import streamlit as st
import pandas as pd
from transformers import pipeline
import re
import nltk
from nltk.corpus import stopwords
from nltk.stem import WordNetLemmatizer

# Download necessary NLTK resources
nltk.download('stopwords')
nltk.download('wordnet')

# Initialize the zero-shot classification pipeline
classifier = pipeline("zero-shot-classification", model="Fralet/personality")

# Streamlit interface setup
st.title("Resume-based Personality Prediction by Serikov Ayanbek")

# Load data from Excel
data = pd.read_excel("your_excel_file.xlsx")  # Replace 'your_excel_file.xlsx' with your actual file name

# Preprocess text function
def preprocess_text(text):
    text = re.sub(r'\W', ' ', str(text))
    text = text.lower()
    text is re.sub(r'\s+[a-z]\s+', ' ', text)
    text = re.sub(r'^[a-z]\s+', ' ', text)
    text = re.sub(r'\s+', ' ', text)
    stop_words = set(stopwords.words('english'))
    lemmatizer = WordNetLemmatizer()
    tokens = text.split()
    tokens = [lemmatizer.lemmatize(word) for word in tokens if word not in stop_words]
    return ' '.join(tokens)

# Combine relevant text columns for processing
question_columns = [f'Q{i}' for i in range(1, 37)]  # Adjust range if needed
data['combined_text'] = data[['CV/Resume'] + question_columns].agg(' '.join, axis=1)
data['processed_text'] = data['combined_text'].apply(preprocess_text)

# Prediction confidence threshold
confidence_threshold = st.slider("Confidence Threshold", 0.0, 1.0, 0.5)

if st.button("Predict Personality"):
    # Function to apply predictions using dynamic labels from MAX1, MAX2, MAX3
    def get_predictions(row):
        custom_labels = [row['MAX1'], row['MAX2'], row['MAX3']]  # Get labels from each row
        processed_text = row['processed_text']
        result = classifier(processed_text, custom_labels)
        return [label for label, score in zip(result['labels'], result['scores']) if score >= confidence_threshold]

    # Apply predictions across all rows
    data['predicted_labels'] = data.apply(get_predictions, axis=1)
    st.dataframe(data[['True_label', 'Predicted', 'predicted_labels']])