small bugfixed and improvements

roboquant/journals/journal.py

@@ -18,3 +18,6 @@ def track(self, event: Event, account: Account, signals: list[Signal], orders: l
         """invoked at each step of a run that provides the journal with the opportunity to
         track and log various metrics."""
         ...
+
+    def reset(self):
+        """reset the state of the journal, default is to do nothing"""

roboquant/journals/metric.py

@@ -9,6 +9,6 @@
 class Metric(Protocol):
     """Metric calculates zero or more values during each step of a run"""
 
-    def calc(self, event: Event, account: Account, signals: dict[str, Signal], orders: list[Order]) -> dict[str, float]:
+    def calc(self, event: Event, account: Account, signals: list[Signal], orders: list[Order]) -> dict[str, float]:
         """Calculate zero or more metrics and return the result as a dict."""
         ...

roboquant/ml/strategies.py

@@ -3,11 +3,12 @@
 import logging
 import numpy as np
 from numpy.typing import NDArray
+from stable_baselines3.common.policies import BasePolicy
 import torch
 from torch.utils.data import DataLoader, Dataset
 
 from roboquant.event import Event
-from roboquant.ml.envs import Action2Signals, StrategyEnv, TraderEnv
+from roboquant.ml.envs import Action2Orders, Action2Signals, StrategyEnv, TraderEnv
 from roboquant.ml.features import Feature, NormalizeFeature
 from roboquant.order import Order
 from roboquant.signal import Signal
@@ -19,7 +20,7 @@
 
 class SB3PolicyStrategy(Strategy):
 
-    def __init__(self, obs_feature: Feature, action_2_signals: Action2Signals, policy):
+    def __init__(self, obs_feature: Feature, action_2_signals: Action2Signals, policy: BasePolicy):
         super().__init__()
         self.obs_feature = obs_feature
         self.action_2_signals = action_2_signals
@@ -44,7 +45,7 @@ def reset(self):
 
 class SB3PolicyTrader(Trader):
 
-    def __init__(self, obs_feature: Feature, action_2_orders, policy):
+    def __init__(self, obs_feature: Feature, action_2_orders: Action2Orders, policy: BasePolicy):
         super().__init__()
         self.obs_feature = obs_feature
         self.action_2_orders = action_2_orders

samples/forwardtest_alpaca.py

@@ -18,7 +18,7 @@
 # %%
 # Let run an EMACrossover strategy
 strategy = rq.strategies.EMACrossover(13, 26)
-timeframe = rq.Timeframe.next(minutes=60)
+timeframe = rq.Timeframe.next(minutes=30)
 journal = rq.journals.BasicJournal()
 account = rq.run(feed, strategy, journal=journal, timeframe=timeframe)
 

samples/papertrade_alpaca.py

@@ -31,6 +31,3 @@
 # %%
 print(account)
 print(journal)
-
-
-# %%

samples/talib_strategy.py

@@ -1,10 +1,9 @@
 # %%
 import talib.stream as ta
 import roboquant as rq
-from roboquant.strategies import BarStrategy
 
 # %%
-class MyStrategy(BarStrategy):
+class MyStrategy(rq.strategies.BarStrategy):
     """Example using talib to create a combined RSI/BollingerBand strategy"""
 
     def _create_signal(self, symbol, ohlcv):
@@ -16,12 +15,12 @@ def _create_signal(self, symbol, ohlcv):
             close, timeperiod=self.size-1, nbdevup=2, nbdevdn=2
         )
 
-        price = close[-1]
+        latest_price = close[-1]
 
-        if rsi < 30 and price < lower:
-            return rq.BUY
-        if rsi > 70 and price > upper:
-            return rq.SELL
+        if rsi < 30 and latest_price < lower:
+            return rq.Signal.buy(symbol)
+        if rsi > 70 and latest_price > upper:
+            return rq.Signal.sell(symbol)
 
         return None