Create app.py

app.py

@@ -0,0 +1,48 @@
+import streamlit as st
+from pyabsa import available_checkpoints
+from pyabsa import ATEPCCheckpointManager
+
+import os
+#import tensorflow_hub as hub
+import numpy as np
+import pandas as pd
+import json
+
+checkpoint_map = available_checkpoints()
+
+aspect_extractor = ATEPCCheckpointManager.get_aspect_extractor(checkpoint='english',
+                                   auto_device=True  # False means load model on CPU
+                                   )
+
+
+
+def main():
+    st.set_page_config(page_title="Aspect based sentiment Anslysis", page_icon=":smiley:", layout="wide")
+    st.title("Aspect based sentiment Anslysis :smiley:")
+
+
+
+    st.header("Aspect based sentiment Anslysis")
+    st.write("Enter a review:")
+    st.write("e.g. Purchased this for my device, it worked as advertised. You can never have too much phone memory, since I download a lot of stuff this was a no brainer for me.")
+    input_string = st.text_input("")
+
+    
+
+    if st.button("Enter"):
+        st.write("Aspect and sentiment is:")
+
+        example=[]
+        example.append(input_string)
+
+        inference_source = examples
+        atepc_result = aspect_extractor.extract_aspect(inference_source=inference_source,  #
+                                  pred_sentiment=True,  # Predict the sentiment of extracted aspect terms
+                                  )
+
+        for aspect, sentiment in zip(atepc_result[0]['aspect'], atepc_result[0]['sentiment']):
+            st.write(aspect + ': ' + sentiment)
+
+
+if __name__ == "__main__":
+    main()