model.transmat_ = [[0.67, 0.13, 0.2], [0, 0.5, 0.5], [0, 0, 1]]
'''
startprob_:
V:
D:
J:
trasmat_:
from each row, row become column (the probability of row become column, each row sum to 1, not column)
'''
model.fit(X, length)
emission = model.emissionprob_
model.n_features
model.transmat_
model.startprob_
model.get_stationary_distribution()
# let's test
train_score = []
for i in cdr3_train_index:
test = string2matrix_plain(cdr3[i]).astype(np.int)
score = model.score(test)
train_score.append(score)
train_score = np.array(train_score)
test_score = []
for i in cdr3_test_index:
test = string2matrix_plain(cdr3[i]).astype(np.int)
score = model.score(test)
test_score.append(score)
test_score = np.array(test_score)
