Implement first version of strategy learner

This version does not pass the automatic test.

strategy_evaluation/StrategyLearner.py

@@ -1,88 +1,94 @@
-"""
-Template for implementing StrategyLearner  (c) 2016 Tucker Balch
-
-Copyright 2018, Georgia Institute of Technology (Georgia Tech)
-Atlanta, Georgia 30332
-All Rights Reserved
-
-Template code for CS 4646/7646
-
-Georgia Tech asserts copyright ownership of this template and all derivative
-works, including solutions to the projects assigned in this course. Students
-and other users of this template code are advised not to share it with others
-or to make it available on publicly viewable websites including repositories
-such as github and gitlab.  This copyright statement should not be removed
-or edited.
-
-We do grant permission to share solutions privately with non-students such
-as potential employers. However, sharing with other current or future
-students of CS 7646 is prohibited and subject to being investigated as a
-GT honor code violation.
-
------do not edit anything above this line---
-
-Student Name: Tucker Balch (replace with your name)
-GT User ID: tb34 (replace with your User ID)
-GT ID: 900897987 (replace with your GT ID)
-"""
-
 import datetime as dt
 import pandas as pd
-import util as ut
+import util
+import indicators
+from BagLearner import BagLearner
+from RTLearner import RTLearner
+
 
 class StrategyLearner(object):
 
-    # constructor
+    def __init__(self, verbose=False, impact=0.0, commission=0.0, testing=False):
-    def __init__(self, verbose = False, impact=0.0, commission=0.0):
         self.verbose = verbose
         self.impact = impact
         self.commission = commission
+        self.testing = testing
 
-    # this method should create a QLearner, and train it for trading
+    def _get_volume(self):
-    def addEvidence(self, symbol = "IBM", \
+        """For reference."""
-        sd=dt.datetime(2008,1,1), \
+        volume_all = ut.get_data(syms, dates, colname="Volume")
-        ed=dt.datetime(2009,1,1), \
-        sv = 10000):
-
-        # add your code to do learning here
-
-        # example usage of the old backward compatible util function
-        syms=[symbol]
-        dates = pd.date_range(sd, ed)
-        prices_all = ut.get_data(syms, dates)  # automatically adds SPY
-        prices = prices_all[syms]  # only portfolio symbols
-        # prices_SPY = prices_all['SPY']  # only SPY, for comparison later
-        if self.verbose: print(prices)
-
-        # example use with new colname
-        volume_all = ut.get_data(syms, dates, colname = "Volume")  # automatically adds SPY
         volume = volume_all[syms]  # only portfolio symbols
         # volume_SPY = volume_all['SPY']  # only SPY, for comparison later
-        if self.verbose: print(volume)
+        if self.verbose:
+            print(volume)
 
-    # this method should use the existing policy and test it against new data
+    def _add_indicators(self, df, symbol):
-    def testPolicy(self, symbol = "IBM", \
+        """Add indicators for learning to DataFrame."""
-        sd=dt.datetime(2009,1,1), \
+        df.drop(columns=["SPY"], inplace=True)
-        ed=dt.datetime(2010,1,1), \
+        indicators.macd(df, symbol)
-        sv = 10000):
+        indicators.rsi(df, symbol)
+        indicators.price_sma(df, symbol, [8])
+        indicators.price_delta(df, symbol, 3)
+        df.dropna(inplace=True)
 
-        # here we build a fake set of trades
+    def addEvidence(self, symbol="IBM",
-        # your code should return the same sort of data
+                    sd=dt.datetime(2008, 1, 1),
-        dates = pd.date_range(sd, ed)
+                    ed=dt.datetime(2009, 1, 1),
-        prices_all = ut.get_data([symbol], dates)  # automatically adds SPY
+                    sv=10000):
-        trades = prices_all[[symbol,]]  # only portfolio symbols
+
-        # trades_SPY = prices_all['SPY']  # only SPY, for comparison later
+        self.indicators = ['macd_diff', 'rsi', 'price_sma_8']
-        trades.values[:,:] = 0 # set them all to nothing
+        df = util.get_data([symbol], pd.date_range(sd, ed))
-        trades.values[0,:] = 1000 # add a BUY at the start
+        self._add_indicators(df, symbol)
-        trades.values[40,:] = -1000 # add a SELL
+
-        trades.values[41,:] = 1000 # add a BUY
+        def classify_y(row):
-        trades.values[60,:] = -2000 # go short from long
+            if row > 0.1:
-        trades.values[61,:] = 2000 # go long from short
+                return 1
-        trades.values[-1,:] = -1000 #exit on the last day
+            elif row < -0.1:
-        if self.verbose: print(type(trades)) # it better be a DataFrame!
+                return -1
-        if self.verbose: print(trades)
+            return 0
-        if self.verbose: print(prices_all)
+
-        return trades
+        self.learner = RTLearner(leaf_size = 7)
+        # self.learner = BagLearner(RTLearner, 5, {'leaf_size': 5})
+        data_x = df[self.indicators].to_numpy()
+        y = df['pct_3'].apply(classify_y)
+        self.learner.addEvidence(data_x, y.to_numpy())
+        return y
+
+    def strat(self, data_y, orders):
+        self.holding = 0
+
+        def strat(row):
+            y = int(data_y.loc[row.name][0])
+            shares = 0
+            if self.holding == 0 and y == 1:
+                shares = 1000
+            elif self.holding == -1000 and y == 1:
+                shares = 2000
+            elif self.holding == 0 and y == -1:
+                shares = -1000
+            elif self.holding == 1000 and y == -1:
+                shares = -2000
+            self.holding += shares
+            return shares
+
+        orders["Shares"] = orders.apply(strat, axis=1)
+
+    def testPolicy(self, symbol="IBM",
+                   sd=dt.datetime(2009, 1, 1),
+                   ed=dt.datetime(2010, 1, 1),
+                   sv=10000):
+        df = util.get_data([symbol], pd.date_range(sd, ed))
+        self._add_indicators(df, symbol)
+        data_x = df[self.indicators].to_numpy()
+        data_y = pd.DataFrame(index=df.index, data=self.learner.query(data_x))
+
+        orders = pd.DataFrame(index=df.index)
+        orders["Symbol"] = symbol
+        orders["Order"] = ""
+        orders["Shares"] = 0
+        self.strat(data_y, orders)
+        if self.testing:
+            return orders
+        else:
+            return orders[["Shares"]]
 
-if __name__=="__main__":
-    print("One does not simply think up a strategy")

strategy_evaluation/experiment1.py

@@ -93,29 +93,29 @@ def compare_manual_strategies(symbol, sv, sd, ed):
 
 def experiment1():
     symbol = "JPM"
-    start_value = 10000
+    sv = 10000
     sd = dt.datetime(2008, 1, 1)  # in-sample
     ed = dt.datetime(2009, 12, 31)  # in-sample
-    # sd = dt.datetime(2010, 1, 1)  # out-sample
+    sd_out = dt.datetime(2010, 1, 1)  # out-sample
-    # ed = dt.datetime(2011, 12, 31)  # out-sample
+    ed_out = dt.datetime(2011, 12, 31)  # out-sample
+
+    df = util.get_data([symbol], pd.date_range(sd, ed_out))
+    df.drop(columns=["SPY"], inplace=True)
 
     # visualize_correlations(symbol, df)
     # plot_indicators(symbol, df)
-    # compare_manual_strategies(symbol, start_value, sd, ed)
+    # compare_manual_strategies(symbol, sv, sd, ed)
-
-    df = util.get_data([symbol], pd.date_range(sd, ed))
-    df.drop(columns=["SPY"], inplace=True)
 
     bs = BenchmarkStrategy()
-    orders = bs.testPolicy(symbol, sd, ed, start_value)
+    orders = bs.testPolicy(symbol, sd_out, ed_out, sv)
-    df["Benchmark"] = marketsim.compute_portvals(orders, start_value)
+    df["Benchmark"] = marketsim.compute_portvals(orders, sv)
     df["Orders Benchmark"] = orders["Shares"]
 
-    sl = StrategyLearner()
+    sl = StrategyLearner(testing=True)
-    orders = ms.testPolicy(symbol, sd, ed, start_value)
+    sl.addEvidence(symbol, sd, ed, sv)
-    df["SL"] = marketsim.compute_portvals(orders, start_value)
+    orders = sl.testPolicy(symbol, sd_out, ed_out, sv)
+    df["SL"] = marketsim.compute_portvals(orders, sv)
     df["Orders SL"] = orders["Shares"]
-    # df["Holding Manual"] = orders["Shares"].cumsum()
 
     fig, ax = plt.subplots(3, sharex=True)
     df[[symbol]].plot(ax=ax[0])
@@ -127,6 +127,12 @@ def experiment1():
     MultiCursor(fig.canvas, ax, color='r', lw=0.5)
     plt.show()
 
+    # For debugging the classification learner:
+    # df["y_train"] = sl.addEvidence(symbol, sd, ed, sv)
+    # df["y_query"] = sl.testPolicy(symbol, sd, ed, sv)
+    # df[["y_train", "y_query"]].plot(ax=ax[1])
+
+
 
 if __name__ == "__main__":
     experiment1()