search

asu-cactus / netsdb

A system that seamlessly integrates Big Data processing and machine learning model serving in distributed relational database
Apache License 2.0
15 stars 5 forks source link

add support for criteo #60

Closed hguan6 closed 2 years ago

jiazou-bigdata commented 2 years ago

@hguan6

Met an error when running this command: python data_processing.py -d criteo -n 10000000

tar: /home/ubuntu/netsdb/model-inference/decisionTree/experiments/dataset: Not found in archive tar: Exiting with failure status due to previous errors

Any suggestions?

hguan6 commented 2 years ago

@hguan6

Met an error when running this command: python data_processing.py -d criteo -n 10000000

tar: /home/ubuntu/netsdb/model-inference/decisionTree/experiments/dataset: Not found in archive tar: Exiting with failure status due to previous errors

Any suggestions?

Sorry, the data processing script has not been fully tested. I manually downloaded the dataset and extract a portion of them to train a model. Will make it work soon. Now the training and testing scripts work well.

hguan6 commented 2 years ago

@hguan6

Met an error when running this command: python data_processing.py -d criteo -n 10000000

tar: /home/ubuntu/netsdb/model-inference/decisionTree/experiments/dataset: Not found in archive tar: Exiting with failure status due to previous errors

Any suggestions?

Now the data_processing.py script should work. Note that the "-n" argument is not implemented in the current version.

I have a question concerning git commit. During development, I made many commits in order to push the changes to GitHub so that I can use the updated code in the agave environment. Shall I save the updated codes somewhere else, and delete the old branch and close this pull request, and then create a new branch and new PR?

hguan6 commented 2 years ago

Sorry, the data processing script has not been fully tested. I manually downloaded the dataset and extract a portion of them to train a model. Will make it work soon.

On Thu, Sep 8, 2022 at 3:46 PM Jia Zou @.***> wrote:

@hguan6 https://urldefense.com/v3/__https://github.com/hguan6__;!!IKRxdwAv5BmarQ!f0rRtEsy08M5P6utVrqJ27rOp8Vv0B3tyk-1BtvdAf-mLXfdKjiGmW8ne2aU-a-Mah6f_KhfxrAnWOveb31Yzdc$

Met an error when running this command: python data_processing.py -d criteo -n 10000000

tar: /home/ubuntu/netsdb/model-inference/decisionTree/experiments/dataset: Not found in archive tar: Exiting with failure status due to previous errors

Any suggestions?

— Reply to this email directly, view it on GitHub https://urldefense.com/v3/__https://github.com/asu-cactus/netsdb/pull/60*issuecomment-1241310823__;Iw!!IKRxdwAv5BmarQ!f0rRtEsy08M5P6utVrqJ27rOp8Vv0B3tyk-1BtvdAf-mLXfdKjiGmW8ne2aU-a-Mah6f_KhfxrAnWOveUz4vPKE$, or unsubscribe https://urldefense.com/v3/__https://github.com/notifications/unsubscribe-auth/AEX53CYABW4EAKOIIF36VYLV5JUDFANCNFSM6AAAAAAQHGQNYE__;!!IKRxdwAv5BmarQ!f0rRtEsy08M5P6utVrqJ27rOp8Vv0B3tyk-1BtvdAf-mLXfdKjiGmW8ne2aU-a-Mah6f_KhfxrAnWOverZVKiaQ$ . You are receiving this because you were mentioned.Message ID: @.***>

--

Hong Guan, MS

School of Computing and Augmented Intelligence

Arizona State University

hguan6 commented 2 years ago

This pull request has been merged to 41-decisiontree-gpu.