# Words by the Numbers 1, Exercise 1: a short passage, counted
# Count a short invented passage: tokens, types, the top five words,
# and how many types appear exactly once (hapax legomena).
import re
from collections import Counter

text = (
    "The rain fell on the town and the river rose. The people of the town "
    "watched the river and waited, and when the rain stopped the river fell."
)
tokens = re.findall(r"[a-z']+", text.lower())
counts = Counter(tokens)
print("tokens:", len(tokens))
print("types:", len(counts))
print("top five:", counts.most_common(5))
hapax = sorted(w for w, n in counts.items() if n == 1)
print("seen once:", len(hapax), hapax)

# Output when run:
# tokens: 28
# types: 14
# top five: [('the', 8), ('and', 3), ('river', 3), ('rain', 2), ('fell', 2)]
# seen once: 8 ['of', 'on', 'people', 'rose', 'stopped', 'waited', 'watched', 'when']