Philippe Libioulle - Fab Futures - Data Science

Home About

< Previous dataset - Week 2 home - Next dataset>

Week 2: tools - "Anomaly detection in network traffic" dataset

Context

• Source: Kaggle
• Description: this dataset is designed for the development and evaluation of anomaly detection models in embedded system network security. It includes network traffic features that simulate both normal and malicious behavior, making it suitable for supervised learning tasks focused on identifying security breaches in networked embedded systems. The data in this file is structured with various network-related features, including packet size, inter-arrival time, protocol type, source and destination IPs, TCP flags, and frequency-domain features extracted using Wavelet Transform. The dataset also includes a target column that marks each data entry as either normal (0) or anomalous (1).

Load dataset

import pandas as pd 
import seaborn as sb
import matplotlib.pyplot as plt

df_traffic = pd.read_csv("datasets/embedded_system_network_security_dataset.csv")

# 🧾 Display dataset informations
print("Traffic dataset shape:", df_traffic.shape)
#print(df.info)

Traffic dataset shape: (1000, 18)

Explore content

df_traffic.head()

	packet_size	inter_arrival_time	src_port	dst_port	packet_count_5s	mean_packet_size	spectral_entropy	frequency_band_energy	label	protocol_type_TCP	protocol_type_UDP	src_ip_192.168.1.2	src_ip_192.168.1.3	dst_ip_192.168.1.5	dst_ip_192.168.1.6	tcp_flags_FIN	tcp_flags_SYN	tcp_flags_SYN-ACK
0	0.405154	0.620362	62569	443	0.857143	0.0	0.834066	0.534891	0.0	False	True	True	False	False	False	False	False	False
1	0.527559	0.741288	59382	443	0.785714	0.0	0.147196	0.990757	0.0	False	True	False	False	False	True	False	True	False
2	0.226199	0.485116	65484	80	0.285714	0.0	0.855192	0.031781	0.0	False	True	False	False	True	False	False	False	False
3	0.573372	0.450965	51707	53	0.142857	0.0	0.153220	0.169958	0.0	False	False	False	True	False	False	False	False	False
4	0.651396	0.888740	26915	53	0.714286	0.0	0.923916	0.552053	0.0	True	False	False	True	False	False	False	True	False

Display a nice chart

import plotly.graph_objects as go
import plotly.offline as pyo
pyo.init_notebook_mode()

df_traffic_sample= df_traffic #[df_traffic['label'] > 0]
series_from_range = pd.Series(range(100000))

fig = go.Figure(data=[go.Sankey(
    node = dict(
      pad = 15,
      thickness = 20,
      line = dict(color = "grey", width = 0.1),
      label = series_from_range,
      color = "red"
    ),
    link = dict(
      source = df_traffic_sample['src_port'].to_numpy(),      
      target = df_traffic_sample['dst_port'].to_numpy(),
      value = df_traffic_sample['packet_size'].to_numpy()
  ))])

fig.update_layout(title_text="Source to destination traffic", font_size=5, height=1200)
fig.show()