Update app.py

app.py

@@ -2,187 +2,96 @@ import os
 import gradio as gr
 from transformers import pipeline
 import spacy
+import subprocess
 import nltk
 from nltk.corpus import wordnet
 from spellchecker import SpellChecker
-import re
-import inflect
+import language_tool_python
 
-# 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()
+# Initialize the LanguageTool for grammar correction
+tool = language_tool_python.LanguageTool('en-US')
 
 # Ensure necessary NLTK data is downloaded
-nltk.download('wordnet', quiet=True)
-nltk.download('omw-1.4', quiet=True)
+nltk.download('wordnet')
+nltk.download('omw-1.4')
+
+# 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")
 
-# Function to remove redundant/filler words
+# Function to predict the label and score for English text (AI Detection)
+def predict_en(text):
+    res = pipeline_en(text)[0]
+    return res['label'], res['score']
+
+# Function to remove redundant and meaningless words
 def remove_redundant_words(text):
     doc = nlp(text)
-    meaningless_words = {"actually", "basically", "literally", "really", "very", "just", "quite", "rather", "simply", 
-                         "that", "kind of", "sort of", "you know", "honestly", "seriously"}
+    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)
 
-# Function to capitalize sentences and proper nouns
+# Function to apply grammatical corrections using LanguageTool
+def correct_grammar(text):
+    corrected_text = tool.correct(text)
+    return corrected_text
+
+# Function to correct spelling errors
+def correct_spelling(text):
+    words = text.split()
+    corrected_words = []
+    for word in words:
+        corrected_word = spell.correction(word)
+        corrected_words.append(corrected_word if corrected_word else word)  # Keep original word if no correction
+    return ' '.join(corrected_words)
+
+# Function to capitalize the first letter of each sentence 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":
+            if token.i == sent.start:  # First word of the sentence
+                sentence.append(token.text.capitalize())
+            elif token.pos_ == "PROPN":  # Proper noun
                 sentence.append(token.text.capitalize())
             else:
-                sentence.append(token.text.lower())
+                sentence.append(token.text)
         corrected_text.append(' '.join(sentence))
-    return ' '.join(corrected_text)
 
-# Function to correct verb tenses
-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)
 
-# Function to ensure subject-verb agreement
-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_)
-            else:
-                corrected_text.append(token.head.text)
-        else:
-            corrected_text.append(token.text)
-    return ' '.join(corrected_text)
-
-# Function to correct apostrophe usage
-def correct_apostrophes(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
-
-# Function to enhance punctuation usage
-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
-    text = re.sub(r'\s*"\s*', '" ', text).strip()         # Clean up spaces around quotes
-    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)  # Ensure sentences start with capitalized words
-    return text
-
-# Function to correct semantic errors and replace with more appropriate 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)
-
-# Function to rephrase using synonyms and adjust verb forms
+# Function to rephrase with contextually appropriate synonyms
 def rephrase_with_synonyms(text):
     doc = nlp(text)
     rephrased_text = []
 
     for token in doc:
         pos_tag = None
-        if token.pos_ in ["NOUN", "VERB", "ADJ", "ADV"]:
-            pos_tag = getattr(wordnet, token.pos_)
-
+        if token.pos_ == "NOUN":
+            pos_tag = wordnet.NOUN
+        elif token.pos_ == "VERB":
+            pos_tag = wordnet.VERB
+        elif token.pos_ == "ADJ":
+            pos_tag = wordnet.ADJ
+        elif token.pos_ == "ADV":
+            pos_tag = wordnet.ADV
+        
         if pos_tag:
-            synonyms = get_synonyms_nltk(token.lemma_, pos_tag)
+            synonyms = wordnet.synsets(token.text, pos=pos_tag)
             if synonyms:
-                synonym = synonyms[0]
-                if token.pos_ == "VERB":
-                    if token.tag_ == "VBG":
-                        synonym = synonym + 'ing'
-                    elif token.tag_ in ["VBD", "VBN"]:
-                        synonym = synonym + 'ed'
-                    elif token.tag_ == "VBZ":
-                        synonym = synonym + 's'
+                synonym = synonyms[0].lemmas()[0].name()  # Choose the first synonym
                 rephrased_text.append(synonym)
             else:
                 rephrased_text.append(token.text)
@@ -191,46 +100,45 @@ def rephrase_with_synonyms(text):
 
     return ' '.join(rephrased_text)
 
-# Function to apply enhanced spell check
-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)
-
-# Comprehensive function to correct the entire text
+# Comprehensive function for paraphrasing and grammar correction
 def paraphrase_and_correct(text):
-    text = enhanced_spell_check(text)
-    text = remove_redundant_words(text)
-    text = capitalize_sentences_and_nouns(text)
-    text = correct_tense_errors(text)
-    text = ensure_subject_verb_agreement(text)
-    text = enhance_punctuation(text)
-    text = correct_apostrophes(text)
-    text = correct_semantic_errors(text)
-    text = rephrase_with_synonyms(text)
-    return text
-
-# Gradio interface function
-def gradio_interface(text):
-    corrected_text = paraphrase_and_correct(text)
-    return corrected_text
+    # Step 1: Remove meaningless or redundant words
+    cleaned_text = remove_redundant_words(text)
+    
+    # Step 2: Capitalize sentences and proper nouns
+    paraphrased_text = capitalize_sentences_and_nouns(cleaned_text)
+    
+    # Step 3: Correct grammar using LanguageTool
+    paraphrased_text = correct_grammar(paraphrased_text)
+    
+    # Step 4: Rephrase with contextually appropriate synonyms
+    paraphrased_text = rephrase_with_synonyms(paraphrased_text)
+    
+    # Step 5: Correct spelling errors
+    paraphrased_text = correct_spelling(paraphrased_text)
+    
+    # Step 6: Correct any remaining grammar issues after rephrasing
+    paraphrased_text = correct_grammar(paraphrased_text)
+    
+    return paraphrased_text
+
+# Gradio app setup with two tabs
+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')
+
+        # Connect the prediction function to the button
+        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')
+
+        # Connect the paraphrasing and correction function to the button
+        button2.click(fn=paraphrase_and_correct, inputs=t2, outputs=result2)
 
-# Setting up Gradio interface
-iface = gr.Interface(
-    fn=gradio_interface,
-    inputs=gr.Textbox(lines=5, placeholder="Enter text here..."),
-    outputs=[gr.Textbox(label="Corrected Text")],
-    title="Grammar & Semantic Error Correction",
-)
-
-# Run the Gradio interface
-if __name__ == "__main__":
-    iface.launch()
+demo.launch(share=True)