Python: Data-Stream Sampling

python_data_stream_sampling.py

#!python
# Background https://www.springer.com/cda/content/document/cda_downloaddocument/9783540286073-c2.pdf
# Example 1 adapted from https://stackoverflow.com/questions/12581437/python-random-sample-with-a-generator-iterable-iterator/
# 
# Reference: 1) https://docs.python.org/3/library/functions.html
#            2) https://docs.python.org/3/library/itertools.html
#            3) https://docs.python.org/3/library/random.html

from itertools import islice
from random import randint

stream = # Data stream that implements __iter__
sample_size = # Size of sample to select from data stream

# Example 1: Reservoir Sampling
iterator = iter(stream)
sample = list(islice(iterator, sample_size))

for i, v in enumerate(iterator, sample_size):
    r = randint(0, i)
    if r < sample_size:
        sample[r] = v
        
#