felixm/ML4T
1
0
Fork 0
Code Releases Activity

Improve QLearner so that commission is considered

Browse Source
This commit is contained in:
Felix Martin
2020-11-10 11:01:21 -05:00
parent 761a0366e4
commit 6e1f70bcba
2 changed files with 38 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
strategy_evaluation/QLearner.py
View File

@@ -28,18 +28,25 @@ class QLearner(object):
def row_to_state(self, holding, df_row):
"""Transforms a row into a state value."""
assert(holding in [-1000, 0, 1000])
holding = (holding + 1000) // 1000
remaining_states = self.num_states
state = holding * (remaining_states // 3)
remaining_states //= 3
assert(holding in [0, 1, 2])
# For each indicator that goes into the state the interval becomes
# smaller based on how many bins the indicator has. The first
# 'indicator' is the information about how many shares we are currently
# holding. So for example, if I have 450 states then the intervall (aka
# remaining_states) is 150 because there are three values for holding:
# holding = 0 -> state = 0 * 150 = 0
# holding = 1 -> state = 1 * 150 = 150
# holding = 2 -> state = 2 * 150 = 300
remaining_states = self.num_states // 3
state = holding * remaining_states
for indicator in self.indicators:
value = df_row[indicator]
bin_n = self.indicator_value_to_bin(indicator, value)
interval = remaining_states // self.n_bins
state += bin_n * interval
remaining_states //= self.n_bins
state += bin_n * remaining_states
return state
def indicator_value_to_bin(self, indicator, value):
@@ -103,18 +110,21 @@ class QLearner(object):
def train(self, df, symbol, sv):
holding = Holding(sv, 0, sv)
row = df.iloc[0]
state = self.row_to_state(holding.shares, row)
action = self.learner.querysetstate(state)
adj_closing_price = row[symbol]
equity = holding.equity
self.handle_order(action, holding, adj_closing_price)
for index, row in df.iloc[1:].iterrows():
adj_closing_price = row[symbol]
new_equity = holding.cash + holding.shares * adj_closing_price
r = self.get_reward(holding.equity, new_equity)
r = self.get_reward(equity, new_equity)
s_prime = self.row_to_state(holding.shares, row)
a = self.learner.query(s_prime, r)
equity = new_equity
self.handle_order(a, holding, adj_closing_price)
if self.verbose:
print(f"{holding=} {s_prime=} {r=} {a=}")