app.py

import gradio as gr
from transformers import pipeline
import pandas as pd
import spaces
import plotly.express as px

# 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
def classify_comments(categories):
    global df  # Ensure we're modifying the global DataFrame
    sentiments = []
    assigned_categories = []

    # Debugging output
    print("Classifying comments...")

    for comment in df['customer_comment']:
        # Classify sentiment
        sentiment = classifier(comment)[0]['label']
        # Generate category
        category_str = ', '.join(categories)
        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']
        assigned_categories.append(category)
        sentiments.append(sentiment)
    
    df['comment_sentiment'] = sentiments
    df['comment_category'] = assigned_categories
    
    # Debugging output
    print(df.head())  
    print(df['comment_sentiment'].value_counts())  
    print(df['comment_category'].value_counts())  

    return df[['customer_id', 'customer_comment', 'comment_sentiment', 'comment_category', 'customer_nps', 'customer_segment']].to_html(index=False)

# Function to generate visualizations
def visualize_output():
    global df

    # Check if DataFrame is empty
    if df.empty:
        return None, None, None, "Error: DataFrame is empty. Please check the data or classification step.", None

    # Check for required columns
    required_columns = ['comment_sentiment', 'comment_category', 'customer_nps', 'customer_segment']
    if not all(col in df.columns for col in required_columns):
        return None, None, None, "Error: Required columns are missing. Please classify comments first.", None

    # Explicitly convert data types
    df['comment_sentiment'] = df['comment_sentiment'].astype(str)
    df['comment_category'] = df['comment_category'].astype(str)
    df['customer_nps'] = pd.to_numeric(df['customer_nps'], errors='coerce')
    df['customer_segment'] = df['customer_segment'].astype(str)

    # Drop NaN values
    df = df.dropna(subset=['comment_sentiment', 'comment_category', 'customer_nps', 'customer_segment'])

    # Debugging output
    print(df.head())  
    print(df['comment_sentiment'].value_counts())  
    print(df['comment_category'].value_counts())  

    # Pie Chart of Sentiment
    sentiment_counts = df['comment_sentiment'].value_counts()
    sentiment_pie = px.pie(
        values=sentiment_counts.values,
        names=sentiment_counts.index,
        title="Sentiment Distribution"
    )

    # Pie Chart of Comment Categories
    category_counts = df['comment_category'].value_counts()
    category_pie = px.pie(
        values=category_counts.values,
        names=category_counts.index,
        title="Comment Category Distribution"
    )

    # Stacked Bar Chart of Sentiment by Category
    sentiment_by_category = df.groupby(['comment_category', 'comment_sentiment']).size().unstack()
    stacked_bar = px.bar(
        sentiment_by_category,
        barmode='stack',
        title="Sentiment by Comment Category",
        labels={'value': 'Count', 'comment_category': 'Category', 'comment_sentiment': 'Sentiment'}
    )

    # KPI Visualizations
    avg_nps = df['customer_nps'].mean()
    avg_nps_positive = df[df['comment_sentiment'] == 'POSITIVE']['customer_nps'].mean()
    avg_nps_negative = df[df['comment_sentiment'] == 'NEGATIVE']['customer_nps'].mean()
    avg_nps_by_category = df.groupby('comment_category')['customer_nps'].mean().reset_index()
    avg_nps_by_segment = df.groupby('customer_segment')['customer_nps'].mean().reset_index()

    kpi_visualization = f"""
    **Average NPS Scores:**
    - Overall: {avg_nps:.2f}
    - Positive Sentiment: {avg_nps_positive:.2f}
    - Negative Sentiment: {avg_nps_negative:.2f}
    **Average NPS by Category:**
    {avg_nps_by_category.to_markdown(index=False)}
    **Average NPS by Segment:**
    {avg_nps_by_segment.to_markdown(index=False)}
    """

    # Pie Chart of Sentiment by Customer Segment
    sentiment_by_segment = df.groupby(['customer_segment', 'comment_sentiment']).size().unstack()
    sentiment_by_segment_pie = px.pie(
        sentiment_by_segment,
        title="Sentiment by Customer Segment"
    )

    return sentiment_pie, category_pie, stacked_bar, kpi_visualization, sentiment_by_segment_pie

# Gradio Interface
with gr.Blocks() as nps:
    categories = gr.State([])

    def add_category(categories, new_category):
        if new_category.strip() != "" and len(categories) < 5:
            categories.append(new_category.strip())
        return categories, "", f"**Categories:**\n" + "\n".join([f"- {cat}" for cat in categories])

    def reset_categories():
        return [], "**Categories:**\n- None"

    with gr.Row():
        category_input = gr.Textbox(label="New Category", placeholder="Enter category name")
        add_category_btn = gr.Button("Add Category")
        reset_btn = gr.Button("Reset Categories")
        category_status = gr.Markdown("**Categories:**\n- None")

    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()

    visualize_btn = gr.Button("Visualize Output")
    sentiment_pie = gr.Plot(label="Sentiment Distribution")
    category_pie = gr.Plot(label="Comment Category Distribution")
    stacked_bar = gr.Plot(label="Sentiment by Comment Category")
    kpi_visualization = gr.Markdown()
    sentiment_by_segment_pie = gr.Plot(label="Sentiment by Customer Segment")

    add_category_btn.click(fn=add_category, inputs=[categories, category_input], outputs=[categories, category_input, category_status])
    reset_btn.click(fn=reset_categories, outputs=[categories, category_status])
    classify_btn.click(fn=classify_comments, inputs=categories, outputs=output)
    visualize_btn.click(fn=visualize_output, outputs=[sentiment_pie, category_pie, stacked_bar, kpi_visualization, sentiment_by_segment_pie])

nps.launch(share=True)