feat: migrate to 1min EURUSD data (2020-2026)

- data_config.yaml: frequency 15min -> 1min, path -> eurusd_1min_data
- patches/generate.py: updated qlib.init path and freq
- patches/eva_utils.py: updated intraday label to 1min
- all prompts/configs: replaced 15min references with 1min
- fx_validator config, trader, graph: 1min intraday trading context

.gitignore

@@ -10,3 +10,6 @@ __pycache__/
 *.pyc
 *.pyo
 prompt_cache.db
+convert_1min.py
+import_1min_qlib.py
+data_raw/

data_config.yaml

@@ -5,8 +5,8 @@
 # ============================================================
 
 instrument: EURUSD
-frequency: 15min          # 1min, 5min, 15min, 1h, 1d
-data_path: ~/.qlib/qlib_data/eurusd_data
+frequency: 1min          # 1min, 5min, 15min, 1h, 1d
+data_path: ~/.qlib/qlib_data/eurusd_1min_data
 
 # Verfügbare Spalten (keine $factor Spalte!)
 columns:

patches/eva_utils.py

@@ -243,7 +243,7 @@ class FactorDatetimeDailyEvaluator(FactorEvaluator):
                 False,
             )
         if min_diff <= pd.Timedelta(minutes=30):
-            return "The generated dataframe is intraday (15min bars). This is correct for EURUSD.", True
+            return "The generated dataframe is intraday (1min bars). This is correct for EURUSD.", True
         return "The generated dataframe is daily.", True
 
 

patches/generate.py

@@ -7,12 +7,12 @@ result = subprocess.run(
     ["/home/nico/miniconda3/envs/rdagent4qlib/bin/python3", "-c", """
 import qlib
 from qlib.data import D
-qlib.init(provider_uri="~/.qlib/qlib_data/eurusd_data")
+qlib.init(provider_uri="~/.qlib/qlib_data/eurusd_1min_data")
 fields = ["$open", "$close", "$high", "$low", "$volume"]
-data = (D.features(["EURUSD"], fields, start_time="2022-03-14", end_time="2026-03-20", freq="15min")
+data = (D.features(["EURUSD"], fields, start_time="2022-03-14", end_time="2026-03-20", freq="1min")
         .swaplevel().sort_index())
 data.to_hdf("./daily_pv_all.h5", key="data")
-data_debug = (D.features(["EURUSD"], fields, start_time="2024-01-01", end_time="2026-03-20", freq="15min")
+data_debug = (D.features(["EURUSD"], fields, start_time="2024-01-01", end_time="2026-03-20", freq="1min")
               .swaplevel().sort_index())
 data_debug.to_hdf("./daily_pv_debug.h5", key="data")
 print(f"Done: {data.shape[0]} rows")

patches/qlib_rd_loop_prompts.yaml

@@ -1,7 +1,7 @@
 hypothesis_generation:
   system: |-
     You are an expert in FX and quantitative trading, specialized in EURUSD intraday strategies.
-    Your task is to generate a well-reasoned hypothesis for new alpha factors based on EURUSD 15min OHLCV data.
+    Your task is to generate a well-reasoned hypothesis for new alpha factors based on EURUSD 1min OHLCV data.
     
     Key market knowledge:
     - EURUSD trades 24h with three main sessions: Asian (00:00-08:00 UTC), London (08:00-16:00 UTC), NY (13:00-21:00 UTC)

patches/qlib_scenarios_prompts.yaml

@@ -101,7 +101,7 @@ factor_hypothesis_specification: |-
   - Asian session shows mean reversion tendencies
   - Spread cost ~1.5 bps per trade — avoid high-turnover factors
   - No $factor column exists — use only $open, $close, $high, $low, $volume
-  - Each "instrument" is EURUSD, each "day" is a 15min bar
+  - Each "instrument" is EURUSD, each "day" is a 1min bar
 
   **Factor Generation Rules:**
   1. **3-5 Factors per Generation** — cover different signal types per round
@@ -183,7 +183,7 @@ factor_feedback_generation:
     Your feedback should specify whether the current result supports or refutes the hypothesis, compare it with previous SOTA results, and suggest FX-specific improvements.
 
     **FX-specific evaluation criteria:**
-    - IC > 0.02 is meaningful for 15min EURUSD data
+    - IC > 0.02 is meaningful for 1min EURUSD data
     - Annualized return target: >9.62% (current SOTA to beat)
     - Spread cost ~1.5 bps per trade — penalize high-turnover factors
     - Factors using $factor column are INVALID — only $open $close $high $low $volume allowed
@@ -198,7 +198,7 @@ factor_feedback_generation:
       2. Development Directions:
         a) New Direction: Propose a new FX-specific factor (session filter, volatility regime, volume spike).
         b) Optimization: Refine lookback windows (4/8/16/32 bars), add ADX filter, adjust for spread costs.
-      3. Final Goal: Beat 9.62% ARR on EURUSD 15min with controlled drawdown (<20%).
+      3. Final Goal: Beat 9.62% ARR on EURUSD 1min with controlled drawdown (<20%).
 
     When judging results:
       1. Any small improvement in annualized return → set Replace Best Result as yes.

rdagent/app/qlib_rd_loop/prompts.yaml

@@ -20,7 +20,7 @@ hypothesis_generation:
     - Statistical: Regime-switching (HMM), Kalman filter
 
     Available features in the dataset:
-    - OHLCV: open, high, low, close, volume (15min bars)
+    - OHLCV: open, high, low, close, volume (1min bars)
     - Returns: ret_1, ret_4, ret_8, ret_16, ret_96
     - Technical: rsi_14, macd_hist, adx_14, atr_14, bb_pct, stoch_k, cci_14
     - Volatility: vol_real_4, vol_real_16, vol_ratio, zscore_ret_96
@@ -36,7 +36,7 @@ hypothesis_generation:
 
     Please ensure your response is in JSON format:
     {
-      "hypothesis": "A clear and concise trading hypothesis for EURUSD 15min.",
+      "hypothesis": "A clear and concise trading hypothesis for EURUSD 1min.",
       "reason": "Detailed explanation including session, model choice, and expected edge.",
       "model_type": "One of: TimeSeries / Tabular / XGBoost",
       "target_session": "london / ny / asian / all",

rdagent/scenarios/qlib/fx_validator/agents/analysts/macro_analyst.py

@@ -27,11 +27,16 @@ def get_fx_macro_data() -> str:
         else:
             vol_24h = "N/A"
 
+        eurusd_last_str = f"{eurusd_last:.5f}" if isinstance(eurusd_last, float) else str(eurusd_last)
+        eurusd_change_str = f"{eurusd_change:.3f}%" if isinstance(eurusd_change, float) else str(eurusd_change)
+        dxy_last_str = f"{dxy_last:.2f}" if isinstance(dxy_last, float) else str(dxy_last)
+        vol_24h_str = f"{vol_24h:.4f}%" if isinstance(vol_24h, float) else str(vol_24h)
+
         return f"""
-EURUSD Current: {eurusd_last:.5f if isinstance(eurusd_last, float) else eurusd_last}
-EURUSD 24h Change: {eurusd_change:.3f}% if isinstance(eurusd_change, float) else eurusd_change}
-DXY (Dollar Index): {dxy_last:.2f if isinstance(dxy_last, float) else dxy_last}
-Realized Volatility 24h: {vol_24h:.4f}% if isinstance(vol_24h, float) else vol_24h}
+EURUSD Current: {eurusd_last_str}
+EURUSD 24h Change: {eurusd_change_str}
+DXY (Dollar Index): {dxy_last_str}
+Realized Volatility 24h: {vol_24h_str}
 """
     except Exception as e:
         return f"Macro data unavailable: {e}"

rdagent/scenarios/qlib/fx_validator/agents/trader/fx_trader.py

@@ -13,7 +13,7 @@ def create_fx_trader(llm):
         debate_history = debate_state.get("history", "")
         risk_report = state.get("risk_report", "")
 
-        prompt = f"""You are an FX Trading Decision Agent for EURUSD 15min intraday trading.
+        prompt = f"""You are an FX Trading Decision Agent for EURUSD 1min intraday trading.
 
 You have received reports from your team:
 

rdagent/scenarios/qlib/fx_validator/config.py

@@ -1,12 +1,12 @@
 """
 FX Validator Configuration
-Angepasst für EURUSD 15min intraday trading
+Angepasst für EURUSD 1min intraday trading
 """
 import os
 
 FX_CONFIG = {
     "instrument": "EURUSD=X",
-    "frequency": "15min",
+    "frequency": "1min",
     "llm_provider": "openai",
     "backend_url": os.getenv("OPENAI_API_BASE", "http://localhost:8081/v1"),
     "api_key": os.getenv("OPENAI_API_KEY", "local"),

rdagent/scenarios/qlib/fx_validator/fx_graph.py

@@ -1,6 +1,6 @@
 """
 FX Validator Graph — Multi-Agent Validierung für Predix Faktoren
-Inspiriert von TradingAgents, angepasst für EURUSD 15min
+Inspiriert von TradingAgents, angepasst für EURUSD 1min
 """
 from typing import TypedDict, Optional
 from langgraph.graph import StateGraph, END