Update app.py

app.py

@@ -1,68 +1,150 @@
 import os
 import gradio as gr
 import spacy
+import subprocess
 import nltk
 from nltk.corpus import wordnet
-from nltk.stem import WordNetLemmatizer
-from collections import defaultdict
 
-# Ensure necessary NLTK data is downloaded
+# Clone and install CorrectLy
+def install_correctly():
+    if not os.path.exists('CorrectLy'):
+        print("Cloning CorrectLy repository...")
+        subprocess.run(["git", "clone", "https://github.com/rounakdatta/CorrectLy.git"], check=True)
+        
+        # Install dependencies from CorrectLy
+        subprocess.run([sys.executable, "-m", "pip", "install", "-r", "CorrectLy/requirements.txt"], check=True)
+
+        # Add CorrectLy to Python path
+        sys.path.append(os.path.abspath('CorrectLy'))
+
+# Install CorrectLy
+install_correctly()
+
+# Import CorrectLy after installation
+from CorrectLy.correctly import CorrectLy
+
+# Initialize CorrectLy for grammar correction
+corrector = CorrectLy()
+
+# Initialize the English text classification pipeline for AI detection
+from transformers import pipeline
+pipeline_en = pipeline(task="text-classification", model="Hello-SimpleAI/chatgpt-detector-roberta")
+
+# 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']
+
+# Ensure necessary NLTK data is downloaded for Humanifier
 nltk.download('wordnet')
-nltk.download('averaged_perceptron_tagger')
-nltk.download('punkt')
+nltk.download('omw-1.4')
 
-# Ensure the SpaCy model is installed for POS tagging
+# Ensure the SpaCy model is installed for Humanifier
 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")
 
-# Initialize lemmatizer
-lemmatizer = WordNetLemmatizer()
-
-# Helper function to map nltk POS tags to wordnet POS tags
-def get_wordnet_pos(treebank_tag):
-    if treebank_tag.startswith('J'):
-        return wordnet.ADJ
-    elif treebank_tag.startswith('V'):
-        return wordnet.VERB
-    elif treebank_tag.startswith('N'):
-        return wordnet.NOUN
-    elif treebank_tag.startswith('R'):
-        return wordnet.ADV
-    else:
-        return None
-
-# Function to correct tense, singular/plural, and verb forms
-def grammar_correction(text):
-    words = nltk.word_tokenize(text)
-    tagged = nltk.pos_tag(words)
-    
+# Function to correct grammar using CorrectLy
+def correct_grammar_with_correctly(text):
+    return corrector.correct(text)
+
+# Function to get synonyms using NLTK WordNet (Humanifier)
+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]
+    return []
+
+# Function to capitalize the first letter of sentences and proper nouns (Humanifier)
+def capitalize_sentences_and_nouns(text):
+    doc = nlp(text)
     corrected_text = []
-    for word, tag in tagged:
-        wordnet_pos = get_wordnet_pos(tag) or wordnet.NOUN
-        lemma = lemmatizer.lemmatize(word, pos=wordnet_pos)
+
+    for sent in doc.sents:
+        sentence = []
+        for token in sent:
+            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)
+        corrected_text.append(' '.join(sentence))
+
+    return ' '.join(corrected_text)
+
+# Paraphrasing function using SpaCy and NLTK (Humanifier)
+def paraphrase_with_spacy_nltk(text):
+    doc = nlp(text)
+    paraphrased_words = []
+    
+    for token in doc:
+        # Map SpaCy POS tags to WordNet POS tags
+        pos = None
+        if token.pos_ in {"NOUN"}:
+            pos = wordnet.NOUN
+        elif token.pos_ in {"VERB"}:
+            pos = wordnet.VERB
+        elif token.pos_ in {"ADJ"}:
+            pos = wordnet.ADJ
+        elif token.pos_ in {"ADV"}:
+            pos = wordnet.ADV
         
-        # Apply basic rules for common errors
-        if tag.startswith('VB') and word.lower() != lemma:  # Verb tense correction
-            corrected_text.append(lemma)
-        elif tag.startswith('NNS') and word.lower() == lemma:  # Singular/plural correction
-            corrected_text.append(word + 's')
+        synonyms = get_synonyms_nltk(token.text.lower(), pos) if pos else []
+        
+        # Replace with a synonym only if it makes sense
+        if synonyms and token.pos_ in {"NOUN", "VERB", "ADJ", "ADV"} and synonyms[0] != token.text.lower():
+            paraphrased_words.append(synonyms[0])
         else:
-            corrected_text.append(word)
+            paraphrased_words.append(token.text)
     
-    return ' '.join(corrected_text)
+    # Join the words back into a sentence
+    paraphrased_sentence = ' '.join(paraphrased_words)
+    
+    # Capitalize sentences and proper nouns
+    corrected_text = capitalize_sentences_and_nouns(paraphrased_sentence)
+    
+    return corrected_text
 
-# Gradio app setup
+# Combined function: Paraphrase -> Capitalization (Humanifier)
+def paraphrase_and_correct(text):
+    # Step 1: Paraphrase the text
+    paraphrased_text = paraphrase_with_spacy_nltk(text)
+    
+    # Step 2: Capitalize sentences and proper nouns
+    final_text = capitalize_sentences_and_nouns(paraphrased_text)
+    
+    return final_text
+
+# Gradio app setup with three 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(predict_en, inputs=[t1], outputs=[label1, score1], api_name='predict_en')
+    
+    with gr.Tab("Humanifier"):
+        text_input = gr.Textbox(lines=5, label="Input Text")
+        paraphrase_button = gr.Button("Paraphrase & Correct")
+        output_text = gr.Textbox(label="Paraphrased Text")
+
+        # Connect the paraphrasing function to the button
+        paraphrase_button.click(paraphrase_and_correct, inputs=text_input, outputs=output_text)
+    
     with gr.Tab("Grammar Correction"):
         grammar_input = gr.Textbox(lines=5, label="Input Text")
         grammar_button = gr.Button("Correct Grammar")
         grammar_output = gr.Textbox(label="Corrected Text")
 
-        # Connect the grammar correction function to the button
-        grammar_button.click(grammar_correction, inputs=grammar_input, outputs=grammar_output)
+        # Connect the CorrectLy grammar correction function to the button
+        grammar_button.click(correct_grammar_with_correctly, inputs=grammar_input, outputs=grammar_output)
 
-# Launch the app
+# Launch the app with all functionalities
 demo.launch()