Changes to inplace operations for large dataframes.
This commit is contained in:
@@ -194,14 +194,14 @@ if __name__ == "__main__":
|
|||||||
# Get the frequency, PDF and CDF for each value in the series
|
# Get the frequency, PDF and CDF for each value in the series
|
||||||
|
|
||||||
# Frequency
|
# Frequency
|
||||||
transmission_df.groupby("goodput")["goodput"].agg("count").pipe(pd.DataFrame)
|
transmission_df["gp_frequency"] = transmission_df["goodput"]
|
||||||
transmission_df.rename(columns={"goodput": 'frequency'}, inplace=True)
|
transmission_df.groupby("gp_frequency")["gp_frequency"].agg("count").pipe(pd.DataFrame)
|
||||||
|
|
||||||
# PDF
|
# PDF
|
||||||
transmission_df['pdf'] = transmission_df['frequency'] / sum(transmission_df['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.reset_index(inplace=True)
|
||||||
|
|
||||||
transmission_df.plot(x="goodput", y=["cdf"], grid=True)
|
transmission_df.plot(x="goodput", y=["cdf"], grid=True)
|
||||||
|
|||||||
Reference in New Issue
Block a user