import os
from pathlib import Path

import torch
from fastapi import APIRouter
from datetime import datetime
from datasets import load_dataset
from sklearn.metrics import accuracy_score

from .utils.evaluation import AudioEvaluationRequest
from .utils.emissions import tracker, clean_emissions_data, get_space_info

from dotenv import load_dotenv

load_dotenv()

from .fast_model import FastModel

router = APIRouter()

DESCRIPTION = "model_cuda_perf"
MODEL_PATH_PERF = Path(__file__).parent / "model_files/model_perf_cuda_test_dataset.txt"
MODEL_PATH_FRUGAL = Path(__file__).parent / "model_files/model_frugal_cuda_test_dataset.txt"
MASK_FILE = Path(__file__).parent / "model_files/mask.pkl"
ROUTE = "/audio"


@router.post(ROUTE, tags=["Audio Task"], description=DESCRIPTION)
async def evaluate_audio(request: AudioEvaluationRequest):
    """
    Evaluate audio classification for rainforest sound detection.

    Current Model: Model 1
    - Optimizes the computation time of the model_0
    """
    # Get space info
    username, space_url = get_space_info()

    # Define the label mapping
    LABEL_MAPPING = {"chainsaw": 0, "environment": 1}
    # Load and prepare the dataset
    # Because the dataset is gated, we need to use the HF_TOKEN environment variable to authenticate
    dataset = load_dataset(request.dataset_name, token=os.getenv("HF_TOKEN"))

    # Split dataset
    test_dataset = dataset["test"]

    # Start tracking emissions
    tracker.start()
    tracker.start_task("inference")

    # --------------------------------------------------------------------------------------------
    # YOUR MODEL INFERENCE CODE HERE
    # Update the code below to replace the random baseline by your model inference within the inference pass where the energy consumption and emissions are tracked.
    # --------------------------------------------------------------------------------------------

    # Make predictions
    true_labels = test_dataset["label"]
    feature_params = {
        "n_fft": 512,
        "hop_length": 256,
        "pad": 0,
        "win_spectrogram": torch.hamming_window,
        "win_cepstral": torch.hamming_window,
        "power": 2,
        "pad_mode": "reflect",
        "f_min": 70,
        "f_max": 1525,
        "fc_min": 0.05,
        "fc_max": 0.8,
    }
    # PERF
    model = FastModel(
        feature_params,
        None,
        model_file=MODEL_PATH_PERF,
        padding_method="reflect",
        device="cuda",
        mask_file="mask.pkl",
        mask_features=False,
        mask_ratio=0.25,
        waveform_duration=3,
        apply_offset_on_fit=False,
        batch_size=5000,
    )
    # MORE FRUGAL LESS PERFORMANT
    # model = FastModel(
    #     feature_params,
    #     None,
    #     model_file=MODEL_PATH_FRUGAL,
    #     padding_method="reflect",
    #     device="cuda",
    #     mask_file=MASK_FILE,
    #     mask_features=True,
    #     mask_ratio=0.25,
    #     waveform_duration=1,
    #     apply_offset_on_fit=True,
    #     batch_size=5000,
    # )
    predictions = model.predict(test_dataset)
    # --------------------------------------------------------------------------------------------
    # YOUR MODEL INFERENCE STOPS HERE
    # --------------------------------------------------------------------------------------------

    # Stop tracking emissions
    emissions_data = tracker.stop_task()

    # Calculate accuracy
    accuracy = accuracy_score(true_labels, predictions)

    # Prepare results dictionary
    results = {
        "username": username,
        "space_url": space_url,
        "submission_timestamp": datetime.now().isoformat(),
        "model_description": DESCRIPTION,
        "accuracy": float(accuracy),
        "energy_consumed_wh": emissions_data.energy_consumed * 1000,
        "emissions_gco2eq": emissions_data.emissions * 1000,
        "emissions_data": clean_emissions_data(emissions_data),
        "api_route": ROUTE,
        "dataset_config": {
            "dataset_name": request.dataset_name,
            "test_size": request.test_size,
            "test_seed": request.test_seed,
        },
    }

    return results