I use reuters dataset in Keras.
And I want to know the 46 topics' names.
How can I show topics of reuters dataset in Keras?
https://keras.io/datasets/#reuters-newswire-topics-classification
Associated mapping of topic labels as per original Reuters Dataset with the topic indexes in Keras version is:
['cocoa','grain','veg-oil','earn','acq','wheat','copper','housing','money-supply',
'coffee','sugar','trade','reserves','ship','cotton','carcass','crude','nat-gas',
'cpi','money-fx','interest','gnp','meal-feed','alum','oilseed','gold','tin',
'strategic-metal','livestock','retail','ipi','iron-steel','rubber','heat','jobs',
'lei','bop','zinc','orange','pet-chem','dlr','gas','silver','wpi','hog','lead']
To understand the approach of extracting the above mapping, please follow this thread comment.
来源：https://stackoverflow.com/questions/45138290/how-to-show-topics-of-reuters-dataset-in-keras