Telecommunications

Data mapping

Entity

subscriber

Group

circle or region

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": "Abonne", "time": "Date Usage", "type": "Usage Type", "value": "Conso", "group": "Circle", "attrs": ["Plan"], "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("telco")
def usage_trend(entity, before, cut):   # receives only events recorded before the cutoff
    m1 = sum(e.value for e in before if e.at >= cut - timedelta(days=30))
    m2 = sum(e.value for e in before if cut - timedelta(days=60) <= e.at < cut - timedelta(days=30))
    return {"usage_ratio": (m1 + 1) / (m2 + 1)}

task = predict_event(ds, target="recharge", window_days=30, pack="telco")
print(task.status, task.report())     # "trained" only if the model outperformed the baseline on held-out entities
if task.status == "trained":
    print(task.score("9812345670"))  # probability with contributing factors

size = predict_value(ds, target="data", window_days=30, pack="telco")
print(size.status, size.report())

flags = rules.run(ds, [
    rules.repeat(1, type="complaint"),   # two complaints from one subscriber in a day
])
print(flags["summary"])

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