restructured code

bedms/attr_standardizer.py

@@ -7,6 +7,7 @@
 import torch.nn.functional as torch_functional
 
 from .const import (
+    AVAILABLE_SCHEMAS,
     CONFIDENCE_THRESHOLD,
     DROPOUT_PROB,
     EMBEDDING_SIZE,
@@ -17,8 +18,8 @@
     OUTPUT_SIZE_BEDBASE,
     OUTPUT_SIZE_ENCODE,
     OUTPUT_SIZE_FAIRTRACKS,
-    SENTENCE_TRANSFORMER_MODEL,
     PROJECT_NAME,
+    SENTENCE_TRANSFORMER_MODEL,
 )
 from .model import BoWSTModel
 from .utils import (
@@ -200,7 +201,8 @@ def standardize(
     def get_available_schemas() -> list[str]:
         """
         Stores a list of available schemas.
+
         :return list: List of available schemas.
         """
-        schemas = ["ENCODE", "FAIRTRACKS", "BEDBASE"]
-        return schemas
+
+        return AVAILABLE_SCHEMAS

bedms/const.py

@@ -1,5 +1,7 @@
 PROJECT_NAME = "bedmess"
 
+AVAILABLE_SCHEMAS = ["ENCODE", "FAIRTRACKS", "BEDBASE"]
+
 REPO_ID = "databio/attribute-standardizer-model6"
 MODEL_ENCODE = "model_encode.pth"
 MODEL_FAIRTRACKS = "model_fairtracks.pth"

bedms/utils.py

@@ -8,7 +8,7 @@
 import peppy
 import torch
 from huggingface_hub import hf_hub_download
-from pephubclient import PEPHubClient
+
 from sentence_transformers import SentenceTransformer
 from sklearn.cluster import KMeans
 from sklearn.feature_extraction.text import CountVectorizer

requirements/requirements-all.txt

@@ -3,4 +3,4 @@ numpy
 torch
 sentence-transformers
 pephubclient>=0.4.2
-peppy>=0.40.5
+peppy>=0.40.6

tests/test_bedms.py

@@ -1,16 +1,9 @@
-import pytest
 from bedms import AttrStandardizer
 
 
 class TestBEDMES:
     def test_bedmes(self):
-
         model = AttrStandardizer("ENCODE")
-
-        schemas = model.get_available_schemas()
-
-        assert schemas
-        # results = model.standardize(pep="geo/gse178283:default")
         results = model.standardize(pep="geo/gse228634:default")
 
         assert results