Update app.py

app.py

@@ -1,71 +1,68 @@
 from flask import Flask, render_template, request
-from textblob import TextBlob
-import re
-import nltk
-from nltk.translate.bleu_score import sentence_bleu
 from nltk.corpus import wordnet
-from nltk.corpus import sentiwordnet as swn
-from nltk.sentiment import SentimentIntensityAnalyzer
+from nltk.tokenize import word_tokenize
+from nltk.corpus import stopwords
+from nltk.stem import WordNetLemmatizer
+from summa.summarizer import summarize
+from textblob import TextBlob
+import spacy
 
 app = Flask(__name__)
 
-@app.route('/')
+@app.route("/")
 def index():
-    return render_template('index.html')
+    return render_template("index.html")
 
-@app.route('/paraphrase', methods=['POST'])
+@app.route("/paraphrase", methods=["POST"])
 def paraphrase():
-    input_text = request.form['input_text']
-    input_text = re.sub(r'[^\w\s]', '', input_text) # remove special characters
-
-    # Correct grammar using TextBlob
-    input_text = str(TextBlob(input_text).correct())
-
-    # Summarize the text using TextBlob
-    summarized_text = str(TextBlob(input_text).summarize())
-
-    # Paraphrase the text
-    paraphrased_text = generate_paraphrase(input_text)
-
-    # Emotion detection
-    emotion = detect_emotion(input_text)
-
-    # Named Entity Recognition
-    entities = nltk.ne_chunk(nltk.pos_tag(nltk.word_tokenize(input_text)))
-
-    # Part-of-Speech Tagging
-    pos_tags = nltk.pos_tag(nltk.word_tokenize(input_text))
-
-    # Sentiment Analysis
-    sentiment = SentimentIntensityAnalyzer().polarity_scores(input_text)
-
-    return render_template('index.html', input_text=input_text, summarized_text=summarized_text, paraphrased_text=paraphrased_text, entities=entities, pos_tags=pos_tags, sentiment=sentiment, emotion=emotion)
-
-def generate_paraphrase(text):
-    # Use TextBlob to generate paraphrased text
-    paraphrased_text = str(TextBlob(text).words)
-
-    # Custom synonyms
-    custom_synonyms = [('happy', 'joyful'), ('sad', 'unhappy')]
-    for syn in custom_synonyms:
-        paraphrased_text = paraphrased_text.replace(syn[0], syn[1])
-
-    return paraphrased_text
-
-def detect_emotion(text):
-    # Use SentiWordNet to detect emotion in text
-    emotions = []
-    words = nltk.word_tokenize(text)
-    for word in words:
-        synset = swn.senti_synsets(word)
-        if len(synset) > 0:
-            emotions.append(synset[0].pos_score() - synset[0].neg_score())
-    if emotions:
-        emotion = max(emotions)
-    else:
-        emotion = 0
-
-    return 'positive' if emotion > 0 else 'negative' if emotion < 0 else 'neutral'
-
-if __name__ == '__main__':
+    input_text = request.form["input_text"]
+    
+    # Option to correct grammar using TextBlob
+    corrected_text = str(TextBlob(input_text).correct())
+    
+    # Option to remove special characters
+    clean_text = ''.join(e for e in corrected_text if e.isalnum() or e.isspace())
+    
+    # Perform text summarization
+    summary = summarize(clean_text)
+    
+    # Perform word tokenization and remove stopwords
+    stop_words = set(stopwords.words("english"))
+    words = word_tokenize(summary)
+    words = [word for word in words if word.lower() not in stop_words]
+    
+    # Perform lemmatization on the words
+    lemmatizer = WordNetLemmatizer()
+    lemmatized_words = [lemmatizer.lemmatize(word, pos=get_wordnet_pos(word)) for word in words]
+    
+    # Load spaCy's NER model
+    nlp = spacy.load("en_core_web_sm")
+    
+    # Use spaCy's NER to identify named entities in the input text
+    doc = nlp(summary)
+    entities = []
+    for ent in doc.ents:
+        entities.append((ent.text, ent.label_))
+    
+    # Use spaCy's POS tagging on the input text
+    pos_tags = []
+    for token in doc:
+        pos_tags.append((token.text, token.pos_))
+    
+    # Use TextBlob to perform sentiment analysis on the input text
+    sentiment = TextBlob(summary).sentiment.polarity
+    
+    return render_template("paraphrase.html", input_text=input_text, output_text=' '.join(lemmatized_words), entities=entities, pos_tags=pos_tags, sentiment=sentiment)
+
+def get_wordnet_pos(word):
+    """Map POS tag to first character used by WordNetLemmatizer"""
+    tag = nltk.pos_tag([word])[0][1]
+    tag = tag[0].upper()
+    tag_dict = {"J": wordnet.ADJ,
+                "N": wordnet.NOUN,
+                "V": wordnet.VERB,
+                "R": wordnet.ADV}
+    return tag_dict.get(tag, wordnet.NOUN)
+
+if __name__ == "__main__":
     app.run(host="0.0.0.0",port=7860,debug=True)