spongebbob / tabular_automl_nni Goto Github PK
View Code? Open in Web Editor NEWPAKDD AutoML challenge 2nd Feature Engineering Part
Home Page: https://www.4paradigm.com/competition/pakdd2019
PAKDD AutoML challenge 2nd Feature Engineering Part
Home Page: https://www.4paradigm.com/competition/pakdd2019
Hi,
I am wondering if it is possible to also add hyperparameter tuning step with autoEF? Do you have suggestions how to do it?
I setup the environment with the file requirments.txt and run experiments with command provided in readme.md.
but the first trial failed and the dispatch log looks like
File "/Users/admin/Desktop/tabular_automl_NNI/./autofe_tuner.py", line 65, in generate_parameters sample_p = np.array(self.estimate_sample_prob) / np.sum(self.estimate_sample_prob) TypeError: unsupported operand type(s) for /: 'NoneType' and 'NoneType'
you give link to criteo example
https://labs.criteo.com/category/dataset/
but there are many data sets in this page
which one to use?
Thanks for your sharing.
I have this problem when trying to run the demo code and train.tiny.csv. The program failed at the first time. When I switched to other sample data like heart or haberman, sample problems happened.
(I'm using windows、lightgbm 2.3.1、nni 0.9.1)
Could anyone tell how to solve this problem. Thanks!
Here is the dispatcher.log:
[05/02/2020, 12:13:50 PM] INFO (nni.msg_dispatcher_base/MainThread) Start dispatcher
[05/02/2020, 12:14:05 PM] ERROR (nni.msg_dispatcher_base/Thread-1) unsupported operand type(s) for /: 'NoneType' and 'NoneType'
Traceback (most recent call last):
File "D:\Anaconda3\lib\site-packages\nni\msg_dispatcher_base.py", line 102, in command_queue_worker
self.process_command(command, data)
File "D:\Anaconda3\lib\site-packages\nni\msg_dispatcher_base.py", line 160, in process_command
command_handlerscommand
File "D:\Anaconda3\lib\site-packages\nni\msg_dispatcher.py", line 106, in handle_request_trial_jobs
params_list = self.tuner.generate_multiple_parameters(ids)
File "D:\Anaconda3\lib\site-packages\nni\tuner.py", line 52, in generate_multiple_parameters
res = self.generate_parameters(parameter_id, **kwargs)
File "D:\git\tabular_automl_NNI.\autofe_tuner.py", line 65, in generate_parameters
sample_p = np.array(self.estimate_sample_prob) / np.sum(self.estimate_sample_prob)
TypeError: unsupported operand type(s) for /: 'NoneType' and 'NoneType'
[05/02/2020, 12:14:09 PM] INFO (nni.msg_dispatcher_base/MainThread) Dispatcher exiting...
[05/02/2020, 12:14:11 PM] INFO (nni.msg_dispatcher_base/MainThread) Terminated by NNI manager
If set trialConcurrency to any number > 1, the program would crush.
If some feature name in dataset include "_" ( like A_B), it will cause error.
solution: just rename your feature.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 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. 📊📈🎉
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 ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.