GoldenFlow overview

goldenflow transform messy_data.csv
goldenflow demo

import goldenflow

result = goldenflow.transform_file("messy_data.csv")
print(result.df)        # clean Polars DataFrame
print(result.manifest)  # audit trail

import { TransformEngine } from "goldenflow";

const result = new TransformEngine().transformDf([
  { name: "  JOHN  ", phone: "(555) 123-4567", email: "John@Example.COM" },
]);
console.log(result.rows[0]);
// { name: "JOHN", phone: "+15551234567", email: "john@example.com" }

import goldenflow
from goldenflow import GoldenFlowConfig, TransformSpec

config = GoldenFlowConfig(transforms=[
    TransformSpec(column="first_name", ops=["strip", "title_case"]),
    TransformSpec(column="last_name", ops=["strip", "title_case"]),
    TransformSpec(column="email", ops=["strip", "lowercase"]),
    TransformSpec(column="phone", ops=["strip", "phone_national"]),
])
result = goldenflow.transform_df(df, config=config)

result = goldenflow.transform({"phone": ["212-555-0100"]}, config=config)
result = goldenflow.transform("customers.parquet", config=config)  # pyarrow, no Polars
result = goldenflow.transform("customers.csv", config=None)        # zero-config, Polars-free

from goldenflow import SchemaMapper
import polars as pl

source = pl.DataFrame({"fname": ["John"], "lname": ["Smith"]})
target = pl.DataFrame({"first_name": [""], "last_name": [""]})

mapper = SchemaMapper()
for m in mapper.map(source, target):
    print(f"{m.source} → {m.target} ({m.confidence:.0%})")

from goldenflow.streaming import StreamProcessor

processor = StreamProcessor(config=config)
for result in processor.stream_file("large_data.csv", chunk_size=10_000):
    write_to_output(result.df)
print(f"Processed {processor.batches_processed} batches")

-- CLI: duckdb -unsigned   (or: SET allow_unsigned_extensions = true;)
LOAD 'goldenflow_duckdb.duckdb_extension';

SELECT
  goldenflow_email_normalize(email)     AS email,
  goldenflow_name_proper(name)          AS name,
  goldenflow_address_standardize(addr)  AS address
FROM read_parquet('s3://bucket/raw/*.parquet');