0 ×

04_​Using_​Jupyter_​from_​KNIME_​to_​embed_​documents

Workflow

Using Jupyter from KNIME: embedding documentsThis workflow demonstrates the use of functionality defined in a Jupyter notebook from inside of KNIME. Afterbuilding a topic model for a set of documents, we use a Python function from a Jupyter notebook to perform t-SNEembedding of the documents into a 2D space. As a final step we do an interactive visualization to allow exploring theresults.The documents used are taken from the Fun with Tags post on the KNIME Blog: https://www.knime.com/blog/fun-with-tagsKNIME Extensions required: - Textprocessing - KNIME Python ScriptingThe Python Scripting integration needs to be configured to use a Python environment that has scikit-learn and jupyterinstalled. Load data and build topic model Visualize results t-SNE embedding Embed using tSNERead documents Python Script (1⇒1) Topic Extractor(Parallel LDA) Create CollectionColumn Color Manager ReferenceRow Filter Joiner Interactivevisualization Table Reader Pick 10 randomqueries Preprocessdocuments Using Jupyter from KNIME: embedding documentsThis workflow demonstrates the use of functionality defined in a Jupyter notebook from inside of KNIME. Afterbuilding a topic model for a set of documents, we use a Python function from a Jupyter notebook to perform t-SNEembedding of the documents into a 2D space. As a final step we do an interactive visualization to allow exploring theresults.The documents used are taken from the Fun with Tags post on the KNIME Blog: https://www.knime.com/blog/fun-with-tagsKNIME Extensions required: - Textprocessing - KNIME Python ScriptingThe Python Scripting integration needs to be configured to use a Python environment that has scikit-learn and jupyterinstalled. Load data and build topic model Visualize results t-SNE embedding Embed using tSNERead documentsPython Script (1⇒1) Topic Extractor(Parallel LDA) Create CollectionColumn Color Manager ReferenceRow Filter Joiner Interactivevisualization Table Reader Pick 10 randomqueries Preprocessdocuments

Download

Get this workflow from the following link: Download

Nodes

04_​Using_​Jupyter_​from_​KNIME_​to_​embed_​documents consists of the following 20 nodes(s):

Plugins

04_​Using_​Jupyter_​from_​KNIME_​to_​embed_​documents contains nodes provided by the following 4 plugin(s):