src/streamlit_app.py

import os
os.environ['HF_HOME'] = '/tmp'
import time
import streamlit as st
import pandas as pd
import io
import plotly.express as px
import zipfile
import json
from cryptography.fernet import Fernet
from streamlit_extras.stylable_container import stylable_container
from typing import Optional
from gliner import GLiNER
from comet_ml import Experiment

st.markdown(
    """
    <style>
    /* Main app background and text color */
    .stApp {
        background-color: #F5FFFA; /* Mint cream, a very light green */
        color: #000000; /* Black for the text */
    }
    /* Sidebar background color */
    .css-1d36184 {
        background-color: #B2F2B2; /* A pale green for the sidebar */
        secondary-background-color: #B2F2B2;
    }
    
    /* Expander background color */
    .streamlit-expanderContent {
        background-color: #F5FFFA;
    }
    /* Expander header background color */
    .streamlit-expanderHeader {
        background-color: #F5FFFA;
    }
    /* Text Area background and text color */
    .stTextArea textarea {
        background-color: #D4F4D4; /* A light, soft green */
        color: #000000; /* Black for text */
    }
    /* Button background and text color */
    .stButton > button {
        background-color: #D4F4D4;
        color: #000000;
    }
    /* Warning box background and text color */
    .stAlert.st-warning {
        background-color: #C8F0C8; /* A light green for the warning box */
        color: #000000;
    }
    /* Success box background and text color */
    .stAlert.st-success {
        background-color: #C8F0C8; /* A light green for the success box */
        color: #000000;
    }
    </style>
    """,
    unsafe_allow_html=True
)

# --- Page Configuration and UI Elements ---
st.set_page_config(layout="wide", page_title="Named Entity Recognition App")
st.subheader("HR.ai", divider="green")
st.link_button("by nlpblogs", "https://nlpblogs.com", type="tertiary")
expander = st.expander("**Important notes**")
expander.write("""**Named Entities:** This HR.ai web app predicts thirty-six (36) labels: "Email", "Phone_number", "Street_address", "City", "Country", "Date_of_birth", "Marital_status", "Person", "Full_time", "Part_time", "Contract", "Terminated", "Retired", "Job_title", "Date", "Organization", "Role", "Performance_score", "Leave_of_absence", "Retirement_plan", "Bonus", "Stock_options", "Health_insurance", "Pay_rate", "Annual_salary", "Tax", "Deductions", "Interview_type", "Applicant", "Referral", "Job_board", "Recruiter", "Offer_letter", "Agreement", "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     

**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>
    '''
    st.code(code, language="html")
    st.text("")
    st.text("")
    st.divider()
    st.subheader("🚀 Ready to build your own NER Web App?", divider="green")
    st.link_button("NER Builder", "https://nlpblogs.com", 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 = ["Email", "Phone_number", "Street_address", "City", "Country", "Date_of_birth", "Marital_status", "Person", "Full_time", "Part_time", "Contract", "Terminated", "Retired", "Job_title", "Date", "Organization", "Role", "Performance_score", "Leave_of_absence", "Retirement_plan", "Bonus", "Stock_options", "Health_insurance", "Pay_rate", "Annual_salary", "Tax", "Deductions", "Interview_type", "Applicant", "Referral", "Job_board", "Recruiter", "Offer_letter", "Agreement", "Certification", "Skill"]



# Create a mapping dictionary for labels to categories

category_mapping = {
    "Contact Information": ["Email", "Phone_number", "Street_address", "City", "Country"],
    "Personal Details": ["Date_of_birth", "Marital_status", "Person"],
    "Employment Status": ["Full_time", "Part_time", "Contract", "Terminated", "Retired"],
    "Employment Information" : ["Job_title", "Date", "Organization", "Role"],
    "Performance": ["Performance_score"],
    "Attendance": ["Leave_of_absence"],
    "Benefits": ["Retirement_plan", "Bonus", "Stock_options", "Health_insurance"],
    "Compensation": ["Pay_rate", "Annual_salary"],
    "Deductions": ["Tax", "Deductions"],
    "Recruitment & Sourcing": ["Interview_type", "Applicant", "Referral", "Job_board", "Recruiter"],
    "Legal & Compliance": ["Offer_letter", "Agreement"],
    "Professional_Development": [ "Certification", "Skill"]
}








# --- 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)
    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()

# 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 ---
text = st.text_area("Type or paste your text below, and then press Ctrl + Enter", height=250, key='my_text_area')

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"):
    start_time = time.time()
    if not text.strip():
        st.warning("Please enter some text to extract entities.")
    else:
        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:
                    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)
                
                st.subheader("Grouped Entities by Category", divider = "green")
                
                # 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)
                        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']
                    - **score**: ['accuracy score; how accurately a tag has been assigned to a given entity']
                    - **label**: ['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']
                    ''')
                st.divider()
                                
                # Tree map
                st.subheader("Tree map", divider = "green")
                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')
                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 = "green")
                    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='#F5FFFA',
                        plot_bgcolor='#F5FFFA'
                    )
                    st.plotly_chart(fig_pie)
                
                with col2:
                    st.subheader("Bar chart", divider = "green")
                    fig_bar = px.bar(grouped_counts, x="count", y="category", color="category", text_auto=True, title='Occurrences of predicted categories')
                    fig_pie.update_layout(
                        paper_bgcolor='#F5FFFA',
                        plot_bgcolor='#F5FFFA'
                    )
                    st.plotly_chart(fig_bar)
                
                # Most Frequent Entities
                st.subheader("Most Frequent Entities", divider="green")
                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')
                    fig_repeating_bar.update_layout(xaxis={'categoryorder': 'total descending'},
                        paper_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'],
                        '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",
                    )
                                
                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()
    elapsed_time = end_time - start_time
    st.text("")
    st.text("")
    st.info(f"Results processed in **{elapsed_time:.2f} seconds**.")