Update app.py

app.py

@@ -12,7 +12,7 @@ from pathlib import Path
 # CONFIG ------------------------------------------
 # -------------------------------------------------
 CSV_PATH = Path("price_data.csv")
-PARQUET_PATH = Path("domae-202503.parquet")  # 1996‑1993-03 가격 데이터
+PARQUET_PATH = Path("domae-202503.parquet")  # 1996-2025-03 일간 가격
 MACRO_START, MACRO_END = "1996-01-01", "2030-12-31"
 MICRO_START, MICRO_END = "2020-01-01", "2026-12-31"
 
@@ -21,18 +21,50 @@ st.set_page_config(page_title="품목별 가격 예측", page_icon="📈", layou
 # -------------------------------------------------
 # UTILITIES ---------------------------------------
 # -------------------------------------------------
+DATE_CANDIDATES = {"date", "ds", "ymd", "날짜"}
+ITEM_CANDIDATES = {"item", "품목", "code", "category"}
+PRICE_CANDIDATES = {"price", "y", "value", "가격"}
+
+def _standardize_columns(df: pd.DataFrame) -> pd.DataFrame:
+    """Rename date/item/price cols to date, item, price (in-place)."""
+    col_map = {}
+    for c in df.columns:
+        lc = c.lower()
+        if lc in DATE_CANDIDATES:  # date
+            col_map[c] = "date"
+        elif lc in ITEM_CANDIDATES:
+            col_map[c] = "item"
+        elif lc in PRICE_CANDIDATES:
+            col_map[c] = "price"
+    df.rename(columns=col_map, inplace=True)
+
+    # date might be index
+    if "date" not in df.columns:
+        if df.index.dtype.kind == "M":
+            df.reset_index(inplace=True)
+            df.rename(columns={df.columns[0]: "date"}, inplace=True)
+    return df
+
 @st.cache_data(show_spinner=False)
 def load_data() -> pd.DataFrame:
-    """Load price data from Parquet if available, else CSV."""
+    """Load price data from Parquet if available, else CSV. Tries to infer column names."""
     if PARQUET_PATH.exists():
         df = pd.read_parquet(PARQUET_PATH)
     elif CSV_PATH.exists():
         df = pd.read_csv(CSV_PATH)
     else:
-        st.error("데이터 파일을 찾을 수 없습니다. price_data.csv 또는 domae-202503.parquet" )
+        st.error("💾 price_data.csv 또는 domae-202503.parquet 파일을 찾을 수 없습니다.")
+        st.stop()
+
+    df = _standardize_columns(df)
+
+    missing = {c for c in ["date", "item", "price"] if c not in df.columns}
+    if missing:
+        st.error(f"필수 컬럼 누락: {', '.join(missing)} — 파일 컬럼명을 확인하세요.")
         st.stop()
-    # 표준화
-    df["date"] = pd.to_datetime(df["date"])
+
+    df["date"] = pd.to_datetime(df["date"], errors="coerce")
+    df.dropna(subset=["date", "item", "price"], inplace=True)
     df.sort_values("date", inplace=True)
     return df
 
@@ -44,7 +76,8 @@ def get_items(df: pd.DataFrame):
 def fit_prophet(df: pd.DataFrame, horizon_end: str):
     m = Prophet(yearly_seasonality=True, weekly_seasonality=False, daily_seasonality=False)
     m.fit(df.rename(columns={"date": "ds", "price": "y"}))
-    future = m.make_future_dataframe(periods=(pd.Timestamp(horizon_end) - df["date"].max()).days, freq="D")
+    periods = (pd.Timestamp(horizon_end) - df["date"].max()).days
+    future = m.make_future_dataframe(periods=periods, freq="D")
     forecast = m.predict(future)
     return m, forecast
 
@@ -64,12 +97,11 @@ if item_df.empty:
     st.stop()
 
 # -------------------------------------------------
-# PLOTS -------------------------------------------
+# MACRO FORECAST 1996-2030 ------------------------
 # -------------------------------------------------
 st.header(f"📈 {selected_item} 가격 예측 대시보드")
-
-# Macro forecast 1996–2030
 macro_df = item_df[item_df["date"] >= MACRO_START]
+
 m_macro, fc_macro = fit_prophet(macro_df, MACRO_END)
 fig_macro = px.line(fc_macro, x="ds", y="yhat", title="Macro Forecast 1996–2030")
 fig_macro.add_scatter(x=macro_df["date"], y=macro_df["price"], mode="lines", name="Actual")
@@ -80,8 +112,11 @@ macro_pred = fc_macro.loc[fc_macro["ds"] == MACRO_END, "yhat"].iloc[0]
 macro_pct = (macro_pred - latest_price) / latest_price * 100
 st.metric("2030 예측가", f"{macro_pred:,.0f}", f"{macro_pct:+.1f}%")
 
-# Micro forecast 2024–2026
+# -------------------------------------------------
+# MICRO FORECAST 2024-2026 ------------------------
+# -------------------------------------------------
 st.subheader("🔎 2024–2026 단기 예측")
+
 micro_df = item_df[item_df["date"] >= MICRO_START]
 m_micro, fc_micro = fit_prophet(micro_df, MICRO_END)
 fig_micro = px.line(fc_micro, x="ds", y="yhat", title="Micro Forecast 2024–2026")
@@ -92,36 +127,43 @@ micro_pred = fc_micro.loc[fc_micro["ds"] == MICRO_END, "yhat"].iloc[0]
 micro_pct = (micro_pred - latest_price) / latest_price * 100
 st.metric("2026 예측가", f"{micro_pred:,.0f}", f"{micro_pct:+.1f}%")
 
-# Seasonality components
+# -------------------------------------------------
+# SEASONALITY & PATTERN ---------------------------
+# -------------------------------------------------
 with st.expander("📆 시즈널리티 & 패턴 설명"):
     comp_fig = m_micro.plot_components(fc_micro)
     st.pyplot(comp_fig)
+
     month_season = (fc_micro[["ds", "yearly"]]
                     .assign(month=lambda d: d.ds.dt.month)
                     .groupby("month")["yearly"].mean())
     st.markdown(
-        f"**연간 피크 월:** {int(month_season.idxmax())}월\n\n"
-        f"**연간 저점 월:** {int(month_season.idxmin())}월\n\n"
+        f"**연간 피크 월:** {int(month_season.idxmax())}월  \n"
+        f"**연간 저점 월:** {int(month_season.idxmin())}월  \n"
         f"**연간 변동폭:** {month_season.max() - month_season.min():.1f}")
 
-# Correlation heatmap
+# -------------------------------------------------
+# CORRELATION HEATMAP -----------------------------
+# -------------------------------------------------
 st.subheader("🧮 품목 간 상관관계")
 monthly_pivot = (raw_df.assign(month=lambda d: d.date.dt.to_period("M"))
                         .groupby(["month", "item"], as_index=False)["price"].mean()
                         .pivot(index="month", columns="item", values="price"))
 
 corr = monthly_pivot.corr()
-mask = np.triu(np.ones_like(corr, dtype=bool))
 fig, ax = plt.subplots(figsize=(12, 10))
+mask = np.triu(np.ones_like(corr, dtype=bool))
 sns.heatmap(corr, mask=mask, cmap="RdBu_r", center=0, linewidths=.5, ax=ax)
 st.pyplot(fig)
 
-st.info("빨간 영역: 가격 동조화 / 파란 영역: 대체재 가능성.")
+st.info("빨간 영역: 가격 동조화 / 파란 영역: 대체재 가능성")
 
-# Volatility Chart
+# -------------------------------------------------
+# VOLATILITY --------------------------------------
+# -------------------------------------------------
 st.subheader("📊 30일 이동 표준편차 (가격 변동성)")
 vol = item_df.set_index("date")["price"].rolling(30).std().dropna().reset_index()
 fig_vol = px.area(vol, x="date", y="price", title="Rolling 30D Std Dev")
 st.plotly_chart(fig_vol, use_container_width=True)
 
-st.caption("데이터: domae-202503.parquet · Prophet 예측 · Streamlit 대시보드")
+st.caption("데이터: domae-202503.parquet · Prophet 예측 · Streamlit 대시보드")