import gradio as gr
from transformers import pipeline
import pandas as pd
import spaces

# Load dataset
from datasets import load_dataset
ds = load_dataset('ZennyKenny/demo_customer_nps')
df = pd.DataFrame(ds['train'])

# Initialize model pipeline
from huggingface_hub import login
import os

# Login using the API key stored as an environment variable
hf_api_key = os.getenv("API_KEY")
login(token=hf_api_key)

classifier = pipeline("text-classification", model="distilbert/distilbert-base-uncased-finetuned-sst-2-english")
generator = pipeline("text2text-generation", model="google/flan-t5-base")

# Function to classify customer comments
# https://huggingface.co/docs/hub/spaces-zerogpu
@spaces.GPU
def classify_comments():
    sentiments = []
    categories = []
    results = []
    for comment in df['customer_comment']:
        sentiment = classifier(comment)[0]['label']
        category_list = [box.value for box in category_boxes if box.value.strip() != '']
        category_str = ', '.join([cat.strip() for cat in category_list])
        prompt = f"What category best describes this comment? '{comment}' Please answer using only the name of the category: {category_str}."
        category = generator(prompt, max_length=30)[0]['generated_text']
        categories.append(category)
        sentiments.append(sentiment)
    df['comment_sentiment'] = sentiments
    df['comment_category'] = categories
    return df[['customer_comment', 'comment_sentiment', 'comment_category']].to_html(index=False)

# Gradio Interface
with gr.Blocks() as nps:
    def add_category():
        new_box = gr.Textbox(label="Category", placeholder="Enter a category")
        category_boxes.append(new_box)
        return new_box

    add_category_btn.click(fn=add_category, outputs=category_boxes)
    category_boxes = []  # Store category input boxes
    add_category_btn = gr.Button("Add Category")
    uploaded_file = gr.File(label="Upload CSV", type="filepath")
    template_btn = gr.Button("Use Template")
    gr.Markdown("# NPS Comment Categorization")
    classify_btn = gr.Button("Classify Comments")
    output = gr.HTML()

    def load_data(file):
        if file is not None:
            file.seek(0)  # Reset file pointer
            import io
            if file.name.endswith('.csv'):
                file.seek(0)  # Reset file pointer
                custom_df = pd.read_csv(file, encoding='utf-8')
                custom_df = pd.read_csv(io.StringIO(content))
            else:
                return "Error: Uploaded file is not a CSV."
            if 'customer_comment' not in custom_df.columns:
                return "Error: Uploaded CSV must contain a column named 'customer_comment'"
            global df
            df = custom_df
            return "Custom CSV loaded successfully!"
        else:
            return "No file uploaded."

    uploaded_file.change(fn=load_data, inputs=uploaded_file, outputs=output)
    template_btn.click(fn=lambda: "Using Template Dataset", outputs=output)
    classify_btn.click(fn=classify_comments, inputs=[category_input], outputs=output)

nps.launch()