app.py

import streamlit as st
import pandas as pd
import spacy
from transformers import pipeline, AutoModelForTokenClassification, AutoTokenizer
import PyPDF2
import docx
import io

st.set_page_config(layout="wide")

# Function to read text from uploaded file
def read_file(file):
    if file.type == "text/plain":
        return file.getvalue().decode("utf-8")
    elif file.type == "application/pdf":
        pdf_reader = PyPDF2.PdfReader(io.BytesIO(file.getvalue()))
        return " ".join(page.extract_text() for page in pdf_reader.pages)
    elif file.type == "application/vnd.openxmlformats-officedocument.wordprocessingml.document":
        doc = docx.Document(io.BytesIO(file.getvalue()))
        return " ".join(paragraph.text for paragraph in doc.paragraphs)
    else:
        st.error("Unsupported file type")
        return None

# Rest of your code remains the same
example_list = [
    "Mustafa Kemal Atatürk 1919 yılında Samsun'a çıktı.",
    """Mustafa Kemal Atatürk, Türk asker, devlet adamı ve Türkiye Cumhuriyeti'nin kurucusudur.
    # ... (rest of the example text)
    """
]

st.title("Demo for Turkish NER Models")

model_list = [
    'akdeniz27/bert-base-turkish-cased-ner',
    'akdeniz27/convbert-base-turkish-cased-ner',
    'girayyagmur/bert-base-turkish-ner-cased',
    'FacebookAI/xlm-roberta-large',
    'savasy/bert-base-turkish-ner-cased',
    'xlm-roberta-large-finetuned-conll03-english',
    'asahi417/tner-xlm-roberta-base-ontonotes5'
]

st.sidebar.header("Select NER Model")
model_checkpoint = st.sidebar.radio("", model_list)

st.sidebar.write("For details of models: 'https://huggingface.co/akdeniz27/")
st.sidebar.write("")

if model_checkpoint in ["akdeniz27/xlm-roberta-base-turkish-ner", "xlm-roberta-large-finetuned-conll03-english", "asahi417/tner-xlm-roberta-base-ontonotes5"]:
    aggregation = "simple"
    if model_checkpoint != "akdeniz27/xlm-roberta-base-turkish-ner":
        st.sidebar.write("The selected NER model is included just to show the zero-shot transfer learning capability of XLM-Roberta pretrained language model.")
else:
    aggregation = "first"

st.subheader("Select Text Input Method")
input_method = st.radio("", ('Select from Examples', 'Write or Paste New Text', 'Upload File'))

if input_method == 'Select from Examples':
    selected_text = st.selectbox('Select Text from List', example_list, index=0, key=1)
    input_text = st.text_area("Selected Text", selected_text, height=128, max_chars=None, key=2)
elif input_method == "Write or Paste New Text":
    input_text = st.text_area('Write or Paste Text Below', value="", height=128, max_chars=None, key=2)
else:
    uploaded_file = st.file_uploader("Choose a file", type=["txt", "pdf", "docx"])
    if uploaded_file is not None:
        input_text = read_file(uploaded_file)
        if input_text:
            st.text_area("Extracted Text", input_text, height=128, max_chars=None, key=2)
    else:
        input_text = ""

# Rest of your functions (setModel, get_html, entity_comb) remain the same

@st.cache_resource
def setModel(model_checkpoint, aggregation):
    model = AutoModelForTokenClassification.from_pretrained(model_checkpoint)
    tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
    return pipeline('ner', model=model, tokenizer=tokenizer, aggregation_strategy=aggregation)

@st.cache_resource
def get_html(html: str):
    WRAPPER = """<div style="overflow-x: auto; border: 1px solid #e6e9ef; border-radius: 0.25rem; padding: 1rem; margin-bottom: 2.5rem">{}</div>"""
    html = html.replace("\n", " ")
    return WRAPPER.format(html)

@st.cache_resource
def entity_comb(output):
    output_comb = []
    for ind, entity in enumerate(output):
        if ind == 0:
            output_comb.append(entity)
        elif output[ind]["start"] == output[ind-1]["end"] and output[ind]["entity_group"] == output[ind-1]["entity_group"]:
            output_comb[-1]["word"] = output_comb[-1]["word"] + output[ind]["word"]
            output_comb[-1]["end"] = output[ind]["end"]
        else:
            output_comb.append(entity)
    return output_comb

Run_Button = st.button("Run", key=None)

if Run_Button and input_text != "":
    # Your existing processing code remains the same
    ner_pipeline = setModel(model_checkpoint, aggregation)
    output = ner_pipeline(input_text)
    
    output_comb = entity_comb(output)
    
    df = pd.DataFrame.from_dict(output_comb)
    cols_to_keep = ['word','entity_group','score','start','end']
    df_final = df[cols_to_keep]
    
    st.subheader("Recognized Entities")
    st.dataframe(df_final)

    st.subheader("Spacy Style Display")
    spacy_display = {}
    spacy_display["ents"] = []
    spacy_display["text"] = input_text
    spacy_display["title"] = None

    for entity in output_comb:
        spacy_display["ents"].append({"start": entity["start"], "end": entity["end"], "label": entity["entity_group"]})
        
    tner_entity_list = ["person", "group", "facility", "organization", "geopolitical area", "location", "product", "event", "work of art", "law", "language", "date", "time", "percent", "money", "quantity", "ordinal number", "cardinal number"]
    spacy_entity_list = ["PERSON", "NORP", "FAC", "ORG", "GPE", "LOC", "PRODUCT", "EVENT", "WORK_OF_ART", "LAW", "LANGUAGE", "DATE", "TIME", "PERCENT", "MONEY", "QUANTITY", "ORDINAL", "CARDINAL", "MISC"]
    
    for ent in spacy_display["ents"]:
        if model_checkpoint == "asahi417/tner-xlm-roberta-base-ontonotes5":
            ent["label"] = spacy_entity_list[tner_entity_list.index(ent["label"])]
        else:
            if ent["label"] == "PER": ent["label"] = "PERSON"
    
    html = spacy.displacy.render(spacy_display, style="ent", minify=True, manual=True, options={"ents": spacy_entity_list})
    style = "<style>mark.entity { display: inline-block }</style>"
    st.write(f"{style}{get_html(html)}", unsafe_allow_html=True)