app.py

import gradio as gr
import pandas as pd
from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline
import matplotlib.pyplot as plt
import spaces

# Load model and tokenizer
model_name = "ac0hik/Sentiment_Analysis_French"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name)

# Create sentiment analysis pipeline
classifier = pipeline('sentiment-analysis', model=model, tokenizer=tokenizer)



# Function to process a single text input
@spaces.GPU
def analyze_text(text):
    result = classifier(text)[0]
    return result

# Function to process a CSV file and update results live
@spaces.GPU

# Function to process a single text input
def analyze_text(text):
    result = classifier(text)[0]
    return result

# Function to process a CSV file and update results live
def analyze_csv(file):
    df = pd.read_csv(file.name)
    texts = df['text'].tolist()

    results = []
    pos_count = neg_count = neu_count = 0

    for text in texts:
        result = classifier(text)[0]
        results.append({'text': text, 'sentiment': result['label']})

        if result['label'] == 'positive':
            pos_count += 1
        elif result['label'] == 'negative':
            neg_count += 1
        else:
            neu_count += 1

        # Create a pie chart
        labels = 'Positive', 'Negative', 'Neutral'
        sizes = [pos_count, neg_count, neu_count]
        colors = ['#ff9999','#66b3ff','#99ff99']
        fig, ax = plt.subplots()
        ax.pie(sizes, labels=labels, colors=colors, autopct='%1.1f%%', startangle=90)
        ax.axis('equal')

        # Update results live
        yield pd.DataFrame(results), fig, pos_count, neg_count, neu_count

# Function to save the DataFrame to a CSV file
def save_csv(df):
    file_path = "/mnt/data/sentiment_analysis_results.csv"
    df.to_csv(file_path, index=False)
    return file_path

# Gradio interface
with gr.Blocks() as demo:
    with gr.Row():
        with gr.Column():
            gr.Markdown("## Sentiment Analysis")
            text_input = gr.Textbox(label="Enter Text")
            text_output = gr.JSON(label="Sentiment Analysis Result")
            text_button = gr.Button("Analyze Text")

            csv_input = gr.File(label="Upload CSV", file_types=['csv'])
            csv_output = gr.Dataframe(label="Sentiment Analysis Results")
            csv_button = gr.Button("Analyze CSV")

        with gr.Column():
            gr.Markdown("## csv Result")
            pos_count_output = gr.Number(label="Positive Count", value=0)
            neg_count_output = gr.Number(label="Negative Count", value=0)
            neu_count_output = gr.Number(label="Neutral Count", value=0)
            csv_chart = gr.Plot(label="Sentiment Distribution")

    text_button.click(analyze_text, inputs=text_input, outputs=text_output)
    csv_button.click(analyze_csv, inputs=csv_input, outputs=[csv_output, csv_chart, pos_count_output, neg_count_output, neu_count_output])

# Launch the Gradio app
demo.launch()