Sample code for Analysing the user behavior from the logs

import pandas as pd

from sklearn.preprocessing import LabelEncoder

from sklearn.cluster import KMeans

from sklearn.ensemble import IsolationForest

# Load log data from a CSV file

log_data = pd.read_csv('log_file.csv')

# Preprocessing: Encode categorical variables

label_encoder = LabelEncoder()

log_data['user_id'] = label_encoder.fit_transform(log_data['user_id'])

log_data['action'] = label_encoder.fit_transform(log_data['action'])

# User Session Identification: Group log entries by user sessions

session_duration = pd.Timedelta(minutes=30)

log_data['timestamp'] = pd.to_datetime(log_data['timestamp'])

log_data['session_id'] = (log_data['timestamp'].diff() > session_duration).cumsum()

# Behavioral Metrics Calculation: Calculate session duration and action frequency

session_metrics = log_data.groupby('session_id').agg({

    'user_id': 'first',

    'timestamp': ['min', 'max'],

    'action': 'count'

})

session_metrics.columns = ['user_id', 'start_time', 'end_time', 'action_count']

# Anomaly Detection: Identify anomalous user sessions

model = IsolationForest(contamination=0.05)  # Adjust contamination based on expected anomaly rate

session_metrics['is_anomaly'] = model.fit_predict(session_metrics[['action_count']])

# Visualization: Plot session duration and action count

plt.scatter(session_metrics['action_count'], session_metrics['end_time'] - session_metrics['start_time'])

plt.xlabel('Action Count')

plt.ylabel('Session Duration')

plt.title('User Session Duration vs. Action Count')

plt.show()

Sample csv file is as below 

timestamp,user_id,action

2023-06-01 10:00:00,user1,login

2023-06-01 10:01:00,user1,browse

2023-06-01 10:02:00,user1,purchase

2023-06-01 10:03:00,user2,login

2023-06-01 10:04:00,user2,browse

2023-06-01 10:05:00,user2,add_to_cart

2023-06-01 10:06:00,user3,login

2023-06-01 10:07:00,user3,browse

2023-06-01 10:08:00,user3,browse

2023-06-01 10:09:00,user3,checkout