TinyTorch/tinytorch/core/dataloader.py

# AUTOGENERATED! DO NOT EDIT! File to edit: ../../modules/source/06_dataloader/dataloader_dev.ipynb.

# %% auto 0
__all__ = ['Dataset', 'DataLoader', 'SimpleDataset']

# %% ../../modules/source/06_dataloader/dataloader_dev.ipynb 1
import numpy as np
import sys
import os
import pickle
import struct
from typing import List, Tuple, Optional, Union, Iterator
import matplotlib.pyplot as plt
import urllib.request
import tarfile

# Import our building blocks - try package first, then local modules
try:
    from tinytorch.core.tensor import Tensor
except ImportError:
    # For development, import from local modules
    sys.path.append(os.path.join(os.path.dirname(__file__), '..', '01_tensor'))
    from tensor_dev import Tensor

# %% ../../modules/source/06_dataloader/dataloader_dev.ipynb 2
def _should_show_plots():
    """Check if we should show plots (disable during testing)"""
    # Check multiple conditions that indicate we're in test mode
    is_pytest = (
        'pytest' in sys.modules or
        'test' in sys.argv or
        os.environ.get('PYTEST_CURRENT_TEST') is not None or
        any('test' in arg for arg in sys.argv) or
        any('pytest' in arg for arg in sys.argv)
    )
    
    # Show plots in development mode (when not in test mode)
    return not is_pytest

# %% ../../modules/source/06_dataloader/dataloader_dev.ipynb 7
class Dataset:
    """
    Base Dataset class: Abstract interface for all datasets.
    
    The fundamental abstraction for data loading in TinyTorch.
    Students implement concrete datasets by inheriting from this class.
    """
    
    def __getitem__(self, index: int) -> Tuple[Tensor, Tensor]:
        """
        Get a single sample and label by index.
        
        Args:
            index: Index of the sample to retrieve
            
        Returns:
            Tuple of (data, label) tensors
            
        TODO: Implement abstract method for getting samples.
        
        APPROACH:
        1. This is an abstract method - subclasses will implement it
        2. Return a tuple of (data, label) tensors
        3. Data should be the input features, label should be the target
        
        EXAMPLE:
        dataset[0] should return (Tensor(image_data), Tensor(label))
        
        HINTS:
        - This is an abstract method that subclasses must override
        - Always return a tuple of (data, label) tensors
        - Data contains the input features, label contains the target
        """
        ### BEGIN SOLUTION
        # This is an abstract method - subclasses must implement it
        raise NotImplementedError("Subclasses must implement __getitem__")
        ### END SOLUTION
    
    def __len__(self) -> int:
        """
        Get the total number of samples in the dataset.
        
        TODO: Implement abstract method for getting dataset size.
        
        APPROACH:
        1. This is an abstract method - subclasses will implement it
        2. Return the total number of samples in the dataset
        
        EXAMPLE:
        len(dataset) should return 50000 for CIFAR-10 training set
        
        HINTS:
        - This is an abstract method that subclasses must override
        - Return an integer representing the total number of samples
        """
        ### BEGIN SOLUTION
        # This is an abstract method - subclasses must implement it
        raise NotImplementedError("Subclasses must implement __len__")
        ### END SOLUTION
    
    def get_sample_shape(self) -> Tuple[int, ...]:
        """
        Get the shape of a single data sample.
        
        TODO: Implement method to get sample shape.
        
        APPROACH:
        1. Get the first sample using self[0]
        2. Extract the data part (first element of tuple)
        3. Return the shape of the data tensor
        
        EXAMPLE:
        For CIFAR-10: returns (3, 32, 32) for RGB images
        
        HINTS:
        - Use self[0] to get the first sample
        - Extract data from the (data, label) tuple
        - Return data.shape
        """
        ### BEGIN SOLUTION
        # Get the first sample to determine shape
        data, _ = self[0]
        return data.shape
        ### END SOLUTION
    
    def get_num_classes(self) -> int:
        """
        Get the number of classes in the dataset.
        
        TODO: Implement abstract method for getting number of classes.
        
        APPROACH:
        1. This is an abstract method - subclasses will implement it
        2. Return the number of unique classes in the dataset
        
        EXAMPLE:
        For CIFAR-10: returns 10 (classes 0-9)
        
        HINTS:
        - This is an abstract method that subclasses must override
        - Return the number of unique classes/categories
        """
        ### BEGIN SOLUTION
        # This is an abstract method - subclasses must implement it
        raise NotImplementedError("Subclasses must implement get_num_classes")
        ### END SOLUTION

# %% ../../modules/source/06_dataloader/dataloader_dev.ipynb 11
class DataLoader:
    """
    DataLoader: Efficiently batch and iterate through datasets.
    
    Provides batching, shuffling, and efficient iteration over datasets.
    Essential for training neural networks efficiently.
    """
    
    def __init__(self, dataset: Dataset, batch_size: int = 32, shuffle: bool = True):
        """
        Initialize DataLoader.
        
        Args:
            dataset: Dataset to load from
            batch_size: Number of samples per batch
            shuffle: Whether to shuffle data each epoch
            
        TODO: Store configuration and dataset.
        
        APPROACH:
        1. Store dataset as self.dataset
        2. Store batch_size as self.batch_size
        3. Store shuffle as self.shuffle
        
        EXAMPLE:
        DataLoader(dataset, batch_size=32, shuffle=True)
        
        HINTS:
        - Store all parameters as instance variables
        - These will be used in __iter__ for batching
        """
        ### BEGIN SOLUTION
        self.dataset = dataset
        self.batch_size = batch_size
        self.shuffle = shuffle
        ### END SOLUTION
    
    def __iter__(self) -> Iterator[Tuple[Tensor, Tensor]]:
        """
        Iterate through dataset in batches.
        
        Returns:
            Iterator yielding (batch_data, batch_labels) tuples
            
        TODO: Implement batching and shuffling logic.
        
        APPROACH:
        1. Create indices list: list(range(len(dataset)))
        2. Shuffle indices if self.shuffle is True
        3. Loop through indices in batch_size chunks
        4. For each batch: collect samples, stack them, yield batch
        
        EXAMPLE:
        for batch_data, batch_labels in dataloader:
            # batch_data.shape: (batch_size, ...)
            # batch_labels.shape: (batch_size,)
        
        HINTS:
        - Use list(range(len(self.dataset))) for indices
        - Use np.random.shuffle() if self.shuffle is True
        - Loop in chunks of self.batch_size
        - Collect samples and stack with np.stack()
        """
        ### BEGIN SOLUTION
        # Create indices for all samples
        indices = list(range(len(self.dataset)))
        
        # Shuffle if requested
        if self.shuffle:
            np.random.shuffle(indices)
        
        # Iterate through indices in batches
        for i in range(0, len(indices), self.batch_size):
            batch_indices = indices[i:i + self.batch_size]
            
            # Collect samples for this batch
            batch_data = []
            batch_labels = []
            
            for idx in batch_indices:
                data, label = self.dataset[idx]
                batch_data.append(data.data)
                batch_labels.append(label.data)
            
            # Stack into batch tensors
            batch_data_array = np.stack(batch_data, axis=0)
            batch_labels_array = np.stack(batch_labels, axis=0)
            
            yield Tensor(batch_data_array), Tensor(batch_labels_array)
        ### END SOLUTION
    
    def __len__(self) -> int:
        """
        Get the number of batches per epoch.
        
        TODO: Calculate number of batches.
        
        APPROACH:
        1. Get dataset size: len(self.dataset)
        2. Divide by batch_size and round up
        3. Use ceiling division: (n + batch_size - 1) // batch_size
        
        EXAMPLE:
        Dataset size 100, batch size 32 → 4 batches
        
        HINTS:
        - Use len(self.dataset) for dataset size
        - Use ceiling division for exact batch count
        - Formula: (dataset_size + batch_size - 1) // batch_size
        """
        ### BEGIN SOLUTION
        # Calculate number of batches using ceiling division
        dataset_size = len(self.dataset)
        return (dataset_size + self.batch_size - 1) // self.batch_size
        ### END SOLUTION

# %% ../../modules/source/06_dataloader/dataloader_dev.ipynb 15
class SimpleDataset(Dataset):
    """
    Simple dataset for testing and demonstration.
    
    Generates synthetic data with configurable size and properties.
    Perfect for understanding the Dataset pattern.
    """
    
    def __init__(self, size: int = 100, num_features: int = 4, num_classes: int = 3):
        """
        Initialize SimpleDataset.
        
        Args:
            size: Number of samples in the dataset
            num_features: Number of features per sample
            num_classes: Number of classes
            
        TODO: Initialize the dataset with synthetic data.
        
        APPROACH:
        1. Store the configuration parameters
        2. Generate synthetic data and labels
        3. Make data deterministic for testing
        
        EXAMPLE:
        SimpleDataset(size=100, num_features=4, num_classes=3)
        creates 100 samples with 4 features each, 3 classes
        
        HINTS:
        - Store size, num_features, num_classes as instance variables
        - Use np.random.seed() for reproducible data
        - Generate random data with np.random.randn()
        - Generate random labels with np.random.randint()
        """
        ### BEGIN SOLUTION
        self.size = size
        self.num_features = num_features
        self.num_classes = num_classes
        
        # Set seed for reproducible data
        np.random.seed(42)
        
        # Generate synthetic data
        self.data = np.random.randn(size, num_features).astype(np.float32)
        self.labels = np.random.randint(0, num_classes, size=size)
        ### END SOLUTION
    
    def __getitem__(self, index: int) -> Tuple[Tensor, Tensor]:
        """
        Get a single sample and label by index.
        
        Args:
            index: Index of the sample to retrieve
            
        Returns:
            Tuple of (data, label) tensors
            
        TODO: Return the sample and label at the given index.
        
        APPROACH:
        1. Get data at index from self.data
        2. Get label at index from self.labels
        3. Convert to tensors and return as tuple
        
        EXAMPLE:
        dataset[0] returns (Tensor([1.2, -0.5, 0.8, 0.1]), Tensor(2))
        
        HINTS:
        - Use self.data[index] and self.labels[index]
        - Convert to Tensor objects
        - Return as tuple (data, label)
        """
        ### BEGIN SOLUTION
        data = Tensor(self.data[index])
        label = Tensor(self.labels[index])
        return data, label
        ### END SOLUTION
    
    def __len__(self) -> int:
        """
        Get the total number of samples in the dataset.
        
        TODO: Return the dataset size.
        
        HINTS:
        - Return self.size
        """
        ### BEGIN SOLUTION
        return self.size
        ### END SOLUTION
    
    def get_num_classes(self) -> int:
        """
        Get the number of classes in the dataset.
        
        TODO: Return the number of classes.
        
        HINTS:
        - Return self.num_classes
        """
        ### BEGIN SOLUTION
        return self.num_classes
        ### END SOLUTION