1from __future__ import annotations
2
3import os
4
5import daft
6from daft import col
7
8from daft.aihc.common.udf import aihc_udf
9from daft.aihc.functions.text.repeated_lines_calculator import RepeatedLinesCalculator
10
11if __name__ == "__main__":
12    if os.getenv("DAFT_RUNNER", "native") == "ray":
13        import ray
14        ray.init(dashboard_host="0.0.0.0", ignore_reinit_error=True)
15        daft.set_runner_ray()
16    daft.set_execution_config(actor_udf_ready_timeout=6000, min_cpu_per_task=0)
17
18    samples = {"text": ["line1\nline1\nline2\nline3", "abc\nabc\nabc", "unique line"]}
19    ds = daft.from_pydict(samples)
20    ds = ds.with_column(
21        "repeated_ratio",
22        aihc_udf(
23            RepeatedLinesCalculator,
24            num_cpus=1,
25            concurrency=4,
26            batch_size=1024,
27        )(col("text")),
28    )
29    ds.show()