app.py

import os
import csv
import logging
import gradio as gr
import nltk
from datasets import Dataset, DatasetDict, DatasetInfo, Features, Value, ClassLabel
from huggingface_hub import HfApi, Repository, create_repo
from tqdm import tqdm
from nltk.tokenize import word_tokenize
from nltk.corpus import wordnet as wn
import random
import string

# Ensure necessary NLTK resources are downloaded
nltk.download('all')
#nltk.download('wordnet')

# Set up logging
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)

# Function to generate random words
def generate_random_words(num_words=100):
    words = []
    for _ in range(num_words):
        word_length = random.randint(3, 10)
        word = ''.join(random.choices(string.ascii_lowercase, k=word_length))
        words.append(word)
    return words

# Function to get meanings of words using NLTK WordNet
def get_word_meanings(words):
    meanings = {}
    for word in words:
        synsets = wn.synsets(word)
        if synsets:
            meanings[word] = synsets[0].definition()
        else:
            meanings[word] = "No definition found."
    return meanings

# Function to convert data to CSV format
def convert_to_csv(data, filename='dataset.csv'):
    fieldnames = ['word', 'meaning']
    with open(filename, mode='w', newline='', encoding='utf-8') as file:
        writer = csv.DictWriter(file, fieldnames=fieldnames)
        writer.writeheader()
        for word, meaning in data.items():
            writer.writerow({'word': word, 'meaning': meaning})

# Function to create and push dataset to Hugging Face
def create_and_push_dataset(csv_file='dataset.csv', repo_name='DeepFocus-X3'):
    # Create a new dataset repository on Hugging Face
    create_repo(repo_name, exist_ok=True)
    api = HfApi()
    api.upload_file(
        path_or_fileobj=csv_file,
        path_in_repo=csv_file,
        repo_id=repo_name,
        repo_type='dataset'
    )
    logger.info(f"Dataset {repo_name} created and file {csv_file} uploaded.")

# Gradio interface functions
def generate_words_interface():
    num_words = random.randint(50, 200)
    words = generate_random_words(num_words)
    meanings = get_word_meanings(words)
    convert_to_csv(meanings)
    return f"Generated {num_words} random words and saved to dataset.csv."

def about_interface():
    return "This is a dataset generation tool that creates a dataset of random words and their meanings, then uploads it to Hugging Face."

def logs_interface():
    with open('dataset_generation.log', 'r') as file:
        logs = file.read()
    return logs

# Gradio app setup
with gr.Blocks() as demo:
    with gr.Tabs():
        with gr.Tab("About"):
            about_text = gr.Markdown(about_interface)
        with gr.Tab("Generate"):
            generate_button = gr.Button("Generate Dataset")
            generate_output = gr.Textbox()
            generate_button.click(generate_words_interface, outputs=generate_output)
        with gr.Tab("Logs"):
            logs_output = gr.Textbox(value=logs_interface(), interactive=False)

# Run the Gradio app
if __name__ == "__main__":
    demo.launch()