search

BoChengHuang / Bluemix_RR_Nodejs

Bluemix API of Retrieve and rank in Node.js
0 stars 0 forks source link

how to create ranker #2

Open sridhar-natuva opened 8 years ago

sridhar-natuva commented 8 years ago

what is answer.csv file. what is training.csv file.. what is the ranker_meta.json files

and what i data i need to add into these files?

BoChengHuang commented 8 years ago

Just like machine learning, you should train Watson at first, so you need training data, in this tutorial it's csv file By the way, RR needs pool to search something, in this tutorial it's cranfield-data.json.

You should read carefully this DOC, then you will grasp the point.

sridhar-natuva commented 8 years ago

you have added documents(to cluster) from cranfield-data.json right? and

what is "184","3","29","3","31","3","12","2","51","2","102","2","13","1","14","1","15","1","57","3","378","3","859","3","185","2","30","2","37","2","52","1","142","1","195","1","875","3","56","2","66","2","95","2","462","1","497","2","858","2","876","2","879","2","880","2","486","0"

this numbers implies in CSV file?

BoChengHuang commented 8 years ago

format: "Question", {"doc_id": "rating"} (a dictionary which is mapping to json document and length is not fixed.)

in your example, "what's the weather" imply that doc_id:184 get 3 point and doc_id:29 get 3 point.