added more utils to retrieve sus data and get true and fake model certainty

utils.py

@@ -1,4 +1,9 @@
 import streamlit.components.v1 as components
+from random import randrange, uniform
+import pandas as pd
+import joblib
+import dill
+from omnixai.data.tabular import Tabular
 
 def ChangeButtonColour(widget_label, font_color, background_color='transparent'):
     htmlstr = f"""
@@ -76,4 +81,39 @@ feature_texts = {0: "Day out of 30", 1: "Type of transaction: ", 2: "Amount tran
                  5: "Initial balance of recipient: ", 6: "New balance of recipient: ", 7: "Sender's balance was exactly credited: ",
                    8: "Receiver's balance was exactly credited: ", 9: "Transaction over 450.000: ", 10: "Frequent receiver of transactions: ", 11: "Receiver is merchant: ", 12: "Sender ID: ", 13: "Receiver ID: "}
 
-example_input = {"instances":[[1,"PAYMENT",9839.64,170136,160296.36,0,0,1,1,0,0,1,84,2424]]}
+example_input = {"instances":[[1,"PAYMENT",9839.64,170136,160296.36,0,0,1,1,0,0,1,84,2424]]}
+
+
+def get_fake_certainty():
+    # Generate a random certainty between 75% and 99%
+    fake_certainty = uniform(0.75, 0.99)
+    formatted_fake_certainty = "{:.2%}".format(fake_certainty)
+    return formatted_fake_certainty
+
+
+def get_random_suspicious_transaction():
+    data = pd.read_pickle("data/preprocessed_data.pkl")
+    suspicious_data=data[data["isFraud"]==1]
+    max_n=len(suspicious_data)
+    random_nr=randrange(max_n)
+    suspicous_transaction = suspicious_data[random_nr-1:random_nr].drop("isFraud", axis=1)
+    return suspicous_transaction
+
+
+def get_model_certainty(data_point):
+    # load the trained model
+    model = joblib.load('model/model.joblib')
+    # load transformer
+    with open("transformer/transformer.dill", "rb") as f:
+            transformer = dill.load(f)
+    
+    # create tabular object of datapoint and apply transformation
+    sample = Tabular(data_point, categorical_columns=[1])
+    transformed = transformer.transform(sample)
+
+    # get model certainty for sample and transform it to smth intelligble
+    probability = model.predict_proba(transformed)
+    positive_class_probability = probability[:, 1][0]
+    formatted_probability = "{:.5%}".format(positive_class_probability)
+    # Print the formatted probability
+    return formatted_probability