Updated Gradio App

app.py

@@ -7,27 +7,55 @@ Original file is located at
     https://colab.research.google.com/drive/1SKjRNc67_9TZPKUGhtfiYMfcpZuMh6s0
 """
 
-# Commented out IPython magic to ensure Python compatibility.
 # %pip install gradio transformers -q
+# %pip install nltk
 
 # Import the key libraries
 import gradio as gr
 import torch
 from transformers import AutoTokenizer, AutoModelForSequenceClassification
 from scipy.special import softmax
+import nltk
+import re
+from nltk.corpus import stopwords
+from nltk.stem import WordNetLemmatizer
+
+# Download NLTK resources (if not already downloaded)
+nltk.download('stopwords')
+nltk.download('wordnet')
 
 # Load the tokenizer and model from Hugging Face
-model_path = "rasmodev/Covid-19_Sentiment_Analysis_BERT_Model"
+model_path = "rasmodev/Covid-19_Sentiment_Analysis_RoBERTa_Model"
 tokenizer = AutoTokenizer.from_pretrained(model_path)
 model = AutoModelForSequenceClassification.from_pretrained(model_path)
 
-# Preprocess text (username and link placeholders)
+# Preprocess text (username and link placeholders, and text preprocessing)
 def preprocess(text):
+    # Convert text to lowercase
+    text = text.lower()
+
+    # Remove special characters, numbers, and extra whitespaces
+    text = re.sub(r'[^a-zA-Z\s]', '', text)
+
+    # Remove stopwords (common words that don't carry much meaning)
+    stop_words = set(stopwords.words('english'))
+    words = text.split()  # Split text into words
+    words = [word for word in words if word not in stop_words]
+
+    # Lemmatize words to their base form
+    lemmatizer = WordNetLemmatizer()
+    words = [lemmatizer.lemmatize(word) for word in words]
+
+    # Rejoin the preprocessed words into a single string
+    processed_text = ' '.join(words)
+
+    # Process placeholders
     new_text = []
-    for t in text.split(" "):
+    for t in processed_text.split(" "):
         t = '@user' if t.startswith('@') and len(t) > 1 else t
         t = 'http' if t.startswith('http') else t
         new_text.append(t)
+
     return " ".join(new_text)
 
 # Perform sentiment analysis
@@ -72,9 +100,10 @@ interface = gr.Interface(
         ["This vaccine is terrible!"],
         ["I don't have a strong opinion about this vaccines."],
         ["The Vaccine is Good I have had no issues!"]
-    ]
+    ],
+    custom_css="""body { background-color: #f5f5f5; }"""
 )
 
 # Launch the Gradio app
-if __name__ == '__main__':
-    interface.launch(server_name="0.0.0.0", server_port=7860)
+interface.launch()
+