process.py

import json

words = open('words.txt').read().splitlines()
freqs = {}
for word in words:
    for c in word:
        if c not in freqs:
            freqs[c] = 0
        freqs[c] += 1
tuples = []

for c in freqs:
    tuples.append((freqs[c], c))
tuples.sort(reverse=True)
primes = [
2,3,5,7,11,13,17,19,23,29,31,37,41,43,47,53,59,61,67,71,73,79,83,89,97,101,103,107,109,113,127,131,137,139,149,151,157,163,167,173,179,181,191,193,197,199,211,223,227,229,233,239,241,251,257,263,269,271,277,281,283,293,307,311,313,317,331,337,347,349,353,359,367,373,379,383,389,397,401,409,419,421,431,433,439,443,449,457,461,463,467,479,487,491,499,503,509,521,523,541,547,557,563,569,571,577,587,593,599,601,607,613,617,619,631,641,643,647,653,659,661,673,677,683,691,701,709,719,727,733,739,743,751,757,761,769,773,787,797,809,811,821,823,827,829,839,853,857,859,863,877,881,883,887,907,911,919,929,937,941,947,953,967,971,977,983,991,997,1009,1013,1019,1021,1031]
dups = [1, 1, 4800648691259650729, 93445708553524800143627380012419329729]

charDict = {}
i = 0
for freq, c in tuples:
    charDict[c] = {
        'yellow': primes[i],
        'green': primes[i+1:i+6],
    }
    i += 6

print(tuples)

with open('charDict.json', 'w') as f:
    json.dump(charDict, f)


wfreqs = {}
wf = open('en_wikt_words_1_5-5.txt', encoding="utf8").read().splitlines()
for fr in wf:
    fr = fr.split(' ')
    wfreqs[fr[0]] = int(fr[2])

wordList = []
for word in words:
    num = 1
    freq = {}
    for i in range(len(word)):
        if word[i] not in freq:
            freq[word[i]] = 0
        freq[word[i]] += 1
        c = word[i]
        num *= charDict[c]['green'][i]*charDict[c]['yellow']
    for k in freq:
        num *= dups[freq[k]]
    wordList.append((num, wfreqs.get(word, 0), word))


wordList.sort()


f = open("wordList.txt", "w")
for num, wfreq, word in wordList:
    f.write(str(num) + "," + str(wfreq) + "," + word + "\n")


f.close()