From 1caa2d1d16babb43b346e3eebcf229367bcc47f5 Mon Sep 17 00:00:00 2001
From: Maarten Grootendorst <maartengrootendorst@gmail.com>
Date: Tue, 19 Jul 2022 12:37:18 +0200
Subject: [PATCH] Added BERTopic to Spacy Universe (#11159)

* Added BERTopic to Spacy Universe

* Fix no render of visualization
---
 website/meta/universe.json | 31 +++++++++++++++++++++++++++++++
 1 file changed, 31 insertions(+)

diff --git a/website/meta/universe.json b/website/meta/universe.json
index 29d436ec4..53cc53024 100644
--- a/website/meta/universe.json
+++ b/website/meta/universe.json
@@ -544,6 +544,37 @@
                 "website": "https://koaning.io"
             }
         },
+        {
+            "id": "bertopic",
+            "title": "BERTopic",
+            "slogan": "Leveraging BERT and c-TF-IDF to create easily interpretable topics.",
+            "description": "BERTopic is a topic modeling technique that leverages embedding models and c-TF-IDF to create dense clusters allowing for easily interpretable topics whilst keeping important words in the topic descriptions. BERTopic supports guided, (semi-) supervised, hierarchical, and dynamic topic modeling.",
+            "github": "maartengr/bertopic",
+            "pip": "bertopic",
+            "thumb": "https://i.imgur.com/Rx2LfBm.png",
+            "image": "https://raw.githubusercontent.com/MaartenGr/BERTopic/master/images/topic_visualization.gif",
+            "code_example": [
+                "import spacy",
+                "from bertopic import BERTopic",
+                "from sklearn.datasets import fetch_20newsgroups",
+                "",
+                "docs = fetch_20newsgroups(subset='all',  remove=('headers', 'footers', 'quotes'))['data']",
+                "nlp = spacy.load('en_core_web_md', exclude=['tagger', 'parser', 'ner', 'attribute_ruler', 'lemmatizer'])",
+                "",
+                "topic_model = BERTopic(embedding_model=nlp)",
+                "topics, probs = topic_model.fit_transform(docs)",
+                "",
+                "fig = topic_model.visualize_topics()",
+                "fig.show()"
+            ],
+            "category": ["visualizers", "training"],
+            "author": "Maarten Grootendorst",
+            "author_links": {
+                "twitter": "maartengr",
+                "github": "maartengr",
+                "website": "https://maartengrootendorst.com"
+            }
+        },
         {
             "id": "tokenwiser",
             "title": "tokenwiser",