Alan Lee

可以尝试使用 GitHub 上最新版安装： 1. `pip install https://github.com/lancopku/pkuseg-python/archive/master.zip`； 2. 在 [release](https://github.com/lancopku/pkuseg-python/releases) 处下载你想要的模型，比如 [default_v2](https://github.com/lancopku/pkuseg-python/releases/download/v0.0.25/default_v2.zip)； 3. 下载下来后解压放到某目录下； 4. 代码中这样使用： ```python import pkuseg seg = pkuseg.pkuseg('某目录/default_v2') print(seg.cut('我爱北京天安门')) ``` 我用此方法成功了。

> I wanted to tell you that you're crazy, but apparently not > > ``` > >>> from stanza.models.common.bert_embedding import load_bert > >>> m, t = load_bert("cahya/roberta-base-indonesian-1.5G") > >>> m2,...

> Alternatively, if you can share your NER conversion code, that would also go a long way towards working it out. I take it you were using this Roberta model?...

This seems to be a time conversion issue, using UTC time under the default view, while using local time (GMT+8 in my case) when manually selecting the date range.

> > upgrade gcc version from 4.8.5 to 9.5.0 fix this issue, but met another issue " AttributeError : module 'math' has not attribute prod " > > Great. The...

> > > > upgrade gcc version from 4.8.5 to 9.5.0 fix this issue, but met another issue " AttributeError : module 'math' has not attribute prod " > >...

> How did you install the python you are trying to profile ? Sorry for late reply. I install the python and pip by: ``` sudo apt install python3.8 sudo...

I guess the stopwords-removing step is done in the last steps, i.e.: 1. split words 2. extract candidates 3. score, dedup and **remove stopwords**.

Looking forward to this feature.

Agree. I have to use `except BaseException as e` to catch the error. Really confused. What's the design purpose?