from src.utils.clearml import ClearMLHelper

#### ClearML ####
clearml_helper = ClearMLHelper(project_name="Thesis/NrvForecast")
task = clearml_helper.get_task(task_name="Perfect Baseline")
task.execute_remotely(queue_name="default", exit_process=True)

from src.policies.simple_baseline import BaselinePolicy, Battery
from src.data import DataProcessor, DataConfig
from policies.baselines.PerfectBaseline import PerfectBaseline

### Data Processor ###
data_config = DataConfig()
data_config.NRV_HISTORY = True
data_config.LOAD_HISTORY = True
data_config.LOAD_FORECAST = True

data_config.WIND_FORECAST = True
data_config.WIND_HISTORY = True

data_config.QUARTER = False
data_config.DAY_OF_WEEK = False

data_config.NOMINAL_NET_POSITION = True

data_processor = DataProcessor(data_config, path="", lstm=False)
data_processor.set_batch_size(64)
data_processor.set_full_day_skip(True)

### Policy Evaluator ###
battery = Battery(2, 1)
baseline_policy = BaselinePolicy(battery, data_path="")
policy_evaluator = PerfectBaseline(baseline_policy, task)

penalty, profit, charge_cycles = (
    policy_evaluator.optimize_penalty_for_target_charge_cycles(
        data_processor=data_processor,
        initial_penalty=0,
        target_charge_cycles=283,
        learning_rate=2,
        max_iterations=100,
        tolerance=1,
    )
)
# policy_evaluator.plot_profits_table()
print()
print("Test Set Results")
print(f"Penalty: {penalty}, Profit: {profit}, Charge Cycles: {charge_cycles}")

task.get_logger().report_single_value(name="Optimal Penalty", value=penalty)
task.get_logger().report_single_value(name="Optimal Profit", value=profit)
task.get_logger().report_single_value(name="Optimal Charge Cycles", value=charge_cycles)

task.close()