Awesome

Please read our Documentation: The Origin of Bunka

Bunkatopics

Bunkatopics is a package designed for Data Cleaning, Topic Modeling Visualization and Frame Analysis. Its primary goal is to assist developers in gaining insights from unstructured data, potentially facilitating data cleaning and optimizing LLMs through fine-tuning processes. Bunkatopics is constructed using well-known libraries like sentence_transformers, langchain and transformers, enabling seamless integration into various environments.

Discover the different Use Case:

• Fine-Tuning: To achieve precise fine-tuning, it's crucial to exercise control over the data, filtering what is relevant and discarding what isn't. Bunka is a valuable tool for accomplishing this task.

• Content Overview: As an example, the Medium website offers a wealth of content across various categories such as Data Science, Technology, Programming, Poetry, Cryptocurrency, Machine Learning, Life, and more. While these categories facilitate exploration of data, they may not provide a granular overview. For instance, within the Technology category, what specific topics does Medium cover?

• Framing Analysis: Data can be analyzed in countless ways, contingent on your objectives and interests. We've developed a tool that enables you to visualize data by semantically customizing your own axes.

Discover different examples using our Google Colab Notebooks

Theme	Google Colab Link
Visual Topic Modeling with Bunka
Cleaning dataset for fine-tuning LLM using Bunka
Understanding a dataset using Frame Analysis with Bunka
Full Introduction to Topic Modeling, Data Cleaning and Frame Analysis with Bunka.

Installation via Pip

pip install bunkatopics

Installation via Git Clone

git clone https://github.com/charlesdedampierre/BunkaTopics.git
cd BunkaTopics
pip install -e .

Quick Start

Uploading Sample Data

To get started, let's upload a sample of Medium Articles into Bunkatopics:

from datasets import load_dataset
docs = load_dataset("bunkalab/medium-sample-technology")["train"]["title"] # 'docs' is a list of text [text1, text2, ..., textN]

Choose Your Embedding Model

Bunkatopics offers seamless integration with Huggingface's extensive collection of embedding models. You can select from a wide range of models, but be mindful of their size.

# Load Embedding model
from sentence_transformers import SentenceTransformer
embedding_model = SentenceTransformer(model_name_or_path="all-MiniLM-L6-v2")

# Load Projection Model
import umap
projection_model = umap.UMAP(
                n_components=2,
                random_state=42)

from bunkatopics import Bunka

bunka = Bunka(embedding_model=embedding_model, 
            projection_model=projection_model)  # the language is automatically detected, make sure the embedding model is adapted

# Fit Bunka to your text data
 bunka.fit(docs)

from sklearn.cluster import KMeans
clustering_model = KMeans(n_clusters=15)
>>> bunka.get_topics(name_length=5, custom_clustering_model=clustering_model)# Specify the number of terms to describe each topic

Topics are described by the most specific terms belonging to the cluster.

Visualize Your Topics

Finally, let's visualize the topics that Bunka has computed for your text data:

>>> bunka.visualize_topics(width=800, height=800, colorscale='delta')

Topic Modeling with GenAI Summarization of Topics

Explore the power of Generative AI for summarizing topics!

from langchain.llms import OpenAI

llm = OpenAI(openai_api_key = 'OPEN_AI_KEY')

Note: It is recommended to use an Instruct model ie a model that has been fine-tuned on a discussion task. If not, the results might be meaningless.

# Obtain clean topic names using Generative Model
bunka.get_clean_topic_name(llm=llm)

Check the top documents for every topic!

>>> bunka.df_top_docs_per_topic_

Finally, let's visualize again the topics. We can chose from different colorscales.

>>> bunka.visualize_topics(width=800, height=800)

YlGnBu	Portland

delta	Blues

We can now access the newly made topics

>>> bunka.df_topics_

Visualise Dimensions on topics

dataset = load_dataset("bunkalab/medium-sample-technology-tags")['train']
docs = list(dataset['title'])
ids = list(dataset['doc_id'])
tags = list(dataset['tags'])

metadata = {'tags':tags}

from bunkatopics import Bunka

bunka = Bunka()

# Fit Bunka to your text data
bunka.fit(docs=docs, ids=ids, metadata=metadata)
bunka.get_topics(n_clusters=10)
bunka.visualize_topics(color='tags', width=800, height=800) # Adjust the color

Manually Cleaning the topics

If you are not happy with the resulting topics, you can change them manually. Click on Apply changes when you are done. In the example, we changed the topic Cryptocurrency Impact to Cryptocurrency and Internet Discounts to Advertising.

>>> bunka.manually_clean_topics()

Removing Data based on topics for fine-tuning purposes

You have the flexibility to construct a customized dataset by excluding topics that do not align with your interests. For instance, in the provided example, we omitted topics associated with Advertising and High-Definition television, as these clusters primarily contain promotional content that we prefer not to include in our model's training data.

>>> bunka.clean_data_by_topics()

>>> bunka.df_cleaned_

Bourdieu Map

The Bourdieu map provides a 2-Dimensional unsupervised scale to visualize various texts. Each region on the map represents a distinct topic, characterized by its most specific terms. Clusters are formed, and their names are succinctly summarized using Generative AI.

The significance of this visualization lies in its ability to define axes, thereby creating continuums that reveal data distribution patterns. This concept draws inspiration from the work of the renowned French sociologist Bourdieu, who employed 2-Dimensional maps to project items and gain insights.

from langchain.llms import HuggingFaceHub

# Define the HuggingFaceHub instance with the repository ID and API token
llm = HuggingFaceHub(
    repo_id='mistralai/Mistral-7B-v0.1',
    huggingfacehub_api_token="HF_TOKEN"
)

## Bourdieu Fig
bourdieu_fig = bunka.visualize_bourdieu(
        llm=llm,
        x_left_words=["This is about business"],
        x_right_words=["This is about politics"],
        y_top_words=["this is about startups"],
        y_bottom_words=["This is about governments"],
        height=800,
        width=800,
        clustering=True,
        topic_n_clusters=10,
        density=False,
        convex_hull=True,
        radius_size=0.2,
        min_docs_per_cluster = 5, 
        label_size_ratio_clusters=80)

>>> bourdieu_fig.show()

positive/negative vs humans/machines	politics/business vs humans/machines

politics/business vs positive/negative	politics/business vs startups/governments

Saving and loading Bunka

bunka.save_bunka("bunka_dump")
...

from bunkatopics import Bunka
bunka = Bunka().load_bunka("bunka_dump")
>>> bunka.get_topics(n_clusters = 15)

Loading customed embeddings (Beta)

'''
ids = ['doc_1', 'doc_2'...., 'doc_n']
embeddings = [[0.05121125280857086,
  -0.03985324501991272,
  -0.05017390474677086,
  -0.03173152357339859,
  -0.07367539405822754,
  0.0331297293305397,
  -0.00685789855197072...]]

'''

pre_computed_embeddings = [{'doc_id': doc_id, 'embedding': embedding} for doc_id, embedding in zip(ids, embeddings)]
...

from bunkatopics import Bunka
bunka = Bunka()
bunka.fit(docs=docs, ids = ids, pre_computed_embeddings = pre_computed_embeddings)


from sklearn.cluster import KMeans
clustering_model = KMeans(n_clusters=15)
>>> bunka.get_topics(name_length=5, 
                    custom_clustering_model=clustering_model)# Specify the number of terms to describe each topic

Front-end (Beta)

This is a beta feature. First, git clone the repository

git clone https://github.com/charlesdedampierre/BunkaTopics.git
cd BunkaTopics
pip install -e .

cd web # got the web directory
npm install # install the needed React packages

from bunkatopics import Bunka

from sentence_transformers import SentenceTransformer
embedding_model = SentenceTransformer(model_name_or_path="all-MiniLM-L6-v2")

# Initialize Bunka with your chosen model
bunka = Bunka(embedding_model=embedding_model) 

# Fit Bunka to your text data
bunka.fit(docs)
bunka.get_topics(n_clusters=15, name_length=3) # Specify the number of terms to describe each topic

>>> bunka.start_server() # A serveur will open on your computer at http://localhost:3000/