Update src/streamlit_app.py

src/streamlit_app.py

@@ -14,7 +14,6 @@ import nltk
 from nltk.corpus import stopwords
 from nltk.sentiment.vader import SentimentIntensityAnalyzer
 from transformers import pipeline
-from tqdm import tqdm
 
 # ==============================
 # KONFIGURASI HALAMAN
@@ -35,16 +34,17 @@ download_nltk_resources()
 stop_words = set(stopwords.words('english'))
 
 # ==============================
-# LOAD MODELS
+# LOAD MODELS (DIPERBAIKI)
 # ==============================
 @st.cache_resource
 def load_all_models():
-    with st.spinner('Memuat Model. Mohon tunggu...'):
+    with st.spinner('...'):
         vader = SentimentIntensityAnalyzer()
-        bertweet = pipeline("sentiment-analysis", model="finiteautomata/bertweet-base-sentiment-analysis", device=-1)
-        roberta = pipeline("sentiment-analysis", model="cardiffnlp/twitter-roberta-base-sentiment", device=-1)
-        roberta_large = pipeline("sentiment-analysis", model="siebert/sentiment-roberta-large-english", device=-1)
+        bertweet = pipeline("sentiment-analysis", model="finiteautomata/bertweet-base-sentiment-analysis", device=-1, truncation=True, max_length=128)
+        roberta = pipeline("sentiment-analysis", model="cardiffnlp/twitter-roberta-base-sentiment", device=-1, truncation=True, max_length=512)
+        roberta_large = pipeline("sentiment-analysis", model="siebert/sentiment-roberta-large-english", device=-1, truncation=True, max_length=512)
         return vader,  bertweet, roberta, roberta_large
+
 vader, bertweet, roberta, roberta_large = load_all_models()
 
 # ==============================
@@ -102,13 +102,14 @@ with tab1:
         try: t_label = classify_tb(TextBlob(text).sentiment.polarity)
         except: t_label = "neutral"
 
-        try: b_label = map_bertweet(bertweet(text[:128])[0]['label'])
+        # Slicing [:128] dan [:512] dihapus karena sudah di-handle oleh pipeline truncation
+        try: b_label = map_bertweet(bertweet(text)[0]['label'])
         except: b_label = "neutral"
             
-        try: r_label = map_roberta(roberta(text[:512])[0]['label'])
+        try: r_label = map_roberta(roberta(text)[0]['label'])
         except: r_label = "neutral"
             
-        try: rl_label = roberta_large(text[:512])[0]['label'].lower()
+        try: rl_label = roberta_large(text)[0]['label'].lower()
         except: rl_label = "neutral"
 
         data_test = {
@@ -135,7 +136,8 @@ with tab2:
         
         total_tweets_uploaded = 0
         for idx, file in enumerate(tweet_files):
-            content = file.getvalue().decode("utf-8").strip()
+            # Perbaikan: replace("\r\n", "\n") memastikan format enter dibaca utuh
+            content = file.getvalue().decode("utf-8").replace("\r\n", "\n").strip()
             tweets = content.split("\n\n")
             
             for tweet in tweets:
@@ -157,13 +159,14 @@ with tab2:
                 try: tb_label = classify_tb(TextBlob(text).sentiment.polarity)
                 except: tb_label = "neutral"
 
-                try: bertweet_label = map_bertweet(bertweet(text[:128])[0]['label'])
+                # Slicing [:128] dan [:512] dihapus
+                try: bertweet_label = map_bertweet(bertweet(text)[0]['label'])
                 except: bertweet_label = "neutral"
 
-                try: roberta_label = map_roberta(roberta(text[:512])[0]['label'])
+                try: roberta_label = map_roberta(roberta(text)[0]['label'])
                 except: roberta_label = "neutral"
 
-                try: roberta_large_label = roberta_large(text[:512])[0]['label'].lower()
+                try: roberta_large_label = roberta_large(text)[0]['label'].lower()
                 except: roberta_large_label = "neutral"
 
                 data.append({
@@ -188,19 +191,16 @@ with tab2:
             st.success(f"Berhasil mengekstrak {total_tweets_uploaded} tweets!")
             
             target_dates = sorted(df['date'].unique())
-            oldest_date = pd.to_datetime(target_dates[0])
-            today_date = datetime.now()
-            
-            delta_days = (today_date - oldest_date).days + 2
-            fetch_days = max(7, delta_days) 
+            start_unix = int(datetime.strptime(target_dates[0], "%Y-%m-%d").timestamp()) - 86400
+            end_unix = int(datetime.strptime(target_dates[-1], "%Y-%m-%d").timestamp()) + 86400
             
-            st.write(f"Mencari data harga Bitcoin dari CoinGecko API untuk {fetch_days} hari ke belakang...")
+            st.write(f"Mencari data harga Bitcoin dari CoinGecko API menggunakan rentang Unix Timestamp...")
             
-            url = "https://api.coingecko.com/api/v3/coins/bitcoin/market_chart"
+            url = "https://api.coingecko.com/api/v3/coins/bitcoin/market_chart/range"
             params = {
                 "vs_currency": "usd",
-                "days": str(fetch_days),
-                "interval": "daily"
+                "from": start_unix,
+                "to": end_unix
             }
             headers = {"accept": "application/json", "User-Agent": "Mozilla/5.0"}
             
@@ -383,10 +383,10 @@ with tab2:
                             arah_text = "berbanding lurus (positif)" if strongest_model["r"] > 0 else "berbanding terbalik (negatif)"
 
                             # ==============================
-                            # KESIMPULAN & PEMBAHASAN AKHIR (BAB IV & V)
+                            # KESIMPULAN & PEMBAHASAN AKHIR
                             # ==============================
                             st.write("---")
-                            st.header("📝 BAB IV & V: Hasil, Pembahasan, dan Kesimpulan Akhir")
+                            st.header("📝 Hasil, Pembahasan, dan Kesimpulan")
                             
                             # 1. Pembahasan
                             st.subheader("1. Pembahasan Analisis")
@@ -414,7 +414,7 @@ with tab2:
                                 st.write(f"- **Metode {res['metode']}:** Menghasilkan nilai korelasi *r* sebesar **{res['r']:.4f}** dengan *p-value* **{res['p']:.4f}**. Arah garis tren {arah_garis}, menandakan bahwa kekuatan hubungan antara sentimen opini publik dan volatilitas harga masuk ke dalam kategori **{kategori}**.")
 
                             # 2. Kesimpulan
-                            st.subheader("2. Kesimpulan Penelitian")
+                            st.subheader("2. Kesimpulan")
                             
                             if len(sig_models) > 0:
                                 st.success(f"""