Update app.py

app.py

@@ -22,21 +22,10 @@ def read_file(file):
         st.error("Unsupported file type")
         return None
 
-# Rest of your code remains the same
-example_list = [
-    "Mustafa Kemal Atatürk 1919 yılında Samsun'a çıktı.",
-    """Mustafa Kemal Atatürk, Türk asker, devlet adamı ve Türkiye Cumhuriyeti'nin kurucusudur.
-    # ... (rest of the example text)
-    """
-]
-
 st.title("Demo for Turkish NER Models")
 
 model_list = [
-    'akdeniz27/bert-base-turkish-cased-ner',
-    'akdeniz27/convbert-base-turkish-cased-ner',
     'girayyagmur/bert-base-turkish-ner-cased',
-    'FacebookAI/xlm-roberta-large',
     'savasy/bert-base-turkish-ner-cased',
     'xlm-roberta-large-finetuned-conll03-english',
     'asahi417/tner-xlm-roberta-base-ontonotes5'
@@ -46,46 +35,41 @@ st.sidebar.header("Select NER Model")
 model_checkpoint = st.sidebar.radio("", model_list)
 
 st.sidebar.write("For details of models: 'https://huggingface.co/akdeniz27/")
-st.sidebar.write("")
+st.sidebar.write("Only PDF, DOCX, and TXT files are supported.")
 
-if model_checkpoint in ["akdeniz27/xlm-roberta-base-turkish-ner", "xlm-roberta-large-finetuned-conll03-english", "asahi417/tner-xlm-roberta-base-ontonotes5"]:
-    aggregation = "simple"
-    if model_checkpoint != "akdeniz27/xlm-roberta-base-turkish-ner":
-        st.sidebar.write("The selected NER model is included just to show the zero-shot transfer learning capability of XLM-Roberta pretrained language model.")
-else:
-    aggregation = "first"
+# Determine aggregation strategy
+aggregation = "simple" if model_checkpoint in ["akdeniz27/xlm-roberta-base-turkish-ner", 
+                                                "xlm-roberta-large-finetuned-conll03-english", 
+                                                "asahi417/tner-xlm-roberta-base-ontonotes5"] else "first"
 
 st.subheader("Select Text Input Method")
 input_method = st.radio("", ('Select from Examples', 'Write or Paste New Text', 'Upload File'))
 
+example_list = [
+    "Mustafa Kemal Atatürk 1919 yılında Samsun'a çıktı.",
+    """Mustafa Kemal Atatürk, Türk asker, devlet adamı ve Türkiye Cumhuriyeti'nin kurucusudur."""
+]
+
 if input_method == 'Select from Examples':
-    selected_text = st.selectbox('Select Text from List', example_list, index=0, key=1)
-    input_text = st.text_area("Selected Text", selected_text, height=128, max_chars=None, key=2)
+    selected_text = st.selectbox('Select Text from List', example_list, index=0)
+    input_text = st.text_area("Selected Text", selected_text, height=128)
 elif input_method == "Write or Paste New Text":
-    input_text = st.text_area('Write or Paste Text Below', value="", height=128, max_chars=None, key=2)
+    input_text = st.text_area('Write or Paste Text Below', value="", height=128)
 else:
     uploaded_file = st.file_uploader("Choose a file", type=["txt", "pdf", "docx"])
     if uploaded_file is not None:
         input_text = read_file(uploaded_file)
         if input_text:
-            st.text_area("Extracted Text", input_text, height=128, max_chars=None, key=2)
+            st.text_area("Extracted Text", input_text, height=128)
     else:
         input_text = ""
 
-# Rest of your functions (setModel, get_html, entity_comb) remain the same
-
 @st.cache_resource
 def setModel(model_checkpoint, aggregation):
     model = AutoModelForTokenClassification.from_pretrained(model_checkpoint)
     tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
     return pipeline('ner', model=model, tokenizer=tokenizer, aggregation_strategy=aggregation)
 
-@st.cache_resource
-def get_html(html: str):
-    WRAPPER = """<div style="overflow-x: auto; border: 1px solid #e6e9ef; border-radius: 0.25rem; padding: 1rem; margin-bottom: 2.5rem">{}</div>"""
-    html = html.replace("\n", " ")
-    return WRAPPER.format(html)
-
 @st.cache_resource
 def entity_comb(output):
     output_comb = []
@@ -93,46 +77,31 @@ def entity_comb(output):
         if ind == 0:
             output_comb.append(entity)
         elif output[ind]["start"] == output[ind-1]["end"] and output[ind]["entity_group"] == output[ind-1]["entity_group"]:
-            output_comb[-1]["word"] = output_comb[-1]["word"] + output[ind]["word"]
+            output_comb[-1]["word"] += output[ind]["word"]
             output_comb[-1]["end"] = output[ind]["end"]
         else:
             output_comb.append(entity)
     return output_comb
 
-Run_Button = st.button("Run", key=None)
+Run_Button = st.button("Run")
 
-if Run_Button and input_text != "":
-    # Your existing processing code remains the same
+if Run_Button and input_text:
     ner_pipeline = setModel(model_checkpoint, aggregation)
     output = ner_pipeline(input_text)
     
     output_comb = entity_comb(output)
     
     df = pd.DataFrame.from_dict(output_comb)
-    cols_to_keep = ['word','entity_group','score','start','end']
+    cols_to_keep = ['word', 'entity_group', 'score', 'start', 'end']
     df_final = df[cols_to_keep]
     
     st.subheader("Recognized Entities")
     st.dataframe(df_final)
 
-    st.subheader("Spacy Style Display")
-    spacy_display = {}
-    spacy_display["ents"] = []
-    spacy_display["text"] = input_text
-    spacy_display["title"] = None
-
+    # Spacy display logic
+    spacy_display = {"ents": [], "text": input_text, "title": None}
     for entity in output_comb:
         spacy_display["ents"].append({"start": entity["start"], "end": entity["end"], "label": entity["entity_group"]})
-        
-    tner_entity_list = ["person", "group", "facility", "organization", "geopolitical area", "location", "product", "event", "work of art", "law", "language", "date", "time", "percent", "money", "quantity", "ordinal number", "cardinal number"]
-    spacy_entity_list = ["PERSON", "NORP", "FAC", "ORG", "GPE", "LOC", "PRODUCT", "EVENT", "WORK_OF_ART", "LAW", "LANGUAGE", "DATE", "TIME", "PERCENT", "MONEY", "QUANTITY", "ORDINAL", "CARDINAL", "MISC"]
-    
-    for ent in spacy_display["ents"]:
-        if model_checkpoint == "asahi417/tner-xlm-roberta-base-ontonotes5":
-            ent["label"] = spacy_entity_list[tner_entity_list.index(ent["label"])]
-        else:
-            if ent["label"] == "PER": ent["label"] = "PERSON"
     
-    html = spacy.displacy.render(spacy_display, style="ent", minify=True, manual=True, options={"ents": spacy_entity_list})
-    style = "<style>mark.entity { display: inline-block }</style>"
-    st.write(f"{style}{get_html(html)}", unsafe_allow_html=True)
+    html = spacy.displacy.render(spacy_display, style="ent", minify=True, manual=True)
+    st.write(html, unsafe_allow_html=True)