Update app.py

app.py

@@ -110,6 +110,7 @@ tfidf_vectorizer = joblib.load(tfidf_model_path)
 #---------------------------------------------------Milih Model----------------------------------------------------------------------
 
 # Fungsi untuk memilih model berdasarkan pilihan pengguna
+@st.cache_data
 def select_sentiment_model(selected_model):
     if selected_model == "Ensemble":
         model_path = 'ensemble_clf_soft_smote.joblib'
@@ -135,10 +136,10 @@ def predict_sentiment(text, _model, _tfidf_vectorizer, slang_dict):
     norm_slang_text = normalize_slang(cleaned_text, slang_dict)
 
     # Tahap-2: Ekstraksi fitur TF-IDF
-    tfidf_matrix = tfidf_vectorizer.transform([norm_slang_text])
+    tfidf_matrix = _tfidf_vectorizer.transform([norm_slang_text])
 
     # Tahap-3: Lakukan prediksi sentimen
-    sentiment = model.predict(tfidf_matrix)
+    sentiment = _model.predict(tfidf_matrix)
 
     # Tahap-4: Menggantikan indeks dengan label sentimen
     labels = {0: "Negatif", 1: "Netral", 2: "Positif"}
@@ -275,71 +276,73 @@ with st.expander ("Preference Settings :"):
 # Analisis sentimen
 results = []
 analisis = False
-if st.button("Analysis") and input_option == "Teks Manual" and user_input:
-    # Pisahkan teks yang dimasukkan pengguna menjadi baris-baris terpisah
-    user_texts = user_input.split('\n')
-    for text in user_texts:
-        sentiment_label = predict_sentiment(text, sentiment_model, tfidf_vectorizer, lookp_dict)
-        emoticon = get_emoticon(sentiment_label)
-        cleaned_text = clean_text(text)
-        norm_slang_text = normalize_slang(cleaned_text, lookp_dict)
-        tanpa_stopwords = remove_stopwords(norm_slang_text, stop_words)
-        
-        results.append({
-            'Text': text, 
-            'cleaned-text' : cleaned_text, 
-            'normalisasi-text' : norm_slang_text, 
-            'stopwords-remove' : tanpa_stopwords,
-            'label' : sentiment_label,
-            'emotikon' : emoticon,
-        })
-        analisis = True
+if input_option == "Teks Manual" and user_input:
+    if st.button("Analysis"):
+        # Pisahkan teks yang dimasukkan pengguna menjadi baris-baris terpisah
+        user_texts = user_input.split('\n')
+        for text in user_texts:
+            sentiment_label = predict_sentiment(text, sentiment_model, tfidf_vectorizer, lookp_dict)
+            emoticon = get_emoticon(sentiment_label)
+            cleaned_text = clean_text(text)
+            norm_slang_text = normalize_slang(cleaned_text, lookp_dict)
+            tanpa_stopwords = remove_stopwords(norm_slang_text, stop_words)
+            
+            results.append({
+                'Text': text, 
+                'cleaned-text' : cleaned_text, 
+                'normalisasi-text' : norm_slang_text, 
+                'stopwords-remove' : tanpa_stopwords,
+                'label' : sentiment_label,
+                'emotikon' : emoticon,
+            })
+            analisis = True
 
 elif input_option == "Unggah Berkas XLSX" and uploaded_file is not None:
-    if 'Text' in df.columns:
-        if 'Date' in df.columns:
-            for text, date in zip(texts, df['Date']):
-                sentiment_label = predict_sentiment(text, sentiment_model, tfidf_vectorizer, lookp_dict)
-                emoticon = get_emoticon(sentiment_label)
-                cleaned_text = clean_text(text)
-                norm_slang_text = normalize_slang(cleaned_text, lookp_dict)
-                tanpa_stopwords = remove_stopwords(norm_slang_text, stop_words)
-    
-                result_entry = {
-                    'Text': text,
-                    'cleaned-text': cleaned_text,
-                    'normalisasi-text': norm_slang_text,
-                    'stopwords-remove': tanpa_stopwords,
-                    'label': sentiment_label,
-                    'emotikon': emoticon,
-                    'Date': date,
-                }
-    
-                results.append(result_entry)
-    
-            analisis = True
+    if st.button("Analysis"):
+        if 'Text' in df.columns:
+            if 'Date' in df.columns:
+                for text, date in zip(texts, df['Date']):
+                    sentiment_label = predict_sentiment(text, sentiment_model, tfidf_vectorizer, lookp_dict)
+                    emoticon = get_emoticon(sentiment_label)
+                    cleaned_text = clean_text(text)
+                    norm_slang_text = normalize_slang(cleaned_text, lookp_dict)
+                    tanpa_stopwords = remove_stopwords(norm_slang_text, stop_words)
+        
+                    result_entry = {
+                        'Text': text,
+                        'cleaned-text': cleaned_text,
+                        'normalisasi-text': norm_slang_text,
+                        'stopwords-remove': tanpa_stopwords,
+                        'label': sentiment_label,
+                        'emotikon': emoticon,
+                        'Date': date,
+                    }
+        
+                    results.append(result_entry)
+        
+                analisis = True
+            else:
+                for text in texts:
+                    sentiment_label = predict_sentiment(text, sentiment_model, tfidf_vectorizer, lookp_dict)
+                    emoticon = get_emoticon(sentiment_label)
+                    cleaned_text = clean_text(text)
+                    norm_slang_text = normalize_slang(cleaned_text, lookp_dict)
+                    tanpa_stopwords = remove_stopwords(norm_slang_text, stop_words)
+        
+                    result_entry = {
+                        'Text': text,
+                        'cleaned-text': cleaned_text,
+                        'normalisasi-text': norm_slang_text,
+                        'stopwords-remove': tanpa_stopwords,
+                        'label': sentiment_label,
+                        'emotikon': emoticon,
+                    }
+        
+                    results.append(result_entry)
+        
+                analisis = True   
         else:
-            for text in texts:
-                sentiment_label = predict_sentiment(text, sentiment_model, tfidf_vectorizer, lookp_dict)
-                emoticon = get_emoticon(sentiment_label)
-                cleaned_text = clean_text(text)
-                norm_slang_text = normalize_slang(cleaned_text, lookp_dict)
-                tanpa_stopwords = remove_stopwords(norm_slang_text, stop_words)
-    
-                result_entry = {
-                    'Text': text,
-                    'cleaned-text': cleaned_text,
-                    'normalisasi-text': norm_slang_text,
-                    'stopwords-remove': tanpa_stopwords,
-                    'label': sentiment_label,
-                    'emotikon': emoticon,
-                }
-    
-                results.append(result_entry)
-    
-            analisis = True   
-    else:
-        st.warning("Berkas XLSX harus memiliki kolom bernama 'Text' untuk analisis sentimen.")
+            st.warning("Berkas XLSX harus memiliki kolom bernama 'Text' untuk analisis sentimen.")
 
         
 st.info('Tekan "Analysis" kembali jika tampilan menghilang', icon = 'ℹ️')