Changes goodput calculation.

plot_transmission_timeline.py

@@ -44,6 +44,24 @@ def chunk(it, size):
     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("-f", "--gps_file", required=True, help="GPS csv file.")
@@ -126,7 +144,16 @@ if __name__ == "__main__":
     transmission_df = transmission_df.sort_index()
 
     print("Calculate goodput...")
-    transmission_df["goodput"] = transmission_df["payload_size"].rolling("{}s".format(args.interval)).sum()
+
+    range_start_time = transmission_df["datetime"].min()
+    range_sum_interval = "{}s".format(args.interval)
+
+    # create timedelta range with maximum timedelta
+    time_range = pd.timedelta_range(pd.Timedelta(range_start_time), transmission_df["datetime"].max(), freq=range_sum_interval)
+
+    # create bins by pd.cut, aggregate sum
+    transmission_df = transmission_df.groupby(pd.cut(transmission_df["datetime"], bins=time_range, labels=time_range[:-1]))["goodput"].sum().reset_index()
+    #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
     )
@@ -191,26 +218,9 @@ if __name__ == "__main__":
     plt.clf()
 
     print("Calculate and polt CDF...")
-    # Get the frequency, PDF and CDF for each value in the series
+    plot_cdf(transmission_df, "goodput")
-
-    # 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))
+        plt.savefig("{}{}_cdf_plot.pdf".format(args.save, "goodput"))
     else:
         plt.show()