1from __future__ import annotations
2
3import os
4import daft
5import pandas as pd
6from daft import col
7
8from daft.aihc.common.udf import aihc_udf
9from daft.aihc.functions.text.chinese_text_converter import ChineseTextConverter
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 = {
19        "text": [
20            "這是一段純繁體中文測試句子，歡迎使用軟體開發工具。",
21            "使用 Python 進行資料處理，pip install 安裝套件非常方便。",
22            "这是简体，這是繁體，and this is English，三种文字混合测试。",
23            None,
24        ]
25    }
26
27    df = pd.DataFrame(samples)
28    ds = daft.from_pandas(df)
29
30    ds = ds.with_column(
31        "converted_text",
32        aihc_udf(
33            ChineseTextConverter,
34            construct_args={
35                "direction": "t2s",
36            },
37            num_gpus=0,
38            num_cpus=1,
39            batch_size=1,
40            concurrency=1,
41        )(col("text")),
42    )
43
44    ds.show()