Implement marketsim without commission and impact

marketsim/marketsim.py

@@ -29,9 +29,11 @@ import pandas as pd
 import numpy as np
 import datetime as dt
 import os
+import sys
 from util import get_data, plot_data
 from optimize_something.optimization import calculate_stats
 
+
 def read_orders(orders_file):
     """
     Parser orders into the form:
@@ -48,35 +50,78 @@ def read_orders(orders_file):
         2011-01-10,AAPL,SELL,1500
     """
     orders = pd.read_csv(orders_file,
+                         index_col=['Date'],
                          dtype='|str, str, str,  i4',
-                         parse_dates=["Date"])
+                         parse_dates=['Date'])
     orders.sort_values(by="Date", inplace=True)
     return orders
 
 
 def get_order_book_info(orders):
     """Return start_date, end_date, and symbols (as a list)."""
-    start_date = orders.iloc[0].Date
-    end_date = orders.iloc[0].Date
+    start_date = orders.index[0]
+    end_date = orders.index[-1]
     symbols = sorted(list((set(orders.Symbol.tolist()))))
     return start_date, end_date, symbols
 
 
+def get_portfolio_value(holding, prices):
+    """Calculate the current portofolio value."""
+    value = 0
+    for ticker, shares in holding.items():
+        if ticker == 'cash':
+            value += shares
+        else:
+            value += shares * prices[ticker]
+    return value
+
+
+def handle_orders(orders, holding, adj_closing_prices):
+    """Process the orders."""
+    for date, order in orders.iterrows():
+        symbol, order, shares = order
+        adj_closing_price = adj_closing_prices[symbol]
+        cost = shares * adj_closing_price
+        if order == "BUY":
+            # print(f"Buy  {shares:6} of {symbol:4} on {date}")
+            holding['cash'] -= cost
+            holding[symbol] += shares
+        elif order == "SELL":
+            # print(f"Sell {shares:6} of {symbol:4} on {date}")
+            holding['cash'] += cost
+            holding[symbol] -= shares
+        else:
+            raise Exception("Unexpected order type.")
+
+
 def compute_portvals(orders_file="./orders/orders-01.csv", start_val=1000000, commission=9.95, impact=0.005):
     orders = read_orders(orders_file)
     start_date, end_date, symbols = get_order_book_info(orders)
 
-    # In the template, instead of computing the value of the portfolio, we just
-    # read in the value of IBM over 6 months
-    start_date = dt.datetime(2008, 1, 1)
-    end_date = dt.datetime(2008, 6, 1)
-    portvals = get_data(['IBM'], pd.date_range(start_date, end_date))
-    portvals = portvals[['IBM']]  # remove SPY
+    # Tickers in the orderbook over the date_range in the order book.
+    prices = get_data(symbols, pd.date_range(start_date, end_date))
+    prices['Portval'] = pd.Series(0.0, index=prices.index)
 
+    # A dictionary to keep track of the assets we are holding.
+    holding = {s: 0 for s in symbols}
+    holding['cash'] = start_val
+
+    orders_processed = 0
+    for date, values in prices.iterrows():
+        if date in orders.index:
+            current_orders = orders.loc[date:date]
+            orders_processed += current_orders.shape[0]
+            handle_orders(current_orders, holding, values)
+
+        # Compute portfolio value at the end of day.
+        values['Portval'] = get_portfolio_value(holding, values)
+
+    # Make sure we have processed all orders. If there was an order on a
+    # non-trading day we would currently not handle it.
+    assert(orders.shape[0] == orders_processed)
+
+    portvals = prices[['Portval']]
     return portvals
-    # Don't know why this was in template. Keep for now.
-    # rv = pd.DataFrame(index=portvals.index, data=portvals.values)
-    # return rv
 
 
 def test_code():
@@ -89,20 +134,14 @@ def test_code():
     else:
         raise Exception("warning, code did not return a DataFrame")
 
-    # One way of getting the portfolio dates
-    # print(portvals.index[0])
-
-    # Get portfolio stats.
-    start_date = dt.datetime(2008, 1, 1)
-    end_date = dt.datetime(2008, 6, 1)
-
-
+    start_date = portvals.index[0]
+    end_date = portvals.index[-1]
     cum_ret, avg_daily_ret, \
-    std_daily_ret, sharpe_ratio = calculate_stats(portvals.to_frame(), [1])
+        std_daily_ret, sharpe_ratio = calculate_stats(portvals.to_frame(), [1])
 
     spy = get_data(['SPY'], pd.date_range(start_date, end_date))
     cum_ret_SPY, avg_daily_ret_SPY, \
-    std_daily_ret_SPY, sharpe_ratio_SPY = calculate_stats(spy, [1])
+        std_daily_ret_SPY, sharpe_ratio_SPY = calculate_stats(spy, [1])
 
     # Compare portfolio against $SPY
     print(f"Date Range: {start_date} to {end_date}")