Great idea, but unfortunately I did not get results for some companies I’ve searched.

Thanks for trying it out, sorry if we did not find the companies you’ve searched for. What companies did you search? I’d like to investigate, where the problem comes from...

AFAIK SparkML pipeline is 'just' for text, whereas 'KeystoneML also presents a richer set of operators than those present in spark.ml including featurizers for images, text, and speech, and provides several example pipelines that reproduce state-of-the-art academic results on public data sets.'

Cool. Thx, especially for the link to the data dump. Nice stuff!