import pandas as pd
from statistics import median

# Read dataset and fill missing rows with zeroes
dataset = pd.read_csv('data/global_last10years.csv', index_col=0).fillna(0)

# List of unique source IPs per hour (daily avg)
ts_uIPs = dataset.iloc[:,2]

# List of unique destination IPs per hour (daily avg)
ts_uIPd = dataset.iloc[:,3]

ratio_uIPd_uIPs = median(ts_uIPd) / median(ts_uIPs)
print('Ratio between median IP destinations and median IP sources: ', round(ratio_uIPd_uIPs, 2))