didw
August 2, 2022, 9:36am
1
Hello,
I’m trying to do bulk labeling referenced by below link.
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Bulk Labelling as a Notebook\n",
"\n",
"This notebook contains a convenient pattern to cluster and label new text data. The end-goal is to discover intents that might be used in a virtual assistant setting. This can be especially useful in an early stage and is part of the \"iterate on your data\"-mindset. Note that this tactic won't generate \"gold\" labels but it should generate something useful to help you get started. \n",
"\n",
"## Dependencies \n",
"\n",
"You'll need to install a few things to get started. \n",
"\n",
"- [whatlies](https://rasahq.github.io/whatlies/)\n",
"- [human-learn](https://koaning.github.io/human-learn/)\n",
"- [ipywidgets](https://ipywidgets.readthedocs.io/en/stable/)\n",
"\n",
"You can install all tools by running this line in an empty cell; \n",
"\n",
show original
But when I run this notebook I couldn’t see the chart on jupyter notebook.
Does any one can help me?
My environment is like this.
bokeh==2.4.3
human-learn==0.3.1
ipywidgets==7.7.1
jupyter-client==7.3.4
jupyter-core==4.11.1
jupyter-server==1.18.1
jupyterlab==3.4.4
jupyterlab-pygments==0.2.2
jupyterlab-server==2.15.0
jupyterlab-widgets==1.1.1
whatlies==0.7.0
nik202
August 2, 2022, 10:21am
2
@didw are you sure it’s related to Conversational AI or with Rasa? If so can you elaborate what is your use case?
didw
August 9, 2022, 6:01am
3
I retested the code above and found that it was a human-learn library problem.
What I’m going to do now is label a lot of un-labeled data.
If there is a library or tool to make bulk-labeling easier that you would recommend, please let me know.
