Yes. You can apply HashingTF on your input stream and then use
StreamingKMeans for training and prediction. -Xiangrui
On Mon, Jun 8, 2015 at 11:05 AM, Ruslan Dautkhanov wrote:
> Hello,
>
> https://spark.apache.org/docs/latest/mllib-feature-extraction.html
> would Feature Extraction and Transforma
Hello,
https://spark.apache.org/docs/latest/mllib-feature-extraction.html
would Feature Extraction and Transformation work in a streaming context?
Wanted to extract text features, build K-means clusters for streaming
context
to detect anomalies on a continuous text stream.
Would it be possible?
