great_tables_formatting_question

import random
import pandas
import string

import great_tables
from great_tables import GT


aa_list = ["A","C","D","E","F","G","H","I","K","L","M","N","P","R","S","T","V","W","Y"]
def create_random_aa_seq(size=200):
    aa_seq = []
    for i in range(size):
        aa_seq.append(random.choice(aa_list))
    return "".join(aa_seq)

def mutate_sequence_randomly(input_seq, num_pos = 10):
    positions_to_mutate = list(range(len(input_seq)))
    output_seq = list(input_seq)
    for i in range(num_pos):
        pos = random.choice(positions_to_mutate)
        output_seq[pos] = random.choice(aa_list)
    return "".join(output_seq)

def create_dummy_pat_ids():
    random_choice = range(1,9,1)
    random_num = []
    for i in range(8):
        random_num.append(str(random.choice(random_choice)))
    suffix = "".join(random_num)
    return f"US{suffix}"

def write_alignment_string_mkdown(seq_top , seq_bot):
    ref_id = create_mock_id()
    #outstring = f"{ref_id:>30}:\t{seq_top}\n{" "*30}:{seq_bot.lower()}\n{create_mock_id():>30}:\t{seq_bot}"
    outstring = f"""
    | {ref_id} | {seq_top} |
    |---|---|
    | {create_mock_id()} | {seq_bot} |
    """
    return outstring

def create_mock_id(max_len = 10):
    return ''.join(random.choices(string.ascii_uppercase + string.digits, k=max_len))

def create_dummy_dataframe_mkdown(num_elements = 100):
    pat_id = []
    seq_top = create_random_aa_seq(150)
    seq_bot = []
    ali = []
    for i in range(num_elements):
        pat_id.append(create_dummy_pat_ids())
        seq_bottom_new = mutate_sequence_randomly(seq_top)
        seq_bot.append(seq_bottom_new)
        ali.append(write_alignment_string_mkdown(seq_top, seq_bottom_new))
    data ={"pat_id": pat_id, "seq_bot":seq_bot , "Alignment": ali}
    return pandas.DataFrame(data)

df_mkdown = create_dummy_dataframe_mkdown()

gt_mkdown = GT(df_mkdown)
gt_mkdown.cols_width(cases={"Alignment":"3000px"}).fmt_markdown(columns="Alignment")
gt_mkdown.show()