chore: Lint tests and scripts folders

Author: roquelopez

.github/workflows/lint.yml

@@ -9,4 +9,7 @@ jobs:
       - uses: actions/checkout@v3
       - uses: psf/black@stable
         with:
-          src: ./bdikit/
+          src: |
+            ./bdikit/
+            ./tests/
+            ./scripts/

Makefile

@@ -3,9 +3,11 @@
 
 
 RAW_SYNAPSE_PATH = join(dirname(__file__), "./synapse_raw_schema.json")
-FORMATTED_SYNAPSE_PATH = join(dirname(__file__), "../../bdikit/resource/synapse_schema.json")
+FORMATTED_SYNAPSE_PATH = join(
+    dirname(__file__), "../../bdikit/resource/synapse_schema.json"
+)
 
-data = {'entity':{}, 'subschema':{}}
+data = {"entity": {}, "subschema": {}}
 
 
 with open(RAW_SYNAPSE_PATH) as json_file:
@@ -16,20 +18,22 @@
     entry_description = entry.get("rdfs:comment", "")
     entry_parents = entry.get("rdfs:subClassOf", [{}])
 
-    if entry_parents[0]['@id'] == "bts:Thing":
+    if entry_parents[0]["@id"] == "bts:Thing":
 
         if entry_name.endswith("Enum"):
             continue
         values = entry.get("schema:rangeIncludes", [])
         new_entry = {
             "column_description": entry_description,
-            "value_data": {x["@id"].replace("bts:", ""): "" for x in values}
+            "value_data": {x["@id"].replace("bts:", ""): "" for x in values},
         }
-        data['entity'][entry_name] = new_entry
+        data["entity"][entry_name] = new_entry
 
     if entry_name.endswith("Template") and "sms:requiresDependency" in entry:
-        dependencies = [x["@id"].replace("bts:", "") for x in entry["sms:requiresDependency"]]
-        data['subschema'][entry_name] = dependencies
+        dependencies = [
+            x["@id"].replace("bts:", "") for x in entry["sms:requiresDependency"]
+        ]
+        data["subschema"][entry_name] = dependencies
 
 with open(FORMATTED_SYNAPSE_PATH, "w") as f:
     json.dump(data, f, indent=4)

scripts/format_schema/format_synapse.py

@@ -286,7 +286,7 @@ def test_preview_domain():
     preview = bdi.preview_domain(source, "age")
 
     # then
-    # preview must contain only the column "value_name" and the unique 
+    # preview must contain only the column "value_name" and the unique
     # values of the column "age"
     assert preview is not None
     assert isinstance(preview, pd.DataFrame)

tests/test_api.py

@@ -10,6 +10,7 @@
 from bdikit.schema_matching.twophase import TwoPhase
 from bdikit.schema_matching.contrastivelearning import ContrastiveLearning
 
+
 def test_basic_schema_matching_algorithms():
     for column_matcher in [
         SimFlood(),

tests/test_schema_matching.py

@@ -12,7 +12,7 @@ def test_textual_transformation_value_matching_algorithms():
         TFIDF(threshold=threshold),
         EditDistance(threshold=threshold),
     ]:
-    
+
         # given
         source_values = ["Red Apple", "Banana", "Oorange", "dragon-fruits"]
         target_values = ["apple", "banana", "orange", "kiwi"]
@@ -74,4 +74,4 @@ def test_semantic_value_matching_algorithms():
     assert mapped_matches["Display"][0] == "Monitor"
 
     scores = [match[2] for match in matches]
-    assert all(score > threshold for score in scores)
+    assert all(score > threshold for score in scores)