dotnet / dotnet/machinelearning-modelbuilder
Request: Text Clustering
- Vorherrschende Sprache
- Dockerfile
- Sterne
- 285
- Forks
- 66
- PR-Merge-Kennzahlen
- Keine gemergten PRs in 30 T.
Beschreibung
**Is your feature request related to a problem? Please describe.**
Sometimes we have a set of uncategorized texts. Either we do not care about categorization models, or we want to create a model to help categorization. Examples could be: products, credit card transaction, climate measurements, customer feedback etc.
In this request I am mainly talking about text based clustering.
**Describe the solution you'd like**
I would like to use Model Builder to cluster a set of texts, such as customer feedback.
**Describe alternatives you've considered**
Manually create the clustering code from samples. Perhaps, Model Builder could also help only with downloading sample code, or copy-paste snippets? Not ideal, but better than needing to search online.
**Additional context**
In contrast to other scenarios, this scenario would ideally also return the final clusters for each item in the input file.
This file could have multiple purposes, but considering building models, I think it is first step towards classification model.
However, if this were the only use of it, then users should use other data analysis tools. I believe the clusteration model itself will be useful for many users. We do not always need, or even can, categorize items.
Beitragsleitfaden
Für dieses Repository ist kein Beitragsleitfaden indexiert
Bewertung
Dieses Issue wurde noch nicht bewertet.