cluster.py

from sklearn.cluster import KMeans
import pandas as pd

def classify_workload_patterns(usage_df, n_clusters=4):
    """
    Cluster storage volumes by access frequency, size, and
    read/write ratio to recommend appropriate storage tiers.
    """
    features = usage_df[["avg_daily_accesses", "size_gb", "read_write_ratio"]]

    kmeans = KMeans(n_clusters=n_clusters, random_state=42, n_init=10)
    usage_df["cluster"] = kmeans.fit_predict(features)

    tier_map = {
        0: "hot_storage",
        1: "standard_storage",
        2: "infrequent_access",
        3: "archive"
    }

    usage_df["recommended_tier"] = usage_df["cluster"].map(tier_map)
    return usage_df

volumes = pd.read_csv("volume_usage_metrics.csv")
recommendations = classify_workload_patterns(volumes)
print(recommendations[["volume_id", "recommended_tier"]].head(10))