import streamlit as st
import pandas as pd
import json
import joblib
from huggingface_hub import hf_hub_download

# Display the version of huggingface_hub
import huggingface_hub
st.write(f"Hugging Face Hub version: {huggingface_hub.__version__}")

# Function to download models from Hugging Face using huggingface_hub
def download_model_from_huggingface(repo_id, filename):
    """Downloads a model file from Hugging Face repository."""
    try:
        # Using huggingface_hub API to download model directly
        model_file = hf_hub_download(repo_id, filename)
        return model_file
    except Exception as e:
        st.error(f"Error downloading model {filename}: {e}")
        return None

# Function to load models safely
def load_model(model_file):
    """Loads a model from a file."""
    try:
        # Here we're assuming the model is in a `.joblib` file format
        return joblib.load(model_file)
    except Exception as e:
        st.error(f"Error loading model: {e}")
        return None

# Set repository ID and model filenames
REPO_ID = "totoro74/Intelligent_Customer_Analyzer"

# Load models using the download function
try:
    # Download and load the BERTopic model
    bert_topic_model_file = download_model_from_huggingface(REPO_ID, "models/bertopic_model.joblib")
    bert_topic_model = load_model(bert_topic_model_file)

    # Download and load the Recommendation model
    recommendation_model_file = download_model_from_huggingface(REPO_ID, "models/recommendation_model.joblib")
    recommendation_model = load_model(recommendation_model_file)

except Exception as e:
    st.error(f"⚠️ Error loading models: {e}")

# Streamlit app layout
st.title("📊 Intelligent Customer Feedback Analyzer")
st.write("Analyze customer feedback for sentiment, topics, and get personalized recommendations.")

# User input for customer feedback file
uploaded_file = st.file_uploader("📂 Upload a Feedback File (CSV, JSON, TXT)", type=["csv", "json", "txt"])

# Function to extract feedback text from different file formats
def extract_feedback(file):
    """Extracts text data from CSV, JSON, or TXT files."""
    try:
        if file.type == "text/csv":
            df = pd.read_csv(file)
            feedback_text = df.iloc[:, 0].dropna().astype(str).tolist()
            return feedback_text
        elif file.type == "application/json":
            json_data = json.load(file)
            feedback_text = [item.get('feedback', '') for item in json_data if isinstance(item, dict)]
            return feedback_text
        elif file.type == "text/plain":
            return file.getvalue().decode("utf-8").split("\n")
        else:
            return ["Unsupported file type"]
    except Exception as e:
        st.error(f"Error processing file: {e}")
        return []

# Process uploaded file
if uploaded_file:
    feedback_text_list = extract_feedback(uploaded_file)

    if feedback_text_list and bert_topic_model and recommendation_model:
        for feedback_text in feedback_text_list:
            with st.expander(f'🔍 Analyze Feedback: "{feedback_text[:30]}..."'):
                try:
                    # Topic Prediction
                    topics = bert_topic_model.predict([feedback_text])
                    st.write(f"**Predicted Topic(s):** {topics}")

                    # Recommendations
                    recommendations = recommendation_model.predict([feedback_text])
                    st.write(f"**Recommended Actions:** {recommendations}")

                except Exception as e:
                    st.error(f"Error analyzing feedback: {e}")
    else:
        st.error("⚠️ Unable to analyze feedback. Please check if models are correctly loaded.")
else:
    st.info("📌 Please upload a feedback file to analyze.")