GitModel
scattertext
GitModel | scattertext | |
---|---|---|
6 | 3 | |
60 | 2,203 | |
- | - | |
6.8 | 4.7 | |
11 months ago | 2 months ago | |
Python | Python | |
Apache License 2.0 | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
GitModel
-
[P] I built a chatbot that lets you talk to any Github repository
That's exactly what we've been exploring. Here's another approach I've seen to this problem of building a summary tree representation of a codebase: https://github.com/danielpatrickhug/GitModel/
-
[D] Modern Topic Modeling/Discovery
https://github.com/danielpatrickhug/GitModel/blob/main/src/system_prompts/format_system_prompts.py the basic components of the self instruction prompting are format_system_prompts which has the base prompt and extract_questions which just uses regex to extract the questions from the output.
- GITModel: decompose Git repositories and generate coherent topic trees
-
[P] GITModel: Dynamically generate high-quality hierarchical topic tree representations of GitHub repositories using customizable GNN message passing layers, chatgpt, and topic modeling.
Decompose Python libraries and generate Coherent hierarchical topic models of the repository. https://github.com/danielpatrickhug/GitModel
scattertext
-
Clustering of text - Where to start?
If what you want is to determine how similar two categories are, or to learn something about the structure or words that compose those categories, you might consider word shift graphs or Scattertext.
- [Data] Principali parole degli ultimi (circa) 200 post sul sub
-
Alternate approaches to TF-IDF?
Other suggestions: Take a look at Scattertext. Compare keywords to the problem of aspect extraction. I think an underutilized way to look at textual data when you have a single group of interest is the word-frequency-based odds ratio.
What are some alternatives?
textbeat - 🎹 plaintext music sequencer and midi shell, with vim playback and the powers of music theory 🥁
BERTopic - Leveraging BERT and c-TF-IDF to create easily interpretable topics.
HVM - A massively parallel, optimal functional runtime in Rust
KeyBERT - Minimal keyword extraction with BERT
clrs
stopwords-it - Italian stopwords collection
hummingbot - Open source software that helps you create and deploy high-frequency crypto trading bots
word_cloud - A little word cloud generator in Python
shifterator - Interpretable data visualizations for understanding how texts differ at the word level
lit - The Learning Interpretability Tool: Interactively analyze ML models to understand their behavior in an extensible and framework agnostic interface.
yake - Single-document unsupervised keyword extraction
dutch-word-embeddings - Dutch word embeddings, trained on a large collection of Dutch social media messages and news/blog/forum posts.