Comments (12)
@marco-c I will try this up. :)
from bugbug.
@pradeepgangwar cool, thanks! I would do one PR at a time, one per model. When you make the PR, please write down both the results before adding the features and the results after adding the features.
from bugbug.
@marco-c can i take this issue? I am contributing for the first time.
from bugbug.
Sure. As described at https://github.com/mozilla/bugbug#contributing, any issue that is open and has no PR linked to it can be considered unassigned.
from bugbug.
Hi @marco-c ,i,ve made some changes to use these features, how do i know if these features are being used now and i,ve done things correctly?
from bugbug.
Train the model to which you have added the feature before and after adding the feature, and see if there's any change in the metrics.
from bugbug.
Hey @marco-c , i checked the change in metrics for different models,and found significant change in only bug model.can i make PR?
from bugbug.
Sure, but please attach here one text file per model showing your results before/after.
from bugbug.
bug_model.txt
This is for bugmodel,like this for all?
uplift_model.txt
For Uplift.
from bugbug.
Yes, thanks!
from bugbug.
qaneeded_model.txt
Here is the 'qaneeded' model, no changes at all. I think the rest of the models don't need to use these features and some are already using. So should i only implement this for 'bug' model?
And Thank you @marco-c :)
from bugbug.
OK, sounds good!
from bugbug.
Related Issues (20)
- Refactor the logic in the `bug_to_types` function and extract it from the `bugtype` model file
- [model:performance] Experiment with including bugs with their performance impact is `none` in the training set only
- Integrate with Weights & Biases
- Create a pipeline to retrieve crash reports from BigQuery and make them available to the model training tasks
- Create a model to predict actionable crashes
- [model:stepstoreproduce] Training task exit with status code 137
- [model:regressor] AttributeError: 'IsotonicRegressionCalibrator' object has no attribute 'n_features_in_' HOT 2
- Refactor the way that we apply `CalibratedClassifierCV` to the models
- [model:performance] Experiment with including bugs from performance components in the training set only
- Add more detailed guidance and recommendations to CONTRIBUTING.md
- Remove duplicate imports for `dateutil.parser`
- [model:bugtype] The `Keywords` feature accepts keywords but is given keyword prefixes
- [model:performance] Add the model to `http_service` and `data_pipeline`
- [model:accessibility] Add the model to `http_service` and `data_pipeline`
- UnboundLocalError: local variable 'median_fix_time_text' referenced before assignment when generating quality report
- [model:bugtype] ValueError: y should be a 1d array, got an array of shape (198635, 5) instead.
- [model:bugtype] ValueError: The truth value of an array with more than one element is ambiguous. Use a.any() or a.all() HOT 1
- Show the number of not classified instances for multi-label models HOT 1
- Include certain comment fields which will help the model to tag spam comments
- OOM Error when running data pipeline tasks to train `accessibility` and `performance` bug models
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from bugbug.