liyaooi / fetch Goto Github PK
View Code? Open in Web Editor NEWAn automated feature engineering framework 'FETCH' accepted in ICLR 2023.
Home Page: https://openreview.net/forum?id=688hNNMigVX
An automated feature engineering framework 'FETCH' accepted in ICLR 2023.
Home Page: https://openreview.net/forum?id=688hNNMigVX
Can I ask a favor?
The code occurs the error : FETCH-main\feature_engineer\attention_searching\training_ops.py", line 12, in
from models import model_fuctions
ImportError: cannot import name 'model_fuctions' from 'models' (unknown location)
and I don't find the "model_fuctions" file from the folder 'models'
Hello,
I am confused about the following code. I wonder what the meaning of //8
, //4
is and how they are specified to these values.
arithmetic = OPS["arithmetic"]
value_convert_c = OPS["value_convert"] * max(1, n_features_c // 8) + max(1, n_features_c // 4) * OPS["special_ops"]
special_ops = max(1, (n_features_c + n_features_d) // 12) * OPS["special_ops"]
And another problem is that a fully connected network containing an input layer and dense layer, It changes the dimension of a variable-length feature vector to a fixed length. It seems that you transpose the tabular data and regard the features(e.g., A, B, C, D)
as the batch dimension and regard the samples as the feature dimension, so that the dimension of the input layer is equal to the num of the data.
self.reduction_dimension = ReductionDimension(data_nums, d_model)
If so, I am confused about the meanings of the attention layer, one sample attend to another sample? And how can I choose one variable (e.g., A)
to conduct an action (e.g., +B)
as (A, B)
are even not in the same batch?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.