2.set_ylabel("ACK RTT")
+
+    ax.yaxis.label.set_color(p1.get_color())
+    twin1.yaxis.label.set_color(p2.get_color())
+    twin2.yaxis.label.set_color(p3.get_color())
+
+    tkw = dict(size=4, width=1.5)
+    ax.tick_params(axis='y', colors=p1.get_color(), **tkw)
+    twin1.tick_params(axis='y', colors=p2.get_color(), **tkw)
+    twin2.tick_params(axis='y', colors=p3.get_color(), **tkw)
+    ax.tick_params(axis='x', **tkw)
+
+    #ax.legend(handles=[p1, p2, p3])
+
+    if args.save:
+        plt.savefig("{}timeline_plot.pdf".format(args.save))
+    else:
+        plt.show()
+
+    #goodput cdf
+    plt.clf()
+
+    print("Calculate and polt goodput CDF...")
+    plot_cdf(transmission_df, "goodput")
+    plt.xlabel("goodput [mbps]")
+    plt.ylabel("CDF")
+    plt.legend([cc_algo])
+    plt.title("{} with {}".format(transmission_direction, cc_algo))
+
+    if args.save:
+        plt.savefig("{}{}_cdf_plot.pdf".format(args.save, "goodput"))
+    else:
+        plt.show()
+
+    # rtt cdf
+    plt.clf()
+
+    print(transmission_df["ack_rtt"])
+    print("Calculate and polt rtt CDF...")
+    plot_cdf(transmission_df, "ack_rtt")
+    plt.xlabel("ACK RTT [s]")
+    plt.ylabel("CDF")
+    plt.xscale("log")
+    plt.legend([cc_algo])
+    plt.title("{} with {}".format(transmission_direction, cc_algo))
+
+    if args.save:
+        plt.savefig("{}{}_cdf_plot.pdf".format(args.save, "ack_rtt"))
+    else:
+        plt.show()

plot_transmission_timeline.py

@@ -65,15 +65,9 @@ def plot_cdf(dataframe, column_name):
 
 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",