Examples of vector X and Y
Opened this issue · 8 comments
Thank you for you code. But sorry, I don't understand how to use it. Could you please explain how to set up data for training in vector X and Y? Could you please provide more details?
Hello, I have the same question. Have you got it?
@whuissyxa I have the same question too , have you got it?
It's on README. https://github.com/shiba24/learning2rank#usage
X is numpy array with the shape of (num_samples, num_features) and y is numpy array with the shape of (num_samples, ). y is the score which you would like to rank based on (e.g., Sales of the products, page view, etc).
if you have any further questions, feel free to post it here.
@jiasudemotuohe
no qid/ group id is required?
@shiba24 , I'm also interested in the answer to the question @Royisaboy is asking. How can we do "listwise" training without being able to specify lists? Are we supposed to call "fit" multiple times in a row for all the lists we have? Or is it meant to be trained on a single very long list? Thank you
我也有疑问，希望能给出示例，谢谢。
I have the same question. And I have read README.
Model.fit(X, y)
Here, X is numpy array with the shape of (num_samples, num_features) and y is numpy array with the shape of (num_samples, ). y is the score which you would like to rank based on (e.g., Sales of the products, page view, etc).
In my recommendation system, I got a recommended list. And I want to re-rank the list by adding more info. But I don't understand the data format of X, y in your code.
Can I directly set X with N_features, and y with only probabilities (such as 0/1), if the data is not divided into groups. Thank you.
@shiba24, I have a question : Each problem has several documents. Does X contain all the document features of a problem, or can it contain all the document features of all problems? That is to say, when you train, do you just train one problem at a time or do you train all problems together. What would the X form look like if we could train it together. Suppose I now have two questions, qid1 contains four documents, each with a feature, and qid2 contains three documents, can I type X and y like this? X = np. Array ([[[1], [2], [3], [4]], [[2], [3], [5]]]), y = np. Array ([,2,1,1 [2], [1 0]])