Update app.py

app.py

@@ -1,66 +1,25 @@
-import os
-import gradio as gr
-from transformers import pipeline
-import spacy
-import nltk
-from nltk.corpus import wordnet
-from spellchecker import SpellChecker
-import re
-import inflect
-
-# Initialize components
-try:
-    nlp = spacy.load("en_core_web_sm")
-except OSError:
-    print("Downloading spaCy model...")
-    spacy.cli.download("en_core_web_sm")
-    nlp = spacy.load("en_core_web_sm")
-
-# 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()
-
-# Initialize the inflect engine for pluralization
-inflect_engine = inflect.engine()
-
-# Ensure necessary NLTK data is downloaded
-nltk.download('wordnet', quiet=True)
-nltk.download('omw-1.4', quiet=True)
-
-def predict_en(text):
-    res = pipeline_en(text)[0]
-    return res['label'], res['score']
-
-def get_synonyms_nltk(word, pos):
-    synsets = wordnet.synsets(word, pos=pos)
-    if synsets:
-        lemmas = synsets[0].lemmas()
-        return [lemma.name() for lemma in lemmas if lemma.name() != word]
-    return []
-
+# Added more redundant/filler words
 def remove_redundant_words(text):
     doc = nlp(text)
-    meaningless_words = {"actually", "basically", "literally", "really", "very", "just"}
+    meaningless_words = {"actually", "basically", "literally", "really", "very", "just", "quite", "rather", "simply", "that", "kind of", "sort of", "you know", "honestly", "seriously"}
     filtered_text = [token.text for token in doc if token.text.lower() not in meaningless_words]
     return ' '.join(filtered_text)
 
+# Capitalize sentences and proper nouns
 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 or token.pos_ == "PROPN":
                 sentence.append(token.text.capitalize())
             else:
-                sentence.append(token.text)
+                sentence.append(token.text.lower())
         corrected_text.append(' '.join(sentence))
-
     return ' '.join(corrected_text)
 
+# Function to dynamically correct tenses and verb forms
 def correct_tense_errors(text):
     doc = nlp(text)
     corrected_text = []
@@ -72,47 +31,7 @@ def correct_tense_errors(text):
             corrected_text.append(token.text)
     return ' '.join(corrected_text)
 
-def correct_singular_plural_errors(text):
-    doc = nlp(text)
-    corrected_text = []
-    
-    for token in doc:
-        if token.pos_ == "NOUN":
-            if token.tag_ == "NN" and any(child.text.lower() in ['many', 'several', 'few'] for child in token.head.children):
-                corrected_text.append(inflect_engine.plural(token.lemma_))
-            elif token.tag_ == "NNS" and any(child.text.lower() in ['a', 'one'] for child in token.head.children):
-                corrected_text.append(inflect_engine.singular_noun(token.text) or token.text)
-            else:
-                corrected_text.append(token.text)
-        else:
-            corrected_text.append(token.text)
-    
-    return ' '.join(corrected_text)
-
-def correct_article_errors(text):
-    doc = nlp(text)
-    corrected_text = []
-    for i, token in enumerate(doc):
-        if token.text.lower() in ['a', 'an']:
-            next_token = doc[i + 1] if i + 1 < len(doc) else None
-            if next_token and next_token.text[0].lower() in "aeiou":
-                corrected_text.append("an")
-            else:
-                corrected_text.append("a")
-        else:
-            corrected_text.append(token.text)
-    return ' '.join(corrected_text)
-
-def correct_double_negatives(text):
-    doc = nlp(text)
-    corrected_text = []
-    for token in doc:
-        if token.dep_ == "neg" and any(child.dep_ == "neg" for child in token.head.children):
-            continue
-        else:
-            corrected_text.append(token.text)
-    return ' '.join(corrected_text)
-
+# Enhanced function to handle subject-verb agreement
 def ensure_subject_verb_agreement(text):
     doc = nlp(text)
     corrected_text = []
@@ -128,119 +47,28 @@ def ensure_subject_verb_agreement(text):
             corrected_text.append(token.text)
     return ' '.join(corrected_text)
 
-def enhanced_spell_check(text):
-    words = text.split()
-    corrected_words = []
-    for word in words:
-        if '_' in word:
-            sub_words = word.split('_')
-            corrected_sub_words = [spell.correction(w) or w for w in sub_words]
-            corrected_words.append('_'.join(corrected_sub_words))
-        else:
-            corrected_word = spell.correction(word) or word
-            corrected_words.append(corrected_word)
-    return ' '.join(corrected_words)
-
-def correct_semantic_errors(text):
-    semantic_corrections = {
-        "animate_being": "animal",
-        "little": "smallest",
-        "big": "largest",
-        "mammalian": "mammals",
-        "universe": "world",
-        "manner": "ways",
-        "continue": "preserve",
-        "dirt": "soil",
-        "wellness": "health",
-        "modulate": "regulate",
-        "clime": "climate",
-        "function": "role",
-        "keeping": "maintaining",
-        "lend": "contribute",
-        "better": "improve",
-        "cardinal": "key",
-        "expeditiously": "efficiently",
-        "marauder": "predator",
-        "quarry": "prey",
-        "forestalling": "preventing",
-        "bend": "turn",
-        "works": "plant",
-        "croping": "grazing",
-        "flora": "vegetation",
-        "dynamical": "dynamic",
-        "alteration": "change",
-        "add-on": "addition",
-        "indispensable": "essential",
-        "nutrient": "food",
-        "harvest": "crops",
-        "pollenateing": "pollinating",
-        "divers": "diverse",
-        "beginning": "source",
-        "homo": "humans",
-        "fall_in": "collapse",
-        "takeing": "leading",
-        "coinage": "species",
-        "trust": "rely",
-        "angleworm": "earthworm",
-        "interrupt": "break",
-        "affair": "matter",
-        "air_out": "aerate",
-        "alimentary": "nutrient",
-        "distributeed": "spread",
-        "country": "areas",
-        "reconstruct": "restore",
-        "debauched": "degraded",
-        "giant": "whales",
-        "organic_structure": "bodies",
-        "decease": "die",
-        "carcase": "carcasses",
-        "pin_downing": "trapping",
-        "cut_downs": "reduces",
-        "ambiance": "atmosphere",
-        "extenuateing": "mitigating",
-        "decision": "conclusion",
-        "doing": "making",
-        "prolongs": "sustains",
-        "home_ground": "habitats",
-        "continueing": "preserving",
-        "populateing": "living",
-        "beingness": "beings"
-    }
-    
-    words = text.split()
-    corrected_words = [semantic_corrections.get(word.lower(), word) for word in words]
-    return ' '.join(corrected_words)
-
-def enhance_punctuation(text):
-    text = re.sub(r'\s+([?.!,";:])', r'\1', text)
-    text = re.sub(r'([?.!,";:])(\S)', r'\1 \2', text)
-    text = re.sub(r'\s*"\s*', '" ', text).strip()
-    text = re.sub(r'([.!?])\s*([a-z])', lambda m: m.group(1) + ' ' + m.group(2).upper(), text)
-    text = re.sub(r'([a-z])\s+([A-Z])', r'\1. \2', text)
-    return text
-
+# Ensure proper apostrophe usage and possessives
 def correct_apostrophes(text):
-    text = re.sub(r"\b(\w+)s\b(?<!\'s)", r"\1's", text)
-    text = re.sub(r"\b(\w+)s'\b", r"\1s'", text)
+    text = re.sub(r"\b(\w+)s\b(?<!\'s)", r"\1's", text)  # Simple apostrophe correction
+    text = re.sub(r"\b(\w+)s'\b", r"\1s'", text)         # Handles plural possessives
     return text
 
-def handle_possessives(text):
-    text = re.sub(r"\b(\w+)'s\b", r"\1's", text)
+# Enhanced punctuation
+def enhance_punctuation(text):
+    text = re.sub(r'\s+([?.!,";:])', r'\1', text)         # Remove extra space before punctuation
+    text = re.sub(r'([?.!,";:])(\S)', r'\1 \2', text)     # Add space after punctuation if needed
     return text
 
+# Paraphrasing using synonyms and correcting semantic errors
 def rephrase_with_synonyms(text):
     doc = nlp(text)
     rephrased_text = []
 
     for token in doc:
-        if token.text.lower() == "earth":
-            rephrased_text.append("Earth")
-            continue
-        
         pos_tag = None
         if token.pos_ in ["NOUN", "VERB", "ADJ", "ADV"]:
             pos_tag = getattr(wordnet, token.pos_)
-        
+
         if pos_tag:
             synonyms = get_synonyms_nltk(token.lemma_, pos_tag)
             if synonyms:
@@ -260,9 +88,9 @@ def rephrase_with_synonyms(text):
 
     return ' '.join(rephrased_text)
 
+# Comprehensive text correction
 def paraphrase_and_correct(text):
     text = enhanced_spell_check(text)
-    text = correct_semantic_errors(text)
     text = remove_redundant_words(text)
     text = capitalize_sentences_and_nouns(text)
     text = correct_tense_errors(text)
@@ -270,32 +98,22 @@ def paraphrase_and_correct(text):
     text = correct_article_errors(text)
     text = enhance_punctuation(text)
     text = correct_apostrophes(text)
-    text = handle_possessives(text)
     text = rephrase_with_synonyms(text)
     text = correct_double_negatives(text)
     text = ensure_subject_verb_agreement(text)
-    text = ' '.join(word.capitalize() if word.lower() in ['i', 'earth'] else word for word in text.split())
     return text
 
-def detect_ai(text):
-    label, score = predict_en(text)
-    return label, score
-
+# Integrate with Gradio UI
 def gradio_interface(text):
-    label, score = detect_ai(text)
     corrected_text = paraphrase_and_correct(text)
-    return {label: score}, corrected_text
+    return corrected_text
 
 iface = gr.Interface(
     fn=gradio_interface,
     inputs=gr.Textbox(lines=5, placeholder="Enter text here..."),
-    outputs=[
-        gr.Label(num_top_classes=1),
-        gr.Textbox(label="Corrected Text")
-    ],
-    title="AI Detection and Grammar Correction",
-    description="Detect AI-generated content and correct grammar issues."
+    outputs=[gr.Textbox(label="Corrected Text")],
+    title="Grammar & Semantic Error Correction",
 )
 
 if __name__ == "__main__":
-    iface.launch()
+    iface.launch()