Update app.py

app.py

@@ -1,36 +1,226 @@
+import os
 import gradio as gr
-from gector.gec_model import GecBERTModel
-
-# Load the GECToR model
-def load_model():
-    model = GecBERTModel(
-        vocab_path='data/output_vocabulary',
-        model_paths=['data/model_files/xlnet_0_gector.th'],
-        max_len=128, min_len=3
-    )
-    return model
-
-# Function to correct grammar using GECToR model
-def correct_grammar(text):
-    # Initialize the model (you can load it once and use globally to avoid reloading each time)
-    model = load_model()
-    # Correct the input text
-    corrected_text = model.handle_batch([text])
-    return corrected_text[0]  # Since the result is a list, return the first (and only) item
-
-# Define Gradio interface
-def create_gradio_interface():
-    # Input and output in Gradio
-    interface = gr.Interface(
-        fn=correct_grammar,  # Function to run
-        inputs="text",  # Input is plain text
-        outputs="text",  # Output is plain text
-        title="Grammar Correction App using GECToR",
-        description="Enter your text, and this app will correct its grammar using GECToR."
-    )
-    return interface
-
-# Launch the Gradio app
-if __name__ == "__main__":
-    gradio_interface = create_gradio_interface()
-    gradio_interface.launch()
+from transformers import pipeline
+import spacy
+import subprocess
+import nltk
+from nltk.corpus import wordnet
+from nltk.corpus import stopwords
+from nltk.tokenize import word_tokenize
+from spellchecker import SpellChecker
+import re
+import string
+import random
+
+# Download necessary NLTK data
+nltk.download('punkt')
+nltk.download('stopwords')
+nltk.download('averaged_perceptron_tagger')
+nltk.download('wordnet')
+
+# Initialize stopwords
+stop_words = set(stopwords.words("english"))
+
+# Words we don't want to replace
+exclude_tags = {'PRP', 'PRP$', 'MD', 'VBZ', 'VBP', 'VBD', 'VBG', 'VBN', 'TO', 'IN', 'DT', 'CC'}
+exclude_words = {'is', 'am', 'are', 'was', 'were', 'have', 'has', 'do', 'does', 'did', 'will', 'shall', 'should', 'would', 'could', 'can', 'may', 'might'}
+
+# Initialize the English text classification pipeline for AI detection
+pipeline_en = pipeline(task="text-classification", model="Hello-SimpleAI/chatgpt-detector-roberta")
+
+# Initialize the spell checker
+spell = SpellChecker()
+
+# Ensure the SpaCy model is installed
+try:
+    nlp = spacy.load("en_core_web_sm")
+except OSError:
+    subprocess.run(["python", "-m", "spacy", "download", "en_core_web_sm"])
+    nlp = spacy.load("en_core_web_sm")
+
+def plagiarism_removal(text):
+    def plagiarism_remover(word):
+        if word.lower() in stop_words or word.lower() in exclude_words or word in string.punctuation:
+            return word
+        
+        # Find synonyms
+        synonyms = set()
+        for syn in wordnet.synsets(word):
+            for lemma in syn.lemmas():
+                if "_" not in lemma.name() and lemma.name().isalpha() and lemma.name().lower() != word.lower():
+                    synonyms.add(lemma.name())
+
+        pos_tag_word = nltk.pos_tag([word])[0]
+
+        if pos_tag_word[1] in exclude_tags:
+            return word
+        
+        filtered_synonyms = [syn for syn in synonyms if nltk.pos_tag([syn])[0][1] == pos_tag_word[1]]
+
+        if not filtered_synonyms:
+            return word
+
+        synonym_choice = random.choice(filtered_synonyms)
+
+        if word.istitle():
+            return synonym_choice.title()
+        return synonym_choice
+
+    para_split = word_tokenize(text)
+    final_text = [plagiarism_remover(word) for word in para_split]
+    
+    corrected_text = []
+    for i in range(len(final_text)):
+        if final_text[i] in string.punctuation and i > 0:
+            corrected_text[-1] += final_text[i]  
+        else:
+            corrected_text.append(final_text[i])
+
+    return " ".join(corrected_text)
+
+def predict_en(text):
+    res = pipeline_en(text)[0]
+    return res['label'], res['score']
+
+def remove_redundant_words(text):
+    doc = nlp(text)
+    meaningless_words = {"actually", "basically", "literally", "really", "very", "just"}
+    filtered_text = [token.text for token in doc if token.text.lower() not in meaningless_words]
+    return ' '.join(filtered_text)
+
+def fix_punctuation_spacing(text):
+    words = text.split(' ')
+    cleaned_words = []
+    punctuation_marks = {',', '.', "'", '!', '?', ':'}
+
+    for word in words:
+        if cleaned_words and word and word[0] in punctuation_marks:
+            cleaned_words[-1] += word
+        else:
+            cleaned_words.append(word)
+
+    return ' '.join(cleaned_words).replace(' ,', ',').replace(' .', '.').replace(" '", "'") \
+                                    .replace(' !', '!').replace(' ?', '?').replace(' :', ':')
+
+def fix_possessives(text):
+    text = re.sub(r'(\w)\s\'\s?s', r"\1's", text)
+    return text
+
+def capitalize_sentences_and_nouns(text):
+    doc = nlp(text)
+    corrected_text = []
+
+    for sent in doc.sents:
+        sentence = []
+        for token in sent:
+            if token.i == sent.start:
+                sentence.append(token.text.capitalize())
+            elif token.pos_ == "PROPN":
+                sentence.append(token.text.capitalize())
+            else:
+                sentence.append(token.text)
+        corrected_text.append(' '.join(sentence))
+
+    return ' '.join(corrected_text)
+
+def force_first_letter_capital(text):
+    sentences = re.split(r'(?<=\w[.!?])\s+', text)
+    capitalized_sentences = []
+    
+    for sentence in sentences:
+        if sentence:
+            capitalized_sentence = sentence[0].capitalize() + sentence[1:]
+            if not re.search(r'[.!?]$', capitalized_sentence):
+                capitalized_sentence += '.'
+            capitalized_sentences.append(capitalized_sentence)
+    
+    return " ".join(capitalized_sentences)
+
+def correct_tense_errors(text):
+    doc = nlp(text)
+    corrected_text = []
+    for token in doc:
+        if token.pos_ == "VERB" and token.dep_ in {"aux", "auxpass"}:
+            lemma = wordnet.morphy(token.text, wordnet.VERB) or token.text
+            corrected_text.append(lemma)
+        else:
+            corrected_text.append(token.text)
+    return ' '.join(corrected_text)
+
+def correct_article_errors(text):
+    doc = nlp(text)
+    corrected_text = []
+    for token in doc:
+        if token.text in ['a', 'an']:
+            next_token = token.nbor(1)
+            if token.text == "a" and next_token.text[0].lower() in "aeiou":
+                corrected_text.append("an")
+            elif token.text == "an" and next_token.text[0].lower() not in "aeiou":
+                corrected_text.append("a")
+            else:
+                corrected_text.append(token.text)
+        else:
+            corrected_text.append(token.text)
+    return ' '.join(corrected_text)
+
+def ensure_subject_verb_agreement(text):
+    doc = nlp(text)
+    corrected_text = []
+    for token in doc:
+        if token.dep_ == "nsubj" and token.head.pos_ == "VERB":
+            if token.tag_ == "NN" and token.head.tag_ != "VBZ":
+                corrected_text.append(token.head.lemma_ + "s")
+            elif token.tag_ == "NNS" and token.head.tag_ == "VBZ":
+                corrected_text.append(token.head.lemma_)
+        corrected_text.append(token.text)
+    return ' '.join(corrected_text)
+
+def correct_spelling(text):
+    words = text.split()
+    corrected_words = []
+    for word in words:
+        corrected_word = spell.correction(word)
+        if corrected_word is not None:
+            corrected_words.append(corrected_word)
+        else:
+            corrected_words.append(word)
+    return ' '.join(corrected_words)
+
+def paraphrase_and_correct(text):
+    paragraphs = text.split("\n\n")  # Split by paragraphs
+
+    # Process each paragraph separately
+    processed_paragraphs = []
+    for paragraph in paragraphs:
+        cleaned_text = remove_redundant_words(paragraph)
+        plag_removed = plagiarism_removal(cleaned_text)
+        paraphrased_text = capitalize_sentences_and_nouns(plag_removed)
+        paraphrased_text = force_first_letter_capital(paraphrased_text)
+        paraphrased_text = correct_article_errors(paraphrased_text)
+        paraphrased_text = correct_tense_errors(paraphrased_text)
+        paraphrased_text = ensure_subject_verb_agreement(paraphrased_text)
+        paraphrased_text = fix_possessives(paraphrased_text)  # Fixed typo here
+        paraphrased_text = correct_spelling(paraphrased_text)
+        paraphrased_text = fix_punctuation_spacing(paraphrased_text)
+        processed_paragraphs.append(paraphrased_text)
+
+    return "\n\n".join(processed_paragraphs)  # Reassemble the text with paragraphs
+
+# Gradio app setup
+with gr.Blocks() as demo:
+    with gr.Tab("AI Detection"):
+        t1 = gr.Textbox(lines=5, label='Text')
+        button1 = gr.Button("🤖 Predict!")
+        label1 = gr.Textbox(lines=1, label='Predicted Label 🎃')
+        score1 = gr.Textbox(lines=1, label='Prob')
+
+        button1.click(fn=predict_en, inputs=t1, outputs=[label1, score1])
+
+    with gr.Tab("Paraphrasing & Grammar Correction"):
+        t2 = gr.Textbox(lines=5, label='Enter text for paraphrasing and grammar correction')
+        button2 = gr.Button("🔄 Paraphrase and Correct")
+        result2 = gr.Textbox(lines=5, label='Corrected Text')
+
+        button2.click(fn=paraphrase_and_correct, inputs=t2, outputs=result2)
+
+demo.launch(share=True)