Update app.py

app.py

@@ -6,27 +6,48 @@ from transformers import pipeline
 from streamlit_extras.stylable_container import stylable_container
 import plotly.express as px
 import zipfile
-
 from PyPDF2 import PdfReader
 import docx
-
-
 import os
 from comet_ml import Experiment
 import re
-import numpy as np 
+import numpy as np
+
+st.set_page_config(layout="wide", page_title="Named Entity Recognition App")
 
 
 
+# --- Configuration ---
+COMET_API_KEY = os.environ.get("COMET_API_KEY")
+COMET_WORKSPACE = os.environ.get("COMET_WORKSPACE")
+COMET_PROJECT_NAME = os.environ.get("COMET_PROJECT_NAME")
+
+comet_initialized = False
+if COMET_API_KEY and COMET_WORKSPACE and COMET_PROJECT_NAME:
+    comet_initialized = True
+
+# --- Initialize session state ---
+if 'file_upload_attempts' not in st.session_state:
+    st.session_state['file_upload_attempts'] = 0
 
-st.subheader("58-Italian Named Entity Recognition Web App", divider = "orange")
-st.link_button("by nlpblogs", "https://nlpblogs.com", type = "tertiary")
+max_attempts = 10
 
-expander = st.expander("**Important notes on the 58-Italian Named Entity Recognition Web App**")
+# --- Helper function for model loading ---
+@st.cache_resource
+def load_ner_model():
+    """Loads the pre-trained NER model and caches it."""
+    return pipeline("token-classification", model="DeepMount00/Italian_NER_XXL", aggregation_strategy="max")
+
+# --- UI Elements ---
+st.subheader("58-Italian Named Entity Recognition Web App", divider="rainbow")
+st.link_button("by nlpblogs", "https://nlpblogs.com", type="tertiary")
+
+
+expander = st.expander("**Important notes on the 58-Italian-Named Entity Recognition Web App**")
 expander.write('''
     
     **Named Entities:**
-    This 58-Italian Named Entity Recognition Web App predicts fifty-eight (58) labels
+    This 58-Italian-Named Entity Recognition Web App predicts fifty-eight (58) labels
     
     ("**INDIRIZZO**: Identifica un indirizzo fisico.
     
@@ -142,7 +163,7 @@ expander.write('''
      
      **DOSAGGIO**: Quantità di un medicinale da assumere.
      
-     **FORM**: Forma del medicinale, ad esempio compresse.")
+     **FORM**: Forma del medicinale, ad esempio compresse"). 
      
      Results are presented in an easy-to-read table, visualized in an interactive tree map, pie chart, and bar chart, and are available for download along with a Glossary of tags.
     
@@ -166,34 +187,15 @@ expander.write('''
 with st.sidebar:
     container = st.container(border=True)
     container.write("**Named Entity Recognition (NER)** is the task of extracting and tagging entities in text data. Entities can be persons, organizations, locations, countries, products, events etc.")
-    st.subheader("Related NLP Web Apps", divider = "orange")
-    st.link_button("8-Named Entity Recognition Web App", "https://nlpblogs.com/shop/named-entity-recognition-ner/8-named-entity-recognition-web-app/", type = "primary")
-
-
-COMET_API_KEY = os.environ.get("COMET_API_KEY")
-COMET_WORKSPACE = os.environ.get("COMET_WORKSPACE")
-COMET_PROJECT_NAME = os.environ.get("COMET_PROJECT_NAME")
-
-if COMET_API_KEY and COMET_WORKSPACE and COMET_PROJECT_NAME:
-    comet_initialized = True
-else:
-    comet_initialized = False
-    st.warning("Comet ML not initialized. Check environment variables.")
-
-    
-
-if 'file_upload_attempts' not in st.session_state:
-    st.session_state['file_upload_attempts'] = 0
-
-max_attempts = 10
-
+    st.subheader("Related NLP Web Apps", divider="rainbow")
+    st.link_button("8-Named Entity Recognition Web App", "https://nlpblogs.com/shop/named-entity-recognition-ner/8-named-entity-recognition-web-app/", type="primary")
 
+# --- File Upload ---
 upload_file = st.file_uploader("Upload your file. Accepted file formats include: .pdf, .docx", type=['pdf', 'docx'])
 text = None
 df = None
 
 if upload_file is not None:
-    
     file_extension = upload_file.name.split('.')[-1].lower()
     if file_extension == 'pdf':
         try:
@@ -201,47 +203,53 @@ if upload_file is not None:
             text = ""
             for page in pdf_reader.pages:
                 text += page.extract_text()
-            st.write("Due to security protocols, the file content is hidden.")
+            st.write("File uploaded successfully. Due to security protocols, the file content is hidden.")
         except Exception as e:
             st.error(f"An error occurred while reading PDF: {e}")
+            text = None
     elif file_extension == 'docx':
         try:
             doc = docx.Document(upload_file)
             text = "\n".join([para.text for para in doc.paragraphs])
-            st.write("Due to security protocols, the file content is hidden.")
+            st.write("File uploaded successfully. Due to security protocols, the file content is hidden.")
         except Exception as e:
             st.error(f"An error occurred while reading docx: {e}")
+            text = None
     else:
         st.warning("Unsupported file type.")
-    
-        st.stop()
-
+        text = None
 
 st.divider()
 
+# --- Results Button and Processing Logic ---
 if st.button("Results"):
+    if not comet_initialized:
+        st.warning("Comet ML not initialized. Check environment variables if you wish to log data.")
+
     if st.session_state['file_upload_attempts'] >= max_attempts:
         st.error(f"You have requested results {max_attempts} times. You have reached your daily request limit.")
         st.stop()
-    st.session_state['file_upload_attempts'] += 1
-    
 
-    with st.spinner("Wait for it...", show_time=True):
-        time.sleep(5)
-        model = pipeline("token-classification", model="DeepMount00/Italian_NER_XXL", aggregation_strategy = "max")
-        text1 = model(text)
-       
-        df1 = pd.DataFrame(text1)
-        pattern = r'[^\w\s]'
-        df1['word'] = df1['word'].replace(pattern, '', regex=True)
+    if text is None:
+        st.warning("Please upload a supported file (.pdf or .docx) before requesting results.")
+        st.stop()
 
-        df2 = df1.replace('', 'Unknown')
-        df = df2.dropna()
+    st.session_state['file_upload_attempts'] += 1
 
-        
-        
+    with st.spinner("Analyzing text...", show_time=True):
+        # Load model (cached)
+        model = load_ner_model()
+        text_entities = model(text)
+        df = pd.DataFrame(text_entities)
 
-        
+        # Clean and filter DataFrame
+        pattern = r'[^\w\s]'
+        df['word'] = df['word'].replace(pattern, '', regex=True)
+        df = df.replace('', 'Unknown').dropna()
+
+        if df.empty:
+            st.warning("No entities were extracted from the uploaded text.")
+            st.stop()
 
         if comet_initialized:
             experiment = Experiment(
@@ -249,12 +257,13 @@ if st.button("Results"):
                 workspace=COMET_WORKSPACE,
                 project_name=COMET_PROJECT_NAME,
             )
-            experiment.log_parameter("input_text", text)
+            experiment.log_parameter("input_text_length", len(text))
             experiment.log_table("predicted_entities", df)
 
+        # --- Display Results ---
         properties = {"border": "2px solid gray", "color": "blue", "font-size": "16px"}
         df_styled = df.style.set_properties(**properties)
-        st.dataframe(df_styled)
+        st.dataframe(df_styled, use_container_width=True)
 
         with st.expander("See Glossary of tags"):
             st.write('''
@@ -269,45 +278,48 @@ if st.button("Results"):
             '**end**': ['index of the end of the corresponding entity']
             ''')
 
-        if df is not None:
-            fig = px.treemap(df, path=[px.Constant("all"), 'word', 'entity_group'],
+        # --- Visualizations ---
+        st.subheader("Tree map", divider="rainbow")
+        fig_treemap = px.treemap(df, path=[px.Constant("all"), 'word', 'entity_group'],
                                  values='score', color='entity_group')
-            fig.update_layout(margin = dict(t=50, l=25, r=25, b=25))
-            st.subheader("Tree map", divider = "rainbow")
-            st.plotly_chart(fig)
+        fig_treemap.update_layout(margin=dict(t=50, l=25, r=25, b=25))
+        st.plotly_chart(fig_treemap)
+        if comet_initialized:
+            experiment.log_figure(figure=fig_treemap, figure_name="entity_treemap")
+
+        value_counts1 = df['entity_group'].value_counts()
+        final_df_counts = value_counts1.reset_index().rename(columns={"index": "entity_group"})
+
+        col1, col2 = st.columns(2)
+        with col1:
+            st.subheader("Pie Chart", divider="rainbow")
+            fig_pie = px.pie(final_df_counts, values='count', names='entity_group', hover_data=['count'], labels={'count': 'count'}, title='Percentage of predicted labels')
+            fig_pie.update_traces(textposition='inside', textinfo='percent+label')
+            st.plotly_chart(fig_pie)
+            if comet_initialized:
+                experiment.log_figure(figure=fig_pie, figure_name="label_pie_chart")
+
+        with col2:
+            st.subheader("Bar Chart", divider="rainbow")
+            fig_bar = px.bar(final_df_counts, x="count", y="entity_group", color="entity_group", text_auto=True, title='Occurrences of predicted labels')
+            st.plotly_chart(fig_bar)
             if comet_initialized:
-                experiment.log_figure(figure=fig, figure_name="entity_treemap")
-
-        if df is not None:
-            value_counts1 = df['entity_group'].value_counts()
-            df1 = pd.DataFrame(value_counts1)
-            final_df = df1.reset_index().rename(columns={"index": "entity_group"})
-            col1, col2 = st.columns(2)
-            with col1:
-                fig1 = px.pie(final_df, values='count', names='entity_group', hover_data=['count'], labels={'count': 'count'}, title='Percentage of predicted labels')
-                fig1.update_traces(textposition='inside', textinfo='percent+label')
-                st.subheader("Pie Chart", divider = "orange")
-                st.plotly_chart(fig1)
-                if comet_initialized:
-                    experiment.log_figure(figure=fig1, figure_name="label_pie_chart")
-            with col2:
-                fig2 = px.bar(final_df, x="count", y="entity_group", color="entity_group", text_auto=True, title='Occurrences of predicted labels')
-                st.subheader("Bar Chart", divider = "orange")
-                st.plotly_chart(fig2)
-                if comet_initialized:
-                    experiment.log_figure(figure=fig2, figure_name="label_bar_chart")
+                experiment.log_figure(figure=fig_bar, figure_name="label_bar_chart")
 
+        # --- Downloadable Content ---
         dfa = pd.DataFrame(
             data={
-                'word': ['entity extracted from your text data'], 'score': ['accuracy score; how accurately a tag has been assigned to a given entity'], 'entity_group': ['label (tag) assigned to a given extracted entity'],
+                'word': ['entity extracted from your text data'],
+                'score': ['accuracy score; how accurately a tag has been assigned to a given entity'],
+                'entity_group': ['label (tag) assigned to a given extracted entity'],
                 'start': ['index of the start of the corresponding entity'],
                 'end': ['index of the end of the corresponding entity'],
-                })
+            })
+
         buf = io.BytesIO()
         with zipfile.ZipFile(buf, "w") as myzip:
             myzip.writestr("Summary of the results.csv", df.to_csv(index=False))
             myzip.writestr("Glossary of tags.csv", dfa.to_csv(index=False))
-            
 
         with stylable_container(
             key="download_button",
@@ -316,7 +328,7 @@ if st.button("Results"):
             st.download_button(
                 label="Download zip file",
                 data=buf.getvalue(),
-                file_name="zip file.zip",
+                file_name="nlpblogs_ner_results.zip",
                 mime="application/zip",
             )
             if comet_initialized:
@@ -325,4 +337,5 @@ if st.button("Results"):
         st.divider()
         if comet_initialized:
             experiment.end()
-st.write(f"Number of times you requested results: {st.session_state['file_upload_attempts']}/{max_attempts}")
+
+st.write(f"Number of times you requested results: **{st.session_state['file_upload_attempts']}/{max_attempts}**")