- Remove group_col_name (dw_ek_borger) in training data in split trainer (
3b3ee4a)
- Allow passing custom populate registry fn to hparam search (
244231d)
- Preprocess additinoal data in selective cv (
f50d22a)
- Add selective cross validator trainer (
fd9b713)
- Examine LDL sampling (
1ae827b)
- F20/f25 filter wokrs (
5eaf0b7)
- Figure output formats (
91f80ca)
- Add pathchwork (
a5d4d3f) - Boxplot added (
b80ca1b) - Add density plot (
b5d810d) - Update plot (
c8653ea) - Update plot (
74e787a) - Add wip plot code (
265947f) - Add new eval plpts (
703d8e7) - Add eval (
de8dafa) - Add model training (
3cb7517) - Add feature generation (
c199724)
- Better parameters for plot axis/title texts (#877) (
9e5c735) - Rewind eval split args (
963190f) - Better params for plot texts (
1c4f2f4) - Remove old test (
87a5536) - Remvoe old files (
5cd3072) - Update feature gen args (
33e30ed)
- Add runpath suggester and remove run path from projectinfo (
faf7d2d)
- Upload pred df to mlflow (
af15191)
- Unify naming classification model steps (
31fc24a)
- Study creation before parallelization (
a4126af)
- Update perf table (
354021a)
- Subset tfidf columns (
c28353a)
- Add dataset logging (
ae662d3)
- #834: T2d add MCC and F1 to results table (
a306f8b) - Create descriptive_stats_by_outcome.py (
fe9d23e)
- Generate features with tsflattener v2 (
759fcc0)
- Migrate to v2 (
c18450c)
- Add pse keyword count embedding (
6cbdb42)
- Feature gen for sczbp text experiment (
13a3622)
- Lightgbm suggester (
7b9569a) - Joblib based hyperparameter search (
4df2dec) - #789: CVD, hyperparam tune for layer 2 (
075313d) - Lightgbm suggester (
feb6a68)
- Base table works (
d5d6645)
- Minor bugs (
29c3a19)
- #787: Add LightGBM (
fef71b9)
- #780: Terminallogger pretty print should print non-flattened cfg (#783) (
7abd94a) - #780: Terminallogger pretty print should print non-flattened cfg (
356ca28) - Fix c/b plot (
2594b54)
- #772: Use rich for pretty printing in terminallogger (#777) (
c924a95) - #772: Use rich for pretty printing in terminallogger (
48cff23)
- #775: Log outcome column as string, not Index (
a4ff66b)
- Do not init mlflow until first logging operation (
9085833)
- Test effect of interval (
4dbafb5)
- Mlflow logger on overtaci (
a0eef17)
- #700: Pretrain and finetune a sequential model for T2D (
470b0bc)
- Use namedtemporaryfile (
19fcf49)
- #717: Remove-PredictionTimeFilterer (#719) (
a6e3a2d) - Remove
PredictionTimeFilterer(bd3e3f0) - #717: Remove-PredictionTimeFilterer (
0bcf8bd)
- Runtime_checkable (
6048d8a)
- Match suggester regex in hparam tuning (
be443f4) - Hyperparameter tuning with optuna (
679dffb) - #699: Optuna-hparam-optimization (
7773099)
- Test on Ovartaci (
57364ce)
- #702: Allow filtering when generating patient slices (
5970ec0)
- #709: Support temporary uuid in quarantine filter (
1d3058a)
- Correct splitting of text data for sentence transformers (
7040115)
- Update (
fd53ac7)
- Decrease joins (
cd5fb9d)
- Circular import (
5ae8d43)
- #671: Improve-error-when-cannot-parse-registered-config (#672) (
4aa5cff) - #671: Improve-error-when-cannot-parse-registered-config (
15ca60b)
- Literal type hint parsing. Fixes #667. (
19dd234)
- Pretty-annotation-extraction-in-confection-placheholder-configs (
2ab73a6)
- Imports (
f817aad)
- Update gain table to be more flexible (
9e8cc4d) - Update perf by ppr (
8d1084c) - Update perf by ppr table (
5711773) - Update performance table (
16183d5) - Add calibration curve (
f5719cf) - Map vocab to tfidf indxs in gain table (
279f404) - Save vocabs from text models (
a084da1)
- Comment instruction (
3cbb09b) - Add decimal on roc_auc plot (
a54c283) - Tfidf matching in gain table (
6a954c0) - Lint (
cd63ad1) - Gain table flexibility (
ab70e4d) - Add arg to aggr eval (
db8f828)
- Use SplitIDs to generate splits in (issue #593) (
590cce6)
- Fill defaults from function signatures into .cfg (issue #426) (#638) (
cae3021) - Fill defaults from function signatures into .cfg (issue #426) (
a821915) - Fill defaults from function signatures into .cfg (issue #426) (
f96b839)
- RegionalFilter should not load at init (
7fa1a34)
- Registry testing project-specific registered functions (#637) (
fa09dfe) - Only check registered functions in common (
a27bfd8) - Move sczbp specific estimator steps to own registry (
bb9981e)
- Typo (
7dd3ced)
- Validated frame (
07b5f03)
- Sanitise dict keys for mlflow (
fc5eac9) - Remove unused extensions (
a50d5e7) - Disable graphite user pager (
dea1c75)
- Joint interface for loading different split ids (
b6b2be2)
- Add cleanlab processing step (
498403b) - Add missforest imputer (
05100b3) - Synthetic data augmenter estimator step (
8712caf) - Simple imputer estimator step (
1f72094) - Standardscaler that infers numeric columns (
4be5abc) - Imblearn pipeline and constructor (
c81f98b)
- Snyk syntax (
751c764)
- Replace disallowed symbols in config before logging to mlflow (
a49faa2)
- Analysis of time from first contact to outcome (
14380bd)
- First pretrain (
22e7eef)
- Finish apply (
e850710)
- Type ignore (
6685920)
- Generate new checkpoint (
558666e)
- Convert
patient_slice_gettersto classes (d2771d4) - Convert
patient_slice_gettersto classes (ec5fe84)
- Pretrain with
mlflow(#563) (a0d21ba) - Install invoke (
e5377a7) - Finetune trainer from pretrained checkpoint (#560) (
eec5816) - Pretraining with mlflow (
7033842) - Create finetuning-trainer from pretrained checkpoint (
62dbb8d)
- Filter based on insufficient lookahead (#541) (
9624405) - Filter based on insufficient lookahead (
21e545a) - Filter based on insufficient lookahead (
ab51a6e)
- Improvements (
1562df8)
- Add SplitDataset generic (
d4b99ea)
- Add support for mlflow experiment tracker (#432) (
9922000) - Add support for mlflow experiment tracker (
7048cb0) - Add support for mlflow experiment tracker (
db8db5b)
- Actually apply all filters (
5aaa13c)
- Minor rename and documentation (
428d2ff)
- Speed up cohort definers (
3a7bfab) - Use lazyframes for filter prediction times (
b9972b2) - Speed up cohort definers (
fac749a)
- Add washout as an arg during feature gen (
82ec387)
- Overwrite log on new run (
c60e5d5)
- Add multilogger to registry (
972b929)
- Add disk logger (
fcd1b46)
- Run linter (
6c30f8e)
- Add snyk workflow (#493) (
72381b3) - Add snyk workflow (
1114d13) - Load geographical split (
45917e2) - Make geographical split ids file (
f206bce) - Add dataloaderfilterer (
3e2768c) - update of full eval pipeline (
a408542) - Add full eval pipeline (
08fa21c) - Add auroc by time to event (
2026ee3) - Main performance figure (
d0ba595) - Finish adaptning robustness (
2199f01) - Adapt robustness eval (
7f9fcff)
- Arg updates (
066471b) - Update run arg type (
460b851) - Run full eval pipeline (
5beefdf) - Naming and etc. (
88be891) - Robustness figs (
2290be0)
- Updated based on new pre-commit (
e58adfb)
- Log text representation of config (#486) (
5866cd2) - Log text representation of config (
8fc4b91) - Log text representation of config (
dc1585a)
- Small improvements to docstrings (
f659c96) - Small improvements to docstrings (
f2e019b) - Add relevant docstring (
987f4d8)
- Add RegexColumnBlacklist to common (#472) (
a34066a) - Add RegexColumnBlacklist to common (
12f30f9) - Add cfg (
3fe31ed) - Add RegexColumnBlacklist to common (
a67b1bc)
- Better scaffolding cfg generation (
349a5f4)
- Train cvd with v2 (#455) (
6f66569) - Add xgboost defaults (
51bde84) - Add vertical concatenator (
607cf3a)
- Add todo (
01fe0e7)
- Add xgboost defaults (
2ead123)
- Prefix conut validator (
c42178c)
- More info on config update. (
5e546e9)
- Override type (
c2638a6)
- Comment readability (
590a946)
- Ran pre-commit (
7ba17a4) - Update test to match changes in test patients (
814b525) - Ran pre-commit (
06d849d) - Ensure mapping data is only loaded once (
389adca) - Ran pre-commit (
9c7f7db) - Updated behrt embedder with filtering (
9b3ca61) - Update output of create config to ensure correct type (
c336a34) - Convert output of resolve config to configschema (
2771693)
- Ensure that evaluation can run with different outcome col names (#418) (
c236d58) - Support spaces within column names (
abfb810) - Add support for spaces in header titles (
6109822)
- Filter cols by lookbehind combination filter (
92b6998)
- Change BinaryClassificatinoPipeline to take sklearn Pipeline instead of Sequence[ModelStep] (
aa5615e)
- Change BinaryClassificatinoPipeline to take sklearn Pipeline instead of Sequence[ModelStep] (
b23e6e0)
- Pass pred time uuid to binaryclassification task (
078cb92)
- Invalid imports (
4d27c03)
- Add multilogger (
dc52e55)
- Collect lazyframe and return pl.series (
ffca056)
- Performance by lookahead (
671f4e9) - Different lookaheads (
d7538bf) - Add script for train test on diff lookaheads (
41a29d8) - Add script for train test on diff lookaheads (
ce8f59f) - Add shap (
4029cd8)
- Refactor tasks structure (
12f2632) - Allow training from overtaci remote desktop (
7e9b1d7) - Remove warnings (
66c529e) - Added hotfix for wandb folder during debugging (
52fb95e) - Error made by pl lightning when saving hp (
e1f507d) - Added callbacks (
983908a) - Removed hotfix for behrt embedder (
7112773) - Fix based on pr comments (
4e71238) - Undo edit (
af04d12) - Removed todo comment (
17c463a)
- Allow list of data dirs for multirtun (
d77186e) - Update fa subset feature fns (
7197efe) - Allow list of data dirs in cfg (
064f8cb) - Remove redundant quatation marks (
f61209f)
- Pydantic requires types to be callable. Removed subscripting of pd.Series. (
95d89a6)
- Add cls token to behrt embedder (
568224f)
- Error-handling (
c5f8997)
- Add smoking data (
6547223)
- Improve documentatin (
0fdca6f)
- Add todo (
5eab729)
- Merge multiple feature sets (
6526bdd) - Test xgboost assumption (
5a3222a) - Add test of xgboost hyperparams assumption (
0768f62)
- Misc (
b63d22d) - Misc (
f8e35a0) - Correct checking whether dfs can be joined (
7630572) - Move feature merging to data_loader (
a31c9ca)
- Add devcontainer.json (
b9230b4) - Allow levels of granularity in diagnosis mapping (
a06fd75) - Add subsetting script (
dcd10ee)
- Update train val descriptive comp script (
b1f3e72)
- Comment test (
7dbeb53)
- Extract runs to functions, to avoid instantiation on import (
afc94cb)
- Renames (
5ea1fe5)
- How to install cuda enabled pytorch on overtaci (
25608d2)
- Create plot when training xgboost hba1c only (
cd52ec8)
- Change typehint for patient colnames (
22d9317) - Do not import get_best_eval_pipeline unless main (
d5da51f) - Fixed mutable default error in config (
a2d8294) - Source subtype filtering works (
1259203)
- Add overwrite eval warnings (
6d5657f)
- Added fine-tuning script (
bef7c88)
- Ran precommit (
6e6bf80) - Don't run bf16 on tests (
5a624ca) - Ran pre-commit (
11536be) - Ran pre-commit (
42b8e29) - Added description of how to create checkpoint (
453c5a9) - Updated the checkpoint (
b04f37c) - Ran pre-commit (
7e40ed1) - Added test for multilabel (
1f29927) - Based on review from @MartinBernstorff (
643c1e4) - Ran pre-commit (
b2a98ec) - Remove .conftest antipattern (
5e5a693) - Ran pre-commit (
fab110a) - Ran pre-commit (
ff41ad2)
- Added test documentation (
448ce4d)
- Add tasks.json (
84546d1) - Add vscode dev task (
8a349b8) - Create diagnosis mapping (icd10->caliber) (
e27af96)
- Delete unused file (
1e4cab7)
- Add procedure codes (
002d488)
- Define cohort (
7434bac)
- Gradient accumulation fix OutOfMemoryError? (
7cfc47b) - Lr scheduler linear with warm-up (
0f2d433) - Pretrain version (
5e9091c) - Ready for training (
1218794) - Expand test to cover model checkpointing (
1f0bece) - Lightning module saves hyperparams (
59e7ac6) - Adapt sequence training script to pytorch lightnign (
005cbdf) - Initial changes to pytorch lightning module (
d919009) - Added training script for sequence model (
7d2c2bb)
- Configs should be initialised with factories (
7ddbf9b) - Ruff (
626e0fc) - Fully transitioned to pl (
d3a8d32) - Replaced print with logging statements (
769530f) - Make sure parameters is actually moved to the gpu (
131e1f0)
- Typo (
0dfeb69)
- Add dev container (
84301b8) - Add corr plot (
d0c116f) - Add feature outcome corrs (
4376b19) - Add hist (
708ca45) - Descriptive stats (
8c0b038)
- Time from first pos pred to next hba1c (
b0d805d) - Ned script for retraining model with new cv (
eba749f) - Add feature importance table (
423cc23) - Add baseline table one (
8695e29) - Adding eval plots (
5b81f26) - Add new eval branch (
5e8aea3) - Wip new eval structure (
8728545)
- Lint (
5bbdd7c) - Missing path arg (
f4fe5e1) - Spelling in comments (
58de461) - Lint (
0eeb957) - Lint (
f084a83) - Various minor changes (
4a8f6de) - Missing return type annotation (
cd2f8f9) - Formatting (
b8521e4) - Delete old eval folder (
5e5cc6a) - Eval paths (
6f1f1a1) - Selected runs (
a448ab4) - Configs (
80d1907)
- Implement classifierchain (
097cc0a)
- Unpack dataframe to series in eval df (
dcf9b93)
- Main test passes 🥳 (
622adf7) - Add missing methods from PSYCOPModule to BEHRTForMaskedLM (
79f8a26) - Update trainer to match checkpoint savers (
ab9a234) - Add wandb logger (
7eef76a) - Flesh out trainining (
40b1032) - Add dataclass-based vocab (
25f7d3e) - Implemented masking task (
b0ffbf4) - Embedder skeleton (
81479c7)
- Fix error from static type checks (
13f5a38) - Updated format of the mask function to allow for testing (
d49dadc) - Make sure that the tests test the outer masking_fn (
679cd54) - Renamed PsycopModule -> TrainableModule (
fadc9a1) - Remove testing assumption from Logger (
861c162) - Updated logger to handle allow logging configs seperately (
604dc2e) - Moved logger interface to its own script (
4c83ff4) - Added vocab_size (
3789834) - Added type hints (
370aebe) - Forward pass in embedding module works (
5cd38d9) - Added patient dataset (
2a00c32) - Added behrt embedder (
a2bbd8b)
- Rename cohort definition to cvd_definition (
27c5e59) - Minor examples (
f2d99ad) - Cvd outcome definition (
89dcf49) - Add cvd filters (
9dcfe33)
- Remove use of hba1c in cvd filters (
395487e) - Unneeded newline handling (
311d15d) - Strip lines of whitespace before generating dataframes (
628db49)
- First version (
2fc715c)
- Possibly unbound variable (
864f59b)
- Point to patient object tests (
d727664)
- Add tfidf (
fba845a)
- Config of last model (
250d854) - Naming (
5bca53b) - Configurations for new tfidf feat set (
fe33f0f) - Update configurations of model train and eval (
dd0f83c) - Reconfigure text lookbehinds (
f6151ad) - Text specs (
a0ac8bf)
- Parse date of birth to all patients (
c469997)
- Train new tfidf model and encode text (
1fdd3ce)
- Don't shadow python builtin (
c05d307)
- Get patients from sql (
d9ebba4)
- Rename from merge (
38257e4) - Type checking block for circular imports (
a33a8de) - Typo in shak codes (
e2cd184)
- Convert getters to properties (
cbe130b) - Handle lookahead-based outcome resolution (
489003f) - Remove patient_ids and fix downstream type consequences (
2918452) - Misc. (
bd3d6ea) - First working unpacker (
c65219b) - First stab at unpacking to patient dfs (
74ba12a) - Filter prediction sequences (
402eee9)
- Rename patient id in tests (
da79654) - Spelling errors (
114b624) - Missing type import (
575689b) - Downstream type fixes (
1cd438b)
- Add comments explaining eq (
d99c0be)
- Filename check earlier for feature-gen (
17b3404)
- Cohort creation for the cancer project (
4a408b9)
- Correct type hints for aggregation (
ac9fc29) - Reconfigure lab tests (
caebc33) - Replaced unsued function (
75f241c)
- Type annotation (
a18cc64) - Wandb back to offline (
b67d4f7) - Config (
f5e2c73) - Wandb config (
761ea6a) - Lookbehind combi config (
09919f4) - Update configs (
6ad6fef) - Correct type hints for aggregation (
d6f4311) - Param changes (
650912d) - Add missing arg (
500be32) - Minor changes to params (
dd1dcea)
- Add new dir param and user prompt (
fe46dbf)
- Broken tests due to missing arg (
74cd065) - Add arg to general function (
6395109) - Update general function (
81506ee) - Instructions in README.md (
c2de501)
- Ignore type check (
17a3b45)
- First stab at chunked feature gen (
0a31a61) - Add loader for embedded text (
40c8271) - Train sentence transformer code (
055a572) - Sentence transformer embedding ready to train (
40ce08a) - Sentence transformer embedding (
9b998f8) - Vis qc (
ec8ff15)
- Misc (
df49d9b) - Ignore old import erros (
d6a2105) - Reinstate 'prefixes_to_describe' param (
761c6f0) - Remove old param (
4240440) - Minor changes and typos (
2341abd) - Typo in requirements (
d97aefe) - Text feat specs resolve mltp to mean (
9dd1065) - Paths (
b008a95) - Change chunking pipeline (
781d442) - Updating scz_bp feature gen (
8b1ee14) - Move chunk tests (
df7834d) - Move chunk tests (
295e4c0) - Don't modify prediction_times_df in PredictionTimeFilterer (
e1eae8c) - Type hint for ColNames (
0454b42) - Chunked feature gen (
d8e2ac7) - Set wandb to offline during feature gen (
5ce32be) - Print time taken for sentence embedding (
ac4e8a2)
- Multilabel classification (
5285b2c)
- Simple qc of text (
eff9bfa)
- To polars|pandas method for EvalDataset + fixed threshold (
52fe185) - Add loader for first visit to psychiatry (
9ee9727)
- Set pythonpath for interactive session (
ded552d)
- Change prefix for supplementary outputs (
9b2a15d)
- Only print failed checks if there are any (
ba645ec) - Only do feature description of columns matching prefix (
dc45ab7)
- Add birthdays as default (
17bdc01)
- Add loader for therapeutic leave (
a9f95ec)
- Correct types for aggregation funcs in t2d specify features (
6796f0a)
- Add docs to eventcolumns (
e6585a2) - Explain sequence columns (
be1f89d) - Define behaviour if lookbehind is none (
26a7f0c) - Add docstring (
fe5fd2e)
- Add INP and TCH rules (
4a3d02a)
- Add plot code (
8c0b347) - Remove name and build-system to avoid pip install -e . (
63e871b) - Migrate to requirements.txt (
cab38a5)
- Add correct new models (
fe9d4bb) - New best models (
2db0f03) - Adding more flexibility (
014ba4e) - Adding more flexibility (
fca7264)
- Eval pipeline works (
a663436) - Add typehints to feature specs (
bf42de0) - Turn wandb off for now in main feature_gen script (
2ea9ef3) - Cancer project initial setup (
de8f9cf)
- Minor change (
41e07b2) - Update readable feature names (
a4073c3) - Update readable feature names (
114cd24)
- Add careml to monorepo (
534400a)
- Move markdown handling to common (
bdfeafa)
- Misc. (
482db66)
- Guard for newly optional configs (
e9ff39e)
- Remove project specific md code (
945a0fd)
- Simplify feature describer (
a9f9f7b)
- Patchwork grid of size 1 (
b159a10)
- Increase size of axis labels in t2d pn theme (
71b8dd0) - Increase size of patchwork subpanel labels (
384e06d) - Make HbA1c only configurable (
d2854a8) - Adopt boolean dataset to featuremodifier (
5188047) - Ignore static type checks on Ovartaci (
840c015) - Allow disabling of column name checks (
ad519be) - Boolean cols in place (
8b968e5) - Use native polars column selection (
ef25f17)
- Imports (
e31e18d)
- Improve docs wording (
173807e)
- Correct lookbehind selection (
3807a94)
- Implement full supplementary generation (
530d972) - Switch to TDD for md_object generation (
35b4787) - Create required wandb folder when initialising wandb in WandbHandler (
41037d9) - Misc. (
0a54195) - Eval run on test_set (
76644ee)
- Align plot and table for median warning days (
bda3eed)
- Pin wandb version to avoid failing on tests (
2a92dda)
- Generate a publication-ready performance_by_ppr table (
32c20ed)
- Add thousand separator to conf matrix (
fc9b6dc) - Add thousand separator to conf matrix (
4f98c0b) - Add thousand separator to plotnine conf matrix (
d27d0f7) - Add lines to sens by time to event (
b739267) - First stab at sens by time to event plot (
91571f9) - Add full performance figure (
45c1d6e)
- Do not check for venv for tests, conflicts with CI (
672d43f) - Handle uneven number of plots in patchwork_grid (
a833eb7)
- Convert auroc to plotnine (
80f5cbf)
- Incorrect path (
925c94c)
- Create plotnine confusion matrix (
5045b67)
- Improve docs (
e6a1230)
- Autofix when creating pr (
76470cd)
- Add action (
0490672)
- First robustness plot (
659d30d)
- Split ci after bootstrap (
f3e4f6f)
- Fix typo (
5b8e3be)
- Create pipeline and unified interface for evaluating the best run (
d4fd7f3)
- Better explain utility func (
46396a1)
- Add ci to timedelta plots (
ce8c63f)
- Handle only one true class (
5a90247)
- Increase x-axis text size for base plots (
b5ddf0b)
- Missing polars requirement (
8e277e1)
- Allow str_to_pl_df (
4cd53ac)
- Allow custom splits for training (
6e0bf71)
- Do not support multiclass in calc_performance (
781692b) - Assign sql cache if on local (
2365b65) - Assign sql cache if on local (
d57c9fd)
- Add logging and choose sfi types (
d5f8e23) - Create example scripts (
76e063a) - Initial text model pipelines (
1934db0) - Add tests (
d7a8bab) - Initial simple preprocessing pipeline for all sfis (
f941a4d) - Add include_sfi_name in load_text_split (
4605c88) - Include_sfi_name arg (
58baf9a) - Fit and load tfidf, bow, and lda models (
3d33d9b)
- Preprocess to one regex (
c716653) - Remove symbols again (
1210b7e) - Based on HLasses comments (
32da48f) - Insert model type in filename (
1457387) - Add doc strings to preprocessing functions (
4e27650) - Remove log.info and small fixes (
84f3cc3) - Ruff fixes (
ea9c564) - Return vectorizer and matrix + clean-up (
e1c48a0) - Query string (
cb7424c) - Naming and doc string update (
141e52a) - General clean-up and change corpus in fit functions to list (
22b6a9e) - Change ngram default and clean-up (
387f845) - Small fixes to logging (
c3a3f53) - Remove old comments (
4b88514) - Change view name (
a9bb0fc) - Move save_text_model_to_dir to utils (
469df3b) - Move save_text_model_to_dir to utils (
26a80d2) - Renaming in preprocessing (
c381768) - Remove stop_words arg and return models (
3d29012) - Change arg path to path_str (
f781a74) - Enable multiple splits when loading data + add n_rows arg (
8ae2d2e) - Remove Path from arg (
29b442b)
- Add feature descriptions for text features (
84c696a)
- Add readme link (
217e550)
- Remove unreasonably high or low bmi values (
07f52c2)
- Make sql query executable (
e006490) - Str turned into list of characters instead of list of words (
0fae478)
- Add unpack args to skema 2 wo nutrition (
95c35c8)
- Support new pipe annotation (
a1bde17)
- Correct types (
5cb0d5d)
- Add skema_2_without_nutrition again (
685c5cb)
- Cruft github action (
c8f6278) - Bug in cruft action (
ec8267a) - Remove psycop-ml-utils, no longer exists (
d8fbb65)
- Add more glc loaders (
b765e77) - Add type 1 diabetes loaders (
b682984) - Make sql loader verbose (
602f4f3) - Add caching to sql_load (
a68c15d) - Ibid (
46da732) - Add support for keeping code col when loading diagnoses (
51ca63e) - Add t2d diagnosis loading (
6b8231c) - Add ogtt (
f6c07a9) - Update current blood sugar measurements (
5e8051a)
- Lacking prefix on loading glc (
d9bdbcb) - Inappropriate matching (
e2409ed) - Poetry formatted dependencies (
125500a)
- Disable cache (
0242114)
- Add option for which timestamp to get when loading physical visits (
ef369b8)
- Drop duplicates in the output_df (
636cc48) - Don't load duplicate visits (
5028b1d) - Physical visits should only load physical visits (
b7c50cf) - Did not rename to timestamp before returning (
f43522c)
- Loader names still too long (
3321b88)
- Loader names too long for wandb (
cc14da2)
- ValueError correction (
595479e)
- Adjust function for saving integrity checks (
de2577e) - Restructure overarching description func (
54c24a2)
- Better function description (
7eb9e54)
- Add arg for choosing timestamp and add warning (
159a176)
- Make naming scheme consistent (
c125b48) - Attempted rename of unspecified df (
c266bd8) - Revert logic (
ad110ee) - Quarantine_df and quarantine_days can be left as None (
f130370)
- Allowed types works again (
dbe75ca) - All arg names now congruent, visit_types takes a list of visit types instead of string (
e63e9d4)
- Add text loaders (
9c7d959)
- Use acute outpatient visits as well (
659af23) - Typo, and use newest data (
bbbc8f5) - Use end dates for all contacts (
d8940c1) - Use end times for all diagnosis loading (
4d9e600)
- Remove try/except to avoid debugger getting stuck on it (
3884ab8)
- Move all str operations into the if statement (
91f9174)
- Move logs next to their dataset (
e0ed033)
- Improve quarantine docs (
1b23f19)
- Name wandb project_name-feature-generation (
b601d80)
- Improve logging in flatten_dataset (
63f252f) - Enable minimum specificaitons (
669e3ed) - Enable minimum specificaitons (
523cfd1) - Log rows dropped by PredictionTimeFilterer (
7e02d8e) - Add moves loader (
0521dd0) - First stab at loader (
f9048b8)
- Add pred_time_uuid if not specified when filtering (
acca5b9)
- Avoid groupby in filter_prediction_times (
a66e361)
- Add rows dropped logging (
33ba525) - Allow filtering based on quarantine dates (
3deb052) - Improve logging - debug to file, info to stdout (
aff10a9) - Move wandb init earlier so wandb_alerts can cover values_df loading (
6c153b1) - Generate full feature set (
9ba907a) - Wrap as much of main as possible in wandb exception (
3b085af) - Allow timestamps only return from visit loaders for use as pred_times (
f9534e0) - Migrate some loaders to logging. (
f81fd92) - More explicit logging (
7969210) - Init changes (
f257daa)
- Use lookbehind instead of interval days (
7e14ad5) - Only one feature cache per project (
cb0b8b0) - Unused input args (
fa14461) - Wandb util was missing text kwarg (
64c1729)
- Infer CPU cores from logical cores (
309e9d2)
- Add wandb alert on exception (
3ff6e37)
- Improve create_flattened_dataset docs (
637edfe) - Misc. docs (
4eac2ba) - Fix github test badge (
dffeedc)
- Add n_hba1c_within_n_lookahead_days (
e84b591) - Add outcome (
cd39dd6) - Add birth year as a predictor (
7b186d2) - Allow exclusion of specific atc codes (
75619a1)
- Date of birth col name should respect output prefix (
6ec6535) - Incorrect column name when adding age as predictor (
cdbf25c) - Errors in sql loaders after refactor (
28c9f63) - Correct type hinting in load_diagnoses (
f2d5c5b)
- Speccify that n_rows = None returns all rows. (
a4720a8)
- Shuffle feature specs to even out compute vs. IO load (
0db9f0f) - Tweak n_workers for more performance (
3eeee4d) - Segment feature loading for more parallelisation (
9ee5c87) - Rotate feature addition for debugging (
76af9c7) - Parallelise temporal predictor loading (
8d53f16) - Only create one subprocess per values loader (
1a3e5de) - Parralelise groupspec combination creation (
9ccba2a)
- At groupspec init, iterate over values_loader and check that they exist in the loader registry (
04dfd7e)
- More explanation in error message (
b784991) - Bettee valueerror message formatting (
7b3b994) - Better valueerror message (
d92f798) - Find invalid loaders (
ba2d4c5)
- Allow load_medications to concat a list of medications (
d78f465)
- Remove original functions (
da59110)
- Improve docs (
9aad0af)
- Full run (
142212f) - Rename resolve_multiple registry keys to their previous one (
3fd3f35) - Reimplement (
c99585f) - Use lru cache decorator for values_df loading (
4006818) - Add support for loader kwargs (
127f821) - Move values_df resolution to AnySpec object (
714e83f) - Make date of birth output prefix a param (
0ed1198) - Ensure that dfs are sorted and of same length before concat (
84a4d65) - Use pandas with set_index for concat (
b93290a) - Use pandas with set_index for concat (
995da41) - Speed up dask join by using index (
3402281) - Require feature name for all features, ensures proper specification (
6af454a) - First stab at adapting generate_main (
7243130) - Add exclusion timestamp (
b02de1a) - Improve dd.concat (
429da34) - Handle strs for generate_feature_spec (
7d54488) - Convert to dd before concat (
06101d8) - Add n hba1c (
3780d84) - Add n hba1c (
614245e)
- Coerce by default (
60adb99) - Output_col_name_override applied at loading, not flattening (
95a96ce) - Typo (
01240ed) - Incorrect attribute addressing (
a6e82b5) - Correctly resolve values_df (
def67cd) - MinGroupSpec should take a sequence of name to permute over (
f0c8140) - Typo (
61c7241) - Remove resolve_multiple_fn_name (
617d386) - Old concat resulted in wrong ordering of rrows. (
3759f71) - Set hba1c as eval (
89fe6d2) - Typos (
6eac440) - Correct col name inference for static predictors (
dfe5dc7) - Misc. fixes (
45f8348) - Generate the correct amount of combinations when creating specs (
c472b3c) - Typo resulted in cache breaking (
fdd47d7) - Correct col naming (
bc74ae3) - Do not infer feature name from values_df (
150569f) - Misc. errors found from tests (
3a1b5db) - Revert falttened dataset to use specs (
e4fada7) - Misc. errors after introducing feature specs (
0308eca) - Correctly merge dataframes (
a907885) - Cache error because of loss off UUID (
89d7f6f) - New bugs in resolve_multiple (
5714a39) - Rename outcomespec appropriately (
41fa220) - Lookbehind_days must be iterable (
cc879e9)
- Move pd->dd into subprocesses (
dc5f38d)
- Remove shak_code + operator check (
f97aee8)
- Ignore cat_features (
2052505) - Failing test (
f8190b4) - Incorrect 'latest' and handling of NaN in cache (
dc33f7e)
- Check for value column prediction_times_df (
5356464) - Change variable name (
990a848) - More flex loaders (
bcad700)
- Use wandb to monitor script errors (
67ae9b9)
- Duplicate loading when pre_loading dfs (
7f864dc)
- Add variance to resolve multiple functions (
8c471df)
- Add vairance resolve multiple (
7a64c5b)
- Deleted_irritating_blank_space (
a4cdfc5)
- Auto inferred cat features (
ea0d946) - Auto inferred cat features error (
f244715) - Resolves errors caused from auto cat features (
667a905)
- Incorrect function argument (
33e0a3e) - Expanded test to include outcome, now passes locally (
640e7ec) - Passing local tests (
6ed4b2e) - First stab at bug fix (
339d793)
- Add parents to wandb dir init (
5eefe3a)
- Add BMI loader (
b6681ea)
- Refactor feature spec generation (
17e9f16) - Align arguments with colnames in SQL (
09ae5f7) - Refactor feature specification (
373b0f0)
- Hardcoded file suffix (
0101acc)
- Mismatched version in .tomll (
292979b)
- Pass value_col only when necessary (
dc1019f) - Pass value_col (
4674e4a) - Don't remove NaNs, might be informative. (
1ad5d81) - Remove parquet default argument except in top level functions (
ec3a98b) - Align .toml and release version (
80adbde) - Failing tests (
b5e4321) - Incorrect feature sets path, linting (
605ccb7) - Handle dicts for duplicate checking (
34524c0) - Check for duplicates in feature combinations (
63ad162) - Remove duplicate alat key which prevented file saving (
f0c3e00) - Incorrect argumetn (
b97d54b) - Linting (
7406288) - Use suffix instead of string parsing (
cfa96f0) - Refactor dataset loading into a separate function (
bca8cbf) - More migration to parquet (
f1bc2b7) - Mark hf embedding test as slow, only run if passing --runslow to pytest (
0e03395)
- Wandb not logging on overtaci. (
3baab57)
- Use dask for concatenation, increases perf (
4235f5c)
- Use pypi release of psycopmlutils (
5283b05)
- First release to pypi (
c29aa3c)
- Add test for chunking logic (
199ee6b)
- First release! (
95a557c) - Add automatic release (
a5023e5) - Update dependencies (
34efeaf) - First rename (
879bde9) - Init commit (
cdcab07)