convert_to_canfam_3.py

import pathlib
import csv
from collections import namedtuple

Marker = namedtuple('Marker', 'name, snp, chr, pos')

path = pathlib.Path('Data/PlinkFormat/Samples')

coord_file = 'Data/CanineHD_B.csv'


def get_coord_map(coord_file):
    coord_map = dict()
    with open(coord_file) as cf:
        csv_reader = csv.reader(cf, delimiter=',')

        col_names = []
        data_section = False

        for row in csv_reader:
            if row[0] == '[Assay]':
                data_section = True
                continue

            if data_section:
                if len(col_names) == 0:
                    col_names = row
                    continue

                if row[0] == '[Controls]':
                    data_section = False
                    break

                # Trying to be explicit, probably ends up obtuse
                row_dict = {
                    col_names[j]: row[j] for j in range(len(row))
                }

                coord_map[row_dict['Name']] = Marker(
                    name=row_dict['Name'],
                    snp=row_dict['SNP'],
                    chr=row_dict['Chr'],
                    pos=row_dict['MapInfo']
                )

    return coord_map



coord_map = get_coord_map(coord_file)
print(f"Got {len(coord_map)} markers from '{coord_file}'")



bim_cols = ['chr', 'name', 'idk', 'pos', 'a0', 'a1']

for f in path.glob('*.bim'):
    print(f)

    with open(f) as fp:
        csv_reader = csv.reader(fp, delimiter='\t')

        for row in csv_reader:

            # Trying to be explicit, probably ends up obtuse
            row_dict = {
                bim_cols[j]: row[j] for j in range(len(row))
            }

            try:
                coord_map[row_dict['name']]
            except KeyError:
                print(f"Oh drat... {row_dict['name']}")


#    break