added significant performance improvements

interpretable_text_clustering.py

@@ -48,10 +48,14 @@ if task == "Classification":
 
 form.form_submit_button("Submit")
 
+@st.cache
+def load_and_process_data(path, name, streaming, split_name, number_of_records):
+    dataset = load_dataset(path = path, name = name, streaming=streaming)
+    dataset_head = dataset[split_name].take(number_of_records)
+    df = pd.DataFrame.from_dict(dataset_head)
+    return df
 
-dataset = load_dataset(path = dataset_name, name = dataset_name_2, streaming=True)
-dataset_head = dataset[split_name].take(number_of_records)
-df = pd.DataFrame.from_dict(dataset_head)
+df = load_and_process_data(dataset_name, dataset_name_2, True, split_name, number_of_records)
 
 display_full_df = form.checkbox("Display the full dataset dataframe?")
 display_X_df = form.checkbox("Display the training data?", value = True)
@@ -73,13 +77,17 @@ model_name = form.text_area("Enter the name of the pre-trained model from senten
 form.caption("This will download a new model, so it may take awhile or even break if the model is too large")
 form.caption("See the list of pre-trained models that are available here! https://www.sbert.net/docs/pretrained_models.html")
 
-model = SentenceTransformer(model_name)
+#embeddings = model.encode(sentences, convert_to_numpy = True)
 
 
 
-#embeddings = model.encode(sentences, convert_to_numpy = True)
+@st.cache
+def load_model_and_return_embedder(model_name):
+    model = SentenceTransformer(model_name)
+    embedder = FunctionTransformer(lambda item:model.encode(item, convert_to_numpy=True, show_progress_bar=False))
+    return embedder
 
-embedder = FunctionTransformer(lambda item:model.encode(item, convert_to_numpy=True, show_progress_bar=False))
+embedder = load_model_and_return_embedder(model_name=model_name)
 
 
 
@@ -114,6 +122,7 @@ if task == "Clustering":
         ('vect', embedder),
         ('cluster', KMeans(n_clusters = n_clusters, n_init = n_init, max_iter = max_iter)),
     ])
+    
 
 if task == "Classification":
     text_clf.fit(df[column_name], df[labels_column_name])