Project_Carmignac/clustering/main.py

import pandas as pd
from data_loader import load_and_clean_data
from features import compute_static_features, compute_market_sensitivities
from clustering import run_clustering_pipeline, get_cluster_profiles

def main():
    print("--- Starting Carmignac Client Clustering Pipeline ---")
    
    print("Loading data...")
    flows, aum, rates, gov = load_and_clean_data(
        'data/flows_sample.csv', 
        'data/aum_sample.csv', 
        'data/str_rates.csv', 
        'data/eur_gov_indices.csv'
    )

    print("Computing static features...")
    static_feats = compute_static_features(flows, aum)
    
    print("Computing market sensitivities (Betas)...")
    # Use 'W' (Weekly) to maximize points for the sample. 
    # Use 'M' (Monthly) for the full dataset.
    sensitivity_feats = compute_market_sensitivities(flows, rates, gov, freq='W')
    
    full_features = static_feats.join(sensitivity_feats, how='left')
    
    # Clustering
    print(f"Running Clustering on {len(full_features)} clients...")
    clustered_df, centers = run_clustering_pipeline(full_features, n_clusters=3)
    
    print("\n--- Cluster Profiles (Mean Values) ---")
    profiles = get_cluster_profiles(clustered_df)
    print(profiles.T) 
    
    clustered_df.to_csv('clustering/client_clusters.csv')
    print("\nResults saved to 'clustering/client_clusters.csv'")

if __name__ == "__main__":
    main()