Update app.py

app.py

@@ -33,6 +33,54 @@ class DateRange(BaseModel):
     start_date: str  # ISO date 'YYYY-MM-DD'
     end_date: str    # ISO date 'YYYY-MM-DD'
 
+def clean_yf_csv(df_raw):
+    """
+    Membersihkan struktur CSV seperti hasil export yfinance:
+    - baris pertama: nama kolom
+    - baris kedua: ticker
+    - baris ketiga: header date kosong
+    - sisakan hanya kolom ['date', 'close']
+    """
+    # Jika baris pertama bukan data (mengandung "Price,Close,High,..."), kita re-parse manual
+    if "Price" in df_raw.columns[0]:
+        logger.info("Detected raw yfinance export format, cleaning...")
+        # Baca ulang file tanpa header dulu
+        df_raw.columns = [c.strip().lower() for c in df_raw.columns]
+        # Hapus baris ke-2 dan ke-3
+        df_raw = df_raw.drop(index=[0, 1])
+        # Ganti kolom 'price' menjadi 'date'
+        df_raw = df_raw.rename(columns={"price": "date"})
+        # Pastikan hanya ambil kolom 'date' dan 'close'
+        keep_cols = [c for c in df_raw.columns if c in ["date", "close"]]
+        df_raw = df_raw[keep_cols]
+        # Ubah tipe data tanggal
+        df_raw["date"] = pd.to_datetime(df_raw["date"], errors="coerce")
+        df_raw = df_raw.dropna(subset=["date"])
+        df_raw["close"] = pd.to_numeric(df_raw["close"], errors="coerce")
+        df_raw = df_raw.dropna(subset=["close"])
+        df_raw = df_raw.reset_index(drop=True)
+    return df_raw
+
+def load_yf_data(pair, start, end):
+    """Download yfinance data and ensure 'date' and 'close' columns exist."""
+    df_raw = yf.download(pair, start=start, end=end, auto_adjust=True, progress=False)
+    if df_raw.empty:
+        raise ValueError("No data from yfinance for that range.")
+
+    # Jika data CSV seperti contoh kamu (ada baris Ticker dan Price)
+    if "Price" in df_raw.columns or "Ticker" in df_raw.columns:
+        df_raw = clean_yf_csv(df_raw)
+        return df_raw
+
+    # flatten MultiIndex columns
+    if isinstance(df_raw.columns, pd.MultiIndex):
+        df_raw.columns = df_raw.columns.get_level_values(0)
+
+    df = df_raw.reset_index()[["Date", "Close"]].rename(columns={"Date": "date", "Close": "close"})
+    df["date"] = pd.to_datetime(df["date"]).dt.normalize()
+    return df
+
+
 # -----------------------
 # Utility functions
 # -----------------------