Update src/streamlit_app.py

src/streamlit_app.py

@@ -432,6 +432,9 @@ with st.spinner('Mempersiapkan model AI...'):
 def clean_text(text):
     text = str(text)
 
+    # Hapus prefix metadata Twitter/X 
+    # Format: "DisplayName @handle · Xdtk/mnt/jam [Membalas @target]"
+    # Contoh: "Botanika Intern @botanika_intern · 7dtk Membalas @AshCrypto"
     text = re.sub(
         r'^.*?·\s*\d+\s*(?:dtk|mnt|jam|s|h|sec|min)\s*(?:Membalas\s+@\w+\s*)?',
         '',
@@ -439,25 +442,30 @@ def clean_text(text):
         flags=re.IGNORECASE
     )
 
+    # Hapus "Tampilkan lebih banyak" (artefak UI Twitter)
     text = re.sub(r'Tampilkan lebih banyak.*$', '', text, flags=re.IGNORECASE)
 
+    # Hapus angka trailing engagement (like/retweet count)
+    # Contoh akhir tweet: "...Bitcoin drops. 1 6" → angka dihapus
     text = re.sub(r'(\s+\d+)+\s*$', '', text).strip()
 
+    # Cleaning standar
     text = text.lower()
-    text = re.sub(r"http\S+", "", text)           
-    text = re.sub(r"@\w+", "", text)              
-    text = re.sub(r"#\w+", "", text)             
-    text = re.sub(r"[^\w\s]", "", text)           
-    text = re.sub(r"\b\d+\b", "", text)           
+    text = re.sub(r"http\S+", "", text)           # hapus URL
+    text = re.sub(r"@\w+", "", text)              # hapus @mention
+    text = re.sub(r"#\w+", "", text)              # hapus #hashtag
+    text = re.sub(r"[^\w\s]", "", text)           # hapus tanda baca
+    text = re.sub(r"\b\d+\b", "", text)           # hapus angka sisa
     text = re.sub(r"\s+", " ", text).strip()
 
+    # --- LANGKAH 5: Hapus stopwords ---
     tokens = text.split()
     tokens = [word for word in tokens if word not in stop_words]
     return " ".join(tokens)
 
 
 # ==============================================================================
-# THRESHOLD TEXTBLOB
+# THRESHOLD TEXTBLOB — dinaikkan dari ±0.05 ke ±0.10
 # ==============================================================================
 TEXTBLOB_THRESHOLD = 0.10
 
@@ -473,6 +481,10 @@ def map_roberta(label):
 def map_bertweet(label):
     return {"pos": "positive", "neu": "neutral", "neg": "negative"}.get(label.lower(), "neutral")
 
+
+# ==============================================================================
+# get_daily_label — threshold diselaraskan dengan TEXTBLOB_THRESHOLD
+# ==============================================================================
 def get_daily_label(score):
     if score >  TEXTBLOB_THRESHOLD: return 'Positive'
     elif score < -TEXTBLOB_THRESHOLD: return 'Negative'
@@ -607,7 +619,6 @@ if st.session_state.page == "uji_kalimat":
 
                 for i, (method, label, detail) in enumerate(results):
                     col = col_a if i % 2 == 0 else col_b
-
                     bg  = badge_color(label)
                     tc  = badge_text_color(label)
                     icon = "↗" if label == "positive" else ("↘" if label == "negative" else "→")
@@ -834,295 +845,386 @@ elif st.session_state.page == "analisis_batch":
                 start_unix = int(datetime.strptime(target_dates[0],  "%Y-%m-%d").replace(tzinfo=timezone.utc).timestamp()) - 86400
                 end_unix   = int(datetime.strptime(target_dates[-1], "%Y-%m-%d").replace(tzinfo=timezone.utc).timestamp()) + 86400
 
-                with st.spinner("📡 Mengambil data harga Bitcoin dari CoinGecko API..."):
+                # ==============================================================
+                # FUNGSI FETCH HARGA BTC — Retry + Fallback ke Binance
+                # ==============================================================
+                def fetch_via_coingecko(start_ts, end_ts):
+                    """Coba CoinGecko dengan retry eksponensial. Return list [[ts_ms, price]] atau raise."""
                     url     = "https://api.coingecko.com/api/v3/coins/bitcoin/market_chart/range"
-                    params  = {"vs_currency": "usd", "from": start_unix, "to": end_unix}
+                    params  = {"vs_currency": "usd", "from": start_ts, "to": end_ts}
                     headers = {"accept": "application/json", "User-Agent": "Mozilla/5.0"}
-
+                    wait_times = [5, 15, 30]
+                    for attempt, wait in enumerate(wait_times, 1):
+                        time.sleep(wait)
+                        res = requests.get(url, params=params, headers=headers, timeout=20)
+                        if res.status_code == 200:
+                            data_j = res.json()
+                            if "prices" in data_j:
+                                return data_j["prices"]
+                            raise ValueError("Key 'prices' tidak ada di respons CoinGecko.")
+                        if res.status_code == 429:
+                            if attempt < len(wait_times):
+                                continue   
+                            raise ConnectionError(f"CoinGecko 429 setelah {attempt} percobaan.")
+                        raise ConnectionError(f"CoinGecko error {res.status_code}: {res.text[:200]}")
+                    raise ConnectionError("CoinGecko gagal setelah semua percobaan.")
+
+                def fetch_via_binance(start_ts, end_ts):
+                    """
+                    Fallback: Binance Public API — BTCUSDT daily klines.
+                    Endpoint bebas API key, limit 1000 candles per request.
+                    """
+                    url    = "https://api.binance.com/api/v3/klines"
+                    prices = []
+                    cur_start = start_ts * 1000   
+                    end_ms    = end_ts   * 1000
+                    while cur_start < end_ms:
+                        params = {
+                            "symbol":    "BTCUSDT",
+                            "interval":  "1d",
+                            "startTime": cur_start,
+                            "endTime":   end_ms,
+                            "limit":     1000,
+                        }
+                        res = requests.get(url, params=params, timeout=20)
+                        if res.status_code != 200:
+                            raise ConnectionError(f"Binance error {res.status_code}: {res.text[:200]}")
+                        batch = res.json()
+                        if not batch:
+                            break
+                        for candle in batch:
+                            open_time  = int(candle[0])
+                            close_price = float(candle[4])       
+                            prices.append([open_time, close_price])
+                        cur_start = int(batch[-1][0]) + 1
+                        if len(batch) < 1000:
+                            break
+                    if not prices:
+                        raise ValueError("Binance tidak mengembalikan data.")
+                    return prices   
+
+                def build_df_price(raw_prices, target_date_list):
+                    """Bersihkan raw [[ts_ms, price]] → df_price dengan log_return."""
+                    df_p = pd.DataFrame(raw_prices, columns=["timestamp", "price"])
+                    df_p["date"] = pd.to_datetime(df_p["timestamp"], unit="ms").dt.date
+                    df_p = df_p.groupby("date")["price"].mean().reset_index()
+                    df_p["pct_change"] = df_p["price"].pct_change() * 100
+                    df_p["log_return"] = np.log(df_p["price"] / df_p["price"].shift(1))
+                    df_p.dropna(inplace=True)
+                    df_p = df_p[df_p["date"].isin(pd.to_datetime(target_date_list).date)]
+                    return df_p
+
+                # ── Eksekusi fetch dengan fallback ─────────────────────────────
+                raw_prices  = None
+                api_source  = None
+
+                with st.spinner("📡 Mengambil data harga Bitcoin..."):
                     try:
-                        time.sleep(2)
-                        res = requests.get(url, params=params, headers=headers)
+                        raw_prices = fetch_via_coingecko(start_unix, end_unix)
+                        api_source = "CoinGecko"
+                    except Exception as cg_err:
+                        st.warning(
+                            f"⚠️ CoinGecko tidak tersedia ({cg_err}). "
+                            "Beralih ke **Binance Public API** sebagai fallback..."
+                        )
+                        try:
+                            raw_prices = fetch_via_binance(start_unix, end_unix)
+                            api_source = "Binance"
+                        except Exception as bn_err:
+                            st.error(
+                                f"❌ Kedua sumber data gagal.\n"
+                                f"- CoinGecko: {cg_err}\n"
+                                f"- Binance: {bn_err}\n\n"
+                                "Coba lagi beberapa menit kemudian atau periksa koneksi internet."
+                            )
+
+                if raw_prices is not None:
+                    try:
+                        df_price = build_df_price(raw_prices, target_dates)
+                        st.info(f"✅ Data harga BTC berhasil diambil dari **{api_source}**.")
 
-                        if res.status_code != 200:
-                            st.error(f"API Error {res.status_code}: {res.text}")
+                        if df_price.empty:
+                            st.warning("⚠️ Data Harga API kosong. Pastikan rentang tanggal di .txt sesuai (yyyy-mm-dd).")
                         else:
-                            data_json = res.json()
-
-                            if "prices" not in data_json:
-                                st.error("Data harga tidak ditemukan di respons API.")
-                            else:
-                                prices = data_json["prices"]
-
-                                df_price = pd.DataFrame(prices, columns=["timestamp", "price"])
-                                df_price["date"] = pd.to_datetime(df_price["timestamp"], unit="ms").dt.date
-                                df_price = df_price.groupby("date")["price"].mean().reset_index()
-                                df_price["pct_change"] = df_price["price"].pct_change() * 100
-                                df_price["log_return"] = np.log(df_price["price"] / df_price["price"].shift(1))
-                                df_price.dropna(inplace=True)
-                                df_price = df_price[df_price["date"].isin(pd.to_datetime(target_dates).date)]
-
-                                if df_price.empty:
-                                    st.warning("⚠️ Data Harga API kosong. Pastikan rentang tanggal di .txt sesuai (yyyy-mm-dd).")
-                                else:
-                                    st.markdown("<hr class='vbc-divider'>", unsafe_allow_html=True)
-
-                                    # ── Tabel Data Sentimen ──────────────────────────────
-                                    st.markdown("🗣️ Data Sentimen")
-                                    raw_display_cols = ["date","raw_tweet","vader","textblob","bertweet","roberta","roberta_large","vader_score","tb_score"]
-                                    st.dataframe(df[raw_display_cols], use_container_width=True, hide_index=True)
-
-                                    # ==================================================
-                                    # AGREGASI HARIAN DUAL-MODE
-                                    # ==================================================
-                                    sentiment_map = {"positive": 1, "neutral": 0, "negative": -1}
-                                    df_score = df.copy()
-                                    models_cat = ["vader","textblob","bertweet","roberta","roberta_large"]
-                                    for col in models_cat:
-                                        df_score[col] = df_score[col].map(sentiment_map)
-
-                                    # Agregasi kategorik (−1/0/1 mean)
-                                    df_sentiment_daily = df_score.groupby("date")[models_cat].mean().reset_index()
-                                    df_sentiment_daily["date"] = pd.to_datetime(df_sentiment_daily["date"]).dt.date
-
-                                    # Agregasi numerik VADER compound & TextBlob polarity
-                                    df_numeric_daily = df.groupby("date")[["vader_score","tb_score"]].mean().reset_index()
-                                    df_numeric_daily["date"] = pd.to_datetime(df_numeric_daily["date"]).dt.date
-
-                                    for col in models_cat:
-                                        df_sentiment_daily[f"{col}_label"] = df_sentiment_daily[col].apply(get_daily_label)
-
-                                    daily_display_cols = ["date"]
-                                    for col in models_cat:
-                                        daily_display_cols.extend([col, f"{col}_label"])
-
-                                    # ── Tabel Harga Bitcoin ───────────────────────────
-                                    st.markdown("₿ Data Harga & Volatilitas Bitcoin")
-                                    st.dataframe(df_price[["date","price","pct_change","log_return"]], use_container_width=True, hide_index=True)
-
-                                    # Merge data
-                                    df_merged = pd.merge(df_price, df_sentiment_daily, on="date", how="inner")
-                                    df_merged = pd.merge(df_merged, df_numeric_daily,  on="date", how="inner")
-
-                                    # ── Tabel Data Final ──────────────────────────────
-                                    st.markdown("🗂️ Data Final")
-                                    final_display_cols = (
-                                        ["date","price","pct_change","log_return"]
-                                        + [c for c in daily_display_cols if c != "date"]
-                                        + ["vader_score","tb_score"]
-                                    )
-                                    st.dataframe(df_merged[final_display_cols], use_container_width=True, hide_index=True)
-
-                                    # Download buttons
-                                    col_dl1, col_dl2, _ = st.columns([1, 1, 3])
-                                    csv_data = df_merged.to_csv(index=False).encode('utf-8')
-                                    col_dl1.download_button("📥 Unduh CSV",   data=csv_data, file_name="bitcoin_volatility_sentiment.csv",  mime="text/csv",                          use_container_width=True)
-                                    buffer = io.BytesIO()
-                                    with pd.ExcelWriter(buffer, engine='xlsxwriter') as writer:
-                                        df_merged.to_excel(writer, index=False)
-                                    col_dl2.download_button("📥 Unduh Excel", data=buffer.getvalue(), file_name="bitcoin_volatility_sentiment.xlsx", mime="application/vnd.ms-excel", use_container_width=True)
-
-                                    st.markdown("<hr class='vbc-divider'>", unsafe_allow_html=True)
-
-                                    # ==================================================
-                                    # UJI KORELASI PEARSON DENGAN LAG
-                                    # ==================================================
-                                    st.subheader("🔬 Uji Korelasi Pearson")
-                                    st.caption(
-                                        "Menganalisis hubungan statistik antara skor sentimen harian dan "
-                                        "volatilitas log-return BTC pada lag 0 (hari sama), +1 hari, dan +2 hari. "
-                                        "VADER & TextBlob menggunakan skor numerik kontinu; model BERT menggunakan "
-                                        "rata-rata kategorikal (−1/0/1)."
-                                    )
-
-                                    corr_columns = {
-                                        "VADER (numerik)":          "vader_score",
-                                        "TextBlob (numerik)":       "tb_score",
-                                        "BERTweet (kategorik)":     "bertweet",
-                                        "RoBERTa Base (kategorik)": "roberta",
-                                        "RoBERTa Large (kategorik)":"roberta_large",
-                                    }
-
-                                    corr_rows   = []
-                                    raw_results = []   
-
-                                    n_obs = len(df_merged)
-
-                                    for label_name, col_key in corr_columns.items():
-                                        for lag in [0, 1, 2]:
-                                            log_ret_shifted = df_merged["log_return"].shift(-lag)
-                                            valid_mask      = log_ret_shifted.notna()
-
-                                            x_vals = df_merged.loc[valid_mask, col_key]
-                                            y_vals = log_ret_shifted[valid_mask]
-
-                                            if len(x_vals) < 4:
-                                                corr, pval = np.nan, np.nan
-                                            else:
-                                                try:
-                                                    corr, pval = pearsonr(x_vals, y_vals)
-                                                except Exception:
-                                                    corr, pval = np.nan, np.nan
-
-                                            arah = "Positif" if (corr is not np.nan and corr > 0) else "Negatif"
-                                            sig  = "✅ Signifikan" if (pval is not np.nan and pval < 0.05) else "Tidak Signifikan"
-
-                                            corr_rows.append({
-                                                "Metode":     label_name,
-                                                "Lag":        f"t+{lag}",
-                                                "r":          f"{corr:.4f}" if not np.isnan(corr) else "N/A",
-                                                "Arah":       arah,
-                                                "p-value":    f"{pval:.4f}" if not np.isnan(pval) else "N/A",
-                                                "Signifikansi": sig,
-                                            })
-                                            raw_results.append({
-                                                "metode": label_name,
-                                                "col":    col_key,
-                                                "lag":    lag,
-                                                "r":      corr if not np.isnan(corr) else 0.0,
-                                                "p":      pval if not np.isnan(pval) else 1.0,
-                                            })
-
-                                    df_corr_table = pd.DataFrame(corr_rows)
-
-                                    def highlight_best(row):
+                            st.markdown("<hr class='vbc-divider'>", unsafe_allow_html=True)
+
+                            # ── Tabel Data Sentimen ──────────────────────────────
+                            st.markdown("🗣️ Data Sentimen")
+                            raw_display_cols = ["date","raw_tweet","vader","textblob","bertweet","roberta","roberta_large","vader_score","tb_score"]
+                            st.dataframe(df[raw_display_cols], use_container_width=True, hide_index=True)
+
+                            # ==================================================
+                            # AGREGASI HARIAN DUAL-MODE
+                            # Mode A (Kategorik): konversi {pos:1, neu:0, neg:-1}
+                            #   → tetap ada untuk tabel display & model BERT/RoBERTa
+                            # Mode B (Numerik): rata-rata vader_score & tb_score
+                            #   → dipakai sebagai variabel korelasi utama karena
+                            #     mempertahankan intensitas sentimen
+                            # ==================================================
+                            sentiment_map = {"positive": 1, "neutral": 0, "negative": -1}
+                            df_score = df.copy()
+                            models_cat = ["vader","textblob","bertweet","roberta","roberta_large"]
+                            for col in models_cat:
+                                df_score[col] = df_score[col].map(sentiment_map)
+
+                            # Agregasi kategorik (−1/0/1 mean)
+                            df_sentiment_daily = df_score.groupby("date")[models_cat].mean().reset_index()
+                            df_sentiment_daily["date"] = pd.to_datetime(df_sentiment_daily["date"]).dt.date
+
+                            # Agregasi numerik VADER compound & TextBlob polarity
+                            df_numeric_daily = df.groupby("date")[["vader_score","tb_score"]].mean().reset_index()
+                            df_numeric_daily["date"] = pd.to_datetime(df_numeric_daily["date"]).dt.date
+
+                            for col in models_cat:
+                                df_sentiment_daily[f"{col}_label"] = df_sentiment_daily[col].apply(get_daily_label)
+
+                            daily_display_cols = ["date"]
+                            for col in models_cat:
+                                daily_display_cols.extend([col, f"{col}_label"])
+
+                            # ── Tabel Harga Bitcoin ───────────────────────────
+                            st.markdown("₿ Data Harga & Volatilitas Bitcoin")
+                            st.dataframe(df_price[["date","price","pct_change","log_return"]], use_container_width=True, hide_index=True)
+
+                            # Merge data
+                            df_merged = pd.merge(df_price, df_sentiment_daily, on="date", how="inner")
+                            df_merged = pd.merge(df_merged, df_numeric_daily,  on="date", how="inner")
+
+                            # ── Tabel Data Final ──────────────────────────────
+                            st.markdown("🗂️ Data Final")
+                            final_display_cols = (
+                                ["date","price","pct_change","log_return"]
+                                + [c for c in daily_display_cols if c != "date"]
+                                + ["vader_score","tb_score"]
+                            )
+                            st.dataframe(df_merged[final_display_cols], use_container_width=True, hide_index=True)
+
+                            # Download buttons
+                            col_dl1, col_dl2, _ = st.columns([1, 1, 3])
+                            csv_data = df_merged.to_csv(index=False).encode('utf-8')
+                            col_dl1.download_button("📥 Unduh CSV",   data=csv_data, file_name="bitcoin_volatility_sentiment.csv",  mime="text/csv",                          use_container_width=True)
+                            buffer = io.BytesIO()
+                            with pd.ExcelWriter(buffer, engine='xlsxwriter') as writer:
+                                df_merged.to_excel(writer, index=False)
+                            col_dl2.download_button("📥 Unduh Excel", data=buffer.getvalue(), file_name="bitcoin_volatility_sentiment.xlsx", mime="application/vnd.ms-excel", use_container_width=True)
+
+                            st.markdown("<hr class='vbc-divider'>", unsafe_allow_html=True)
+
+                            # ==================================================
+                            # UJI KORELASI PEARSON DENGAN LAG
+                            # Lag 0 : sentimen hari t vs harga hari t (same-day)
+                            # Lag +1: sentimen hari t vs harga hari t+1
+                            # Lag +2: sentimen hari t vs harga hari t+2
+                            #
+                            # Kolom korelasi yang diuji:
+                            #   - vader_score  (numerik compound, −1 s.d. 1)
+                            #   - tb_score     (numerik polarity, −1 s.d. 1)
+                            #   - bertweet     (kategorik −1/0/1 mean)
+                            #   - roberta      (kategorik −1/0/1 mean)
+                            #   - roberta_large(kategorik −1/0/1 mean)
+                            # ==================================================
+                            st.subheader("🔬 Uji Korelasi Pearson")
+                            st.caption(
+                                "Menganalisis hubungan statistik antara skor sentimen harian dan "
+                                "volatilitas log-return BTC pada lag 0 (hari sama), +1 hari, dan +2 hari. "
+                                "VADER & TextBlob menggunakan skor numerik kontinu; model BERT menggunakan "
+                                "rata-rata kategorikal (−1/0/1)."
+                            )
+
+                            corr_columns = {
+                                "VADER (numerik)":          "vader_score",
+                                "TextBlob (numerik)":       "tb_score",
+                                "BERTweet (kategorik)":     "bertweet",
+                                "RoBERTa Base (kategorik)": "roberta",
+                                "RoBERTa Large (kategorik)":"roberta_large",
+                            }
+
+                            corr_rows   = []
+                            raw_results = []   
+
+                            n_obs = len(df_merged)
+
+                            for label_name, col_key in corr_columns.items():
+                                for lag in [0, 1, 2]:
+                                    # shift(-lag): harga mundur lag hari ke depan
+                                    # artinya: sentimen t berkorelasi dengan harga t+lag
+                                    log_ret_shifted = df_merged["log_return"].shift(-lag)
+                                    valid_mask      = log_ret_shifted.notna()
+
+                                    x_vals = df_merged.loc[valid_mask, col_key]
+                                    y_vals = log_ret_shifted[valid_mask]
+
+                                    if len(x_vals) < 4:
+                                        corr, pval = np.nan, np.nan
+                                    else:
                                         try:
-                                            r_abs = abs(float(row["r"]))
-                                        except:
-                                            r_abs = 0
-                                        sig_ok = "✅" in str(row["Signifikansi"])
-                                        if sig_ok:
-                                            return ["background-color:#e6fff1; font-weight:600"] * len(row)
-                                        return [""] * len(row)
-
-                                    styled = df_corr_table.style.apply(highlight_best, axis=1)
-                                    st.dataframe(styled, use_container_width=True, hide_index=True)
-
-                                    # ── Heatmap Korelasi (r) per Metode × Lag ─────────
-                                    st.subheader("🌡️ Heatmap Korelasi (r) — Metode × Lag")
-                                    pivot_r = pd.DataFrame(raw_results).pivot_table(
-                                        index="metode", columns="lag", values="r"
+                                            corr, pval = pearsonr(x_vals, y_vals)
+                                        except Exception:
+                                            corr, pval = np.nan, np.nan
+
+                                    arah = "Positif" if (corr is not np.nan and corr > 0) else "Negatif"
+                                    sig  = "✅ Signifikan" if (pval is not np.nan and pval < 0.05) else "Tidak Signifikan"
+
+                                    corr_rows.append({
+                                        "Metode":     label_name,
+                                        "Lag":        f"t+{lag}",
+                                        "r":          f"{corr:.4f}" if not np.isnan(corr) else "N/A",
+                                        "Arah":       arah,
+                                        "p-value":    f"{pval:.4f}" if not np.isnan(pval) else "N/A",
+                                        "Signifikansi": sig,
+                                    })
+                                    raw_results.append({
+                                        "metode": label_name,
+                                        "col":    col_key,
+                                        "lag":    lag,
+                                        "r":      corr if not np.isnan(corr) else 0.0,
+                                        "p":      pval if not np.isnan(pval) else 1.0,
+                                    })
+
+                            df_corr_table = pd.DataFrame(corr_rows)
+
+                            # Tandai baris terbaik per metode (|r| terbesar)
+                            def highlight_best(row):
+                                try:
+                                    r_abs = abs(float(row["r"]))
+                                except:
+                                    r_abs = 0
+                                sig_ok = "✅" in str(row["Signifikansi"])
+                                if sig_ok:
+                                    return ["background-color:#e6fff1; font-weight:600"] * len(row)
+                                return [""] * len(row)
+
+                            styled = df_corr_table.style.apply(highlight_best, axis=1)
+                            st.dataframe(styled, use_container_width=True, hide_index=True)
+
+                            # ── Heatmap Korelasi (r) per Metode × Lag ─────────
+                            st.subheader("🌡️ Heatmap Korelasi (r) — Metode × Lag")
+                            pivot_r = pd.DataFrame(raw_results).pivot_table(
+                                index="metode", columns="lag", values="r"
+                            )
+                            pivot_r.columns = [f"Lag t+{c}" for c in pivot_r.columns]
+                            pivot_r.index   = [i.replace(" (numerik)","").replace(" (kategorik)","") for i in pivot_r.index]
+
+                            fig_hm, ax_hm = plt.subplots(figsize=(8, 4))
+                            sns.heatmap(
+                                pivot_r, annot=True, fmt=".3f", cmap="RdYlGn",
+                                center=0, vmin=-1, vmax=1, linewidths=0.5,
+                                ax=ax_hm, cbar_kws={"label": "Pearson r"}
+                            )
+                            ax_hm.set_title("Koefisien Korelasi Pearson (r) per Metode & Lag", fontweight='bold', pad=12)
+                            ax_hm.set_ylabel("")
+                            ax_hm.set_xlabel("Lag")
+                            plt.tight_layout()
+                            st.pyplot(fig_hm)
+
+                            # ── Scatter Plot ──────────────────────────────────
+                            st.subheader("🔵 Pola Distribusi Scatter Plot (Lag t+0)")
+                            scatter_cols = list(corr_columns.values())
+                            cols_sc = st.columns(3)
+                            for idx2, (disp_name, col_key) in enumerate(corr_columns.items()):
+                                with cols_sc[idx2 % 3]:
+                                    fig_s, ax_s = plt.subplots(figsize=(5, 4))
+                                    sns.regplot(
+                                        data=df_merged, x=col_key, y="log_return", ax=ax_s,
+                                        scatter_kws={"s": 40, "color": "#10b981", "alpha": 0.5},
+                                        line_kws={"color": "#0f172a", "linewidth": 2}
                                     )
-                                    pivot_r.columns = [f"Lag t+{c}" for c in pivot_r.columns]
-                                    pivot_r.index   = [i.replace(" (numerik)","").replace(" (kategorik)","") for i in pivot_r.index]
-
-                                    fig_hm, ax_hm = plt.subplots(figsize=(8, 4))
-                                    sns.heatmap(
-                                        pivot_r, annot=True, fmt=".3f", cmap="RdYlGn",
-                                        center=0, vmin=-1, vmax=1, linewidths=0.5,
-                                        ax=ax_hm, cbar_kws={"label": "Pearson r"}
-                                    )
-                                    ax_hm.set_title("Koefisien Korelasi Pearson (r) per Metode & Lag", fontweight='bold', pad=12)
-                                    ax_hm.set_ylabel("")
-                                    ax_hm.set_xlabel("Lag")
+                                    # Tampilkan r dan p pada plot
+                                    try:
+                                        r_val, p_val = pearsonr(df_merged[col_key], df_merged["log_return"])
+                                        ax_s.set_title(f"{disp_name.split(' ')[0]}\nr={r_val:.3f}, p={p_val:.3f}", fontweight='bold', fontsize=9)
+                                    except:
+                                        ax_s.set_title(disp_name.split(' ')[0], fontweight='bold')
+                                    ax_s.set_xlabel("Sentimen Score")
+                                    ax_s.set_ylabel("Log Return")
                                     plt.tight_layout()
-                                    st.pyplot(fig_hm)
-
-                                    # ── Scatter Plot ──────────────────────────────────
-                                    st.subheader("🔵 Pola Distribusi Scatter Plot (Lag t+0)")
-                                    scatter_cols = list(corr_columns.values())
-                                    cols_sc = st.columns(3)
-                                    for idx2, (disp_name, col_key) in enumerate(corr_columns.items()):
-                                        with cols_sc[idx2 % 3]:
-                                            fig_s, ax_s = plt.subplots(figsize=(5, 4))
-                                            sns.regplot(
-                                                data=df_merged, x=col_key, y="log_return", ax=ax_s,
-                                                scatter_kws={"s": 40, "color": "#10b981", "alpha": 0.5},
-                                                line_kws={"color": "#0f172a", "linewidth": 2}
-                                            )
-
-                                            try:
-                                                r_val, p_val = pearsonr(df_merged[col_key], df_merged["log_return"])
-                                                ax_s.set_title(f"{disp_name.split(' ')[0]}\nr={r_val:.3f}, p={p_val:.3f}", fontweight='bold', fontsize=9)
-                                            except:
-                                                ax_s.set_title(disp_name.split(' ')[0], fontweight='bold')
-                                            ax_s.set_xlabel("Sentimen Score")
-                                            ax_s.set_ylabel("Log Return")
-                                            plt.tight_layout()
-                                            st.pyplot(fig_s)
-
-                                    # ── Line Chart ────────────────────────────────────
-                                    st.subheader("📈 Trend Analisis: Sentiment vs BTC Volatility")
-                                    fig_line, ax_line = plt.subplots(figsize=(14, 6))
-                                    ax_line.plot(
-                                        df_merged["date"], df_merged["log_return"],
-                                        label="BTC Log Return", color="#f7931a", linewidth=3
+                                    st.pyplot(fig_s)
+
+                            # ── Line Chart ────────────────────────────────────
+                            st.subheader("📈 Trend Analisis: Sentiment vs BTC Volatility")
+                            fig_line, ax_line = plt.subplots(figsize=(14, 6))
+                            ax_line.plot(
+                                df_merged["date"], df_merged["log_return"],
+                                label="BTC Log Return", color="#f7931a", linewidth=3
+                            )
+                            # Plot semua kolom sentimen (numerik + kategorik)
+                            colors_line = ["#3B82F6","#10B981","#EC4899","#14B8A6","#6366F1"]
+                            for i, (disp_name, col_key) in enumerate(corr_columns.items()):
+                                ax_line.plot(
+                                    df_merged["date"], df_merged[col_key],
+                                    label=f"Sentimen: {disp_name.split(' ')[0]}",
+                                    color=colors_line[i], linewidth=1.5, linestyle="--", alpha=0.8
+                                )
+                            ax_line.set_title("Pergerakan Sentimen vs Log Return Bitcoin", fontsize=14, pad=15, fontweight='bold')
+                            ax_line.set_xlabel("Tanggal", fontsize=11)
+                            ax_line.set_ylabel("Nilai Metrik", fontsize=11)
+                            ax_line.legend(loc='upper left', bbox_to_anchor=(1, 1), frameon=True)
+                            plt.tight_layout()
+                            st.pyplot(fig_line)
+
+                            # ── Distribusi Sentimen Harian (Bar) ──────────────
+                            st.subheader("📊 Distribusi Sentimen Harian per Model")
+                            label_cols = [c for c in df_merged.columns if c.endswith("_label")]
+                            if label_cols:
+                                fig_dist, axes = plt.subplots(1, len(label_cols), figsize=(14, 4), sharey=False)
+                                if len(label_cols) == 1:
+                                    axes = [axes]
+                                palette = {"Positive": "#10b981", "Neutral": "#94a3b8", "Negative": "#f43f5e"}
+                                for ax_d, lc in zip(axes, label_cols):
+                                    counts = df_merged[lc].value_counts()
+                                    bars = ax_d.bar(
+                                        counts.index,
+                                        counts.values,
+                                        color=[palette.get(x, "#94a3b8") for x in counts.index]
                                     )
-
-                                    colors_line = ["#3B82F6","#10B981","#EC4899","#14B8A6","#6366F1"]
-                                    for i, (disp_name, col_key) in enumerate(corr_columns.items()):
-                                        ax_line.plot(
-                                            df_merged["date"], df_merged[col_key],
-                                            label=f"Sentimen: {disp_name.split(' ')[0]}",
-                                            color=colors_line[i], linewidth=1.5, linestyle="--", alpha=0.8
-                                        )
-                                    ax_line.set_title("Pergerakan Sentimen vs Log Return Bitcoin", fontsize=14, pad=15, fontweight='bold')
-                                    ax_line.set_xlabel("Tanggal", fontsize=11)
-                                    ax_line.set_ylabel("Nilai Metrik", fontsize=11)
-                                    ax_line.legend(loc='upper left', bbox_to_anchor=(1, 1), frameon=True)
-                                    plt.tight_layout()
-                                    st.pyplot(fig_line)
-
-                                    # ── Distribusi Sentimen Harian (Bar) ──────────────
-                                    st.subheader("📊 Distribusi Sentimen Harian per Model")
-                                    label_cols = [c for c in df_merged.columns if c.endswith("_label")]
-                                    if label_cols:
-                                        fig_dist, axes = plt.subplots(1, len(label_cols), figsize=(14, 4), sharey=False)
-                                        if len(label_cols) == 1:
-                                            axes = [axes]
-                                        palette = {"Positive": "#10b981", "Neutral": "#94a3b8", "Negative": "#f43f5e"}
-                                        for ax_d, lc in zip(axes, label_cols):
-                                            counts = df_merged[lc].value_counts()
-                                            bars = ax_d.bar(
-                                                counts.index,
-                                                counts.values,
-                                                color=[palette.get(x, "#94a3b8") for x in counts.index]
-                                            )
-                                            ax_d.bar_label(bars, fontsize=9)
-                                            ax_d.set_title(lc.replace("_label", "").upper(), fontweight='bold', fontsize=9)
-                                            ax_d.set_xlabel("")
-                                            ax_d.set_ylabel("Jumlah Hari")
-                                        plt.tight_layout()
-                                        st.pyplot(fig_dist)
-
-                                    # ── KESIMPULAN ────────────────────────────────────
-                                    st.markdown("<hr class='vbc-divider'>", unsafe_allow_html=True)
-                                    st.subheader("📝 Kesimpulan")
-
-                                    max_idx  = df_merged["log_return"].idxmax()
-                                    min_idx  = df_merged["log_return"].idxmin()
-                                    date_max = df_merged.loc[max_idx, "date"]
-                                    date_min = df_merged.loc[min_idx, "date"]
-
-                                    st.write(
-                                        f"Puncak lonjakan positif (*max log return*) terjadi pada **{date_max}**, "
-                                        f"sedangkan penurunan ekstrem terjadi pada **{date_min}**. "
-                                        f"Dataset mencakup **{n_obs} hari** pengamatan."
-                                    )
-
-                                    sig_results  = [r for r in raw_results if r["p"] < 0.05]
-                                    all_results  = raw_results
-
-                                    if sig_results:
-                                        best = max(sig_results, key=lambda x: abs(x["r"]))
-                                        arah_text = "berbanding lurus (positif)" if best["r"] > 0 else "berbanding terbalik (negatif)"
-                                        sig_summary = ", ".join(
-                                            set(f"{r['metode'].split(' ')[0]} (lag t+{r['lag']})" for r in sig_results)
-                                        )
-                                        st.success(f"""
+                                    ax_d.bar_label(bars, fontsize=9)
+                                    ax_d.set_title(lc.replace("_label", "").upper(), fontweight='bold', fontsize=9)
+                                    ax_d.set_xlabel("")
+                                    ax_d.set_ylabel("Jumlah Hari")
+                                plt.tight_layout()
+                                st.pyplot(fig_dist)
+
+                            # ── KESIMPULAN ────────────────────────────────────
+                            st.markdown("<hr class='vbc-divider'>", unsafe_allow_html=True)
+                            st.subheader("📝 Kesimpulan")
+
+                            max_idx  = df_merged["log_return"].idxmax()
+                            min_idx  = df_merged["log_return"].idxmin()
+                            date_max = df_merged.loc[max_idx, "date"]
+                            date_min = df_merged.loc[min_idx, "date"]
+
+                            st.write(
+                                f"Puncak lonjakan positif (*max log return*) terjadi pada **{date_max}**, "
+                                f"sedangkan penurunan ekstrem terjadi pada **{date_min}**. "
+                                f"Dataset mencakup **{n_obs} hari** pengamatan."
+                            )
+
+                            # Cari lag & metode terbaik (|r| terbesar + signifikan)
+                            sig_results  = [r for r in raw_results if r["p"] < 0.05]
+                            all_results  = raw_results
+
+                            if sig_results:
+                                best = max(sig_results, key=lambda x: abs(x["r"]))
+                                arah_text = "berbanding lurus (positif)" if best["r"] > 0 else "berbanding terbalik (negatif)"
+                                sig_summary = ", ".join(
+                                    set(f"{r['metode'].split(' ')[0]} (lag t+{r['lag']})" for r in sig_results)
+                                )
+                                st.success(f"""
 **Hipotesis Diterima (H1):** Ditemukan korelasi linier yang signifikan (*p-value* < 0.05) pada: **{sig_summary}**.
 
 Metode & lag dengan korelasi terkuat adalah **{best['metode']} (lag t+{best['lag']})** dengan r = **{best['r']:.4f}**, sifat hubungan **{arah_text}**.
-                                        """)
-                                    else:
-                                        best_overall = max(all_results, key=lambda x: abs(x["r"]))
-                                        st.warning(f"""
+                                """)
+                            else:
+                                # Tampilkan tetap hasil terbaik meskipun belum signifikan
+                                best_overall = max(all_results, key=lambda x: abs(x["r"]))
+                                st.warning(f"""
 **Hipotesis Ditolak (H0 Diterima):** Belum ditemukan bukti empiris korelasi linier yang signifikan pada seluruh metode dan lag yang diuji (*p-value* ≥ 0.05).
 
 Korelasi terbesar ditemukan pada **{best_overall['metode']} (lag t+{best_overall['lag']})** dengan r = **{best_overall['r']:.4f}**. Volatilitas harga kemungkinan dipengaruhi faktor teknikal/fundamental di luar sentimen X, atau jumlah observasi belum mencukupi (n = {n_obs}, butuh minimal 30 hari agar r ≥ 0.35 bisa signifikan).
-                                        """)
+                                """)
 
                     except Exception as e:
-                        st.error(f"⚠️ Terjadi kesalahan saat mengambil atau memproses data API CoinGecko: {e}")
+                        st.error(f"⚠️ Terjadi kesalahan saat memproses data harga Bitcoin: {e}")
 
     elif analyze_batch_btn and not tweet_files:
         st.warning("⚠️ Silakan unggah minimal satu file .txt terlebih dahulu.")