Changes to inplace operations for large dataframes.

This commit is contained in:
2023-01-11 10:00:13 +01:00
parent 2754882147
commit ab7ef014f8

View File

@@ -192,17 +192,18 @@ if __name__ == "__main__":
print("Calculate and polt CDF...") print("Calculate and polt CDF...")
# Get the frequency, PDF and CDF for each value in the series # Get the frequency, PDF and CDF for each value in the series
# copy column
transmission_df["gp_frequency"] = transmission_df["goodput"]
# Frequency # Frequency
transmission_df["gp_frequency"] = transmission_df["goodput"] transmission_df = transmission_df.groupby("gp_frequency")["gp_frequency"].agg("count").pipe(pd.DataFrame)
transmission_df.groupby("gp_frequency")["gp_frequency"].agg("count").pipe(pd.DataFrame)
# PDF # PDF
transmission_df["pdf"] = transmission_df["gp_frequency"] / sum(transmission_df["gp_frequency"]) transmission_df["pdf"] = transmission_df["gp_frequency"] / sum(transmission_df["gp_frequency"])
# CDF # CDF
transmission_df["cdf"] = transmission_df["pdf"].cumsum() transmission_df["cdf"] = transmission_df["pdf"].cumsum()
transmission_df.reset_index(inplace=True) transmission_df = transmission_df.reset_index()
transmission_df.plot(x="goodput", y=["cdf"], grid=True) transmission_df.plot(x="goodput", y=["cdf"], grid=True)