h5py

import h5py
import numpy as np
import os

file_path = 'my_data.h5'

# Create a new HDF5 file (mode 'w' will overwrite if exists)
with h5py.File(file_path, 'w') as f:
    # Create a group (like a directory)
    group = f.create_group('my_group')
    
    # Create a dataset within the group (like a NumPy array)
    data = np.arange(100).reshape(10, 10)
    dset = group.create_dataset('dataset_1', data=data)
    
    # Add attributes to the dataset (metadata)
    dset.attrs['units'] = 'arbitrary'
    dset.attrs['description'] = 'Sample 2D integer array'
    
    # You can also create datasets directly at the root level
    f.create_dataset('another_dataset', data=np.random.rand(5))

print(f"File '{file_path}' created successfully.")

# Read data from the HDF5 file
with h5py.File(file_path, 'r') as f:
    # List all top-level objects
    print(f"\nKeys in file: {list(f.keys())}")
    
    # Access a group
    group_read = f['my_group']
    print(f"Keys in 'my_group': {list(group_read.keys())}")
    
    # Access a dataset
    dset_read = group_read['dataset_1']
    
    # Read data into memory (using array-style slicing for the whole dataset)
    read_data = dset_read[()]
    print(f"\nShape of read_data: {read_data.shape}")
    print(f"First 5 elements of read_data: {read_data.flatten()[:5]}")
    
    # Access attributes
    print(f"Units attribute: {dset_read.attrs['units']}")
    
    # Read a slice of the data
    slice_data = dset_read[0:5, 0:5]
    print(f"Slice (0:5, 0:5) of dataset_1:\n{slice_data}")

# Clean up the created file
os.remove(file_path)