Every commit scored for change-risk against this repo's own history, so 'elevated' means elevated here rather than on some global curve.
Needs review
30 commits sit in this repo's top risk tercile, which is 33% of the 92scored. The cut is drawn against this codebase's own history rather than a global curve, so a quiet repo still fills its top band, and here it starts at 6.4 out of 10. What pushes a commit up is size and spread together: a large change confined to one area scores below a smaller one scattered across a dozen files.
Commit categories over time, read off the subject line. Fixes carry the accent because that is the series this chart exists to show.
Began docs-led, now leaning other.
Ranked by change-risk, highest first. Priority is a tercile of this repo's own distribution, so a quiet repo still fills its top band.
| # | Commit | Author | When | Lines | Risk | Top driver |
|---|---|---|---|---|---|---|
| 1 | 82c83e4eBoth Jupyters working | Will Macdonald | 6y ago | +11.4K -1.2K | 98%Elevated | more lines added than baseline |
| 2 | afcf3e97samples from dataset. files saved locally only | YarnSaw | 6y ago | +10.0K -0 | 98%Elevated | more lines added than baseline |
| 3 | 12c8aa87samples from dataset. files saved locally only | YarnSaw | 6y ago | +10.0K -0 | 98%Elevated | more lines added than baseline |
| 4 | eba0b893Graphing loss functions and training accuracy | Will Macdonald | 6y ago | +5.2K -83 | 96%Elevated | more lines added than baseline |
| 5 | d15d3fc4gitignore integration | Banee Ishaque K | 2y ago | +469 -0 | 95%Elevated | more lines added than baseline |
| 6 | 7658c098Refactoring | Will Macdonald | 6y ago | +1.2K -46 | 95%Elevated | more lines added than baseline |
| 7 | 28f2e7e3Running Jupyter with working GAN | Will Macdonald | 6y ago | +506 -38 | 93%Elevated | more lines added than baseline |
| 8 | 289c1de4updated the jupyter notebook for our dataset | Ryan | 6y ago | +273 -1 | 91%Elevated | more lines added than baseline |
| 9 | 8838e76cFixed error with adversarial examples and discriminator predictions | Will Macdonald | 6y ago | +368 -39 | 91%Elevated | more lines added than baseline |
| 10 | d91e4151"finished" files, work as needed for now | YarnSaw | 6y ago | +149 -19 | 90%Elevated | more lines added than baseline |
| 11 | e6c9debaCreating Jupyter Notebook as representation of the project Refactoring VisualizeData and LoadData | Will Macdonald | 6y ago | +180 -0 | 89%Elevated | more lines added than baseline |
| 12 | 06708690Addition of functions to generator and discriminator to output a prediction based on input examples and/or noise (for testing purposes and for future use in training) Update to load data and visualize data files | Will Macdonald | 6y ago | +158 -14 | 88%Elevated | more lines added than baseline |
| 13 | 780ec186Implementation of loss function graphing for the training of the GAN | Will Macdonald | 6y ago | +108 -43 | 86%Elevated | more lines added than baseline |
| 14 | 2aeafd2agrouping metadata and vectorized features into groups (malicious, benign, unlabeled). Create histograms representing group distribution. | Will Macdonald | 6y ago | +78 -24 | 86%Elevated | more lines added than baseline |
| 15 | 62914502updated to be able to use our dataset | Ryan | 6y ago | +119 -78 | 84%Elevated | more lines added than baseline |
| 16 | 8a7915c1Implementing Pie chart to track the the predictions throughout training of the models | Will Macdonald | 6y ago | +103 -32 | 82%Elevated | more lines added than baseline |
| 17 | 66d31226Printing and recording data while training Updated README.md | Will Macdonald | 6y ago | +108 -39 | 82%Elevated | more lines added than baseline |
| 18 | d45138ebCommenting the files created for load_data.py and visualized_data.py | Will Macdonald | 6y ago | +99 -10 | 82%Elevated | more lines added than baseline |
| 19 | 31c45f44visualize the malicious and benign predictions for the conference showcase | Will Macdonald | 6y ago | +150 -5.3K | 79%Elevated | more lines added than baseline |
| 20 | 92b7e5f4Everything from features.py in the ember dataset | Ryan | 6y ago | +68 -0 | 79%Elevated | more lines added than baseline |
| 21 | 06c5e973updated to make it work better | Ryan | 6y ago | +60 -32 | 79%Elevated | more lines added than baseline |
| 22 | e07c5b68Extract PE files from jumble of other files | Ryan | 6y ago | +60 -0 | 77%Elevated | more lines added than baseline |
| 23 | 213528ebupdating files | Ryan | 6y ago | +55 -8 | 76%Elevated | more lines added than baseline |
| 24 | adb7866fupdated to make easier to use | Ryan | 6y ago | +54 -60 | 74%Elevated | more lines added than baseline |
| 25 | 7e4ea428Create extractFeatures.py | YarnSaw | 6y ago | +51 -0 | 73%Elevated | more lines added than baseline |
| 26 | 15419679Improved upon data visualization | Will Macdonald | 6y ago | +46 -15 | 72%Elevated | more lines added than baseline |
| 27 | 94882a7eWork on training the GAN | Will Macdonald | 6y ago | +46 -7 | 71%Elevated | more lines added than baseline |
| 28 | adceb3e8Create the outline files required for GAN | Will Macdonald | 6y ago | +44 -0 | 71%Elevated | more lines added than baseline |
| 29 | 168d347fUpdate to Visualize Data and implementation of Load data | Will Macdonald | 6y ago | +44 -7 | 69%Elevated | more lines added than baseline |
| 30 | dd0aa2bfWorking on getting the GAN properly training | Will Macdonald | 6y ago | +43 -48 | 68%Elevated | more lines added than baseline |
| 31 | b5f45ab2Creating Jupyter Notebook as representation of the project Refactoring VisualizeData and LoadData | Will Macdonald | 6y ago | +36 -30 | 66%Typical | more lines added than baseline |
| 32 | f8119a76Gen Update | Cameron | 6y ago | +29 -1 | 66%Typical | more lines added than baseline |
| 33 | e22ef5a7udated | Ryan | 6y ago | +41 -8 | 64%Typical | more lines added than baseline |
| 34 | 1bf30da5Merged version, ember and custom dataset | Will Macdonald | 6y ago | +48 -23 | 64%Typical | more lines added than baseline |
| 35 | 82672f0fImplementing sampling to load_data functionality to only load a portion of the entire ember dataset | Will Macdonald | 6y ago | +27 -18 | 63%Typical | more lines added than baseline |
| 36 | 0d69b157Zip of benign files | Will Macdonald | 6y ago | +40 -372 | 61%Typical | more lines added than baseline |
| 37 | cd41c99fcreating virustotal api connection | YarnSaw | 6y ago | +25 -0 | 60%Typical | more lines added than baseline |
| 38 | 113089c2Committing in order to pull up to date version | Will Macdonald | 6y ago | +42 -383 | 59%Typical | more lines added than baseline |
| 39 | 48413927Made optimizer and chose a loss function | will1032 | 6y ago | +19 -18 | 58%Typical | more lines added than baseline |
| 40 | 68d212bcFixed because I now know how to format md files | Ryan | 6y ago | +20 -14 | 57%Typical | more lines added than baseline |
| 41 | c163ba8cInitial Training for the GAN is working | Will Macdonald | 6y ago | +25 -32 | 57%Typical | more lines added than baseline |
| 42 | fb8ef94crefactoring the training code | Will Macdonald | 6y ago | +23 -10 | 55%Typical | more lines added than baseline |
| 43 | e19c7ffdupdated | Ryan | 6y ago | +16 -29 | 54%Typical | more lines added than baseline |
| 44 | f2d0f94cAdd files via upload | Will Macdonald | 6y ago | +15 -0 | 53%Typical | more lines added than baseline |
| 45 | 2ec5294ddiscriminator model created with initial layer sizes | ConnorC84 | 6y ago | +13 -2 | 52%Typical | more lines added than baseline |
| 46 | 17821d86Update README.md | Will Macdonald | 6y ago | +12 -1 | 51%Typical | more focused than baseline |
| 47 | 06164a69Made optimizer and chose a loss function | will1032 | 6y ago | +11 -0 | 49%Typical | more focused than baseline |
| 48 | c51a8c7eAdding TrainGAN file to repo | Will Macdonald | 6y ago | +11 -0 | 48%Typical | more scattered than baseline |
| 49 | d6f2410badded more data for our dataset | Ryan | 6y ago | +15 -9 | 47%Typical | more lines added than baseline |
| 50 | c0b853c4benign .dat file added, fixed loadingdata files | Ryan | 6y ago | +14 -9 | 47%Typical | more lines added than baseline |
Two views of the same model: where the cuts fall, and what commit shape lands you above them.
Every scored commit, binned on the raw 0 to 10 score rather than the percentile. Percentile ranks are uniform by construction, so that axis has no shape to draw. The dashed lines are the tercile cuts behind each row's priority pill.
The 92 most recent commits, on their own recency sample rather than the feed above: that defaults to risk-sorted, so reusing it would plot only the top tercile and call it the spread. Big and scattered is what the model penalises. Click a dot to open it.
baneeishaque/Cyber_Security has 132 commits in its history from 9 contributors, the first of them Oct 9, 2019. No file in the repository changed in the last 90 days. Every commit is scored for change risk from its size, spread and the history of the files it touches.
