# Words by the Numbers 2, Exercise 1: a rank-frequency table for a short invented passage.
import re
from collections import Counter

text = (
    "the tide came in and the tide went out and the boats rested on the sand "
    "while the gulls watched the water and the children ran to the sea"
)
tokens = re.findall(r"[a-z']+", text.lower())
counts = Counter(tokens)
print("tokens:", len(tokens), "| types:", len(counts))
print("rank word      count  rank*count")
for rank, (word, n) in enumerate(counts.most_common(8), start=1):
    print(f"{rank:4d} {word:<9} {n:5d} {rank * n:10d}")
# Group the ranks by count to see the 'steps' in the tail.
steps = Counter(counts.values())
print("types per count:", sorted(steps.items(), reverse=True))

# Output when run (Python 3.14; the documentation-text counts depend on the Python version):
# tokens: 29 | types: 19
# rank word      count  rank*count
#    1 the           8          8
#    2 and           3          6
#    3 tide          2          6
#    4 came          1          4
#    5 in            1          5
#    6 went          1          6
#    7 out           1          7
#    8 boats         1          8
# types per count: [(8, 1), (3, 1), (2, 1), (1, 16)]