Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Create pylint.yml #46

Merged
merged 5 commits into from
Sep 5, 2024
Merged

Create pylint.yml #46

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
5e2e99b
Create pylint.yml
ChaoPang Sep 5, 2024
43fdc4a
Fixed the pylint error about the UPPER_CASE naming style
ChaoPang Sep 5, 2024
bdbd281
added python-app to run the tests when the main branch is pushed or a…
ChaoPang Sep 5, 2024
b79abd9
Removed unused dependencies from the project and updated README.md
ChaoPang Sep 5, 2024
eac7586
Try to fix the tensorflow reshaping error
ChaoPang Sep 5, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
39 changes: 39 additions & 0 deletions .github/workflows/python-app.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,39 @@
# This workflow will install Python dependencies, run tests and lint with a single version of Python
# For more information see: https://docs.github.com/en/actions/automating-builds-and-tests/building-and-testing-python

name: Python application

on:
push:
branches: [ "main" ]
pull_request:
branches: [ "main" ]

permissions:
contents: read

jobs:
build:

runs-on: ubuntu-latest

steps:
- uses: actions/checkout@v3
- name: Set up Python 3.10.0
uses: actions/setup-python@v3
with:
python-version: "3.10"
- name: Install dependencies
run: |
python -m pip install --upgrade pip
pip install flake8 pytest
pip install -e .
- name: Lint with flake8
run: |
# stop the build if there are Python syntax errors or undefined names
flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
# exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
- name: Test with pytest
run: |
PYTHONPATH=./: pytest
3 changes: 2 additions & 1 deletion README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -73,7 +73,8 @@ tar -xvf omop_synthea.tar .
```
Convert the OMOP dataset to the MEDS format
```console
meds_etl_omop omop_synthea synthea_meds
pip install meds_etl==0.3.6;
meds_etl_omop omop_synthea synthea_meds;
```
Convert MEDS to the meds_reader database to get the patient level data
```console
Expand Down
4 changes: 0 additions & 4 deletions pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,9 +26,6 @@ dependencies = [
"dask==2024.1.1",
"dask[dataframe]==2024.1.1",
"datasets==2.16.1",
"docarray==0.40.0",
"docarray[hnswlib]==0.40.0",
"docarray[weaviate]==0.40.0",
"evaluate==0.4.1",
"fast-ml==3.68",
"fastparquet==0.8.1",
Expand Down Expand Up @@ -58,7 +55,6 @@ dependencies = [
"transformers==4.39.3",
"Werkzeug==3.0.1",
"wandb==0.17.8",
"Whoosh==2.7.4",
"xgboost==2.0.3"
]

Expand Down
18 changes: 9 additions & 9 deletions src/cehrbert/config/output_names.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,9 +1,9 @@
parquet_data_path = 'patient_sequence'
qualified_concept_list_path = 'qualified_concept_list'
time_attention_model_path = 'time_aware_model.h5'
bert_model_validation_path = 'bert_model.h5'
mortality_data_path = 'mortality'
heart_failure_data_path = 'heart_failure'
hospitalization_data_path = 'hospitalization'
information_content_data_path = 'information_content'
concept_similarity_path = 'concept_similarity'
PARQUET_DATA_PATH = 'patient_sequence'
QUALIFIED_CONCEPT_LIST_PATH = 'qualified_concept_list'
TIME_ATTENTION_MODEL_PATH = 'time_aware_model.h5'
BERT_MODEL_VALIDATION_PATH = 'bert_model.h5'
MORTALITY_DATA_PATH = 'mortality'
HEART_FAILURE_DATA_PATH = 'heart_failure'
HOSPITALIZATION_DATA_PATH = 'hospitalization'
INFORMATION_CONTENT_DATA_PATH = 'information_content'
CONCEPT_SIMILARITY_PATH = 'concept_similarity'
16 changes: 8 additions & 8 deletions src/cehrbert/evaluations/evaluation.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -56,7 +56,7 @@ def evaluate_sequence_models(args):
time_attention_tokenizer_path = find_tokenizer_path(args.time_attention_model_folder)
time_aware_model_path = os.path.join(
args.time_attention_model_folder,
p.time_attention_model_path
p.TIME_ATTENTION_MODEL_PATH
)
BiLstmModelEvaluator(
dataset=dataset,
Expand All @@ -83,7 +83,7 @@ def evaluate_sequence_models(args):
validate_folder(args.vanilla_bert_model_folder)
bert_tokenizer_path = find_tokenizer_path(args.vanilla_bert_model_folder)
bert_model_path = os.path.join(args.vanilla_bert_model_folder,
p.bert_model_validation_path)
p.BERT_MODEL_VALIDATION_PATH)
BertFeedForwardModelEvaluator(
dataset=dataset,
evaluation_folder=args.evaluation_folder,
Expand All @@ -108,7 +108,7 @@ def evaluate_sequence_models(args):
validate_folder(args.vanilla_bert_model_folder)
bert_tokenizer_path = find_tokenizer_path(args.vanilla_bert_model_folder)
bert_model_path = os.path.join(args.vanilla_bert_model_folder,
p.bert_model_validation_path)
p.BERT_MODEL_VALIDATION_PATH)
SlidingBertModelEvaluator(
dataset=dataset,
evaluation_folder=args.evaluation_folder,
Expand All @@ -134,7 +134,7 @@ def evaluate_sequence_models(args):
validate_folder(args.vanilla_bert_model_folder)
bert_tokenizer_path = find_tokenizer_path(args.vanilla_bert_model_folder)
bert_model_path = os.path.join(args.vanilla_bert_model_folder,
p.bert_model_validation_path)
p.BERT_MODEL_VALIDATION_PATH)
BertLstmModelEvaluator(
dataset=dataset,
evaluation_folder=args.evaluation_folder,
Expand All @@ -160,7 +160,7 @@ def evaluate_sequence_models(args):
if RANDOM_VANILLA_BERT_LSTM in args.model_evaluators:
validate_folder(args.vanilla_bert_model_folder)
bert_model_path = os.path.join(args.vanilla_bert_model_folder,
p.bert_model_validation_path)
p.BERT_MODEL_VALIDATION_PATH)
bert_tokenizer_path = find_tokenizer_path(args.vanilla_bert_model_folder)
visit_tokenizer_path = find_visit_tokenizer_path(args.vanilla_bert_model_folder)

Expand Down Expand Up @@ -195,7 +195,7 @@ def evaluate_sequence_models(args):
if HIERARCHICAL_BERT_LSTM in args.model_evaluators:
validate_folder(args.vanilla_bert_model_folder)
bert_model_path = os.path.join(args.vanilla_bert_model_folder,
p.bert_model_validation_path)
p.BERT_MODEL_VALIDATION_PATH)

bert_tokenizer_path = find_tokenizer_path(args.vanilla_bert_model_folder)
bert_visit_tokenizer_path = find_visit_tokenizer_path(args.vanilla_bert_model_folder)
Expand Down Expand Up @@ -227,7 +227,7 @@ def evaluate_sequence_models(args):
if HIERARCHICAL_BERT_POOLING in args.model_evaluators:
validate_folder(args.vanilla_bert_model_folder)
bert_model_path = os.path.join(args.vanilla_bert_model_folder,
p.bert_model_validation_path)
p.BERT_MODEL_VALIDATION_PATH)

bert_tokenizer_path = find_tokenizer_path(args.vanilla_bert_model_folder)
bert_visit_tokenizer_path = find_visit_tokenizer_path(args.vanilla_bert_model_folder)
Expand Down Expand Up @@ -259,7 +259,7 @@ def evaluate_sequence_models(args):
if RANDOM_HIERARCHICAL_BERT_LSTM in args.model_evaluators:
validate_folder(args.vanilla_bert_model_folder)
bert_model_path = os.path.join(args.vanilla_bert_model_folder,
p.bert_model_validation_path)
p.BERT_MODEL_VALIDATION_PATH)

bert_tokenizer_path = find_tokenizer_path(args.vanilla_bert_model_folder)
bert_visit_tokenizer_path = find_visit_tokenizer_path(args.vanilla_bert_model_folder)
Expand Down
Loading
Loading