Update src/streamlit_app.py

src/streamlit_app.py

@@ -446,7 +446,7 @@ def clean_text(text):
     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+", "", text)             
     text = re.sub(r"[^\w\s]", "", text)           
     text = re.sub(r"\b\d+\b", "", text)           
     text = re.sub(r"\s+", " ", text).strip()
@@ -466,6 +466,7 @@ def classify_tb(score):
     if score < -TEXTBLOB_THRESHOLD: return 'negative'
     return 'neutral'
 
+
 def map_roberta(label):
     return {"LABEL_0": "negative", "LABEL_1": "neutral", "LABEL_2": "positive"}.get(label, "neutral")
 
@@ -606,27 +607,48 @@ 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 "→")
-                    detail_html = f'<div style="font-size:0.7rem;color:#94a3b8;margin-top:2px;">{detail}</div>' if detail else ''
+                    detail_html = (
+                        '<div style="font-size:0.7rem;color:#94a3b8;margin-top:2px;">'
+                        + detail +
+                        '</div>'
+                    ) if detail else ''
+
+                    if label == 'positive':
+                        border_color = '#10b981'
+                    elif label == 'negative':
+                        border_color = '#f43f5e'
+                    else:
+                        border_color = '#cbd5e1'
+
+                    html_card = (
+                        '<div style="background:#FAFAFA;border:1px solid #e2e8f0;'
+                        'border-left:4px solid ' + border_color + ';'
+                        'border-radius:12px;padding:1rem 1.2rem;margin-bottom:1rem;'
+                        'display:flex;align-items:center;justify-content:space-between;'
+                        'box-shadow:0 2px 4px rgba(0,0,0,0.02);">'
+                            '<div>'
+                                '<div style="font-weight:600;font-size:0.75rem;color:#64748b;margin-bottom:4px;">'
+                                + method +
+                                '</div>'
+                                '<div style="font-weight:800;font-size:1.05rem;color:#0f172a;">'
+                                + label.capitalize() +
+                                '</div>'
+                                + detail_html +
+                            '</div>'
+                            '<div style="background:' + bg + ';color:' + tc + ';'
+                            'font-size:0.75rem;font-weight:700;'
+                            'padding:6px 12px;border-radius:50px;">'
+                            + icon + ' ' + label.upper() +
+                            '</div>'
+                        '</div>'
+                    )
+
                     with col:
-                        st.markdown(f"""
-                        <div style="background:#FAFAFA;border:1px solid #e2e8f0;border-left:4px solid {'#10b981' if label=='positive' else ('#f43f5e' if label=='negative' else '#cbd5e1')};
-                            border-radius:12px;padding:1rem 1.2rem;margin-bottom:1rem;
-                            display:flex;align-items:center;justify-content:space-between;
-                            box-shadow:0 2px 4px rgba(0,0,0,0.02);">
-                            <div>
-                                <div style="font-weight:600;font-size:0.75rem;color:#64748b;margin-bottom:4px;">{method}</div>
-                                <div style="font-weight:800;font-size:1.05rem;color:#0f172a;">{label.capitalize()}</div>
-                                {detail_html}
-                            </div>
-                            <div style="background:{bg};color:{tc};font-size:0.75rem;font-weight:700;
-                                padding:6px 12px;border-radius:50px;">
-                                {icon} {label.upper()}
-                            </div>
-                        </div>
-                        """, unsafe_allow_html=True)
+                        st.markdown(html_card, unsafe_allow_html=True)
 
             with st.expander("🔍 Lihat teks setelah preprocessing"):
                 st.code(text if text.strip() else "(kosong setelah dibersihkan)", language=None)
@@ -849,15 +871,20 @@ elif st.session_state.page == "analisis_batch":
                                     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
 
@@ -897,7 +924,7 @@ elif st.session_state.page == "analisis_batch":
                                     st.markdown("<hr class='vbc-divider'>", unsafe_allow_html=True)
 
                                     # ==================================================
-                                    # UJI KORELASI PEARSON
+                                    # UJI KORELASI PEARSON DENGAN LAG
                                     # ==================================================
                                     st.subheader("🔬 Uji Korelasi Pearson")
                                     st.caption(
@@ -908,11 +935,11 @@ elif st.session_state.page == "analisis_batch":
                                     )
 
                                     corr_columns = {
-                                        "VADER":"vader_score",
-                                        "TextBlob": "tb_score",
-                                        "BERTweet":"bertweet",
-                                        "RoBERTa": "roberta",
-                                        "RoBERTa Large": "roberta_large",
+                                        "VADER (numerik)":          "vader_score",
+                                        "TextBlob (numerik)":       "tb_score",
+                                        "BERTweet (kategorik)":     "bertweet",
+                                        "RoBERTa Base (kategorik)": "roberta",
+                                        "RoBERTa Large (kategorik)":"roberta_large",
                                     }
 
                                     corr_rows   = []
@@ -1002,6 +1029,7 @@ elif st.session_state.page == "analisis_batch":
                                                 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)
@@ -1019,6 +1047,7 @@ elif st.session_state.page == "analisis_batch":
                                         df_merged["date"], df_merged["log_return"],
                                         label="BTC Log Return", color="#f7931a", linewidth=3
                                     )
+
                                     colors_line = ["#3B82F6","#10B981","#EC4899","#14B8A6","#6366F1"]
                                     for i, (disp_name, col_key) in enumerate(corr_columns.items()):
                                         ax_line.plot(