import gradio as gr
from transformers import AutoModelForSequenceClassification, AutoTokenizer, pipeline
import csv

MODEL_URL = "https://huggingface.co/dsfsi/PuoBERTa-News"
WEBSITE_URL = "https://www.kodiks.com/ai_solutions.html"

tokenizer = AutoTokenizer.from_pretrained("dsfsi/PuoBERTa-News")
model = AutoModelForSequenceClassification.from_pretrained("dsfsi/PuoBERTa-News")

categories = {
    "arts_culture_entertainment_and_media": "Botsweretshi, setso, boitapoloso le bobegakgang",
    "crime_law_and_justice": "Bosenyi, molao le bosiamisi",
    "disaster_accident_and_emergency_incident": "Masetlapelo, kotsi le tiragalo ya maemo a tshoganyetso",
    "economy_business_and_finance": "Ikonomi, tsa kgwebo le tsa ditšhelete",
    "education": "Thuto",
    "environment": "Tikologo",
    "health": "Boitekanelo",
    "politics": "Dipolotiki",
    "religion_and_belief": "Bodumedi le tumelo",
    "society": "Setšhaba"
}

def prediction(news):
    classifier = pipeline("text-classification", tokenizer=tokenizer, model=model, return_all_scores=True)
    preds = classifier(news)
    preds_dict = {categories.get(pred['label'], pred['label']): pred['score'] for pred in preds[0]}
    return preds_dict

def file_prediction(file):
    news_list = []

    if file.name.endswith('.csv'):
        file.seek(0)
        reader = csv.reader(file.read().decode('utf-8').splitlines())
        news_list = [row[0] for row in reader if row]
    else:
        file.seek(0)
        file_content = file.read().decode('utf-8')
        news_list = file_content.splitlines()

    results = []
    for news in news_list:
        if news.strip():
            pred = prediction(news)
            results.append([news, pred])  # Return each news and its prediction as a row

    return results  # Gradio expects a list of lists or dicts for DataFrame

gradio_ui = gr.Interface(
    fn=prediction,
    title="Setswana News Classification",
    description=f"Enter Setswana news article to see the category of the news.\n For this classification, the {MODEL_URL} model was used.",
    inputs=gr.Textbox(lines=10, label="Paste some Setswana news here"),
    outputs=gr.Label(num_top_classes=5, label="News categories probabilities"),
    theme="default",
    article="<p style='text-align: center'>For our other AI works: <a href='https://www.kodiks.com/ai_solutions.html' target='_blank'>https://www.kodiks.com/ai_solutions.html</a> | <a href='https://twitter.com/KodiksBilisim' target='_blank'>Contact us</a></p>",
)

gradio_file_ui = gr.Interface(
    fn=file_prediction,
    title="Upload File for Setswana News Classification",
    description=f"Upload a text or CSV file with Setswana news articles. The first column in the CSV should contain the news text.",
    inputs=gr.File(label="Upload text or CSV file"),
    outputs=gr.Dataframe(headers=["News Text", "Category Predictions"], label="Predictions from file"),
    theme="default" 
)

gradio_combined_ui = gr.TabbedInterface([gradio_ui, gradio_file_ui], ["Text Input", "File Upload"])

gradio_combined_ui.launch()