Update app.py

app.py

@@ -76,12 +76,16 @@ def load_file(kamus_path, kamus_sendiri_path):
     stop_words = set(stopwords.words("indonesian"))
 
     tfidf_vectorizer = joblib.load(tfidf_model_path)
-    return lookp_dict, stop_words, tfidf_vectorizer
+    model_ensemble = joblib.load('ensemble_clf_soft_smote.joblib')
+    #model_rf
+    model_nb = joblib.load('naive_bayes_model_smote.joblib')
+    model_lr = joblib.load('logreg_model_smote.joblib')
+    return lookp_dict, stop_words, tfidf_vectorizer, model_ensemble, model_nb, model_lr
     
 kamus_path = '_json_colloquial-indonesian-lexicon (1).txt'
 kamus_sendiri_path = 'kamus_gaul_custom.txt'
 tfidf_model_path = 'X_tfidf_model.joblib'
-lookp_dict, stop_words, tfidf_vectorizer = load_file(kamus_path, kamus_sendiri_path)
+lookp_dict, stop_words, tfidf_vectorizer, model_ensemble, model_nb, model_lr = load_file(kamus_path, kamus_sendiri_path)
 
 # Fungsi untuk normalisasi kata gaul
 @st.cache_data
@@ -112,12 +116,9 @@ def remove_stopwords(text, stop_words):
 #---------------------------------------------------Milih Model----------------------------------------------------------------------
 
 # Fungsi untuk memilih model berdasarkan pilihan pengguna
-@st.cache_data
-def select_sentiment_model(selected_model):
-    model_ensemble = joblib.load('ensemble_clf_soft_smote.joblib')
-    #model_rf
-    model_nb = joblib.load('naive_bayes_model_smote.joblib')
-    model_lr = joblib.load('logreg_model_smote.joblib')
+
+def select_sentiment_model(selected_model, model_enesmble, model_nb, model_lr):
+
     if selected_model == "Ensemble":
         model = model_ensemble
     elif selected_model == "Random Forest":
@@ -225,7 +226,7 @@ def buat_chart(df, target_year):
         color=[warna_label[label] for label in unique_label]
     )
     
-
+@st.cache_data
 def all_data_process(texts, df, _sentiment_model, _tfidf_vectorizer, lookp_dict, stop_words, _predict_sentiment, _get_emoticon, _clean_text, _normalize_slang, _remove_stopwords):
     results = []
     analisis = False