Update app.py

app.py

@@ -141,7 +141,7 @@ st.write("Distribution for Predicted_F")
 plot_predictions_distribution(data, 'Predicted_F_encoded', 'Distribution of Predictions for Female Demographic')
 st.write("Distribution for Predicted_M")
 plot_predictions_distribution(data, 'Predicted_M_encoded', 'Distribution of Predictions for Male Demographic')
-"""
+
 import streamlit as st
 from transformers import pipeline
 import re
@@ -195,4 +195,22 @@ if st.button("Predict Personality"):
             st.write(f"{label}: {score*100:.2f}%")
             displayed = True
     if not displayed:
-        st.write("No predictions exceed the confidence threshold.")
+        st.write("No predictions exceed the confidence threshold.")
+        """
+from transformers import AutoModelForSequenceClassification, AutoTokenizer
+nli_model = AutoModelForSequenceClassification.from_pretrained('facebook/bart-large-mnli')
+tokenizer = AutoTokenizer.from_pretrained('facebook/bart-large-mnli')
+
+premise = 'A few years ago, I was juggling a demanding job, volunteer commitments, and personal relationships, all while trying to manage chronic health issues. The challenge was overwhelming at times, but I approached it by prioritizing open communication with my employer and loved ones about my limits. I learned to delegate and accept help, which was difficult for me as I usually prefer to keep the peace by handling things myself. This experience taught me the importance of setting boundaries and the strength in vulnerability.'
+hypothesis = f'This example is Helper.'
+
+# run through model pre-trained on MNLI
+x = tokenizer.encode(premise, hypothesis, return_tensors='pt',
+                     truncation_strategy='only_first')
+logits = nli_model(x.to(device))[0]
+
+# we throw away "neutral" (dim 1) and take the probability of
+# "entailment" (2) as the probability of the label being true 
+entail_contradiction_logits = logits[:,[0,2]]
+probs = entail_contradiction_logits.softmax(dim=1)
+prob_label_is_true = probs[:,1]