Add application file

app.py

@@ -1,5 +1,26 @@
 import streamlit as st
+import pickle
+import numpy as np
 
+downloads_path = '/Users/preethamreddygollapalli/Downloads/'
+
+# Load the saved models
+with open(downloads_path + 'model_test_steps.pkl', 'rb') as file:
+    model_test_steps = pickle.load(file)
+
+with open(downloads_path + 'model_expected_result.pkl', 'rb') as file:
+    model_expected_result = pickle.load(file)
+
+# Function to process input and make predictions
+def predict_test_steps(input_embedding):
+    input_array = np.array(input_embedding).reshape((1, 1, len(input_embedding)))
+    predicted_steps = model_test_steps.predict(input_array)
+    return predicted_steps[0][0]  # Adjust according to the model's output structure
+
+def predict_expected_result(input_embedding):
+    input_array = np.array(input_embedding).reshape((1, 1, len(input_embedding)))
+    predicted_result = model_expected_result.predict(input_array)
+    return predicted_result[0][0]  # Adjust according to the model's output structure
 
 # Streamlit app interface
 st.title("Test Case Prediction App")
@@ -7,3 +28,21 @@ st.write("Enter the test case criteria below to generate test steps and expected
 
 # Input section
 user_input = st.text_area("Input Test Case Criteria", "")
+
+if st.button("Generate Predictions"):
+    if user_input:
+        # Simple tokenization and embedding logic (you might need to match this to your training process)
+        input_embedding = [0] * 100  # Replace with actual embedding method for user input
+
+        # Predict using the loaded models
+        predicted_test_steps = predict_test_steps(input_embedding)
+        predicted_expected_result = predict_expected_result(input_embedding)
+
+        # Display the results
+        st.subheader("Predicted Test Steps")
+        st.write(predicted_test_steps)
+
+        st.subheader("Predicted Expected Result")
+        st.write(predicted_expected_result)
+    else:
+        st.warning("Please enter test case criteria before generating predictions.")