#Core Packages
import streamlit as st 

#nlp pkgs
import spacy
from spacy import displacy
import spacy_streamlit
from spacy_streamlit import visualize_ner
import en_core_web_sm

nlp = spacy.load("en_core_web_sm")

def main():
    """A simple NLP app with spacy-streamlit"""
    
    spacy_model = "en_core_web_sm"
    st.title('Entity Extraction')

    menu = ["Home","NER"]
    choice = st.sidebar.selectbox("Menu", menu)
    
    if choice == "Home":
        st.subheader("Tokenization")
        
        raw_text = st.text_area("Your Text","Enter the Text Here")
        docx = nlp(raw_text)
        if st.button("Tokenize"):
            spacy_streamlit.visualize_tokens(docx,attrs = ['text','pos_','dep_','ent_type_'])

    elif choice == 'NER':
        st.subheader("Name Entity Recognition")
        raw_text = st.text_area("Your Text","Enter the Text Here")
        docx = nlp(raw_text)
        spacy_streamlit.visualize_ner(docx)



if __name__ == '__main__':
    main()


#def prediction(raw_text):
  #text1= NER(raw_text)
  #st.write("List wise NERs:")
  #st.write("------------------")
  #st.write(f"{'Text' : <10}{'NER' : >10}")
  
  #for word in text1.ents:
   # st.write(word.text,"\t\t",word.label_)
  #print()
  #st.write("------------------")
  #st.write("NERs in the sentence:")
  #spacy_streamlit.visualize(displacy.render(text1,style="ent"))
   
  #models = ["en_core_web_sm"]
  #spacy_streamlit.visualize(text1,models = models)
  #visualize_ner(text1, labels=nlp.get_pipe("ner").labels)

#raw_text = """Ai-Khanoum (/aɪ ˈhɑːnjuːm/, meaning Lady Moon; Uzbek: Oyxonim) is the archaeological site of a Hellenistic city in Takhar Province, Afghanistan. 
#The city, whose original name is unknown,[a] was probably founded by an early ruler of the Seleucid Empire and served as a military and economic centre for the rulers of the Greco-Bactrian Kingdom until its destruction c. 145 BC. 
#Rediscovered in 1961, the ruins of the city were excavated by a French team of archaeologists until the outbreak of conflict in Afghanistan in the late 1970s. """
#prediction(raw_text)