zipf.py

import matplotlib.pyplot as plt

word_frequencies = []
for line in open("top100.txt"): word_frequencies.append(int(line))

word_freq_ideal = []
d = 1
for x in word_frequencies:
    word_freq_ideal.append(word_frequencies[0] / d)
    d = d + 1

plt.plot([log(i) for i in range(1, 1 + len(word_frequencies))], 
         [log(i) or i in word_frequencies])

plt.plot([log(i) for i in range(1, 1 + len(word_frequencies))], 
         [log(i) for i in word_freq_ideal])

plt.title("Top 100 Dutch words compared to Zipf's Law")
plt.xlabel("log(Rank of word)")
plt.ylabel("log(Frequency of the word)")
plt.legend(("Top 100 Dutch words", "1/freq: ideal case"), 
           'upper right')
plt.grid(True)