Update app.py

app.py

@@ -9,6 +9,7 @@ from transformers import AutoTokenizer, AutoModel
 from sklearn.metrics.pairwise import cosine_similarity
 import numpy as np
 import os
+from PIL import Image
 
 # Load the BioBERT model and tokenizer
 @st.cache_resource
@@ -136,7 +137,32 @@ def main():
         similar_trials.to_excel(output_file, index=False)
         with open(output_file, "rb") as f:
             st.download_button("Download Results as Excel", f, file_name="similar_trials_results.xlsx")
+    st.title("Visualizations")
 
+    # t-SNE Plot Section
+    st.subheader("t-SNE Plot")
+    st.write(
+        "t-SNE (t-Distributed Stochastic Neighbor Embedding) is used to visualize high-dimensional embeddings in a lower-dimensional space, helping to identify clusters or patterns in the data."
+    )
+    tsne_image_path = "model/tsne_visualization.png"  # Replace with the actual path to your t-SNE plot image
+    tsne_image = Image.open(tsne_image_path)
+    st.image(tsne_image, caption="t-SNE Plot")
+
+    st.markdown("---")
+
+    # Cosine Similarity Matrix Section
+    st.subheader("Cosine Similarity Matrix")
+    st.write(
+        "The cosine similarity matrix shows the similarity scores between different clinical trial embeddings, where higher scores indicate more similar trials."
+    )
+    cosine_matrix_image_path = "model/cosine_similarity.png"  # Replace with the actual path to your cosine similarity matrix image
+    cosine_matrix_image = Image.open(cosine_matrix_image_path)
+    st.image(cosine_matrix_image, caption="Cosine Similarity Matrix")
+
+    st.markdown(
+        "### Reference\n"
+        "For more information, visit the [code files uploaded on Hugging Face](https://huggingface.co/spaces/yashgupta1512/nest/tree/main/model)."
+    )
 
 if __name__ == "__main__":
     main()