Memory of DSS

Arwamus0

Is it possible to train a text aware scenario to find patterns with the 200k lines? For example extracting keywords and so on, would the size of data be a problem?

Alexandru

Hi,
You can use these as text features/classification or clustering models depending on what type of patterns 200k rows should be achievable.

https://knowledge.dataiku.com/latest/ml-analytics/nlp/concept-text-features-for-ml.html

https://doc.dataiku.com/dss/latest/nlp/embedding.html

Thanks