model_skeletons/model_class_24.py

# Auto-extracted class source (static)

class RRF_Dataset(Dataset):
    def __init__(self, strain, weights, seq_len=160): # Use seq_len=160 to match model input
        self.seq_len = seq_len
        self.strain = strain
        self.weights = weights
        print(f"Debug: RRF_Dataset __init__ - len(strain): {len(strain)}, seq_len: {self.seq_len}") # Debug print
        # Calculate n only if strain is long enough
        if len(strain) >= seq_len:
            self.n = len(strain) // seq_len
        else:
            self.n = 0 # Set n to 0 if strain is too short
        print(f"Debug: RRF_Dataset __init__ - Calculated self.n: {self.n}") # New debug print
        # Add a check to ensure there's at least one sequence
        if self.n == 0:
            raise ValueError(f"Strain data length ({len(strain)}) is less than sequence length ({seq_len}). Cannot create any samples.")


    def __len__(self):
        return self.n

    def __getitem__(self, idx):
        start = idx * self.seq_len
        # Extract the strain sequence x
        x = self.strain[start:start+self.seq_len] # Shape: [seq_len]

        # Use the mean of the provided weights as the global resonance factor w
        w = np.mean(self.weights)  # global resonance factor

        # Define the target label y as the mean of the strain sequence x, scaled by w
        # This creates a regression target derived from the strain data.
        y = np.mean(x) * w  # synthetic label (proxy resonance)

        # Convert x and y to PyTorch tensors with float dtype
        # The model expects input x as [1, seq_len] for a single sample, so add unsqueeze(0)
        return torch.tensor(x).float().unsqueeze(0), torch.tensor(y).float()