Update app.py

app.py

@@ -25,6 +25,28 @@ def classify_image(img, cnn_model):
         return "No Tumor"
 
 
+# Load your DNN SMS spam detection model
+dnn_smsspam_model = tf.keras.models.load_model('dnn_smsspam_model.h5')
+# Load the saved tokenizer
+with open('dnn_smsspam_tokenizer.pickle', 'rb') as handle:
+    dnn_smsspam_tokenizer = pickle.load(handle)
+
+def dnn_predict_message(input_text):
+    max_length=20
+    # Process input text similarly to training data
+    encoded_input = dnn_smsspam_tokenizer.texts_to_sequences([input_text])
+    padded_input = tf.keras.preprocessing.sequence.pad_sequences(encoded_input, maxlen=max_length, padding='post')
+    # Get the probabilities of being classified as "Spam" for each input
+    predictions = dnn_smsspam_model.predict(padded_input)
+    # Define a threshold (e.g., 0.5) for classification
+    threshold = 0.5
+    # Make the predictions based on the threshold for each input
+    for prediction in predictions:
+        if prediction > threshold:
+            return "Spam"
+        else:
+            return "Not spam"
+
 
 # Load your RNN SMS spam detection model
 rnn_smsspam_model = tf.keras.models.load_model('rnn_smsspam_model.h5')
@@ -107,6 +129,17 @@ def main():
                 else:
                     st.write("Please enter some text for prediction")
 
+        elif model == "DNN":
+            st.subheader("SMS Spam Detection")
+            user_input = st.text_area("Enter a message to classify as 'Spam' or 'Not spam': ")
+                
+            if st.button("Predict"):
+                if user_input:
+                    prediction_result = dnn_predict_message(user_input)
+                    st.write(f"The message is classified as: {prediction_result}")
+                else:
+                    st.write("Please enter some text for prediction")
+
         elif model == "LSTM":
             st.subheader("SMS Spam Detection")
             user_input = st.text_area("Enter a message to classify as 'Spam' or 'Not spam': ")