Delete app.py

app.py

@@ -1,47 +0,0 @@
-import streamlit as st
-import numpy as np
-import tensorflow as tf
-
-# Load the TFLite model
-model_path = "Overall_recommendation_model.tflite"  # Adjust the path accordingly
-interpreter = tf.lite.Interpreter(model_path=model_path)
-interpreter.allocate_tensors()
-
-# Define a function to make predictions
-def predict(banq_name):
-    input_details = interpreter.get_input_details()
-    output_details = interpreter.get_output_details()
-
-    # Preprocess the input (if necessary)
-    # For example, convert banq_name to the format expected by the model
-
-    # Set the input tensor
-    interpreter.set_tensor(input_details[0]['index'], np.array([banq_name], dtype=np.str))
-
-    # Run inference
-    interpreter.invoke()
-
-    # Get the output tensor
-    output_data = interpreter.get_tensor(output_details[0]['index'])
-
-    # Postprocess the output (if necessary)
-    # For example, convert the output to human-readable format
-
-    return output_data
-
-# Streamlit UI
-st.title("Banquet Recommendation App")
-
-# Input field for the banquet name
-banq_name = st.text_input("Enter the banquet name:")
-
-# Button to trigger prediction
-if st.button("Recommend"):
-    # Make prediction
-    recommendation = predict(banq_name)
-
-    # Display recommendation
-    st.write("Recommended banquet halls:")
-    for hall in recommendation:
-        st.write("- ", hall)
-