Removing unused labels from spacy_recognizer.py

app.py

@@ -1,7 +1,6 @@
 
 """Streamlit app for Student Name Detection models."""
 
-import spacy
 from spacy_recognizer import CustomSpacyRecognizer
 from presidio_analyzer.nlp_engine import NlpEngineProvider
 from presidio_anonymizer import AnonymizerEngine
@@ -46,18 +45,15 @@ def analyzer_engine():
 
     return analyzer
 
-
 @st.cache(allow_output_mutation=True)
 def anonymizer_engine():
     """Return AnonymizerEngine."""
     return AnonymizerEngine()
 
-
 def get_supported_entities():
     """Return supported entities from the Analyzer Engine."""
     return analyzer_engine().get_supported_entities()
 
-
 def analyze(**kwargs):
     """Analyze input using Analyzer engine and input arguments (kwargs)."""
     if "entities" not in kwargs or "All" in kwargs["entities"]:
@@ -79,11 +75,9 @@ def anonymize(text, analyze_results):
         text,
         analyze_results,
         operators={"STUDENT": OperatorConfig("custom", {"lambda": generate_surrogate})}
-
     )
     return res.text
 
-
 def annotate(text, st_analyze_results, st_entities):
     tokens = []
     # sort by start index
@@ -129,7 +123,6 @@ st.sidebar.info(
     "This is part of a deidentification project for student-generated text."
 )
 
-
 # Main panel
 analyzer_load_state = st.info(
     "Starting Presidio analyzer and loading Longformer-based model...")
@@ -162,6 +155,7 @@ with st.spinner("Analyzing..."):
         annotated_tokens = annotate(st_text, st_analyze_results, st_entities)
         # annotated_tokens
         annotated_text(*annotated_tokens)
+
 # vertical space
 st.text("")
 
@@ -172,7 +166,6 @@ with st.spinner("Anonymizing..."):
         st_anonymize_results = anonymize(st_text, st_analyze_results)
         st_anonymize_results
 
-
 # table result
 st.subheader("Detailed Findings")
 if st_analyze_results:
@@ -197,8 +190,6 @@ else:
 st.session_state['first_load'] = True
 
 # json result
-
-
 class ToDictListEncoder(JSONEncoder):
     """Encode dict to json."""
 
@@ -208,6 +199,5 @@ class ToDictListEncoder(JSONEncoder):
             return o.to_dict()
         return []
 
-
 if st_return_decision_process:
     st.json(json.dumps(st_analyze_results, cls=ToDictListEncoder))