# -*- coding: utf-8 -*-
"""app.py

Automatically generated by Colab.

Original file is located at
    https://colab.research.google.com/drive/1FU-FwNSEDPpESmqMM7bZNA9Qnt24hpna
"""

import nltk
import gradio as gr
from nltk.sentiment import SentimentIntensityAnalyzer

# Download required NLTK resources
nltk.download('punkt_tab')
nltk.download('averaged_perceptron_tagger_eng')
nltk.download('maxent_ne_chunker_tab')
nltk.download('vader_lexicon')
nltk.download('words')

sia = SentimentIntensityAnalyzer()
def analyze_text(text):
    if not text.strip():
        return "Please enter valid text.", "", ""

    # Tokenize and POS tagging
    tokens = nltk.word_tokenize(text)
    pos_tags = nltk.pos_tag(tokens)

    # Format POS output
    pos_output = "Part-of-Speech Tags:\n"
    for word, tag in pos_tags:
        pos_output += f"{word:15} → {tag}\n"

    # Named Entity Recognition
    ner_tree = nltk.ne_chunk(pos_tags)
    ner_output = "Named Entities:\n"
    for subtree in ner_tree:
        if hasattr(subtree, 'label'):
            entity = " ".join([token for token, pos in subtree.leaves()])
            label = subtree.label()
            ner_output += f"{entity:20} → {label}\n"

    # Sentiment Analysis
    sentiment_scores = sia.polarity_scores(text)
    compound = sentiment_scores['compound']
    if compound >= 0.05:
        sentiment = "Positive"
    elif compound <= -0.05:
        sentiment = "Negative"
    else:
        sentiment = "Neutral"

    sentiment_output = f"Sentiment: {sentiment}"
    return pos_output.strip(), ner_output.strip(), sentiment_output.strip()

# Gradio Interface
iface = gr.Interface(
    fn=analyze_text,
    inputs=gr.Textbox(lines=5, placeholder="Enter your text here...", label="Input Text"),
    outputs=[
        gr.Textbox(label="POS Tags"),
        gr.Textbox(label="Named Entities"),
        gr.Textbox(label="Sentiment Analysis")
    ],
    title="Text Analysis with NLTK",
    description="Enter any text to get Part-of-Speech tags, Named Entities, and Sentiment using NLTK."
)

iface.launch()