>>> import os; import psutil; import timeit
>>> from datasets import load_dataset

# Process.memory_info is expressed in bytes, so convert to megabytes 
>>> mem_before = psutil.Process(os.getpid()).memory_info().rss / (1024 * 1024)
>>> wiki = load_dataset("wikimedia/wikipedia", "20220301.en", split="train")
>>> mem_after = psutil.Process(os.getpid()).memory_info().rss / (1024 * 1024)

>>> print(f"RAM memory used: {(mem_after - mem_before)} MB")
RAM memory used: 50 MB

>>> s = """batch_size = 1000
... for batch in wiki.iter(batch_size):
...     ...
... """

>>> elapsed_time = timeit.timeit(stmt=s, number=1, globals=globals())
>>> print(f"Time to iterate over the {wiki.dataset_size >> 30} GB dataset: {elapsed_time:.1f} sec, "
...       f"ie. {float(wiki.dataset_size >> 27)/elapsed_time:.1f} Gb/s")
Time to iterate over the 18 GB dataset: 31.8 sec, ie. 4.8 Gb/s