sorted options words

app.py

@@ -19,8 +19,7 @@ def load_lsj_dict():
 
 @st.cache_data
 def load_all_models_words():
-    return load_compressed_word_list('all_lemmas.pkl.gz')
-
+    return sorted(load_compressed_word_list('corpora/compass_filtered.pkl.gz'), key=custom_sort)
 
 # Load compressed word list
 all_models_words = load_all_models_words()
@@ -38,13 +37,13 @@ active_tab = option_menu(None, ["Nearest neighbours", "Cosine similarity", "3D g
 # Nearest neighbours tab
 if active_tab == "Nearest neighbours":
     
-    # Load the compressed word list
-
+    # All models in a list
     eligible_models = ["Archaic", "Classical", "Hellenistic", "Early Roman", "Late Roman"]
+    all_models_words = load_all_models_words()
     
     with st.form("nn_form"):
         st.markdown("## Nearest Neighbours")
-        target_word = st.multiselect("Enter a word", all_models_words, max_selections=1)
+        target_word = st.multiselect("Enter a word", options=all_models_words, max_selections=1)
         if len(target_word) > 0:
             target_word = target_word[0]
             
@@ -99,24 +98,36 @@ if active_tab == "Nearest neighbours":
    
 # Cosine similarity tab
 elif active_tab == "Cosine similarity":
-    col1, col2 = st.columns(2)
-    col3, col4 = st.columns(2)
-    with st.container():
+    eligible_models_1 = []
+    eligible_models_2 = []
+    all_models_words = load_all_models_words()
+    
+    with st.form("cosine_similarity_form"):
+        st.markdown("## Cosine similarity")
+        col1, col2 = st.columns(2)
+        col3, col4 = st.columns(2)
         with col1:
-            word_1 = st.text_input("Enter a word", placeholder="πατήρ")
+            word_1 = st.multiselect("Enter a word", placeholder="πατήρ", max_selections=1, options=all_models_words)
+            if len(word_1) > 0:
+                word_1 = word_1[0]
+                eligible_models_1 = check_word_in_models(word_1)
+                
             
-        with col2:
-            time_slice_1 = st.selectbox("Time slice word 1", ["Archaic", "Classical", "Hellenistic", "Early Roman", "Late Roman"])
 
-    with st.container():
-        with col3:
-            word_2 = st.text_input("Enter a word", placeholder="μήτηρ")
-            
-        with col4:
-            time_slice_2 = st.selectbox("Time slice word 2", ["Archaic", "Classical", "Hellenistic", "Early Roman", "Late Roman"])
+            time_slice_1 = st.selectbox("Time slice word 1", eligible_models_1)
+
+        with st.container():
+            with col3:
+                word_2 = st.multiselect("Enter a word", placeholder="μήτηρ", max_selections=1, options=all_models_words)
+                if len(word_2) > 0:
+                    word_2 = word_2[0]
+                    eligible_models_2 = check_word_in_models(word_2)
+                
+            with col4:
+                time_slice_2 = st.selectbox("Time slice word 2", eligible_models_2)
     
-    # Create button for calculating cosine similarity
-    cosine_similarity_button = st.button("Calculate cosine similarity")
+        # Create button for calculating cosine similarity
+        cosine_similarity_button = st.form_submit_button("Calculate cosine similarity")
     
     # If the button is clicked, execute calculation
     if cosine_similarity_button: