Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,5 +1,5 @@
 # =============================================================
-# ⚽ LightGBM 3-Class 예측 + 유사 경기 분포 (Full Integration, Mobile-Fix)
+# ⚽ XGBoost 3-Class 예측 + 유사 경기 분포 (Full Integration, Mobile-Fix)
 # =============================================================
 import streamlit as st
 import pandas as pd
@@ -9,23 +9,20 @@ import joblib
 # ===============================
 # 앱 기본 설정 + 모바일 표시 버그 대응 CSS/JS
 # ===============================
-st.set_page_config(page_title="⚽ LightGBM 예측 + 유사 경기 탐색기", layout="wide")
+st.set_page_config(page_title="⚽ XGBoost 예측 + 유사 경기 탐색기", layout="wide")
 
 # 🔧 모바일에서 텍스트/메트릭이 잘리지 않도록 overflow/zoom/글꼴 고정 + 초기 리사이즈 트리거
 st.markdown(
     """
     <style>
-    /* 전역적으로 overflow 숨김을 해제 */
     .stApp, .block-container, [data-testid="stVerticalBlock"], [data-testid="column"] {
         overflow: visible !important;
     }
-    /* 모바일에서 여백/스케일 보정 */
     @media (max-width: 768px) {
         .block-container {
             padding-left: 1rem !important;
             padding-right: 1rem !important;
         }
-        /* 확률 표시에 쓰는 텍스트 박스 공통 스타일 */
         .prob-pill {
             font-size: 1.1rem;
             color: #ffffff;
@@ -43,7 +40,6 @@ st.markdown(
     }
     </style>
     <script>
-    // 첫 렌더 직후 강제 리사이즈로 레이아웃 재계산 유도 (모바일 표시 누락 방지)
     window.addEventListener('load', () => {
       setTimeout(() => { window.dispatchEvent(new Event('resize')); }, 150);
     });
@@ -52,16 +48,16 @@ st.markdown(
     unsafe_allow_html=True,
 )
 
-st.title("⚽ LightGBM 예측 + 유사 경기 분포 + 유사 경기 탐색기")
+st.title("⚽ XGBoost 예측 + 유사 경기 분포 + 유사 경기 탐색기")
 
 EQ_DECIMALS = 2
 def eq(a, b, decimals=EQ_DECIMALS):
     return np.round(a, decimals) == np.round(b, decimals)
 
 # ===============================
-# Feature 목록
+# Feature 목록 (65피처 통합)
 # ===============================
-expected_cols_base59 = [
+expected_cols_65 = [
     'norm_win','norm_draw','norm_lose','mean_odds','std_odds','cv_odds',
     'p_win','p_draw','p_lose','overround','entropy','spread','spread_draw',
     'odds_ratio_wd','odds_ratio_wl','odds_ratio_dl','draw_prob_ratio','draw_ratio',
@@ -71,9 +67,7 @@ expected_cols_base59 = [
     'draw_margin','fav_ratio','draw_skew','log_spread','draw_entropy_component','dominance_score',
     'hmean_odds','hstd_odds','hcv_odds','hentropy','hspread','hspread_draw',
     'hp_win','hp_draw','hp_lose','hp_win_norm','hp_draw_norm','hp_lose_norm','hoverround',
-    'diff_win_prob','diff_draw_prob','diff_lose_prob','diff_draw_odds'
-]
-expected_cols_handicap65 = expected_cols_base59 + [
+    'diff_win_prob','diff_draw_prob','diff_lose_prob','diff_draw_odds',
     'base_win_odds','base_draw_odds','base_lose_odds',
     'base_overround_ex','base_entropy_ex','base_spread_ex'
 ]
@@ -84,9 +78,7 @@ expected_cols_handicap65 = expected_cols_base59 + [
 def build_feature_dict(win, draw, lose, hwin, hdraw, hlose):
     d = {}
     denom = (win+draw+lose)
-    d['norm_win'] = win/denom
-    d['norm_draw'] = draw/denom
-    d['norm_lose'] = lose/denom
+    d['norm_win'], d['norm_draw'], d['norm_lose'] = win/denom, draw/denom, lose/denom
     d['mean_odds'] = np.mean([win,draw,lose])
     d['std_odds'] = np.std([win,draw,lose])
     d['cv_odds'] = d['std_odds']/d['mean_odds'] if d['mean_odds']>0 else 0
@@ -98,37 +90,35 @@ def build_feature_dict(win, draw, lose, hwin, hdraw, hlose):
     d['spread'] = max(win,draw,lose)-min(win,draw,lose)
     d['spread_draw'] = abs(draw-(win+lose)/2)
     d['odds_ratio_wd'],d['odds_ratio_wl'],d['odds_ratio_dl']=win/draw,win/lose,draw/lose
-    d['draw_prob_ratio'] = d['p_draw']/max(d['p_win'],d['p_lose'])
-    d['draw_ratio'] = draw/min(win,lose)
-    d['draw_prob_gap'] = abs(d['p_draw']-(d['p_win']+d['p_lose'])/2)
-    d['fav_gap'] = abs(win-lose)
-    d['fav_draw_gap'] = abs(draw-min(win,lose))
-    d['fav_diff'] = abs(win-lose)
-    d['draw_gap_mean'] = abs(draw-d['mean_odds'])
-    d['rank_win'],d['rank_draw'],d['rank_lose'] = pd.Series([win,draw,lose]).rank().tolist()
-    d['ev_win'],d['ev_draw'],d['ev_lose'] = win*d['p_win_norm'],draw*d['p_draw_norm'],lose*d['p_lose_norm']
-    d['draw_vs_avg'] = draw/d['mean_odds']
-    d['draw_vs_max'] = draw/max(win,draw,lose)
-    d['cv_spread'] = d['spread']/d['mean_odds']
-    d['cv_draw_gap'] = d['fav_draw_gap']/d['mean_odds']
-    d['draw_margin'] = abs(draw-(win+lose)/2)
-    d['fav_ratio'] = min(win,lose)/max(win,lose)
-    d['draw_skew'] = (draw-win)-(lose-draw)
-    d['log_spread'] = np.log(max(win,draw,lose))-np.log(min(win,draw,lose))
-    d['draw_entropy_component'] = -d['p_draw_norm']*np.log(d['p_draw_norm'])
-    d['dominance_score'] = max(d['p_win_norm'],d['p_lose_norm'])-d['p_draw_norm']
-
-    d['hmean_odds'] = np.mean([hwin,hdraw,hlose])
-    d['hstd_odds']  = np.std([hwin,hdraw,hlose])
-    d['hcv_odds']   = d['hstd_odds']/d['hmean_odds'] if d['hmean_odds']>0 else 0
-    p_h = 1/np.array([hwin,hdraw,hlose])
-    p_hn = p_h/p_h.sum()
-    d['hp_win'],d['hp_draw'],d['hp_lose'] = p_h
-    d['hp_win_norm'],d['hp_draw_norm'],d['hp_lose_norm'] = p_hn
-    d['hoverround'] = p_h.sum()
-    d['hentropy'] = -np.sum(p_hn*np.log(p_hn))
-    d['hspread']  = max(hwin,hdraw,hlose)-min(hwin,hdraw,hlose)
-    d['hspread_draw'] = abs(hdraw-(hwin+hlose)/2)
+    d['draw_prob_ratio']=d['p_draw']/max(d['p_win'],d['p_lose'])
+    d['draw_ratio']=draw/min(win,lose)
+    d['draw_prob_gap']=abs(d['p_draw']-(d['p_win']+d['p_lose'])/2)
+    d['fav_gap']=abs(win-lose)
+    d['fav_draw_gap']=abs(draw-min(win,lose))
+    d['fav_diff']=abs(win-lose)
+    d['draw_gap_mean']=abs(draw-d['mean_odds'])
+    d['rank_win'],d['rank_draw'],d['rank_lose']=pd.Series([win,draw,lose]).rank().tolist()
+    d['ev_win'],d['ev_draw'],d['ev_lose']=win*d['p_win_norm'],draw*d['p_draw_norm'],lose*d['p_lose_norm']
+    d['draw_vs_avg']=draw/d['mean_odds']
+    d['draw_vs_max']=draw/max(win,draw,lose)
+    d['cv_spread']=d['spread']/d['mean_odds']
+    d['cv_draw_gap']=d['fav_draw_gap']/d['mean_odds']
+    d['draw_margin']=abs(draw-(win+lose)/2)
+    d['fav_ratio']=min(win,lose)/max(win,lose)
+    d['draw_skew']=(draw-win)-(lose-draw)
+    d['log_spread']=np.log(max(win,draw,lose))-np.log(min(win,draw,lose))
+    d['draw_entropy_component']=-d['p_draw_norm']*np.log(d['p_draw_norm'])
+    d['dominance_score']=max(d['p_win_norm'],d['p_lose_norm'])-d['p_draw_norm']
+    d['hmean_odds']=np.mean([hwin,hdraw,hlose])
+    d['hstd_odds']=np.std([hwin,hdraw,hlose])
+    d['hcv_odds']=d['hstd_odds']/d['hmean_odds'] if d['hmean_odds']>0 else 0
+    p_h=1/np.array([hwin,hdraw,hlose]); p_hn=p_h/p_h.sum()
+    d['hp_win'],d['hp_draw'],d['hp_lose']=p_h
+    d['hp_win_norm'],d['hp_draw_norm'],d['hp_lose_norm']=p_hn
+    d['hoverround']=p_h.sum()
+    d['hentropy']=-np.sum(p_hn*np.log(p_hn))
+    d['hspread']=max(hwin,hdraw,hlose)-min(hwin,hdraw,hlose)
+    d['hspread_draw']=abs(hdraw-(hwin+hlose)/2)
     d['diff_win_prob']=d['p_win_norm']-d['hp_win_norm']
     d['diff_draw_prob']=d['p_draw_norm']-d['hp_draw_norm']
     d['diff_lose_prob']=d['p_lose_norm']-d['hp_lose_norm']
@@ -137,29 +127,30 @@ def build_feature_dict(win, draw, lose, hwin, hdraw, hlose):
     d['base_overround_ex'],d['base_entropy_ex'],d['base_spread_ex']=p_tot,d['entropy'],d['spread']
     return d
 
-def build_feature_frames(win,draw,lose,hwin,hdraw,hlose):
-    d = build_feature_dict(win,draw,lose,hwin,hdraw,hlose)
-    df_all = pd.DataFrame([d])
-    return df_all[expected_cols_base59], df_all[expected_cols_handicap65]
+def build_feature_frame(win, draw, lose, hwin, hdraw, hlose):
+    d = build_feature_dict(win, draw, lose, hwin, hdraw, hlose)
+    df = pd.DataFrame([d])
+    return df[expected_cols_65]
 
 # ===============================
-# 모델 로드
+# 모델 로드 (XGBoost)
 # ===============================
 @st.cache_resource
 def load_models():
-    base = joblib.load("lgbm_model_base_65.pkl")
-    hand = joblib.load("lgbm_model_handicap_65.pkl")
+    base = joblib.load("xgb_model_wdl_softmax.pkl")
+    hand = joblib.load("xgb_model_handicap_65f.pkl")
     enc  = joblib.load("label_encoder_handicap.pkl")
     return base, hand, enc
+
 model_base, model_hand, encoder_hand = load_models()
 
 # ===============================
 # 예측
 # ===============================
 def predict_all(win, draw, lose, hwin, hdraw, hlose):
-    df_base, df_hand = build_feature_frames(win, draw, lose, hwin, hdraw, hlose)
-    probs_base = model_base.predict_proba(df_base)[0]
-    probs_hand = model_hand.predict_proba(df_hand)[0]
+    df_feat = build_feature_frame(win, draw, lose, hwin, hdraw, hlose)
+    probs_base = model_base.predict_proba(df_feat.values)[0]
+    probs_hand = model_hand.predict_proba(df_feat.values)[0]
     return dict(zip(["승","무","패"], probs_base)), dict(zip(["핸디 승","핸디 무","핸디 패"], probs_hand))
 
 # ===============================
@@ -257,23 +248,17 @@ st.divider()
 
 # ===============================
 # 🔢 확률 표시 (모바일 완전 호환)
-#  - columns 사용 안 함
-#  - markdown/HTML만 사용
-#  - 페이지 하단에서 렌더 (모바일 렌더 타이밍 안정)
 # ===============================
 base_probs, hand_probs = predict_all(win, draw, lose, hwin, hdraw, hlose)
 
-# 선택적으로 모바일 강제 호환 모드(텍스트만) 토글
-mobile_text_mode = st.toggle("📱 모바일 강제 호환 모드(텍스트만)", value=True, help="모바일에서 누락될 경우 켜두세요")
+mobile_text_mode = st.toggle("📱 모바일 강제 호환 모드(텍스트만)", value=True)
 
 st.markdown('<div class="prob-section">', unsafe_allow_html=True)
 st.markdown("### ⚽ 기본 승/무/패 확률")
 if mobile_text_mode:
-    # 텍스트만 (가장 안전)
     for k, emoji in zip(["승","무","패"], ["🟢","🟡","🔴"]):
         st.markdown(f"{emoji} **{k}** : {base_probs[k]*100:.2f}%")
 else:
-    # pill 스타일 (모바일에서도 잘 보이도록 커스텀)
     html = "".join([f'<span class="prob-pill"><b>{k}</b>: {base_probs[k]*100:.2f}%</span>'
                     for k in ["승","무","패"]])
     st.markdown(html, unsafe_allow_html=True)
@@ -288,4 +273,4 @@ else:
     st.markdown(html, unsafe_allow_html=True)
 st.markdown('</div>', unsafe_allow_html=True)
 
-st.caption("ⓒ LightGBM 3-Class Softmax Models | 기본: 59피처, 핸디: 65피처")
+st.caption("ⓒ XGBoost 3-Class Softmax Models | 기본·핸디 65피처 통합형")