change function calls, add inital attempt

app.py

@@ -21,7 +21,7 @@ def cosine_similarity(x, y):
     ##################################
     ### TODO: Add code here ##########
     ##################################
-    pass
+    return np.exp(np.dot(x,y)/(np.linalg.norm(x)*np.linalg.norm(y)))
     
 
 # Function to Load Glove Embeddings
@@ -125,6 +125,18 @@ def averaged_glove_embeddings_gdrive(sentence, word_index_dict, embeddings, mode
     ##################################
     ##### TODO: Add code here ########
     ##################################
+    for word in sentence:
+        #print(sentence)
+        words = [word.strip('.,?!').lower() for word in sentence.split()]
+        total = 0
+        for w in words:
+            if w in embeddings:
+                embed += embeddings[w]
+                total +=1
+        if total != 0:
+            embed = embed/total
+    
+    return embed
 
 
 def get_category_embeddings(embeddings_metadata):
@@ -176,6 +188,9 @@ def get_sorted_cosine_similarity(embeddings_metadata):
         ##########################################
         ## TODO: Get embeddings for categories ###
         ##########################################
+        category_embeddings = []
+        for cat in categories:
+            category_embeddings.append(get_glove_embeddings(cat))
 
     else:
         model_name = embeddings_metadata["model_name"]
@@ -190,13 +205,33 @@ def get_sorted_cosine_similarity(embeddings_metadata):
         else:
             input_embedding = get_sentence_transformer_embeddings(st.session_state.text_search)
         for index in range(len(categories)):
-            pass
+            
             ##########################################
             # TODO: Compute cosine similarity between input sentence and categories
             # TODO: Update category embeddings if category not found  
             ##########################################
-
-    return 
+            cat_scores = []
+            cat_idx = 0
+            for cat_embed in category_embeddings:
+                # Calc cosine sim
+                cat_scores.append((cat_idx, np.dot(input,cat_embed)))
+                # Store doc_id and score as a tuple
+                cat_idx +=1
+                
+           
+            sorted_list = sorted(cat_scores, key=lambda x: x[1])
+            
+            sorted_cats = [element[0] for element in sorted_list]
+           
+            #flip sorting order
+            sorted_cats = sorted_cats[::-1]
+            # Add list to Map
+            result = sorted_cats[0]
+            selected_cat = categories[result]
+            print(selected_cat)
+
+
+    return selected_cat
 
 
 def plot_piechart(sorted_cosine_scores_items):
@@ -354,7 +389,8 @@ if st.session_state.text_search:
     }
     with st.spinner("Obtaining Cosine similarity for Glove..."):
         sorted_cosine_sim_glove = get_sorted_cosine_similarity(
-            st.session_state.text_search, embeddings_metadata
+            # st.session_state.text_search, 
+            embeddings_metadata
         )
 
     # Sentence transformer embeddings
@@ -362,7 +398,8 @@ if st.session_state.text_search:
     embeddings_metadata = {"embedding_model": "transformers", "model_name": ""}
     with st.spinner("Obtaining Cosine similarity for 384d sentence transformer..."):
         sorted_cosine_sim_transformer = get_sorted_cosine_similarity(
-            st.session_state.text_search, embeddings_metadata
+            # st.session_state.text_search, 
+            embeddings_metadata
         )
 
     # Results and Plot Pie Chart for Glove