Normalize Data in Python with Comprehensions and Generators

import statistics

# Sample raw data including missing and outlier-ish values
raw = [22, 18, None, 25, 30, 19, 22, 17, None, 28, 24]

# Clean the data: drop None values using a list comprehension
clean = [x for x in raw if x is not None]

# Normalize using min-max scaling with a generator expression
min_val = min(clean)
max_val = max(clean)

def scale(value):
    return (value - min_val) / (max_val - min_val)

# Generator expression: lazy evaluation, yields values one at a time
normalized_gen = (scale(x) for x in clean)

# Convert generator to list to observe results
normalized = list(normalized_gen)

# Show stats and output
print("Raw:", raw)
print("Clean:", clean)
print("Normalized (rounded to 3 decimals):", [round(x, 3) for x in normalized])
print("Mean:", round(statistics.mean(normalized), 3))
print("Min:", round(min(normalized), 3), "Max:", round(max(normalized), 3))

# Demonstrate generator laziness: sum without materializing
total = sum(scale(x) for x in clean)
print("Sum (from generator):", round(total, 3))