import json
import random
from datetime import datetime, timedelta

def generate_random_point():
    # Coordinate approssimative dell'Europa
    lon = random.uniform(-10.0, 30.0)
    lat = random.uniform(35.0, 60.0)
    return [lon, lat]

def generate_data(num_points=500):
    features = []
    operators = ["Operator A", "Operator B", "Operator C", "Operator D", "Operator E"]
    # Status principali (senza timing)
    statuses = ["OPEN", "CLOSED", "IN_PROGRESS", "ON_HOLD"]
    # Timing status solo per CLOSED
    timing_statuses = ["CLOSED_ON_TIME", "CLOSED_LATE"]
    # Task types
    task_types = ["Create Activity", "Close Activity", "Create WF", "Close WF", "Select DTO", "Report Generation", "Report QC"]
    
    base_time = datetime.now()

    for i in range(num_points):
        status = random.choice(statuses)
        operator = random.choice(operators)
        duration = random.randint(10, 300)
        task_type = random.choice(task_types)
        
        # Durations per task (in secondi) - min, max, avg variano per task
        min_duration = random.randint(10, 25)
        max_duration = random.randint(40, 60)
        avg_duration = random.randint(min_duration + 5, max_duration - 5)
        task_duration = random.randint(min_duration, max_duration + 20)
        
        # Lead time in minuti (per Avg Lead Time) - solo per CLOSED
        lead_time = None
        timing_status = None
        if status == "CLOSED":
            lead_time = random.randint(5, 120)  # minuti
            # 70% on time, 30% late (come in figura ~24 vs 11)
            timing_status = random.choices(timing_statuses, weights=[70, 30])[0]
        
        # Random timestamp negli ultimi 7 giorni
        time_offset = random.randint(0, 7 * 24 * 60 * 60)
        timestamp = (base_time - timedelta(seconds=time_offset)).isoformat()

        properties = {
            "status": status,
            "operator": operator,
            "duration": duration,
            "timestamp": timestamp,
            "id": i,
            "task_type": task_type,
            "min_duration": min_duration,
            "max_duration": max_duration,
            "avg_duration": avg_duration,
            "task_duration": task_duration
        }
        
        # Aggiungi lead_time e timing_status solo se CLOSED
        if lead_time is not None:
            properties["lead_time"] = lead_time
        if timing_status is not None:
            properties["timing_status"] = timing_status

        feature = {
            "type": "Feature",
            "properties": properties,
            "geometry": {
                "type": "Point",
                "coordinates": generate_random_point()
            }
        }
        features.append(feature)

    geojson = {
        "type": "FeatureCollection",
        "features": features
    }

    with open('data/sample.geojson', 'w') as f:
        json.dump(geojson, f, indent=2)
    
    print(f"Generated {num_points} data points in data/sample.geojson")

if __name__ == "__main__":
    generate_data(1000)