words = open('/usr/share/dict/ukrainian').read().splitlines() # needs package wukrainian to be installed
itos = ".абвгґдеєжзиіїйклмнопрстуфхцчшщьюя'-"
stoi = {s: i for i, s in enumerate(itos)}
nchars = len(itos)

import torch
import random

N = torch.zeros((len(stoi), len(stoi)), dtype=torch.int32)
for w in words:
    chrs = ['.'] + list(w.lower()) + ['.']
    for c1, c2 in zip(chrs, chrs[1:]):
        i1 = stoi[c1]
        i2 = stoi[c2]
        N[i1, i2] += 1

P = N.float()
P = P / P.sum(1, keepdim=True)

import matplotlib.pyplot as plt
%matplotlib inline
# plt.imshow(N)
fig = plt.figure(figsize=(16, 16))
plt.imshow(P, cmap='Blues')
for i in range(nchars):
    for j in range(nchars):
        chstr = itos[i] + itos[j]
        plt.text(j, i, chstr, ha="center", va="bottom", color='gray')
        plt.text(j, i, '%.1f' % (P[i, j].item()*100.0), ha="center", va="top", color='gray')
plt.axis('off')
fig.savefig('uk_digrams.png', bbox_inches='tight')