Update app.py

app.py

@@ -1,8 +1,14 @@
+import sklearn
 import gradio as gr
+import joblib
 import requests.exceptions
 from huggingface_hub import HfApi, hf_hub_download
 from huggingface_hub.repocard import metadata_load
 
+pipe = joblib.load("./pipeline.pkl")
+inputs = [gr.Textbox(value = "The customer service was satisfactory.")]
+outputs = [gr.Label(label = "Sentiment")]
+title = "Sentiment Analysis"
 app = gr.Blocks()
 
 def load_agent(model_id_1, model_id_2):
@@ -16,18 +22,12 @@ def load_agent(model_id_1, model_id_2):
     # Get the accuracy
     results_1 = parse_metrics_accuracy(metadata_1)
     
-    # Load the video
-    #video_path_1 = hf_hub_download(model_id_1, filename="replay.mp4")
-    
     # Load the metrics
     metadata_2 = get_metadata(model_id_2)
     
     # Get the accuracy
     results_2 = parse_metrics_accuracy(metadata_2)
-    
-    # Load the video
-    #video_path_2 = hf_hub_download(model_id_2, filename="replay.mp4")
-    
+
     return model_id_1, results_1, model_id_2, results_2
 
 def parse_metrics_accuracy(meta):
@@ -53,8 +53,6 @@ def get_metadata(model_id):
         return None
 
 
-
-
 with app:
     gr.Markdown(
     """
@@ -71,11 +69,11 @@ with app:
       with gr.Column():
         model1_name = gr.Markdown()
         #model1_video_output = gr.Video()
-        model1_score_output = gr.Textbox(label="Mean Reward +/- Std Reward")
+        model1_score_output = gr.Textbox(label="Sentiment")
       with gr.Column():
         model2_name = gr.Markdown()
         #model2_video_output = gr.Video()
-        model2_score_output = gr.Textbox(label="Mean Reward +/- Std Reward")
+        model2_score_output = gr.Textbox(label="Sentiment")
 
     app_button.click(load_agent, inputs=[model1_input, model2_input], outputs=[model1_name, model1_score_output, model2_name, model2_score_output])