Update src/streamlit_app.py

src/streamlit_app.py

@@ -6,7 +6,6 @@ import pandas as pd
 import io
 import plotly.express as px
 import zipfile
-import json
 import string
 from cryptography.fernet import Fernet
 from streamlit_extras.stylable_container import stylable_container
@@ -16,11 +15,60 @@ from comet_ml import Experiment
 
 # --- Page Configuration and UI Elements ---
 st.set_page_config(layout="wide", page_title="Named Entity Recognition App")
-st.markdown("""
-<style>
-/* ... (Your CSS Styles) ... */
-</style>
-""", unsafe_allow_html=True)
+
+st.markdown(
+    """
+    <style>
+    /* Overall app container */
+    .stApp {
+        background-color: #F5F5F5; /* A very light grey */
+        color: #333333; /* Dark grey for text for good contrast */
+    }
+    /* Sidebar background */
+    .css-1d36184, .css-1d36184, .st-ck {
+        background-color: #D3D3D3; /* Light grey for the sidebar */
+    }
+    /* Expander header and content background */
+    .streamlit-expanderHeader, .streamlit-expanderContent {
+        background-color: #F5F5F5;
+    }
+    /* Text Area background and text color */
+    .stTextArea textarea {
+        background-color: #E6E6E6; /* Slightly darker grey for input fields */
+        color: #000000;
+        border: 1px solid #B0B0B0; /* Add a subtle border */
+    }
+    /* Button styling */
+    .stButton > button {
+        background-color: #B0B0B0; /* A medium grey for the button */
+        color: #FFFFFF; /* White text for contrast */
+        border: none;
+        padding: 10px 20px;
+        border-radius: 5px;
+    }
+    .stButton > button:hover {
+        background-color: #8C8C8C; /* Darker grey on hover */
+    }
+    /* Alert boxes */
+    .stAlert {
+        color: #000000;
+        border-left: 5px solid #8C8C8C; /* A dark grey border for a clean look */
+    }
+    .stAlert.st-warning {
+        background-color: #C0C0C0; /* Silver grey for warning */
+    }
+    .stAlert.st-success {
+        background-color: #C0C0C0; /* Silver grey for success */
+    }
+    /* Plotly container background */
+    .st-emotion-cache-1ujn73o, .st-emotion-cache-1215v34 {
+        background-color: #F5F5F5 !important;
+    }
+    </style>
+    """,
+    unsafe_allow_html=True
+)
+
 st.subheader("DataHarvest", divider="violet")
 st.link_button("by nlpblogs", "https://nlpblogs.com", type="tertiary")
 st.markdown(':rainbow[**Supported Languages: English**]')
@@ -62,6 +110,7 @@ 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.")
+    print("Warning: Comet ML environment variables are not set. Logging will be disabled.")
 
 # --- Label Definitions ---
 labels = ["person", "country", "city", "organization", "date", "time", "cardinal", "money", "position"]
@@ -69,27 +118,31 @@ category_mapping = {
     "People": ["person", "organization", "position"],
     "Locations": ["country", "city"],
     "Time": ["date", "time"],
-    "Numbers": ["money", "cardinal"]}
+    "Numbers": ["money", "cardinal"]
+}
 
 # --- Model Loading ---
 @st.cache_resource
 def load_ner_model():
+    """Loads the GLiNER model and caches it."""
     try:
-        return GLiNER.from_pretrained("knowledgator/gliner-multitask-large-v0.5", nested_ner=True, num_gen_sequences=2, gen_constraints= labels)
+        return GLiNER.from_pretrained("knowledgator/gliner-multitask-large-v0.5", nested_ner=True, num_gen_sequences=2, gen_constraints=labels)
     except Exception as e:
         st.error(f"Failed to load NER model. Please check your internet connection or model availability: {e}")
         st.stop()
+
 model = load_ner_model()
 reverse_category_mapping = {label: category for category, label_list in category_mapping.items() for label in label_list}
 
 # --- Session State Initialization ---
-# This is the key fix. We use session state to control what is displayed.
 if 'show_results' not in st.session_state:
     st.session_state.show_results = False
 if 'last_text' not in st.session_state:
     st.session_state.last_text = ""
 if 'results_df' not in st.session_state:
     st.session_state.results_df = pd.DataFrame()
+if 'elapsed_time' not in st.session_state:
+    st.session_state.elapsed_time = 0.0
 
 # --- Text Input and Clear Button ---
 word_limit = 200
@@ -102,6 +155,8 @@ def clear_text():
     st.session_state['my_text_area'] = ""
     st.session_state.show_results = False
     st.session_state.last_text = ""
+    st.session_state.results_df = pd.DataFrame()
+    st.session_state.elapsed_time = 0.0
 
 def remove_punctuation(text):
     """Removes punctuation from a string."""
@@ -119,33 +174,39 @@ if st.button("Results"):
         st.warning(f"Your text exceeds the {word_limit} word limit. Please shorten it to continue.")
         st.session_state.show_results = False
     else:
-        st.session_state.show_results = True
-        st.session_state.last_text = text
-        start_time = time.time()
-        with st.spinner("Extracting entities...", show_time=True):
-            cleaned_text = remove_punctuation(text)
-            entities = model.predict_entities(cleaned_text, labels)
-            df = pd.DataFrame(entities)
-            st.session_state.results_df = df
-            if not df.empty:
-                df['category'] = df['label'].map(reverse_category_mapping)
-                if comet_initialized:
-                    experiment = Experiment(api_key=COMET_API_KEY, workspace=COMET_WORKSPACE, project_name=COMET_PROJECT_NAME)
-                    experiment.log_parameter("input_text", text)
-                    experiment.log_table("predicted_entities", df)
-                    experiment.end()
-            
-                end_time = time.time()
-                elapsed_time = end_time - start_time
-                st.session_state.elapsed_time = elapsed_time
+        # Check if the text is different from the last time
+        if text != st.session_state.last_text:
+            st.session_state.show_results = True
+            st.session_state.last_text = text
+            start_time = time.time()
+            with st.spinner("Extracting entities...", show_time=True):
+                cleaned_text = remove_punctuation(text)
+                entities = model.predict_entities(cleaned_text, labels)
+                df = pd.DataFrame(entities)
+                st.session_state.results_df = df
+                if not df.empty:
+                    df['category'] = df['label'].map(reverse_category_mapping)
+                    if comet_initialized:
+                        experiment = Experiment(api_key=COMET_API_KEY, workspace=COMET_WORKSPACE, project_name=COMET_PROJECT_NAME)
+                        experiment.log_parameter("input_text", text)
+                        experiment.log_table("predicted_entities", df)
+                        experiment.end()
+            end_time = time.time()
+            st.session_state.elapsed_time = end_time - start_time
+        # If the text is the same, do nothing but keep results displayed
+        else:
+            st.session_state.show_results = True
 
 # Display results if the state variable is True
 if st.session_state.show_results:
     df = st.session_state.results_df
     if not df.empty:
-        st.subheader("Grouped Entities by Category", divider = "violet")
+        df['category'] = df['label'].map(reverse_category_mapping)
+        st.subheader("Grouped Entities by Category", divider="violet")
+        
         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]
@@ -153,7 +214,7 @@ if st.session_state.show_results:
                     st.dataframe(df_category_filtered.drop(columns=['category']), use_container_width=True)
                 else:
                     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']
@@ -162,10 +223,11 @@ if st.session_state.show_results:
             - **start**: ['index of the start of the corresponding entity']
             - **end**: ['index of the end of the corresponding entity']
             ''')
+        
         st.divider()
 
         # Tree map
-        st.subheader("Tree map", divider = "violet")
+        st.subheader("Tree map", divider="violet")
         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))
         st.plotly_chart(fig_treemap)
@@ -174,13 +236,15 @@ if st.session_state.show_results:
         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="violet")
             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')
             st.plotly_chart(fig_pie)
+            
         with col2:
-            st.subheader("Bar chart", divider = "violet")
+            st.subheader("Bar chart", divider="violet")
             fig_bar = px.bar(grouped_counts, x="count", y="category", color="category", text_auto=True, title='Occurrences of predicted categories')
             st.plotly_chart(fig_bar)
 
@@ -189,6 +253,7 @@ if st.session_state.show_results:
         word_counts = df['text'].value_counts().reset_index()
         word_counts.columns = ['Entity', 'Count']
         repeating_entities = word_counts[word_counts['Count'] > 1]
+        
         if not repeating_entities.empty:
             st.dataframe(repeating_entities, use_container_width=True)
             fig_repeating_bar = px.bar(repeating_entities, x='Entity', y='Count', color='Entity')
@@ -196,20 +261,31 @@ if st.session_state.show_results:
             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'],
                                 'Description': ['entity extracted from your text data', 'label (tag) assigned to a given extracted entity', 'accuracy score; how accurately a tag has been assigned to a given entity', 'index of the start of the corresponding entity', '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", css_styles="""button { background-color: red; border: 1px solid black; padding: 5px; color: white; }""",):
-            st.download_button(label="Download results and glossary (zip)", data=buf.getvalue(), file_name="nlpblogs_results.zip", mime="application/zip")
         
+        with stylable_container(
+            key="download_button",
+            css_styles="""button { background-color: #8C8C8C; border: 1px solid black; padding: 5px; color: white; }""",
+        ):
+            st.download_button(
+                label="Download results and glossary (zip)",
+                data=buf.getvalue(),
+                file_name="nlpblogs_results.zip",
+                mime="application/zip"
+            )
+
         st.text("")
         st.text("")
         st.info(f"Results processed in **{st.session_state.elapsed_time:.2f} seconds**.")
-    else: # If df is empty after the button click
+
+    else:
         st.warning("No entities were found in the provided text.")