Add script for ex3

.gitignore

@@ -1,3 +1,3 @@
 data
 venv
-.idea
+.idea

ex3/exercise3.py

@@ -0,0 +1,43 @@
+import pandas as pd
+import matplotlib.pyplot as plt
+import matplotlib.dates as mdate
+from datetime import datetime
+from statistics import median
+
+'''
+IMPORTANT: Remove leading space from column '# Bytes' in csv file or pandas
+won't read it correctly.
+'''
+
+dataset = pd.read_csv('./global_last10years.csv', index_col=0).dropna()
+
+# Convert unix timestamps to dates
+timestamps = mdate.epoch2num(dataset.index)
+date_formatter = mdate.DateFormatter('%y-%m-%d %H:%M:%S')
+
+# List of packet counts per hour (daily avg)
+ts_packets = dataset.iloc[:,1]
+
+# List of bytes per hour (daily avg)
+ts_bytes = dataset.iloc[:,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]
+
+### rep-14: Signals correlation ###
+
+print('Correlations between different columns (NaNs filtered):')
+print(dataset.corr(method='pearson').round(decimals=2))
+
+### rep-15: Destinations/Sources ratio ###
+
+ratio_uIPd_uIPs = median(ts_uIPd) / median(ts_uIPs)
+print('Ratio between median IP destinations and median IP sources: ', ratio_uIPd_uIPs)
+
+### rep-16: Peak in unique sources ###
+
+date = datetime.fromtimestamp(ts_uIPs.idxmax())
+print('Peak in unique sources: ', date)

ex3/requirements.txt

@@ -0,0 +1,2 @@
+pandas
+matplotlib