Machine Learning

From Lingoport Wiki
Revision as of 20:14, 9 May 2018 by MaryH (talk | contribs) (Work Flow)
Jump to: navigation, search

Upcoming in Globalyzer 6.1

This new feature is under development and will be available starting with Globalyzer 6.1

Machine Learning Overview

Machine Learning prediction is a Globalyzer Workbench and Globalyzer Lite feature that helps users handle false positive issues. We suggest applying machine learning as a follow-up step to scanning with Rule Sets. It helps to determine which candidate issues using Rule Sets are indeed i18n issues.

Installation

Prerequisite: Java 8, Python 3.6.x and H2O.ai 3.x

1. Download Python version 3.6+ from website https://www.python.org/downloads/

2. Install python and add python to PATH environment variable

3. Go to this link http://h2o-release.s3.amazonaws.com/h2o/rel-wheeler/4/index.html and make sure you navigate to the "INSTALL IN PYTHON" tab as shown below.

 Install dependencies (prepending with `sudo` if needed):
 pip install requests
 pip install tabulate
 pip install scikit-learn
 pip install colorama
 pip install future

At the command line, copy and paste these commands one line at a time:

 pip uninstall h2o
 pip install http://h2o-release.s3.amazonaws.com/h2o/rel-wheeler/4/Python/h2o-3.16.0.4-py2.py3-none-any.whl

Success if response messages have "Successfully installed h2o-3.16.0.4"

Test1: Open System Command and type in "python -V", success if reply python version like "Python 3.6.2"

Test2: On the command line, go into python. In python:

> import h2o
> h2o.init()

This should complete without errors.

Work Flow

To use Machine Learning, first create a Globalyzer project with scans in the Globalyzer Workbench. At the Scan Results view, right mouse click on some issues that you determine are not real issues, and choose Mark prediction: FALSE (F) from the menu. Please mark the prediction of several issues as false before applying Machine Learning.

After marking the prediction of several issues as false, please select Machine Learning->GO!, and wait the predicting process to finish. Possible prediction values for each active issue are:

  • -: Issue has not been marked by a user and Machine Learning hasn't been invoked yet
  • T: Marked by a user (or detected by a rule) as a real issue to train Machine Learning
  • F: Marked by a user as a false issue to train Machine Learning
  • ML True: Machine learning prediction that the issue is a true issue, i.e. the issue should be refactored.
  • ML False: Machine Learning prediction that the issue is a false issue and can be ignored
  • ML NULL: Machine Learning cannot make a prediction, so must be considered a true issue

Note that filtered issues are predicted as Negative and used to train Machine Learning.

If you find that issues predicted as ML False are indeed issues, please right mouse click on the issue and select Mark prediction: TRUE(T); the next time you run GO! Machine Learning will learn your correction. If you are not satisfied with the prediction results, please continue marking more issues as F or T, and rerun Machine Learning.

Once you are satisfied with the prediction results, the issues with a prediction value of T, ML True, or ML NULL are the true issues that need to be addressed. The issues with a prediction value of F or ML False can be ignored. The suggested way to view the predicted active issues is to select Scan Views->All Predicted Active.

Tips:

  • View all issues, including filtered issues: One way to understand some of the Machine Learning results is to show all issues, including filtered ones. When an issue is predicted as ML False, it is easier to see why when it is surrounded by filtered issues with the same type of patterns.
  • Scan->Search in Scan Results:
    • Search on the Prediction column for issues which are ML False. From the Search panel, you can right click on the items to change the prediction with Globalyzer->Mark Prediction: TRUE (or FALSE).
    • Search on the Prediction column for issues which are ML NULL and ML True: This will help you see which issues are predicted as True Positives.
  • Sorting: In the Scan Results, a few sorts can be useful:
    • Sort on Issue: Lots of similar issues should be treated the same, either F or T. By sorting on issues, you may see a pattern to use as a category for Machine Learning
    • Sort on File: A sequence of lines may have patterns which can be used to categorize issues quickly. Use multi-selection to accelerate the T or F categorization.
    • Sort on Prediction: Instead of 'Searching', sorting on the Prediction columns can also help you see better some of the potential categories some issues fall into.

Machine Learning FAQ

1. If I change issues status, will machine learning work?

Yes, it will work. when you change issues status, the prediction of the issue will be changed by default. For example, if you move issues to ToDo status, the prediction will be marked as True, if you move issues to Ignore/Invalid status, the prediction will be marked as False. However, you could still mark a ToDo issue as False manually.

2. How does Machine Learning work?

We use h2o.ai to analyze the issue, the issue code line and the issue reason. Based on filtered issues and your marked false issues, Machine Learning will try to find similar issues with them and change the prediction as ML False for those similar issues. So machine learning prediction will be different per project per scan, you won't have an exactly same result every time, Machine Learning just gives the prediction. In addition, Machine Learning needs a category as input to learn, which means if you only mark one issue as False Positives, Machine Learning may not be able to find other issues similar with it.

3. What kind of machine learning algorithm dose Globalyzer use?

Globalyzer uses Gradient Boosting Machine (GBM) algorithm. Gradient Boosting Machine (for Regression and Classification) is a forward learning ensemble method. The guiding heuristic is that good predictive results can be obtained through increasingly refined approximations. H2O’s GBM sequentially builds regression trees on all the features of the dataset in a fully distributed way - each tree is built in parallel. More details: http://docs.h2o.ai/h2o/latest-stable/h2o-docs/data-science/gbm.html

4. What is H2O.ai? Do I have to install it?

H2O is an open source, in-memory, distributed, fast, and scalable machine learning and predictive analytics platform that allows you to build machine learning models on big data and provides easy productionalization of those models in an enterprise environment. And yes, to use machine learning function you have to install H2O.ai to your system. It's an in-memory platform so you don't need to worry about the security of your code and data.