BrianMiner

Errors Training on Large Dataset : LightGBM

13

Im trying to fit a classifier with LightGBM on a large dataset. There are about 900,000,000 rows and 40 columns, 7 of which are integers being treated as categorical. -...

Fantastic videos!! One request if that is ok - I would love to see the following topics: 1) How to use data loader and fit a model where the data...

Question - negative sampling

6

Am I correct that each epoch the negative examples can change and that there is no safeguard that a negative example is not actually a positive example for that user?

Retrieving a csv file in S3 -

2

I am able to access my buckets as ```R library("aws.s3") bucketlist() ``` I have a csv file in a bucket nested in folders. When I try to read in the...

Question: Programmatically creating splines and applying knots to new data

1

I have found that I can create a spline on training data and then apply to test data like this: #create x1= dmatrix("cr(x, df=3) - 1", {"x":TRAIN_DATA.VARIABLE.values}) #apply xx1=build_design_matrices([x1.design_info], {"x":TEST_DATA.VARIABLE.values...

Hello. Thank you for this great lib and all the learning here! I am wondering if anyone has experienced the following error when trying to distribute TF Recommenders with Horovod....

Question on Conclusion of this ROI Notebook

1

This is a great notebook, enjoyed reading it. I do have one question that is really bugging me. It is established that creating an auxiliary variable of revenue divided by...

I am curious is anyone out here has successfully run a basic two tower retrieval model distributing using Horovod or any other method? I am seeing consistently poor results training...

How to add basic priors from uplift experiments?

6

Thank you for just a wonderful library! Really amazing progress! I wanted to make sure that the approach to using information from historical experiments to alter priors is correct /...