Add bar plot for emotions

app.py

@@ -18,6 +18,7 @@ from torch.utils.data import Dataset, DataLoader
 import torch.nn as nn
 import os
 from dotenv import load_dotenv
+import pandas as pd
 load_dotenv()
 
     
@@ -220,6 +221,7 @@ def load_model(tweet):
     print(inputs)
     emotion_list = calc_emotion_score(tweet)
     print(emotion_list)
+    preemotion_list = emotion_list[:]
 
     features_list = extract_features(tweet)
     for i in features_list.values():
@@ -358,22 +360,44 @@ def load_model(tweet):
         return pred
 
     predicted_class = predict_single_text(model, inputs, device)
-    return predicted_class
+    return predicted_class,preemotion_list,personality_list
     # print("Hate speech result",predicted_class)
 
 
 
 
 #Gradio interface
+simple  = None
 def greet(tweet):
     print("start")
-    prediction = load_model(tweet)
+    prediction,preemotion_list,personality_list = load_model(tweet)
+    preemotion_list = [x * 100 for x in preemotion_list]
+    simple = pd.DataFrame(
+    {
+        "keys": ["Anger", "Anticipation", "Disgust", "Fear", "Joy", "Love", "Optimism", "Pessimism", "Sadness","Surprise","Trust"],
+        "values": preemotion_list,
+    }
+)
+    with gr.Blocks() as bar_plot:
+        bar_plot.load(outputs= gr.BarPlot(
+                simple,
+                x="Emotions",
+                y="Values",
+                title="Simple Bar Plot with made up data",
+                tooltip=["a", "b"],
+                y_lim=[20, 100],
+            ))
+
+    bar_plot.launch()
+
     prediction_value = round(prediction.item(),2)
     # features_list = extract_features(tweet)
     # print(personality_detection(tweet))
     # print(str(features_list["Average_Word_Length"]))
     # print(calc_emotion_score(tweet))
     predicted_class = torch.round(prediction).item()
+    print(preemotion_list)
+    print(personality_list)
     print("end")
     if (predicted_class==0.0):
         label = "Non Hate"