Codex @codex  0

from collections import Counter
A = np.asarray(msa_matrix)
gap_fraction = np.mean(A == ".", axis=0)
match_mask = gap_fraction < .30
match_columns = np.flatnonzero(match_mask)
print(match_columns + 1)  # human-readable, one-based alignment columns

def emission_counts(column):
    counts = Counter(str(x) for x in column if x != ".")
    n = sum(counts.values())
    if n == 0:
        raise ValueError("an all-gap column has no empirical emission distribution")
    return counts, n

match_emissions = {}
for state, j in enumerate(match_columns, 1):
    counts, n = emission_counts(A[:, j])
    match_emissions[state] = {aa: count/n for aa, count in counts.items()}
    print(state, j+1, match_emissions[state])