import streamlit as st
import time
import pandas as pd
import io
import zipfile
from gliner import GLiNER
from streamlit_extras.stylable_container import stylable_container
import plotly.express as px
import os
from comet_ml import Experiment

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.")

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

if st.button("Results"):
    with st.spinner("Wait for it...", show_time=True):
        time.sleep(5)
        model = GLiNER.from_pretrained("xomad/gliner-model-merge-large-v1.0")
        labels = ["person", "country", "city", "organization", "date", "money", "percent value", "position"]
        entities = model.predict_entities(text, labels)
        df = pd.DataFrame(entities)

        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)

        properties = {"border": "2px solid gray", "color": "blue", "font-size": "16px"}
        df_styled = df.style.set_properties(**properties)
        st.dataframe(df_styled)

        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']
            ''')

        if df is not None:
            fig = px.treemap(df, path=[px.Constant("all"), 'text', 'label'],
                                 values='score', color='label')
            fig.update_layout(margin = dict(t=50, l=25, r=25, b=25))
            st.subheader("Tree map", divider = "red")
            st.plotly_chart(fig)
            if comet_initialized:
                experiment.log_figure(figure=fig, figure_name="entity_treemap")

        if df is not None:
            value_counts1 = df['label'].value_counts()
            df1 = pd.DataFrame(value_counts1)
            final_df = df1.reset_index().rename(columns={"index": "label"})
            col1, col2 = st.columns(2)
            with col1:
                fig1 = px.pie(final_df, values='count', names='label', hover_data=['count'], labels={'count': 'count'}, title='Percentage of predicted labels')
                fig1.update_traces(textposition='inside', textinfo='percent+label')
                st.subheader("Pie Chart", divider = "red")
                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="label", color="label", text_auto=True, title='Occurrences of predicted labels')
                st.subheader("Bar Chart", divider = "red")
                st.plotly_chart(fig2)
                if comet_initialized:
                    experiment.log_figure(figure=fig2, figure_name="label_bar_chart")

        dfa = pd.DataFrame(
            data={
                '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'],
                })
        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))
            if comet_initialized:
                myzip.writestr("Summary of the results_glossary_combined.csv", pd.concat([df, dfa]).to_csv(index=False))

        with stylable_container(
            key="download_button",
            css_styles="""button { background-color: yellow; border: 1px solid black; padding: 5px; color: black; }""",
        ):
            st.download_button(
                label="Download zip file",
                data=buf.getvalue(),
                file_name="zip file.zip",
                mime="application/zip",
            )
            if comet_initialized:
                experiment.log_asset(buf.getvalue(), file_name="downloadable_results.zip")

        st.divider()
        if comet_initialized:
            experiment.end()