Matthew Gaughan
|
b7c2c9fcd6
|
unifying current data and some repo cleaning
|
2025-09-29 14:10:39 -07:00 |
|
Matthew Gaughan
|
acd8964e73
|
preliminary EDA on the PCA analysis
|
2025-09-25 14:09:39 -07:00 |
|
mgaughan
|
b21ecb02c3
|
running PCA on subcomment values, adding new plot for closed_relevance
|
2025-09-25 10:11:47 -05:00 |
|
mgaughan
|
e29d4bf59c
|
cleaning working directory and re-running PCA with final neurobiber vectors
|
2025-09-25 09:48:23 -05:00 |
|
mgaughan
|
9d1359af36
|
updating biberplus and olmo_batched results
|
2025-09-25 09:20:40 -05:00 |
|
mgaughan
|
265b930578
|
updating library to account for re-running PCA
|
2025-09-23 16:41:32 -05:00 |
|
mgaughan
|
032975c4f0
|
updating to collect new batch job labels
|
2025-09-23 15:09:45 -05:00 |
|
mgaughan
|
b4f0c8f885
|
trying to sample the human label rows again
|
2025-09-22 20:34:31 -05:00 |
|
mgaughan
|
bcfa688e11
|
olmo batched for getting the title in there too, i think
|
2025-09-22 19:21:15 -05:00 |
|
Matthew Gaughan
|
e2413ed955
|
update to gerrit metadata extraction regex
|
2025-09-16 11:37:46 -07:00 |
|
mgaughan
|
bb67fea96b
|
hopefully last update to human sampling
|
2025-09-16 12:16:10 -05:00 |
|
mgaughan
|
89969daab5
|
updating labeling sample to be, uh, correct
|
2025-09-16 11:43:28 -05:00 |
|
mgaughan
|
d83022f184
|
sampled comments for human labeling
|
2025-09-16 11:22:45 -05:00 |
|
mgaughan
|
f68372572f
|
updating some scripts
|
2025-09-14 11:14:49 -05:00 |
|
Matthew Gaughan
|
f9c12bb445
|
shelving some of the merge work for now
|
2025-09-14 09:11:33 -07:00 |
|
Matthew Gaughan
|
77fc3ec541
|
preparing DSL modeling, looking at OLMO category data
|
2025-09-07 13:21:45 -07:00 |
|
mgaughan
|
99c702fe20
|
adding batched OLMO results
|
2025-09-07 11:11:00 -05:00 |
|
Matthew Gaughan
|
6de62f2447
|
some neurobiber PCA analysis
|
2025-09-05 14:59:07 -07:00 |
|
mgaughan
|
a96fd6db2f
|
updates and re-running the batched olmo categorization
|
2025-09-05 13:43:00 -05:00 |
|
mgaughan
|
f2afb7c981
|
should be updated and refined pca analysis
|
2025-09-04 15:47:11 -05:00 |
|
mgaughan
|
a770d9c668
|
looking at kpca
|
2025-09-04 14:30:34 -05:00 |
|
mgaughan
|
5d4df28f94
|
backing up the morning' before taking a few meetings
|
2025-09-04 11:21:07 -05:00 |
|
mgaughan
|
6a5f07872d
|
looking at subcomment authorship
|
2025-09-04 11:13:31 -05:00 |
|
mgaughan
|
0e569ac714
|
comment_type PCA
|
2025-09-04 10:57:11 -05:00 |
|
mgaughan
|
5be22d3bfb
|
looking at ticket status
|
2025-09-04 10:46:33 -05:00 |
|
mgaughan
|
68c95cdb8a
|
trying to look for the pca, with more specificity
|
2025-09-04 10:37:57 -05:00 |
|
mgaughan
|
ccf434db38
|
looking for new phase pca
|
2025-09-04 10:25:00 -05:00 |
|
mgaughan
|
809e858bbf
|
updating with new pca results
|
2025-09-04 10:12:34 -05:00 |
|
mgaughan
|
a3c1a48dc7
|
trying to run olmo cat distributed, also running kernelPCA.
|
2025-09-04 09:35:41 -05:00 |
|
mgaughan
|
a36226eab9
|
trying to look at the pca_plot 3
|
2025-09-02 16:04:06 -05:00 |
|
mgaughan
|
dc23065cc8
|
trying to look at the pca_plot 2
|
2025-09-02 15:55:27 -05:00 |
|
mgaughan
|
b8c12f987b
|
trying to look at the pca_plot 1
|
2025-09-02 15:50:47 -05:00 |
|
mgaughan
|
d97b6e141c
|
trying to look at the pca_plot 0
|
2025-09-02 15:37:07 -05:00 |
|
mgaughan
|
89105b7660
|
first pass at implementing pca for the style vectors
|
2025-09-02 15:30:50 -05:00 |
|
Matthew Gaughan
|
b714e8dedb
|
updates to new script, I guess
|
2025-09-02 12:32:41 -07:00 |
|
mgaughan
|
2d396ceb26
|
scaffolding out some work TODO on getting the olmo categories to be sentence-level
|
2025-09-02 12:48:11 -05:00 |
|
mgaughan
|
53775c51db
|
removing stale todo list
|
2025-09-02 12:37:24 -05:00 |
|
Matthew Gaughan
|
1c709f9a69
|
updating with gerrit information now
|
2025-08-07 19:03:20 -07:00 |
|
Matthew Gaughan
|
41de0cbc7a
|
drop the labels from the FOSSY closed by plot
|
2025-07-31 21:51:51 -07:00 |
|
Matthew Gaughan
|
7232f095e0
|
update to FOSSY tasks resolved plot
|
2025-07-31 21:49:32 -07:00 |
|
Matthew Gaughan
|
34c376dbc3
|
FOSSY resolution share
|
2025-07-31 21:47:24 -07:00 |
|
Matthew Gaughan
|
5239a8458a
|
adding renewed FOSSY heatmap
|
2025-07-31 18:30:23 -07:00 |
|
Matthew Gaughan
|
822103ec3a
|
new task plot
|
2025-07-29 14:48:52 -07:00 |
|
Matthew Gaughan
|
b624109f8d
|
updating with new heatmap for FOSSY presentation
|
2025-07-29 14:25:19 -07:00 |
|
Matthew Gaughan
|
c5966518ef
|
updating similarity vectors
|
2025-07-29 13:38:50 -07:00 |
|
mgaughan
|
23ef7acd01
|
updating 072525 biberplus labels to reflect that they have been pre-processes
|
2025-07-29 13:03:46 -05:00 |
|
mgaughan
|
3e21ac1bb7
|
updating with OLMO-generated classifications
|
2025-07-28 17:09:23 -05:00 |
|
mgaughan
|
9e4c05e347
|
almost done with the classification task
|
2025-07-25 15:37:32 -05:00 |
|
mgaughan
|
862643d5df
|
building out olmo classification pipeline
|
2025-07-25 14:18:27 -05:00 |
|
Matthew Gaughan
|
a08a49d04e
|
adding in analysis of biberplus vectors
|
2025-07-23 14:22:20 -07:00 |
|