Update analyzer.py

analyzer.py

@@ -1,24 +1,27 @@
-!python -m spacy download en_core_web_sm
 from flask import Flask, request, jsonify
 import os
 import re
 import json
+from nltk.stem import WordNetLemmatizer
+from nltk.corpus import stopwords
 import joblib
 from sklearn.feature_extraction.text import CountVectorizer
 from sklearn.naive_bayes import MultinomialNB
 from sklearn.pipeline import Pipeline
-import spacy
 
-nlp = spacy.load('en_core_web_sm')
+nltk.data.path.append('https://drive.google.com/drive/folders/1rc3yfpeKaQswBVe9wJKYWEmz1tHguDzF?usp=sharing')
+nltk.data.path.append('https://drive.google.com/drive/folders/1qpWGiSd0slH0QvUhm8BXwgMx18PvFlW1?usp=sharing')
 app = Flask(__name__)
 
 # Function to preprocess text data
 def clean_text_with_lemmatization(texts):
+    stopwords_set = set(stopwords.words('english'))
+    lemmatizer = WordNetLemmatizer()
     cleaned_texts = []
     for text in texts:
         text = text.lower()
         text = re.sub(r'[^\w\s]', ' ', text)
-        words = [token.lemma_ for token in nlp(text) if not token.is_stop]
+        words = [lemmatizer.lemmatize(word) for word in text.split() if word not in stopwords_set]
         cleaned_texts.append(' '.join(words))
     return cleaned_texts