Accounting and tax compliance

Data mapping

Entity

client (tax identifier)

Group

jurisdiction

Profile

generic; configure time windows with verticals.register

Reference implementation

from datetime import datetime, timedelta
from vertiq import plugins, rules
from vertiq.mapping import Mapping, apply, repair
from vertiq.tasks import predict_event, predict_value

# rows: the source export as a list of dicts, e.g. list(csv.DictReader(open("export.csv")))
mapping = Mapping.parse({"entity": "GSTIN", "time": "Abgabedatum", "type": "Return Type", "value": "Tax Amount", "group": "Jurisdiction", "attrs": ["Status", "Filed By", "Due Date", "Filed On"], "date_format": "%Y%m%d"})
m, notes = repair(mapping, rows)      # validates column names, value types and date format against the rows
ds, problems = apply(m, rows)         # rows that fail to load are reported, not imputed

@plugins.feature("tax")
def late_filings(entity, before, cut):   # receives only events recorded before the cutoff
    return {"late_before": sum(1 for e in before if e.attrs.get("Status") == "late")}

task = predict_event(ds, target="GSTR-3B", window_days=30, pack="tax")
print(task.status, task.report())     # "trained" only if the model outperformed the baseline on held-out entities
if task.status == "trained":
    print(task.score("29ABCDE1234F1Z5"))  # probability with contributing factors

flags = rules.run(ds, [
    rules.overdue("Due Date", "Filed On", tolerance_days=0),   # returns filed after the due date
])
print(flags["summary"])

This code is executed by the test suite (tests/test_guides.py) against generated records with these column names.