import numpy as np
import gc
import os
import torch
import h5py
from lib.normalization import normalize_dataset


def get_dataloader(args, normalizer="std", single=True):
    # args should now include 'cycle'
    data = load_st_dataset(args["type"], args["sample"])  # [T, N, F]
    L, N, F = data.shape

    # compute cycle index
    cycle_arr = np.arange(L) % args["cycle"]  # length-L array

    # Step 1: sliding windows for X and Y
    x = add_window_x(data, args["lag"], args["horizon"], single)
    y = add_window_y(data, args["lag"], args["horizon"], single)
    # window count = M = L - lag - horizon + 1
    M = x.shape[0]

    # Step 2: time features
    time_in_day = np.tile(
        np.array([i % args["steps_per_day"] / args["steps_per_day"] for i in range(L)]),
        (N, 1),
    ).T.reshape(L, N, 1)
    day_in_week = np.tile(
        np.array(
            [(i // args["steps_per_day"]) % args["days_per_week"] for i in range(L)]
        ),
        (N, 1),
    ).T.reshape(L, N, 1)

    x_day = add_window_x(time_in_day, args["lag"], args["horizon"], single)
    x_week = add_window_x(day_in_week, args["lag"], args["horizon"], single)
    x = np.concatenate([x, x_day, x_week], axis=-1)
    # del x_day, x_week
    # gc.collect()

    # Step 3: extract cycle index per window: take value at end of sequence
    cycle_win = np.array([cycle_arr[i + args["lag"]] for i in range(M)])  # shape [M]

    # Step 4: split into train/val/test
    if args["test_ratio"] > 1:
        x_train, x_val, x_test = split_data_by_days(
            x, args["val_ratio"], args["test_ratio"]
        )
        y_train, y_val, y_test = split_data_by_days(
            y, args["val_ratio"], args["test_ratio"]
        )
        c_train, c_val, c_test = split_data_by_days(
            cycle_win, args["val_ratio"], args["test_ratio"]
        )
    else:
        x_train, x_val, x_test = split_data_by_ratio(
            x, args["val_ratio"], args["test_ratio"]
        )
        y_train, y_val, y_test = split_data_by_ratio(
            y, args["val_ratio"], args["test_ratio"]
        )
        c_train, c_val, c_test = split_data_by_ratio(
            cycle_win, args["val_ratio"], args["test_ratio"]
        )
    # del x, y, cycle_win
    # gc.collect()

    # Step 5: normalization on X only
    scaler = normalize_dataset(
        x_train[..., : args["input_dim"]], normalizer, args["column_wise"]
    )
    x_train[..., : args["input_dim"]] = scaler.transform(
        x_train[..., : args["input_dim"]]
    )
    x_val[..., : args["input_dim"]] = scaler.transform(x_val[..., : args["input_dim"]])
    x_test[..., : args["input_dim"]] = scaler.transform(
        x_test[..., : args["input_dim"]]
    )

    # add time features to Y
    y_day = add_window_y(time_in_day, args["lag"], args["horizon"], single)
    y_week = add_window_y(day_in_week, args["lag"], args["horizon"], single)
    y = np.concatenate([y, y_day, y_week], axis=-1)
    # del y_day, y_week, time_in_day, day_in_week
    # gc.collect()

    # split Y time-augmented
    if args["test_ratio"] > 1:
        y_train, y_val, y_test = split_data_by_days(
            y, args["val_ratio"], args["test_ratio"]
        )
    else:
        y_train, y_val, y_test = split_data_by_ratio(
            y, args["val_ratio"], args["test_ratio"]
        )
    # del y

    # Step 6: create dataloaders including cycle index
    train_loader = data_loader_with_cycle(
        x_train, y_train, c_train, args["batch_size"], shuffle=True, drop_last=True
    )
    val_loader = data_loader_with_cycle(
        x_val, y_val, c_val, args["batch_size"], shuffle=False, drop_last=True
    )
    test_loader = data_loader_with_cycle(
        x_test, y_test, c_test, args["batch_size"], shuffle=False, drop_last=False
    )

    return train_loader, val_loader, test_loader, scaler


def data_loader_with_cycle(X, Y, C, batch_size, shuffle=True, drop_last=True):
    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
    X_t = torch.tensor(X, dtype=torch.float32, device=device)
    Y_t = torch.tensor(Y, dtype=torch.float32, device=device)
    C_t = torch.tensor(C, dtype=torch.long, device=device).unsqueeze(-1)  # [B,1]
    dataset = torch.utils.data.TensorDataset(X_t, Y_t, C_t)
    loader = torch.utils.data.DataLoader(
        dataset, batch_size=batch_size, shuffle=shuffle, drop_last=drop_last
    )
    return loader


# Rest of the helper functions (load_st_dataset, split_data..., add_window_x/y) unchanged


def load_st_dataset(dataset, sample):
    # output B, N, D
    match dataset:
        case "PEMSD3":
            data_path = os.path.join("./data/PEMS03/PEMS03.npz")
            data = np.load(data_path)["data"][
                :, :, 0
            ]  # only the first dimension, traffic flow data
        case "PEMSD4":
            data_path = os.path.join("./data/PEMS04/PEMS04.npz")
            data = np.load(data_path)["data"][
                :, :, 0
            ]  # only the first dimension, traffic flow data
        case "PEMSD7":
            data_path = os.path.join("./data/PEMS07/PEMS07.npz")
            data = np.load(data_path)["data"][
                :, :, 0
            ]  # only the first dimension, traffic flow data
        case "PEMSD8":
            data_path = os.path.join("./data/PEMS08/PEMS08.npz")
            data = np.load(data_path)["data"][
                :, :, 0
            ]  # only the first dimension, traffic flow data
        case "PEMSD7(L)":
            data_path = os.path.join("./data/PEMS07(L)/PEMS07L.npz")
            data = np.load(data_path)["data"][
                :, :, 0
            ]  # only the first dimension, traffic flow data
        case "PEMSD7(M)":
            data_path = os.path.join("./data/PEMS07(M)/V_228.csv")
            data = np.genfromtxt(
                data_path, delimiter=","
            )  # Read CSV directly with numpy
        case "METR-LA":
            data_path = os.path.join("./data/METR-LA/METR.h5")
            with h5py.File(
                data_path, "r"
            ) as f:  # Use h5py to handle HDF5 files without pandas
                data = np.array(f["data"])
        case "BJ":
            data_path = os.path.join("./data/BJ/BJ500.csv")
            data = np.genfromtxt(
                data_path, delimiter=",", skip_header=1
            )  # Skip header if present
        case "Hainan":
            data_path = os.path.join("./data/Hainan/Hainan.npz")
            data = np.load(data_path)["data"][:, :, 0]
        case "SD":
            data_path = os.path.join("./data/SD/data.npz")
            data = np.load(data_path)["data"][:, :, 0].astype(np.float32)
        case _:
            raise ValueError(f"Unsupported dataset: {dataset}")

    # Ensure data shape compatibility
    if len(data.shape) == 2:
        data = np.expand_dims(data, axis=-1)

    print("加载 %s 数据集中... " % dataset)
    return data[::sample]


def split_data_by_days(data, val_days, test_days, interval=30):
    t = int((24 * 60) / interval)
    test_data = data[-t * int(test_days) :]
    val_data = data[-t * int(test_days + val_days) : -t * int(test_days)]
    train_data = data[: -t * int(test_days + val_days)]
    return train_data, val_data, test_data


def split_data_by_ratio(data, val_ratio, test_ratio):
    data_len = data.shape[0]
    test_data = data[-int(data_len * test_ratio) :]
    val_data = data[
        -int(data_len * (test_ratio + val_ratio)) : -int(data_len * test_ratio)
    ]
    train_data = data[: -int(data_len * (test_ratio + val_ratio))]
    return train_data, val_data, test_data


def data_loader(X, Y, batch_size, shuffle=True, drop_last=True):
    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
    X = torch.tensor(X, dtype=torch.float32, device=device)
    Y = torch.tensor(Y, dtype=torch.float32, device=device)
    data = torch.utils.data.TensorDataset(X, Y)
    dataloader = torch.utils.data.DataLoader(
        data, batch_size=batch_size, shuffle=shuffle, drop_last=drop_last
    )
    return dataloader


def add_window_x(data, window=3, horizon=1, single=False):
    """
    Generate windowed X values from the input data.

    :param data: Input data, shape [B, ...]
    :param window: Size of the sliding window
    :param horizon: Horizon size
    :param single: If True, generate single-step windows, else multi-step
    :return: X with shape [B, W, ...]
    """
    length = len(data)
    end_index = length - horizon - window + 1
    x = []  # Sliding windows
    index = 0

    while index < end_index:
        x.append(data[index : index + window])
        index += 1

    return np.array(x)


def add_window_y(data, window=3, horizon=1, single=False):
    """
    Generate windowed Y values from the input data.

    :param data: Input data, shape [B, ...]
    :param window: Size of the sliding window
    :param horizon: Horizon size
    :param single: If True, generate single-step windows, else multi-step
    :return: Y with shape [B, H, ...]
    """
    length = len(data)
    end_index = length - horizon - window + 1
    y = []  # Horizon values
    index = 0

    while index < end_index:
        if single:
            y.append(data[index + window + horizon - 1 : index + window + horizon])
        else:
            y.append(data[index + window : index + window + horizon])
        index += 1

    return np.array(y)


if __name__ == "__main__":
    res = load_st_dataset("SD", 1)
    k = 1