Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,4 +1,5 @@
 import os
+os.environ['HF_HOME'] = '/tmp'
 import time
 import streamlit as st
 import pandas as pd
@@ -25,7 +26,8 @@ st.markdown(
         background-color: #B2F2B2; /* A pale green for the sidebar */
         secondary-background-color: #B2F2B2;
     }
-        /* Expander background color */
+    
+    /* Expander background color */
     .streamlit-expanderContent {
         background-color: #F5FFFA;
     }
@@ -63,17 +65,23 @@ st.set_page_config(layout="wide", page_title="Named Entity Recognition App")
 st.subheader("HR.ai", divider="orange")
 st.link_button("by nlpblogs", "https://nlpblogs.com", type="tertiary")
 expander = st.expander("**Important notes**")
-expander.write("""**Named Entities:** This HR.ai predicts sixty (60) labels:"Email", "Phone_number", "Street_address", "City", "State", "Zip_code", "Country", "Date_of_birth", "Gender", "Marital_status", "Person", "Full_time", "Part_time", "Contract", "Temporary", "Terminated", "Active", "Retired", "Job_title", "Employment_type", "Year", "Date", "Company", "Organization", "Role", "Position","Performance_review", "Performance_rating", "Performance_score", "Sick_days", "Vacation_days", "Leave_of_absence", "Holidays", "Pension", "Retirement_plan", "Bonus", "Stock_options", "Health_insurance", "Retire_date", "Pay_rate", "Hourly_wage", "Annual_salary", "Overtime_pay", "Tax", "Social_security", "Deductions", "Job_posting", "Job_description", "Interview_type", "Applicant", "Candidate", "Referral", "Job_board", "Recruiter","Contract", "Offer_letter", "Agreement", "Training_course", "Certification", "Skill"
-      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.
-      **Usage Limits:** You can request results unlimited times for one (1) month.
-      **Supported Languages:** English, German, French, Italian, Spanish, Portuguese
-      **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]""")
+expander.write("""**Named Entities:** This HR.ai predicts sixty (60) labels:"Email", "Phone_number", "Street_address", "City", "State", "Zip_code", "Country", "Date_of_birth", "Gender", "Marital_status", "Person", "Full_time", "Part_time", "Contract", "Temporary", "Terminated", "Active", "Retired", "Job_title", "Employment_type", "Year", "Date", "Company", "Organization", "Role", "Position","Performance_review", "Performance_rating", "Performance_score", "Sick_days", "Vacation_days", "Leave_of_absence", "Holidays", "Pension", "Retirement_plan", "Bonus", "Stock_options", "Health_insurance", "Retire_date", "Pay_rate", "Hourly_wage", "Annual_salary", "Overtime_pay", "Tax", "Social_security", "Deductions", "Job_posting", "Job_description", "Interview_type", "Applicant", "Candidate", "Referral", "Job_board", "Recruiter","Contract", "Offer_letter", "Agreement", "Training_course", "Certification", "Skill"      
+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.      
+**Usage Limits:** You can request results unlimited times for one (1) month.      
+**Supported Languages:** English, German, French, Italian, Spanish, Portuguese      
+**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]""")
 
 with st.sidebar:
     st.write("Use the following code to embed the HR.ai web app on your website. Feel free to adjust the width and height values to fit your page.")
     code = '''
-    <iframe	src="https://aiecosystem-hr-ai.hf.space"	frameborder="0"	width="850"	height="450"    ></iframe>
+    <iframe
+	src="https://aiecosystem-hr-ai.hf.space"
+	frameborder="0"
+	width="850"
+	height="450"
+    ></iframe>
     '''
     st.code(code, language="html")
     st.text("")
@@ -87,6 +95,7 @@ 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.")
 
@@ -132,6 +141,7 @@ def clear_text():
 
 st.button("Clear text", on_click=clear_text)
 
+
 # --- Results Section ---
 if st.button("Results"):
     start_time = time.time()
@@ -141,6 +151,7 @@ if st.button("Results"):
         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:
@@ -151,13 +162,13 @@ if st.button("Results"):
                     )
                     experiment.log_parameter("input_text", text)
                     experiment.log_table("predicted_entities", df)
-                                
+                
                 st.subheader("Extracted Entities", divider = "orange")
-                                
+                
                 # 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]
@@ -165,7 +176,9 @@ if st.button("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']
@@ -176,22 +189,18 @@ if st.button("Results"):
                     - **end**: ['index of the end of the corresponding entity']
                     ''')
                 st.divider()
-                                                
+                                
                 # Tree map
                 st.subheader("Tree map", divider = "orange")
                 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='#F5FFFA',
-                    plot_bgcolor='#F5FFFA'
-                )
+                fig_treemap.update_layout(margin=dict(t=50, l=25, r=25, b=25), paper_bgcolor='#F5FFFA', plot_bgcolor='#F5FFFA')
                 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 = "orange")
                     fig_pie = px.pie(grouped_counts, values='count', names='category', hover_data=['count'], labels={'count': 'count'}, title='Percentage of predicted categories')
@@ -201,16 +210,16 @@ if st.button("Results"):
                         plot_bgcolor='#F5FFFA'
                     )
                     st.plotly_chart(fig_pie)
-                                
+                
                 with col2:
                     st.subheader("Bar chart", divider = "orange")
                     fig_bar = px.bar(grouped_counts, x="count", y="category", color="category", text_auto=True, title='Occurrences of predicted categories')
-                    fig_bar.update_layout(
+                    fig_pie.update_layout(
                         paper_bgcolor='#F5FFFA',
                         plot_bgcolor='#F5FFFA'
                     )
                     st.plotly_chart(fig_bar)
-                                
+                
                 # Most Frequent Entities
                 st.subheader("Most Frequent Entities", divider="orange")
                 word_counts = df['text'].value_counts().reset_index()
@@ -219,18 +228,16 @@ if st.button("Results"):
                 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')
-                    fig_repeating_bar.update_layout(
-                        xaxis={'categoryorder': 'total descending'},
+                    fig_repeating_bar.update_layout(xaxis={'categoryorder': 'total descending'},
                         paper_bgcolor='#F5FFFA',
-                        plot_bgcolor='#F5FFFA'
-                    )
+                        plot_bgcolor='#F5FFFA')
                     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', 'category'],
@@ -248,7 +255,7 @@ 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; }""",
@@ -259,14 +266,15 @@ 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()
             else: # If df is empty
                 st.warning("No entities were found in the provided text.")
-        end_time = time.time()
+    
+    end_time = time.time()
     elapsed_time = end_time - start_time
     st.text("")
     st.text("")
-    st.info(f"Results processed in **{elapsed_time:.2f} seconds**.")
+    st.info(f"Results processed in **{elapsed_time:.2f} seconds**.")