Update src/streamlit_app.py

src/streamlit_app.py

@@ -18,57 +18,66 @@ st.markdown(
     <style>
     /* Main app background and text color */
     .stApp {
-        background-color: #E8F5E9; /* A very light green */
-        color: #1B5E20; /* Dark green for the text */
+        background-color: #F0F8FF; /* AliceBlue */
+        color: #000080; /* Navy */
     }
-        /* Sidebar background color */
+
+    /* Sidebar background color */
     .css-1d36184 {
-        background-color: #A5D6A7; /* A medium light green */
-        secondary-background-color: #A5D6A7;
+        background-color: #B0E0E6; /* PowderBlue */
+        secondary-background-color: #B0E0E6;
     }
-        /* Expander background color and header */
+
+    /* Expander background color and header */
     .streamlit-expanderContent, .streamlit-expanderHeader {
-        background-color: #E8F5E9;
+        background-color: #F0F8FF;
     }
-        /* Text Area background and text color */
+
+    /* Text Area background and text color */
     .stTextArea textarea {
-        background-color: #81C784; /* A slightly darker medium green */
-        color: #1B5E20; /* Dark green for text */
+        background-color: #ADD8E6; /* LightBlue */
+        color: #000080; /* Navy */
     }
-        /* Button background and text color */
+
+    /* Button background and text color */
     .stButton > button {
-        background-color: #81C784;
-        color: #1B5E20;
+        background-color: #ADD8E6;
+        color: #000080;
     }
-        /* Warning box background and text color */
+
+    /* Warning box background and text color */
     .stAlert.st-warning {
-        background-color: #66BB6A; /* A medium-dark green for the warning box */
-        color: #1B5E20;
+        background-color: #87CEFA; /* LightSkyBlue */
+        color: #000080;
     }
-        /* Success box background and text color */
+
+    /* Success box background and text color */
     .stAlert.st-success {
-        background-color: #66BB6A; /* A medium-dark green for the success box */
-        color: #1B5E20;
+        background-color: #87CEFA; /* LightSkyBlue */
+        color: #000080;
     }
     </style>
     """,
-    unsafe_allow_html=True)
+    unsafe_allow_html=True
+)
+
 # --- Page Configuration and UI Elements ---
 st.set_page_config(layout="wide", page_title="Named Entity Recognition App")
-st.subheader("ChainSense", divider="violet")
+st.subheader("ChainSense", divider="blue")
 st.link_button("by nlpblogs", "https://nlpblogs.com", type="tertiary")
+
 expander = st.expander("**Important notes**")
-expander.write("""**Named Entities:** This ChainSense web app predicts eight (8) labels:"Location", "Organization", "Product_or_Good", "Date", "Quantity", "Transportation_Mode", "Person", "Document_or_Form_ID"
+expander.write("""**Named Entities:** This ChainSense web app predicts eight (8) labels: "Location", "Organization", "Product_or_Good", "Date", "Quantity", "Transportation_Mode", "Person", "Document_or_Form_ID"
 
-Results are presented in easy-to-read tables, visualized in an interactive tree map, pie chart and bar chart, and are available for download along with a Glossary of tags.      
+Results are presented in easy-to-read tables, visualized in an interactive tree map, pie chart and bar chart, and are available for download along with a Glossary of tags.
 
-**How to Use:** Type or paste your text into the text area below, then press Ctrl + Enter. Click the 'Results' button to extract and tag entities in your text data.      
+**How to Use:** Type or paste your text into the text area below, then press Ctrl + Enter. Click the 'Results' button to extract and tag entities in your text data.
 
-**Usage Limits:** You can request results unlimited times for one (1) month.      
+**Usage Limits:** You can request results unlimited times for one (1) month.
 
-**Supported Languages:** English 
+**Supported Languages:** English
 
-**Technical issues:** If your connection times out, please refresh the page or reopen the app's URL. 
+**Technical issues:** If your connection times out, please refresh the page or reopen the app's URL.
 
 For any errors or inquiries, please contact us at [email protected]""")
 
@@ -87,15 +96,18 @@ with st.sidebar:
     st.text("")
     st.text("")
     st.divider()
-    st.subheader("🚀 Ready to build your own AI Web App?", divider="violet")
-    st.link_button("AI Web App Builder", "https://nlpblogs.com/build-your-named-entity-recognition-app/", type="primary")
+    st.subheader("🚀 Ready to build your own AI Web App?", divider="blue")
+    st.link_button("AI Web App Builder", "https://nlpblogs.com/custom-web-app-development/", type="primary")
+
 # --- Comet ML Setup ---
 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 = bool(COMET_API_KEY and COMET_WORKSPACE and COMET_PROJECT_NAME)
+
 if not comet_initialized:
     st.warning("Comet ML not initialized. Check environment variables.")
+
 # --- Label Definitions ---
 labels = [
     "Location",
@@ -105,14 +117,18 @@ labels = [
     "Quantity",
     "Transportation_Mode",
     "Person",
-    "Document_or_Form_ID"]
-# Corrected mapping dictionary
+    "Document_or_Form_ID"
+]
+
 # Create a mapping dictionary for labels to categories
 category_mapping = {
     "People & Groups": ["Person", "Organization"],
-    "Goods & Transactions": ["Product_or_Good", "Quantity", "Document_or_Form_ID"],
-    "Temporal & Events": ["Date", "Transportation_Mode"],
-    "Locations": ["Location"]}
+    "Goods & Transactions": ["Product_or_Good", "Quantity"],
+    "Temporal": ["Date"],
+    "Logistics & Operations": ["Transportation_Mode", "Document_or_Form_ID"],
+    "Locations": ["Location"]
+}
+
 # --- Model Loading ---
 @st.cache_resource
 def load_ner_model():
@@ -123,32 +139,34 @@ def load_ner_model():
         st.error(f"Failed to load NER model. Please check your internet connection or model availability: {e}")
         st.stop()
 model = load_ner_model()
+
 # Flatten the mapping to a single dictionary
 reverse_category_mapping = {label: category for category, label_list in category_mapping.items() for label in label_list}
+
 # --- Text Input and Clear Button ---
-# Define the word limit
 word_limit = 200
-# Update text area with the word limit
 text = st.text_area(f"Type or paste your text below (max {word_limit} words), and then press Ctrl + Enter", height=250, key='my_text_area')
-# Calculate and display the word count
 word_count = len(text.split())
 st.markdown(f"**Word count:** {word_count}/{word_limit}")
+
 def clear_text():
     """Clears the text area."""
     st.session_state['my_text_area'] = ""
+
 st.button("Clear text", on_click=clear_text)
+
 # --- Results Section ---
 if st.button("Results"):
-    # Check for word limit and empty text first
+    start_time = time.time()
     if not text.strip():
         st.warning("Please enter some text to extract entities.")
     elif word_count > word_limit:
         st.warning(f"Your text exceeds the {word_limit} word limit. Please shorten it to continue.")
     else:
-        start_time = time.time()
         with st.spinner("Extracting entities...", show_time=True):
             entities = model.predict_entities(text, labels)
             df = pd.DataFrame(entities)
+
             if not df.empty:
                 df['category'] = df['label'].map(reverse_category_mapping)
                 if comet_initialized:
@@ -159,17 +177,21 @@ if st.button("Results"):
                     )
                     experiment.log_parameter("input_text", text)
                     experiment.log_table("predicted_entities", df)
-                st.subheader("Grouped Entities by Category", divider = "violet")
+
+                st.subheader("Grouped Entities by Category", divider="blue")
+                
                 # Create tabs for each category
                 category_names = sorted(list(category_mapping.keys()))
                 category_tabs = st.tabs(category_names)
+
                 for i, category_name in enumerate(category_names):
                     with category_tabs[i]:
                         df_category_filtered = df[df['category'] == category_name]
                         if not df_category_filtered.empty:
-                            st.dataframe(df_category_filtered.drop(columns=['category']), use_container_width=True)
+                           st.dataframe(df_category_filtered.drop(columns=['category']), use_container_width=True)
                         else:
-                            st.info(f"No entities found for the '{category_name}' category.")
+                           st.info(f"No entities found for the '{category_name}' category.")
+
                 with st.expander("See Glossary of tags"):
                     st.write('''
                     - **text**: ['entity extracted from your text data']
@@ -179,34 +201,39 @@ if st.button("Results"):
                     - **end**: ['index of the end of the corresponding entity']
                     ''')
                 st.divider()
+
                 # Tree map
-                st.subheader("Tree map", divider = "violet")
+                st.subheader("Tree map", divider="blue")
                 fig_treemap = px.treemap(df, path=[px.Constant("all"), 'category', 'label', 'text'], values='score', color='category')
-                fig_treemap.update_layout(margin=dict(t=50, l=25, r=25, b=25), paper_bgcolor='#E8F5E9', plot_bgcolor='#E8F5E9')
+                fig_treemap.update_layout(margin=dict(t=50, l=25, r=25, b=25), paper_bgcolor='#F0F8FF', plot_bgcolor='#F0F8FF')
                 st.plotly_chart(fig_treemap)
+
                 # Pie and Bar charts
                 grouped_counts = df['category'].value_counts().reset_index()
                 grouped_counts.columns = ['category', 'count']
                 col1, col2 = st.columns(2)
+
                 with col1:
-                    st.subheader("Pie chart", divider = "violet")
+                    st.subheader("Pie chart", divider="blue")
                     fig_pie = px.pie(grouped_counts, values='count', names='category', hover_data=['count'], labels={'count': 'count'}, title='Percentage of predicted categories')
                     fig_pie.update_traces(textposition='inside', textinfo='percent+label')
                     fig_pie.update_layout(
-                        paper_bgcolor='#E8F5E9',
-                        plot_bgcolor='#E8F5E9'
+                        paper_bgcolor='#F0F8FF',
+                        plot_bgcolor='#F0F8FF'
                     )
                     st.plotly_chart(fig_pie)
+
                 with col2:
-                    st.subheader("Bar chart", divider = "violet")
+                    st.subheader("Bar chart", divider="blue")
                     fig_bar = px.bar(grouped_counts, x="count", y="category", color="category", text_auto=True, title='Occurrences of predicted categories')
-                    fig_bar.update_layout(  # Changed from fig_pie to fig_bar
-                        paper_bgcolor='#E8F5E9',
-                        plot_bgcolor='#E8F5E9'
+                    fig_bar.update_layout(
+                        paper_bgcolor='#F0F8FF',
+                        plot_bgcolor='#F0F8FF'
                     )
                     st.plotly_chart(fig_bar)
+                
                 # Most Frequent Entities
-                st.subheader("Most Frequent Entities", divider="violet")
+                st.subheader("Most Frequent Entities", divider="blue")
                 word_counts = df['text'].value_counts().reset_index()
                 word_counts.columns = ['Entity', 'Count']
                 repeating_entities = word_counts[word_counts['Count'] > 1]
@@ -214,13 +241,15 @@ if st.button("Results"):
                     st.dataframe(repeating_entities, use_container_width=True)
                     fig_repeating_bar = px.bar(repeating_entities, x='Entity', y='Count', color='Entity')
                     fig_repeating_bar.update_layout(xaxis={'categoryorder': 'total descending'},
-                        paper_bgcolor='#E8F5E9',
-                        plot_bgcolor='#E8F5E9')
+                                                    paper_bgcolor='#F0F8FF',
+                                                    plot_bgcolor='#F0F8FF')
                     st.plotly_chart(fig_repeating_bar)
                 else:
                     st.warning("No entities were found that occur more than once.")
+
                 # Download Section
                 st.divider()
+
                 dfa = pd.DataFrame(
                     data={
                         'Column Name': ['text', 'label', 'score', 'start', 'end'],
@@ -237,9 +266,10 @@ if st.button("Results"):
                 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",
-                    css_styles="""button { background-color: red; border: 1px solid black; padding: 5px; color: white; }""",
+                    css_styles="""button { background-color: blue; border: 1px solid black; padding: 5px; color: white; }""",
                 ):
                     st.download_button(
                         label="Download results and glossary (zip)",
@@ -247,15 +277,15 @@ if st.button("Results"):
                         file_name="nlpblogs_results.zip",
                         mime="application/zip",
                     )
+                
                 if comet_initialized:
                     experiment.log_figure(figure=fig_treemap, figure_name="entity_treemap_categories")
                     experiment.end()
-                
-                # Corrected placement for time calculation and display
+
                 end_time = time.time()
                 elapsed_time = end_time - start_time
                 st.text("")
                 st.text("")
                 st.info(f"Results processed in **{elapsed_time:.2f} seconds**.")
-            else: # If df is empty
+            else:  # If df is empty
                 st.warning("No entities were found in the provided text.")