walker-database-client/data1.py

#!/usr/bin/env python3

from pandas import read_csv
from pprint import pprint

df = read_csv("./csv/1.csv")
pprint(list(enumerate(df.columns)))
cols = [
    ('chemical_db_id', 1),
    ('library', 2),
    ('name', 4),
    ('formula', 5),
    ('mass', 6),
    ('pubchem_cid', 7),
    ('pubmed_refcount', 8),
    ('standard_class', 9),
    ('inchikey', 11),
    ('inchikey14', 12),
    ('final_mz', 15),
    ('final_rt', 16),
    ('final_adduct', 17),
    ('adduct', 18),
    ('detected_adducts', 20),
    ('adduct_calc_mz', 21),
    ('msms_detected', 24),
    ('msms_purity', 26)
]
idxs = [x[1] for x in cols]

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']