feat(data): EUR/USD hourly pipeline + 2008-2023 M1 dataset (#2)

- scripts/prepare_hourly.py: M1→hourly aggregation (realized_vol = sqrt(Σr²),
  MIN_BARS=30 threshold, no weekend rows, year-based split preserved)
- tests/test_prepare_hourly.py: 5 TDD tests, all green
- train.py: USE_HOURLY=True, WINDOW=240 (10-day), PATCH_LEN=24 (1-day patches);
  build() prefers eurusd_hourly.parquet, falls back to daily; EXPORT BLOCK updated
- Taskfile.yml: data:fetch:historical, data:prepare:hourly, data:prepare:all, data:test
- 98,591 hourly rows (2008-2023) covering GFC, Euro crisis, Brexit, COVID, Fed cycle

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

train.py

@@ -18,8 +18,9 @@ import torch.nn as nn
 import torch.nn.functional as F
 
 # --- agent-tunable knobs ---
-WINDOW      = 60
-PATCH_LEN   = 10    # non-overlapping patches (6 tokens per window)
+USE_HOURLY  = True   # prefer eurusd_hourly.parquet when available
+WINDOW      = 240    # hourly: 10 trading days; if USE_HOURLY=False reset to 60
+PATCH_LEN   = 24     # hourly: 1-day patches (10 tokens); if USE_HOURLY=False reset to 10
 D_MODEL     = 128
 DEPTH       = 2
 N_HEADS     = 4
@@ -120,9 +121,20 @@ class HorizonPredictor(nn.Module):
 # ── Data ─────────────────────────────────────────────────────────────────────
 
 def build():
-    """Year-based split: encoder trains on 2019-2021; probe evaluates on 2022-2023 OOS."""
-    df = pd.read_parquet("data/processed/eurusd_daily.parquet").reset_index(drop=True)
-    df["date"] = pd.to_datetime(df["date"])
+    """Year-based split: encoder trains on ≤2021; probe evaluates on ≥2022 OOS.
+
+    Uses eurusd_hourly.parquet when USE_HOURLY=True and the file exists;
+    falls back to eurusd_daily.parquet otherwise.
+    """
+    import os
+    hourly_path = "data/processed/eurusd_hourly.parquet"
+    daily_path  = "data/processed/eurusd_daily.parquet"
+    if USE_HOURLY and os.path.exists(hourly_path):
+        df = pd.read_parquet(hourly_path).reset_index(drop=True)
+        df["date"] = pd.to_datetime(df["datetime"])
+    else:
+        df = pd.read_parquet(daily_path).reset_index(drop=True)
+        df["date"] = pd.to_datetime(df["date"])
     feats  = df[["ret", "realized_vol"]].to_numpy(np.float32)
     target = df["realized_vol"].to_numpy(np.float32)
     tr_idx = df.index[df["date"].dt.year <= 2021].tolist()
@@ -195,8 +207,14 @@ def main():
     # Set EXPORT_EMBEDDINGS=1 to write embeddings.json for the Go eval harness.
     import os
     if os.environ.get("EXPORT_EMBEDDINGS") == "1":
-        df2 = pd.read_parquet("data/processed/eurusd_daily.parquet").reset_index(drop=True)
-        df2["date"] = pd.to_datetime(df2["date"])
+        hourly_path2 = "data/processed/eurusd_hourly.parquet"
+        daily_path2  = "data/processed/eurusd_daily.parquet"
+        if USE_HOURLY and os.path.exists(hourly_path2):
+            df2 = pd.read_parquet(hourly_path2).reset_index(drop=True)
+            df2["date"] = pd.to_datetime(df2["datetime"])
+        else:
+            df2 = pd.read_parquet(daily_path2).reset_index(drop=True)
+            df2["date"] = pd.to_datetime(df2["date"])
         tr_mask = df2["date"].dt.year <= 2021
         feats2 = df2[["ret", "realized_vol"]].to_numpy(np.float32)
         mu2 = feats2[tr_mask].mean(0); sd2 = feats2[tr_mask].std(0) + 1e-8