-
Notifications
You must be signed in to change notification settings - Fork 219
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
some questions #4
Comments
Sorry for the late response,. Did you mean the data format? It's the field-wise format, in the form of FieldID:featureID:featureValue. A field is a group of features, such as gender, location, oppucation, etc. |
Thank you very much! |
after reading the article in detail . I also find some problem. can you explain me about how to preprocessing the Criteo Dataset when you do experiment. I want to run the mode CIN in Criteo Dataset , but I don't know how to preprocessing the datasets. Another question is the dataset in that program is ariticial ? Thank you! |
Criteo dataset is frequently used by research groups. I think there are no too much ways to preprocess the dataset, just transform the numerical values into categorical values (by log 2) and filter out some low frequent categorical values. You can leave an email address and I will send you our scripts. The sample dataset in github is a real-world dataset. |
Thanks ! Here is my email [email protected] |
Hi, I have the same problem now. would you email me the scripts ? Thanks! |
I also need the scripts, and the size of criteo dataset in your experience is 45mb? |
Since the criteo script seems to block a few readers, I have uploaded the script to the codebase. |
Happy Lantern Festival ! I also need the scripts and want to know the tensorflow 1.12.0 is OK? Thanks! |
Thank you very much! [email protected] |
Hi, I have the same problem now. would you email me the scripts ? Thanks! |
Hello, I want to know how the movielens data set is processed to meet the required format, thank you |
Can you explain the meaning of the dataset. I am a little confused
The text was updated successfully, but these errors were encountered: