def enrich_with_geo(row): # Assume get_geo is a fast lookup function row["country"] = get_geo(row["ip"]) return row
enrich = lambda src: src.map(enrich_with_geo) Now enrich can be inserted anywhere in a pipeline: juq470
def safe_int(val): return int(val)
def capitalize_name(row): row["name"] = row["name"].title() return row def enrich_with_geo(row): # Assume get_geo is a fast
from juq470 import pipeline, read_csv
(pipeline() .source(read_csv("visits.csv")) .pipe(enrich) .filter(lambda r: r["country"] == "US") .sink(write_jsonl("us_visits.jsonl")) ).run() juq470 provides a catch operator to isolate faulty rows without stopping the whole pipeline: row): return acc + row["sale_amount"]
def sum_sales(acc, row): return acc + row["sale_amount"]