walker-database-client/data2.py

#!/usr/bin/env python3

from pandas import read_csv
from pprint import pprint

df = read_csv("./csv/2.csv")
pprint(list(enumerate(df.columns)))

cols = [
    ('chemical_db_id', 1),
    ('library', 2),
    ('name', 4),
    ('formula', 6),
    ('mass', 7),
    ('pubchem_cid', 10),
    ('pubmed_refcount', 8),
    ('standard_class', 11),
    ('inchikey', 13),
    ('inchikey14', 14),
    ('final_mz', 17),
    ('final_rt', 18),
    ('final_adduct', 19),
    ('adduct', 20),
    ('detected_adducts', 22),
    ('adduct_calc_mz', 23),
    ('msms_detected', 26),
    ('msms_purity', 28)
]

data = [{x[0]: row[x[1]] for x in cols} for row in df.to_dict('tight')['data']]
for x in data:
    if x['msms_detected'] == 'No':
        del x['msms_detected']