From 7f484a665022b8da84e15a068423980d2c098879 Mon Sep 17 00:00:00 2001
From: Khoroshevskyi <sasha99250@gmail.com>
Date: Fri, 13 Sep 2024 13:42:40 -0400
Subject: [PATCH] restructured code

---
 bedms/attr_standardizer.py        |  8 +++++---
 bedms/const.py                    |  2 ++
 bedms/utils.py                    |  2 +-
 requirements/requirements-all.txt |  2 +-
 tests/test_bedms.py               |  7 -------
 trial.py                          | 12 ------------
 6 files changed, 9 insertions(+), 24 deletions(-)
 delete mode 100644 trial.py

diff --git a/bedms/attr_standardizer.py b/bedms/attr_standardizer.py
index 13bf949..fbcaf39 100644
--- a/bedms/attr_standardizer.py
+++ b/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
diff --git a/bedms/const.py b/bedms/const.py
index 54e9b06..e325671 100644
--- a/bedms/const.py
+++ b/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"
diff --git a/bedms/utils.py b/bedms/utils.py
index aff492e..67dbd2e 100644
--- a/bedms/utils.py
+++ b/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
diff --git a/requirements/requirements-all.txt b/requirements/requirements-all.txt
index 848e7e8..3f373a4 100644
--- a/requirements/requirements-all.txt
+++ b/requirements/requirements-all.txt
@@ -3,4 +3,4 @@ numpy
 torch
 sentence-transformers
 pephubclient>=0.4.2
-peppy>=0.40.5
+peppy>=0.40.6
diff --git a/tests/test_bedms.py b/tests/test_bedms.py
index 74382ac..a47dfb1 100755
--- a/tests/test_bedms.py
+++ b/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
diff --git a/trial.py b/trial.py
deleted file mode 100644
index 9c2fec8..0000000
--- a/trial.py
+++ /dev/null
@@ -1,12 +0,0 @@
-from bedms import AttrStandardizer
-
-model = AttrStandardizer("ENCODE")
-
-schemas = model.get_available_schemas()
-
-print(schemas)
-
-# results = model.standardize(pep="geo/gse178283:default")
-results = model.standardize(pep="geo/gse228634:default")
-
-print(results)