generate_dataset_summary.py

import json, os
from scripts import config

# ============================================================
# Dataset Definitions
# ============================================================

DATASETS = {

    "ROADS": [
        ("Road Nodes", config.ROAD_NODES_FILE, "road_nodes"),
        ("Road Edges", config.ROAD_EDGES_FILE, "road_edges"),
    ],

    "DEMAND": [
        ("Hotspots", config.HOTSPOT_FILE, "hotspots"),
        ("Demand Points", config.DEMAND_POINTS_FILE, "demand_points"),
    ],

    "RADIO UNITS": [
        ("Primary RUs", config.RU_OUTPUT_FILE, "radio_units"),
        ("Backup RUs", config.RU_BACKUP_FILE, "radio_units_backup"),
        ("Existing RUs", config.RU_EXISTING_FILE, "radio_units_existing"),
        ("New RUs", config.RU_NEW_FILE, "radio_units_new"),
    ],

    "DISTRIBUTED UNITS": [
        ("DUs", config.DU_OUTPUT_FILE, "distributed_units"),
        ("Existing DUs", config.DU_EXISTING_FILE, "distributed_units_existing"),
        ("New DUs", config.DU_NEW_FILE, "distributed_units_new"),
    ],

    "CENTRALISED UNITS": [
        ("CUs", config.CU_OUTPUT_FILE, "centralised_units"),
    ],

    "PATHS": [
        ("RU-DU Paths", config.RU_DU_PATHS_FILE, None),
        ("RU-DU New Paths", config.RU_DU_PATHS_NEW_FILE, None),
        ("RU-DU Existing Paths", config.RU_DU_PATHS_EXIST_FILE, None),
        ("RU-DU Existing Graph Paths", config.RU_DU_PATHS_EXIST_GRAPH_FILE, None),

        ("DU-CU Paths", config.DU_CU_PATHS_FILE, None),
        ("DU-CU New Paths", config.DU_CU_PATHS_NEW_FILE, None),
        ("DU-CU Existing Paths", config.DU_CU_PATHS_EXIST_FILE, None),
    ]
}

# ============================================================
# Count JSON Entries
# ============================================================

def count_entries(file_path, key=None):

    with open(file_path, "r") as f:
        data = json.load(f)

    # JSON Root is a List
    if isinstance(data, list):

        return len(data)

    # JSON Root is a Dictionary
    if isinstance(data, dict):

        # Auto-detect first list if no key provided
        if key is None:

            for value in data.values():

                if isinstance(value, list):
                    return len(value)

            return 0

        return len(data[key])


def get_user_statistics(file_path):

    with open(file_path, "r") as f:
            users = json.load(f)

    if isinstance(users, dict):

        for value in users.values():

            if isinstance(value, list):
                users = value
                break

    if not isinstance(users, list):

        print(f"[WARNING] User file is not a list:")
        print(f"          {file_path}")

        return {"total_users": 0, "hotspot_users": 0}

    total_users = len(users)

    hotspot_users = sum(1 for user in users if user.get("hotspot_name") not in [None, "", "null"])

    return {"total_users": total_users, "hotspot_users": hotspot_users}

# ============================================================
# Generate Dataset Summary
# ============================================================

def generate_dataset_summary():

    output_lines = []

    output_lines.append("=" * 50)
    output_lines.append("DATASET SUMMARY")
    output_lines.append("=" * 50)
    output_lines.append("")

    total_objects = 0

    for section, entries in DATASETS.items():
        output_lines.append(section)

        for label, file_path, key in entries:
            count = count_entries(file_path, key)
            output_lines.append(f"{label}: {count}")
            total_objects += count

        output_lines.append("")

    # Add user statistics
    user_stats = get_user_statistics(config.USER_MAP_FILE)
    total_objects += user_stats["total_users"]
    output_lines.append("USERS")
    output_lines.append(f"Total Users: {user_stats['total_users']}")
    output_lines.append(f"Hotspot Users: {user_stats['hotspot_users']}")
    output_lines.append(f"Standard Users: {user_stats['total_users'] - user_stats['hotspot_users']}")

    output_lines.append("")
    output_lines.append("=" * 50)
    output_lines.append(f"TOTAL OBJECTS: {total_objects}")
    output_lines.append("=" * 50)

    # ========================================================
    # Save Summary
    # ========================================================

    summary_path = os.path.join(config.BASE_DIR, "dataset_summary.txt")

    with open(summary_path, "w") as f:
        f.write("\n".join(output_lines))

    print(f"Dataset summary saved to:")
    print(summary_path)

if __name__ == "__main__":
    generate_dataset_summary()