wm-semeru / securereqnet Goto Github PK

Configure TFX Pipeline StatisticsGen

Note: if it is decided to go with TFRecords, close this issue

Document StatisticsGen and SchemaGen in pipeline.py

Hi, danaderp. Many thanks for your work. I have a question, in the notebook "alpha_securereqnet
.ipynb", there is a line from vectorize_sentence import Embeddings, but I cannot figure out where to import this module. Is it possible that you did not upload this file? Thanks for your help! Best regards!

Current Flask backend is a development server - deploy a production server on an open port to allow querying from anywhere

Put a function to train a model in either preprocessing or the model files

Create ipynb's for preprocessing and model evaluation capable of loading and exporting data. Put all versions of securereqnet models into one file

Determine and implement tests for Alpha SecureReqNet to verify proper pretrained accuracy and that training works properly

Specifically the Python files in the utils folder, these should be exportable with nbdev

Configure TFX Pipeline Evaluator

Set up a Tensorflow Extended endpoint for internal use and as an API bridge to other team(s)

Determine and provide test cases for Processing_Dataset class to verify functionality

Configure TFX Pipeline ExampleGen

Serve Alpha SecureReqNet on SEMERU servers

Create unit tests for ExampleGen, verify TFRecords are being create properly

02_Statistical Test and 03_Clustering seem to be tests of code necessary for running SecureReqNet, that has now been used elsewhere. Whether these have any use should be verified using coverage tests or by asking the project manager

Pushes blessed models to TFX serving

As the project is migrated to nbdev, continually update index.ipynb with documentation and code examples

The file that contains model architectures should implement functions to allow users to load the prebuilt models

Configure TFX Pipeline Trainer

This is a last step, to be done at the end of development. While working on a development fork it is necessary to change the path to the library documents. This needs to be undone before or after merging back to the main project in order for the documents to generate properly.

As functionality is added to securereqnet in each sprint the project diagram should reflect the additions

The description, project name and keyword section need to be uncommented. The official description should be added and any keywords for nbdev decided on. The project will need to be named in the way that it will be named for package installation. index.ipynb specifically will need this information to compile correctly.

Determine and implement tests for SecureReqNet Shallow to verify proper pretrained accuracy and that training works properly

Configure TFX Pipeline SchemaGen

The ExampleGen component of the TFX pipeline officially supports few data formats for ingestion. As we have decided to go with CSV, this requires a conversion of the contents of augmented_dataset/ from .txt to .csv.

An initial conversion has been made in augmented_dataset_csv/, but beam_dag_runner.py rejects the files which appear to be of the correct format.

It would also be conducive to merge the rows in ground_truth.csv with their respective issues, but this crashes my machine for an unknown reason.

Determine and provide tests for the Dynamic_Dataset class to verify functionality

The read_data's method get_test_and_training doesn't correctly get the data. It needs to be modified to look into the zipped data file. The path from root to the content folder is ./data/augmented_dataset_augmented_dataset.zip

Create test suite for Flask endpoint

Determine and implement tests for Alex-SecureReqNet to verify proper pretrained accuracy and that training works properly

Before moving 08_alpha_securereqnet into nbdev it needs changes to allow it to run with the current code architecture. This issue relies on the read_data issue to be completed first

Configure checks and automate build/testing

Create unit tests for the Transform Component

Create test suite to verify sentences are being vectorized properly

Configure TFX Pipeline InfraValidator

Add testing for the unsupervised word vectorizer using the 02_ Statistical-test [bootstrapping].ipynb file that David recommended

The CS Department is having trouble opening up ports. Work with Team 1 to set up a reverse proxy on port 8080 to redirect to their services and ours.

Integrate shap visualization library into current evaluation suite

Create an initial Flask backend prototype once port forwarding is complete. Prototype endpoints will mirror the input of the TFX Serving models. Output will be translated to True/False. Once Transform is complete.

Vastly speed up preprocessing/training by utilizing the multi-threading functionality of python/tensorflow. Make this optional in case the user lacks the necessary computing resources.

Highlight components crucial to integrating SecureReqNet with a TFX pipeline.

Refer: https://www.tensorflow.org/tfx/guide

Determine and implement tests for SecureReqNet Deep to verify proper pretrained accuracy and that training works properly