Update app.py

app.py

@@ -1,7 +1,6 @@
 import gradio as gr
 import hopsworks
 from datasets import load_dataset
-import numpy as np 
 import pandas as pd
 
 project = hopsworks.login()
@@ -9,9 +8,8 @@ fs = project.get_feature_store()
 
 dataset_api = project.get_dataset_api()
 
-dataset_api.download("Resources/batch_data_predictions.csv")
-dataset = load_dataset("csv", data_files="batch_data_predictions.csv")
-predictions_df = pd.DataFrame(dataset,columns=['Headlines', 'URL','Predictions'],)
+dataset = load_dataset("torileatherman/sentiment_analysis_batch_predictions")
+predictions_df = pd.DataFrame(dataset,columns=['Headlines_seq', 'URL','Headline_str','Predictions'])
 predictions_df_url0 = predictions_df['URL'].iloc[1]
 predictions_df_url1 = predictions_df['URL'].iloc[2]
 predictions_df_url2 = predictions_df['URL'].iloc[3]
@@ -21,10 +19,10 @@ predictions_df_url2 = predictions_df['URL'].iloc[3]
 def article_selection(sentiment):
     if sentiment == "Positive":
             return predictions_df_url0, predictions_df_url1, predictions_df_url2 #f"""The sentence you requested is Positive!"""
-    #elif sentiment == "Negative":
-     #   return f"""The sentence you requested is Negative!""" 
-    #else:
-     #   return f"""The sentence you requested is Neutral!""" 
+    elif sentiment == "Negative":
+        return f"""The sentence you requested is Negative!""" 
+    else:
+        return f"""The sentence you requested is Neutral!"""