Update app.py

app.py

@@ -5,18 +5,39 @@ import spacy
 import subprocess
 import nltk
 from nltk.corpus import wordnet
-from nltk.corpus import stopwords  
+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')
+nltk.download('omw-1.4')
+
+# 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()
 
-nltk.download('punkt')        
-nltk.download('stopwords')    
-nltk.download('averaged_perceptron_tagger')  
-nltk.download('wordnet')  
-nltk.download('stopwords') 
-top_words = set(stopwords.words("english"))  
+# 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):
@@ -67,33 +88,6 @@ def plagiarism_removal(text):
 
     return " ".join(corrected_text)
 
-
-
-
-
-
-
-# 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 necessary NLTK data is downloaded
-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 predict the label and score for English text (AI Detection)
 def predict_en(text):
     res = pipeline_en(text)[0]
@@ -213,14 +207,11 @@ def correct_spelling(text):
             corrected_words.append(word)
     return ' '.join(corrected_words)
 
-
-
-
 # Main function for paraphrasing and grammar correction
 def paraphrase_and_correct(text):
-     # Add synonym replacement here
+    # Add synonym replacement here
     cleaned_text = remove_redundant_words(text)
-    plag_removed=plagiarism_removal(cleaned_text)
+    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)