def get_data(self, sids, start, end):
data = factory.load_bars_from_yahoo(stocks=sids,
indexes={},
start=start,
end=end)
self.sids = data.items
return data
def run_clusters(strategy_class, clustering_tickers, cluster_num, epochs_num,
training_start, training_end, backtest_start, backtest_end,
is_graph, is_elbow):
""" Run the test given command-line args.
Cluster.
For each cluster, train a strategy on that cluster.
For each stock in that cluster, run a backtest.
Graph results.
"""
print "\nGathering data..."
ticker_list, raw_stock_data_list = Manager.getRawStockDataList(
clustering_tickers, training_start, training_end, 252)
normalized_stock_data_list = [
Manager.preprocessData(x) for x in raw_stock_data_list
]
print "\nClustering..."
tickers, clusters = createClusters(ticker_list, normalized_stock_data_list,
cluster_num)
print "# of stocks: " + str(len(normalized_stock_data_list))
print "# of clusters: " + str(len(clusters))
print ""
for t, c in itertools.izip(tickers, clusters):
print "\tCluster: " + str(len(c)), "stocks: ",
for symbol in t:
print symbol,
print ""
if is_graph:
graphClusters(clusters)
if is_elbow:
graphElbowMethod(normalized_stock_data_list)
for t, cluster in itertools.izip(tickers, clusters):
settings.STRATEGY_OBJECT = trainStrategy(strategy_class, cluster,
epochs_num)
for ticker in t:
print "Cluster:", t
print "Stock:", ticker
tmp_ticks, tmp_data = Manager.getRawStockDataList([ticker],
training_start,
training_end,
252)
settings.BACKTEST_STOCK = ticker
settings.PRE_BACKTEST_DATA = tmp_data[0]
print "Create Algorithm..."
algo_obj = TradingAlgorithm(initialize=initialize,
handle_data=handle_data)
try:
backtest_data = load_bars_from_yahoo(stocks=[ticker, 'SPY'],
start=backtest_start,
end=backtest_end)
try:
perf = algo_obj.run(backtest_data)
analyze([ticker], [perf])
except ValueError, e:
print str(e)
except IOError, e:
print "Stock Error: could not load", ticker, "from Yahoo."
print "Only testing one cluster for now - Done!"
return
def test_yahoo_bars_to_panel_source(self, env=None):
stocks = ['AAPL', 'GE']
start = pd.datetime(1993, 1, 1, 0, 0, 0, 0, pytz.utc)
end = pd.datetime(2002, 1, 1, 0, 0, 0, 0, pytz.utc)
data = factory.load_bars_from_yahoo(stocks=stocks,
indexes={},
start=start,
end=end)
check_fields = [
'sid', 'open', 'high', 'low', 'close', 'volume', 'price'
]
source = DataPanelSource(data)
sids = [
asset.sid for asset in [
env.asset_finder.lookup_symbol(symbol, as_of_date=end)
for symbol in stocks
]
]
stocks_iter = cycle(sids)
for event in source:
for check_field in check_fields:
self.assertIn(check_field, event)
self.assertTrue(isinstance(event['volume'], (integer_types)))
self.assertEqual(next(stocks_iter), event['sid'])
def test_yahoo_bars_to_panel_source(self):
env = TradingEnvironment()
finder = AssetFinder(env.engine)
stocks = ['AAPL', 'GE']
env.write_data(equities_identifiers=stocks)
start = pd.datetime(1993, 1, 1, 0, 0, 0, 0, pytz.utc)
end = pd.datetime(2002, 1, 1, 0, 0, 0, 0, pytz.utc)
data = factory.load_bars_from_yahoo(stocks=stocks,
indexes={},
start=start,
end=end)
check_fields = ['sid', 'open', 'high', 'low', 'close',
'volume', 'price']
copy_panel = data.copy()
sids = finder.map_identifier_index_to_sids(
data.items, data.major_axis[0]
)
copy_panel.items = sids
source = DataPanelSource(copy_panel)
for event in source:
for check_field in check_fields:
self.assertIn(check_field, event)
self.assertTrue(isinstance(event['volume'], (integer_types)))
self.assertTrue(event['sid'] in sids)
def test_yahoo_bars_to_panel_source(self):
env = TradingEnvironment()
finder = AssetFinder(env.engine)
stocks = ['AAPL', 'GE']
env.write_data(equities_identifiers=stocks)
start = pd.datetime(1993, 1, 1, 0, 0, 0, 0, pytz.utc)
end = pd.datetime(2002, 1, 1, 0, 0, 0, 0, pytz.utc)
data = factory.load_bars_from_yahoo(stocks=stocks,
indexes={},
start=start,
end=end)
check_fields = [
'sid', 'open', 'high', 'low', 'close', 'volume', 'price'
]
copy_panel = data.copy()
sids = finder.map_identifier_index_to_sids(data.items,
data.major_axis[0])
copy_panel.items = sids
source = DataPanelSource(copy_panel)
for event in source:
for check_field in check_fields:
self.assertIn(check_field, event)
self.assertTrue(isinstance(event['volume'], (integer_types)))
self.assertTrue(event['sid'] in sids)
def prepare_data(ticker,
maMethod='ema',
maPeriod=20,
lookAheadDays=3,
start='',
end='',
useYahoo=False):
if not end:
now = datetime.datetime.now()
end = now.strftime('%Y%m%d')
if not start:
start = (datetime.datetime.strptime(end, '%Y%m%d') +
datetime.timedelta(days=-365 * 5)).strftime('%Y%m%d')
if useYahoo:
from zipline.utils.factory import load_bars_from_yahoo
tmpStart = datetime.datetime.strptime(start, '%Y%m%d')
ystart = datetime.datetime(tmpStart.year, tmpStart.month, tmpStart.day,
0, 0, 0, 0, pytz.utc)
tmpEnd = datetime.datetime.strptime(end, '%Y%m%d')
yend = datetime.datetime(tmpEnd.year, tmpEnd.month, tmpEnd.day, 0, 0,
0, 0, pytz.utc)
stockDf = load_bars_from_yahoo(stocks=[ticker],
start=ystart,
end=yend,
adjusted=False)[ticker].reset_index()
stockDf['TradeDate'] = stockDf['Date'].apply(
lambda x: x.strftime('%Y%m%d'))
stockDf = stockDf[[
'open', 'high', 'low', 'close', 'volume', 'TradeDate'
]]
stockDf.rename(columns={
'open': 'Open',
'high': 'High',
'low': 'Low',
'close': 'Close',
'volume': 'Volume'
},
inplace=True)
else:
sys.path.insert(0, '/home/jinwb/code/IIA/jsforesight/datamodel')
from TickerEodModel import TickerEodModel
eodM = TickerEodModel('testEventDbConfigKey')
stockDf = eodM.get_eod(ticker, start, end)
emaDf = pd.DataFrame(index=stockDf.index)
emaDf['OrigClose'] = stockDf['Close']
emaDf['OrigVolume'] = stockDf['Volume']
emaDf['TradeDate'] = stockDf['TradeDate']
emaDf['PctChg'] = stockDf['Close'].pct_change(periods=lookAheadDays)
emaDf['index'] = emaDf.index
if maMethod.lower() == 'ema':
emaDf['Close'] = ta.EMA(stockDf['Close'].values, maPeriod)
emaDf['Volume'] = ta.EMA(stockDf['Volume'].values, maPeriod)
else:
emaDf['Close'] = ta.MA(stockDf['Close'].values, maPeriod)
emaDf['Volume'] = ta.MA(stockDf['Volume'].values, maPeriod)
print emaDf.tail(10)
return emaDf
def loadData(startYear, endYear, stock_list, startM=1, endM=1): """ Load data, stored as (open, high, low, close, volume, price). Must convert pandas.Panel --> pandas.DataFrame --> List of Lists """ start = datetime(startYear, startM, 1, 0, 0, 0, 0, pytz.utc) end = datetime(endYear, endM, 1, 0, 0, 0, 0, pytz.utc) data = load_bars_from_yahoo(stocks=stock_list, start=start, end=end) return data
def load_data():
"""Load stock data
Both training and testing data
"""
# Load data manually from Yahoo! finance
# Training data
start_train_data = datetime(2010, 1, 1, 0, 0, 0, 0, pytz.utc)
end_train_data = datetime(2014, 1, 1, 0, 0, 0, 0, pytz.utc)
data_train = load_bars_from_yahoo(stocks=['AAPL'],
start=start_train_data,
end=end_train_data)
# Testing data
start_test_data = datetime(2014, 1, 1, 0, 0, 0, 0, pytz.utc)
end_test_data = datetime(2016, 1, 1, 0, 0, 0, 0, pytz.utc)
data_test = load_bars_from_yahoo(stocks=['AAPL'],
start=start_test_data,
end=end_test_data)
return [data_train, data_test]
def load_data():
data_file_name = "data.hdf"
if os.path.exists(data_file_name):
data = pd.read_hdf(data_file_name, 'data', format='fixed')
return data
start = dt.datetime(2010, 1, 1, 0, 0, 0, 0, pytz.utc)
end = dt.datetime(2014, 1, 2, 0, 0, 0, 0, pytz.utc)
symbols = ["LUV", "VRTX"]
data = load_bars_from_yahoo(stocks=symbols, start=start, end=end)
data.to_hdf(data_file_name, 'data', format='fixed')
return data
def prepare_data(tickers, start='', end=''):
assert isinstance(tickers, list)
if not end:
now = datetime.datetime.now()
end = now.strftime('%Y%m%d')
if not start:
start = (datetime.datetime.strptime(end, '%Y%m%d')+datetime.timedelta(days=-365*5)).strftime('%Y%m%d')
tmpStart = datetime.datetime.strptime(start, '%Y%m%d')
ystart = datetime.datetime(tmpStart.year, tmpStart.month, tmpStart.day, 0, 0, 0 ,0, pytz.utc)
tmpEnd = datetime.datetime.strptime(end, '%Y%m%d')
yend = datetime.datetime(tmpEnd.year, tmpEnd.month, tmpEnd.day, 0, 0, 0, 0, pytz.utc)
stockDf = load_bars_from_yahoo(stocks=tickers, start=ystart, end=yend, adjusted=True)
return stockDf.dropna()
def run_clusters(strategy_class, clustering_tickers, cluster_num, epochs_num, training_start,
training_end, backtest_start, backtest_end, is_graph, is_elbow):
""" Run the test given command-line args.
Cluster.
For each cluster, train a strategy on that cluster.
For each stock in that cluster, run a backtest.
Graph results.
"""
print "\nGathering data..."
ticker_list, raw_stock_data_list = Manager.getRawStockDataList(clustering_tickers, training_start, training_end, 252)
normalized_stock_data_list = [Manager.preprocessData(x) for x in raw_stock_data_list]
print "\nClustering..."
tickers, clusters = createClusters(ticker_list, normalized_stock_data_list, cluster_num)
print "# of stocks: " + str(len(normalized_stock_data_list))
print "# of clusters: " + str(len(clusters))
print ""
for t, c in itertools.izip(tickers, clusters):
print "\tCluster: " + str(len(c)), "stocks: ",
for symbol in t:
print symbol,
print ""
if is_graph:
graphClusters(clusters)
if is_elbow:
graphElbowMethod(normalized_stock_data_list)
for t, cluster in itertools.izip(tickers, clusters):
settings.STRATEGY_OBJECT = trainStrategy(strategy_class, cluster, epochs_num)
for ticker in t:
print "Cluster:", t
print "Stock:", ticker
tmp_ticks, tmp_data = Manager.getRawStockDataList([ticker], training_start, training_end, 252)
settings.BACKTEST_STOCK = ticker
settings.PRE_BACKTEST_DATA = tmp_data[0]
print "Create Algorithm..."
algo_obj = TradingAlgorithm(initialize=initialize, handle_data=handle_data)
try:
backtest_data = load_bars_from_yahoo(stocks=[ticker, 'SPY'], start=backtest_start, end=backtest_end)
try:
perf = algo_obj.run(backtest_data)
analyze([ticker], [perf])
except ValueError, e:
print str(e)
except IOError, e:
print "Stock Error: could not load", ticker, "from Yahoo."
print "Only testing one cluster for now - Done!"
return
def loadTrainingData(ticker, start, end):
""" Data stored as (open, high, low, close, volume, price)
Only take adjusted (open, high, low, close)
"""
data = load_bars_from_yahoo(stocks=[ticker], start=start, end=end)
data = Manager.convertPanelToList(data)
data = ([
([ x[0]-x[0], # open
x[1]-x[0], # high
x[2]-x[0], # low
x[3]-x[0], # close
#x[4], # volume
#x[5], # price (same as close)
]) for x in data # data stored as (open, high, low, close, volume, price)
])
return data
def test_load_bars_from_yahoo(self):
stocks = ['AAPL', 'GE']
start = pd.datetime(1993, 1, 1, 0, 0, 0, 0, pytz.utc)
end = pd.datetime(2002, 1, 1, 0, 0, 0, 0, pytz.utc)
data = load_bars_from_yahoo(stocks=stocks, start=start, end=end)
assert data.major_axis[0] == pd.Timestamp('1993-01-04 00:00:00+0000')
assert data.major_axis[-1] == pd.Timestamp('2001-12-31 00:00:00+0000')
for stock in stocks:
assert stock in data.items
for ohlc in ['open', 'high', 'low', 'close', 'volume', 'price']:
assert ohlc in data.minor_axis
np.testing.assert_raises(
AssertionError, load_bars_from_yahoo, stocks=stocks,
start=end, end=start
)
def loadTrainingData(ticker, start, end):
""" Data stored as (open, high, low, close, volume, price)
Only take adjusted (open, high, low, close)
"""
data = load_bars_from_yahoo(stocks=[ticker], start=start, end=end)
data = Manager.convertPanelToList(data)
data = ([
([
x[0], # open
x[1], # high
x[2], # low
x[3], # close
#x[4], # volume
#x[5], # price (same as close)
]) for x in
data # data stored as (open, high, low, close, volume, price)
])
return data
def test_load_bars_from_yahoo(self):
stocks = ['AAPL', 'GE']
start = pd.datetime(1993, 1, 1, 0, 0, 0, 0, pytz.utc)
end = pd.datetime(2002, 1, 1, 0, 0, 0, 0, pytz.utc)
data = load_bars_from_yahoo(stocks=stocks, start=start, end=end)
assert data.major_axis[0] == pd.Timestamp('1993-01-04 00:00:00+0000')
assert data.major_axis[-1] == pd.Timestamp('2001-12-31 00:00:00+0000')
for stock in stocks:
assert stock in data.items
for ohlc in ['open', 'high', 'low', 'close', 'volume', 'price']:
assert ohlc in data.minor_axis
np.testing.assert_raises(
AssertionError, load_bars_from_yahoo, stocks=stocks,
start=end, end=start
)
def test_yahoo_bars_to_panel_source(self):
stocks = ['AAPL', 'GE']
start = pd.datetime(1993, 1, 1, 0, 0, 0, 0, pytz.utc)
end = pd.datetime(2002, 1, 1, 0, 0, 0, 0, pytz.utc)
data = factory.load_bars_from_yahoo(stocks=stocks,
indexes={},
start=start,
end=end)
check_fields = ['sid', 'open', 'high', 'low', 'close',
'volume', 'price']
source = DataPanelSource(data)
stocks_iter = cycle(stocks)
for event in source:
for check_field in check_fields:
self.assertIn(check_field, event)
self.assertTrue(isinstance(event['volume'], (integer_types)))
self.assertEqual(next(stocks_iter), event['sid'])
def test_yahoo_bars_to_panel_source(self):
stocks = ['AAPL', 'GE']
start = pd.datetime(1993, 1, 1, 0, 0, 0, 0, pytz.utc)
end = pd.datetime(2002, 1, 1, 0, 0, 0, 0, pytz.utc)
data = factory.load_bars_from_yahoo(stocks=stocks,
start=start,
end=end)
source = DataPanelSource(data)
for event in source:
self.assertTrue('sid' in event)
self.assertTrue('open' in event)
self.assertTrue('high' in event)
self.assertTrue('low' in event)
self.assertTrue('close' in event)
self.assertTrue('volume' in event)
self.assertTrue('price' in event)
self.assertTrue(isinstance(event['volume'], (int, long)))
def test_yahoo_bars_to_panel_source(self):
stocks = ['AAPL', 'GE']
start = pd.datetime(1993, 1, 1, 0, 0, 0, 0, pytz.utc)
end = pd.datetime(2002, 1, 1, 0, 0, 0, 0, pytz.utc)
data = factory.load_bars_from_yahoo(stocks=stocks,
indexes={},
start=start,
end=end)
check_fields = ['sid', 'open', 'high', 'low', 'close',
'volume', 'price']
source = DataPanelSource(data)
stocks_iter = cycle(stocks)
for event in source:
for check_field in check_fields:
self.assertIn(check_field, event)
self.assertTrue(isinstance(event['volume'], (int, long)))
self.assertEqual(stocks_iter.next(), event['sid'])
def markowitz(stocks, cash):
warnings.filterwarnings("once")
solvers.options['show_progress'] = False
end = pd.Timestamp.utcnow()
start = end - 50 * pd.tseries.offsets.BDay()
data = load_bars_from_yahoo(stocks=stocks, start=start, end=end)
# Instantinate algorithm
algo = TradingAlgorithm(initialize=initialize,
handle_data=handle_data,
cash=cash)
# Run algorithm
results = algo.run(data)
# portfolio value plot
raw_plot = results.portfolio_value.plot()
raw_fig = raw_plot.get_figure()
returns_plot = mpld3.fig_to_html(raw_fig)
raw_fig.clf()
#stock price plot
raw_price_data = data.loc[:, :, 'price'].pct_change(1).fillna(0).applymap(
lambda x: x + 1).cumprod().applymap(lambda x: x * 100)
raw_price_plot = raw_price_data.plot(figsize=(8, 5))
raw_price_fig = raw_price_plot.get_figure()
price_plot = mpld3.fig_to_html(raw_price_fig)
raw_price_fig.clf()
#final returns
equalweight_returns = sum(map(list,
raw_price_data.tail(1).values)[0]) / 4 - 100
equalweight_returns = '{0:.2f}%'.format(float(equalweight_returns))
optimal_returns = (results.portfolio_value.tail(1).iloc[0] - 100000) / 1000
optimal_returns = '{0:.2f}%'.format(float(optimal_returns))
#efficient frontier plot
frontier_plot_data = open("plot.png", "rb").read()
# serialize to HTTP response
frontier_plot = HttpResponse(frontier_plot_data, content_type="image/png")
return (results, returns_plot, price_plot, frontier_plot,
equalweight_returns, optimal_returns)
def fetch_equities_daily(self, symbols, ohlc=False, r_type=False, returns=False, **kwargs):
if len(symbols) == 0:
return pd.DataFrame()
if isinstance(symbols, str):
symbols = symbols.split(",")
if ohlc:
data = load_bars_from_yahoo(stocks=symbols, **kwargs)
# data.items = symbols
else:
data = load_from_yahoo(stocks=symbols, **kwargs)
# data.columns = symbols
# NOTE Would it work with a pandas panel ?
if returns:
data = ((data - data.shift(1)) / data).fillna(method="bfill")
if r_type:
data = convert_to_r_matrix(data)
return data
def markowitz(stocks, cash):
warnings.filterwarnings("once")
solvers.options['show_progress'] = False
end = pd.Timestamp.utcnow()
start = end - 50 * pd.tseries.offsets.BDay()
data = load_bars_from_yahoo(stocks=stocks,
start=start, end=end)
# Instantinate algorithm
algo = TradingAlgorithm(initialize=initialize,
handle_data=handle_data, cash=cash)
# Run algorithm
results = algo.run(data)
# portfolio value plot
raw_plot = results.portfolio_value.plot()
raw_fig = raw_plot.get_figure()
returns_plot = mpld3.fig_to_html(raw_fig)
raw_fig.clf()
#stock price plot
raw_price_data = data.loc[:, :, 'price'].pct_change(1).fillna(0).applymap(lambda x: x + 1).cumprod().applymap(lambda x: x * 100)
raw_price_plot = raw_price_data.plot(figsize=(8,5))
raw_price_fig = raw_price_plot.get_figure()
price_plot = mpld3.fig_to_html(raw_price_fig)
raw_price_fig.clf()
#final returns
equalweight_returns = sum(map(list, raw_price_data.tail(1).values)[0]) / 4 - 100
equalweight_returns = '{0:.2f}%'.format(float(equalweight_returns))
optimal_returns = (results.portfolio_value.tail(1).iloc[0] - 100000) / 1000
optimal_returns = '{0:.2f}%'.format(float(optimal_returns))
#efficient frontier plot
frontier_plot_data = open("plot.png", "rb").read()
# serialize to HTTP response
frontier_plot = HttpResponse(frontier_plot_data, content_type="image/png")
return(results, returns_plot, price_plot, frontier_plot, equalweight_returns, optimal_returns)
def get_prices(symbols, dt_start, dt_end):
""" Returns the 'adjusted' prices for the given timespan and the given symbols.
Args:
symbols [str]: The list of symbols
dt_start (datetime): The data for the first t
dt_end (datetime):
Returns:
Returns a pandas dataframe with the closing prices for the given symbols in the given timespan.
"""
try:
prices = load_bars_from_yahoo(stocks=symbols, start=dt_start, end=dt_end)
except RemoteDataError as e:
msg = "An error occurred reading the prices for the given symbols." \
"Please make sure that the stock symbols are valid: {}".format(e)
logging.getLogger().warning(msg)
raise RemoteDataError(msg)
return prices
def fetch_equities_daily(self, equities, ohlc=False,
r_type=False, returns=False, **kwargs):
if len(equities) == 0:
return pd.DataFrame()
if isinstance(equities, str):
equities = equities.split(',')
symbols = [self.datafeed.guess_name(equity) for equity in equities]
if ohlc:
data = load_bars_from_yahoo(stocks=symbols, **kwargs)
data.items = equities
else:
data = load_from_yahoo(stocks=symbols, **kwargs)
data.columns = equities
#NOTE Would it work with a pandas panel ?
if returns:
data = ((data - data.shift(1)) / data).fillna(method='bfill')
if r_type:
data = convert_to_r_matrix(data)
return data
def preproc_data():
"""Preprocess raw data into TP Matrix format"""
# Load data manually from Yahoo! finance
start = datetime(2009, 1, 1, 0, 0, 0, 0, pytz.utc)
end = datetime(2016, 1, 1, 0, 0, 0, 0, pytz.utc)
data = load_bars_from_yahoo(stocks=['AAPL'], start=start, end=end)
# Initialize TP Matrix
# 3-dimension: # of stock * 18 * 18
# narray
_TP_matrixs = np.zeros((len(data.ix['AAPL']) - 230, 18, 18), dtype=np.bool)
TP_matrixs = pd.Panel(_TP_matrixs, items=data.ix['AAPL'].index[230:])
# Construct TP Matrix
for TP_matrix in TP_matrixs.iteritems():
# Extract raw close price of last 230 days
_list_CP = data.ix['AAPL'][
data.ix['AAPL'].index < TP_matrix[0]]['close'].tolist()
list_CP = _list_CP[len(_list_CP) - 230:len(_list_CP)]
# col[0, 8] for Upward TP Matrix
# col[9, 17] for Downward TP Matrix
for col in range(0, 18):
D = columns[col][0] - 1
for row in range(0, 18):
# For each element of TP Matrix
for TP in range(D, columns[col][1]):
# Change ratio of stock on day D with repect to the price
# at TP
C_TPD = (list_CP[TP] - list_CP[D]) / list_CP[D]
if C_TPD * 100 >= rows[row][0] and C_TPD * 100 < rows[row][
1]:
TP_matrix[1][row][col] = True
break
return TP_matrixs
def get_data(self, sids, start, end):
data = factory.load_bars_from_yahoo(
stocks=sids, indexes={}, start=start, end=end)
self.sids = data.items
return data
import talib
import numpy as np
# Set the start and end dates
start = datetime(2000, 1, 1, 0, 0, 0, 0, pytz.utc)
end = datetime(2016, 4, 30, 0, 0, 0, 0, pytz.utc)
index = {'SPX': '^GSPC'}
stock = None
time_period = 30 # Techinical Indicators time period
pred_window = 1 # prediction window in days
train_ratio = 0.7 # training records ratio
fold_number = 5 # How many folder
# Load data from Yahoo Finance
data = load_bars_from_yahoo(indexes=index, stocks=stock, start=start, end=end)
print data[index.keys()[0]].describe()
# Exploratory analysis
get_ipython().magic(u'matplotlib inline')
import pandas as pd
import matplotlib.pyplot as plt
import matplotlib
matplotlib.style.use('ggplot')
sname = index.keys()[0]
vol = data[sname][['volume']]
bars = data[sname][['open', 'high', 'low', 'close', 'price']]
ax = bars.plot(figsize=(8, 6),
title='(a) 2001-2016 Historical Price of S&P 500 Index')
from zipline.algorithm import TradingAlgorithm
from zipline.utils.factory import load_bars_from_yahoo
#from zipline import run_algorithm
import matplotlib.pyplot as plt
###------------------------------------------------------------------Packages Imported--------------------------
#assign_stock = 'SPY'
assign_stock = 'XLB'
#assign_stock = 'BHANDHOS.BO'
#assign_stock = 'AAPL'
#assign_stock = 'MSFT'
#assign_stock = 'WIPRO.BO'
start = datetime(2014,1,1, 0, 0, 0, 0, pytz.utc).date()
end = datetime(2016,1,1,0,0,0,0, pytz.utc).date()
#data = load_bars_from_yahoo(stocks=['SPY'], start=start,end=end)
data = load_bars_from_yahoo(stocks=[assign_stock], start=start,end=end)
def initialize(context):
#context.stocks = symbols('XLY', # XLY Consumer Discrectionary SPDR Fund
# 'XLF', # XLF Financial SPDR Fund
# 'XLK', # XLK Technology SPDR Fund
# 'XLE', # XLE Energy SPDR Fund
# 'XLV', # XLV Health Care SPRD Fund
# 'XLI', # XLI Industrial SPDR Fund
# 'XLP', # XLP Consumer Staples SPDR Fund
# 'XLB', # XLB Materials SPDR Fund
# 'XLU') # XLU Utilities SPRD Fund
#context.stocks = symbol('SPY')
context.stocks = symbol('XLB')
context.historical_bars = 100
import talib
import numpy as np
# Set the start and end dates
start = datetime(2000, 1, 1, 0, 0, 0, 0, pytz.utc)
end = datetime(2016, 4, 30, 0, 0, 0, 0, pytz.utc)
index = {'SPX': '^GSPC'}
stock = None
time_period = 30 # Techinical Indicators time period
pred_window = 1 # prediction window in days
train_ratio = 0.7 # training records ratio
fold_number = 5 # How many folder
# Load data from Yahoo Finance
data = load_bars_from_yahoo(indexes=index, stocks=stock, start=start, end=end)
print data[index.keys()[0]].describe()
# Exploratory analysis
get_ipython().magic(u'matplotlib inline')
import pandas as pd
import matplotlib.pyplot as plt
import matplotlib
matplotlib.style.use('ggplot')
sname = index.keys()[0]
vol = data[sname][['volume']]
bars = data[sname][['open', 'high', 'low', 'close', 'price']]
ax = bars.plot(figsize=(8,6), title='(a) 2001-2016 Historical Price of S&P 500 Index')
print str(date)[0:10],'LONG:',sym
elif self.portfolio.positions[sym].amount != 0:
if sym_price >= self.atr_plot[sym]['profit'][-1] or sym_price <= self.atr_plot[sym]['loss'][-1]:
q = self.portfolio.positions[sym].amount
self.order(sym,-q)
print str(date)[0:10],'Exit:',sym
else:
self.zscores[sym].append(0)
self.zscores_s[sym].append(0)
atr = self.get_atr(sym)[-1]
self.atr_plot[sym]['profit'].append((atr*3)+sym_price)
self.atr_plot[sym]['loss'].append(-(atr*3)+sym_price)
self.day_count += 1
if __name__ == '__main__':
data = load_bars_from_yahoo(stocks=sym_list, indexes={}, start=start, end=end)
trend_trader = trend_trader()
results = trend_trader.run(data)
###########################################################################
# Generate metrics
print 'Generating Risk Report...........'
print 'Using S&P500 as benchmark........'
start = results.first_valid_index().replace(tzinfo=pytz.utc)
end = results.last_valid_index().replace(tzinfo=pytz.utc)
env = trading.SimulationParameters(start, end)
returns_risk = create_returns_from_list(results.returns, env)
algo_returns = RiskMetricsBase(start, end, returns_risk).algorithm_period_returns
benchmark_returns = RiskMetricsBase(start, end, returns_risk).benchmark_period_returns
# Show the plot.
plt.gcf().set_size_inches(18, 8)
plt.show()
# Note: this if-block should be removed if running
# this algorithm on quantopian.com
if __name__ == '__main__':
from datetime import datetime
import pytz
from zipline.algorithm import TradingAlgorithm
from zipline.utils.factory import load_bars_from_yahoo
asset = "VRX"
print "--->>> Some more changes"
# Set the simulation start and end dates
start = datetime(2015, 1, 1, 0, 0, 0, 0, pytz.utc)
end = datetime(2015, 11, 1, 0, 0, 0, 0, pytz.utc)
# Load price data from yahoo.
data = load_bars_from_yahoo(stocks=[asset], indexes={}, start=start, end=end, adjusted=False)
# Create and run the algorithm.
algo = TradingAlgorithm(initialize=initialize, handle_data=handle_data,
identifiers=[asset])
results = algo.run(data)
#analyze(results=results, asset=asset)
inverse_period = 1.0 / ( dateDelta.days / ( period / 12 ) )
else:
cagr_period = "DAILY"
inverse_period = 1.0 / ( dateDelta.days )
performance = ( self.portfolio.portfolio_value / self.cashStart )
cagr = pow( performance, inverse_period ) - 1.0
print( '%s: %s CAGR %s%%, PNL $%s, CASH $%s, PORTFOLIO $%s' % ( dateStr, cagr_period, ( cagr * 100 ), self.portfolio.pnl, self.portfolio.cash, self.portfolio.portfolio_value ) )
return cagr
# # END OF CLASS GMRE
# Remove previous Yahoo download content to assure clean backtest
# cmd = removeCommand + ' ' + ziplineDataPath
# returnCode = call(cmd, shell=True)
# if returnCode != 0:
# print("Couldn't %s :: %s" % (cmd, returnCode))
# sys.exit()
start = datetime( *startDateTime )
end = datetime( *endDateTime )
data = load_bars_from_yahoo( stocks = basket, indexes = {}, start = start, end = end, adjusted = priceAdjusted )
gmre = GMRE()
perf = gmre.run( data )
# Get the CAGR
gmre.cagr()
def get_data(self, start, end=None):
if end is None:
end = pd.Timestamp.utcnow()
return load_bars_from_yahoo(stocks=self,
start=pd.Timestamp(start, tz='utc'),
end=pd.Timestamp(end, tz='utc'))
plt.show()
# Note: this if-block should be removed if running
# this algorithm on quantopian.com
if __name__ == '__main__':
from datetime import datetime
import pytz
from zipline.algorithm import TradingAlgorithm
from zipline.utils.factory import load_bars_from_yahoo
# Set the simulation start and end dates.
start = datetime(2011, 1, 1, 0, 0, 0, 0, pytz.utc)
end = datetime(2013, 1, 1, 0, 0, 0, 0, pytz.utc)
# Load price data from yahoo.
data = load_bars_from_yahoo(
stocks=['AAPL'],
indexes={},
start=start,
end=end,
)
# Create and run the algorithm.
algo = TradingAlgorithm(initialize=initialize, handle_data=handle_data)
results = algo.run(data)
# Plot the portfolio and asset data.
analyze(results=results)
>>> print proj
array([ 0.33333333, 0.23333333, 0. , 0.43333333])
>>> print proj.sum()
1.0
Original matlab implementation: John Duchi ([email protected])
Python-port: Copyright 2013 by Thomas Wiecki ([email protected]).
"""
v = np.asarray(v)
p = len(v)
# Sort v into u in descending order
v = (v > 0) * v
u = np.sort(v)[::-1]
sv = np.cumsum(u)
rho = np.where(u > (sv - b) / np.arange(1, p+1))[0][-1]
theta = np.max([0, (sv[rho] - b) / (rho+1)])
w = (v - theta)
w[w < 0] = 0
return w
if __name__ == '__main__':
import pylab as pl
data = load_bars_from_yahoo(stocks=STOCKS, indexes={})
olmar = OLMAR()
results = olmar.run(data)
results.portfolio_value.plot()
pl.show()
inverse_period = 1.0 / ( dateDelta.days / ( period / 12 ) )
else:
cagr_period = "Daily"
inverse_period = 1.0 / ( dateDelta.days )
performance = ( self.portfolio.portfolio_value / self.cashStart )
cagr = pow( performance, inverse_period ) - 1.0
print( '%s: %s CAGR %s%%, PNL $%s, CASH $%s, PORTFOLIO $%s' % ( dateStr, cagr_period, ( cagr * 100 ), self.portfolio.pnl, self.portfolio.cash, self.portfolio.portfolio_value ) )
return cagr
# # END OF CLASS GMRE
# Remove previous Yahoo download content to assure clean backtest
# cmd = removeCommand + ' ' + ziplineDataPath
# returnCode = call(cmd, shell=True)
# if returnCode != 0:
# print("Couldn't %s :: %s" % (cmd, returnCode))
# sys.exit()
start = datetime( *startDateTime )
end = datetime( *endDateTime )
data = load_bars_from_yahoo( stocks = basket, indexes = {}, start = start, end = end, adjusted = priceAdjusted )
gmre = GMRE()
perf = gmre.run( data )
# Get the CAGR
gmre.cagr()
def fetch(tickers, tBeg, tEnd, adjusted=False):
return load_bars_from_yahoo(stocks=tickers, indexes={}, start=tBeg, end=tEnd, adjusted=adjusted)
# Instantiate log
mylogger = MyLogger()
# Log directory
directory_log = str(datetime.now())[0:19].replace(':', '-')
# Create log directory
os.makedirs('log/' + stock_name + '/' + directory_log)
# Add file handle to mylogger
mylogger.addFileHandler(directory_log)
# Load data
start_date = datetime(2014, 1, 1, 0, 0, 0, 0, pytz.utc)
end_date = datetime(2016, 1, 1, 0, 0, 0, 0, pytz.utc)
data = load_bars_from_yahoo(stocks=[stock_name],
start=start_date,
end=end_date)
# Create algorithm object passing in initialize and
# handle_data functions
capital_base = 100000
algo_obj = TradingAlgorithm(initialize=initialize,
handle_data=handle_data,
analyze=analyze,
data_frequency='daily',
capital_base=capital_base)
# Run algorithm
perf = algo_obj.run(data)
def fetch(tickers, tBeg, tEnd, adjusted=False):
return load_bars_from_yahoo(stocks=tickers,
indexes={},
start=tBeg,
end=tEnd,
adjusted=adjusted)
# 3: ('HAS', '2/20/2013'),
# 4: ('INTC', '3/12/2012'),
# 5: ('GMCR', '2/20/2013'),
# 6: ('CRM', '12/12/2005'),
# 7: ('VRTX', '8/26/2013'),
# 8: ('DPM', '12/12/2012'),
# 9:('YHOO', '8/14/2002'),
# 10:('GOOGL', '6/24/2005'),
# 11:('FCX', '3/4/2004'),
}
purchases = pd.DataFrame(
{i: (X[i][0], pd.to_datetime(pd.Timestamp(X[i][1], tz='utc')))
for i in X}).T
purchases.columns = columns = ['symbol', 'Date']
data = load_bars_from_yahoo(stocks=purchases.symbol)
prices = data.minor_xs('price')
prices
def thing(days_back, days_ahead):
data = {}
delta = datetime.timedelta
for i in purchases.index:
ticker, dt = purchases.ix[i]
before = dt - delta(days=days_back)
after = dt + delta(days=days_ahead)
data[i] = prices[ticker].truncate(before=before, after=after).dropna()
return data
if __name__ == '__main__':
from datetime import datetime
import pytz
from zipline.algorithm import TradingAlgorithm
from zipline.utils.factory import load_bars_from_yahoo
import pandas as pd
import matplotlib.pyplot as plt
# Create and run the algorithm.
algo = TradingAlgorithm(initialize=initialize, handle_data=handle_data)
start = datetime(2010, 5, 1, 0, 0, 0, 0, pytz.utc)
end = datetime(2016, 5, 31, 0, 0, 0, 0, pytz.utc)
print('Getting Yahoo data for 30 DJIA stocks and DIA ETF as benchmark...')
data = load_bars_from_yahoo(stocks=tickers, start=start, end=end)
# Check price data
data.loc[:, :, 'price'].plot(figsize=(8,7), title='Input Price Data')
plt.ylabel('price in $');
plt.legend(loc='center left', bbox_to_anchor=(1.0, 0.5))
plt.show()
# Run algorithm
results = algo.run(data)
# Fix possible issue with timezone
results.index = results.index.normalize()
if results.index.tzinfo is None:
results.index = results.index.tz_localize('UTC')
# Adjust benchmark returns for delayed trading due to 3 year min data window
portfolios = [solvers.qp(mu * S, -pbar, G, h, A, b)['x'] for mu in mus]
## CALCULATE RISKS AND RETURNS FOR FRONTIER
returns = [blas.dot(pbar, x) for x in portfolios]
risks = [np.sqrt(blas.dot(x, S * x)) for x in portfolios]
## CALCULATE THE 2ND DEGREE POLYNOMIAL OF THE FRONTIER CURVE
m1 = np.polyfit(returns, risks, 2)
x1 = np.sqrt(m1[2] / m1[0])
# CALCULATE THE OPTIMAL PORTFOLIO
wt = solvers.qp(opt.matrix(x1 * S), -pbar, G, h, A, b)['x']
return np.asarray(wt), returns, risks
weights, returns, risks = optimal_portfolio(return_vec)
plt.plot(stds, means, 'o')
plt.ylabel('mean')
plt.xlabel('std')
plt.plot(risks, returns, 'y-o')
from zipline.utils.factory import load_bars_from_yahoo
end = datetime.date.today()
start = datetime.date(2015, 1, 1)
data = load_bars_from_yahoo(
stocks=['IBM', 'GLD', 'XOM', 'AAPL', 'MSFT', 'TLT', 'SHY'],
start=start,
end=end)
data.loc[:, :, 'price'].plot(figsize=(8, 5))
plt.ylabel('price in $')
>>> print proj.sum()
1.0
Original matlab implementation: John Duchi ([email protected])
Python-port: Copyright 2013 by Thomas Wiecki ([email protected]).
"""
v = np.asarray(v)
p = len(v)
# Sort v into u in descending order
v = (v > 0) * v
u = np.sort(v)[::-1]
sv = np.cumsum(u)
rho = np.where(u > (sv - b) / np.arange(1, p + 1))[0][-1]
theta = np.max([0, (sv[rho] - b) / (rho + 1)])
w = v - theta
w[w < 0] = 0
return w
if __name__ == "__main__":
import pylab as pl
data = load_bars_from_yahoo(stocks=STOCKS, indexes={})
olmar = OLMAR()
results = olmar.run(data)
results.portfolio_value.plot()
pl.show()
TickerList.tickers = ['AMD', 'CERN', 'COST', 'DELL', 'GPS', 'INTC', 'MMM']
def genWeights(size):
while True:
#create weights so that sum weights = 1
randomWeights = np.array([[random.choice([0.0, 1.0])] for i in xrange(size)])
#scaledweights = randomWeights * (1 / np.sum(randomWeights))
yield randomWeights
if __name__ == '__main__':
csvFileName = raw_input("CSV File Name: ")
start = datetime(2010, 1, 1, 0, 0, 0, 0, pytz.utc)
end = datetime(2014, 1, 1, 0, 0, 0, 0, pytz.utc)
data = load_bars_from_yahoo(stocks=TickerList.tickers, indexes={}, start=start, end=end)
#use last known price for missing data
data = data.fillna(method='ffill')
#fill data at front of series
data = data.fillna(method='bfill')
#drop any other data
data = data.dropna(how='any')
#now shape of data is finalised
num_tickers = data.shape[0]
print 'Number of stocks', num_tickers
#init csv file
def get_data(ENVIRONMENT, tickers, start, end, benchmark, risk_free, cash_proxy):
if ENVIRONMENT == 'ZIPLINE':
benchmark_symbol = benchmark
cash_proxy_symbol = cash_proxy
risk_free_symbol = risk_free
elif ENVIRONMENT == 'RESEARCH':
benchmark_symbol = symbols(benchmark)
cash_proxy_symbol = symbols(cash_proxy)
risk_free_symbol = symbols(risk_free)
# data is a Panel of DataFrames, one for each security
if ENVIRONMENT == 'ZIPLINE':
data = load_bars_from_yahoo(
stocks = list(set(tickers + [benchmark_symbol, cash_proxy_symbol, risk_free_symbol])),
start = start,
end = end,
adjusted=False).transpose(2,1,0)
data.price = data.close # use this for comparing to Quantopian 'get_pricing'
elif ENVIRONMENT == 'RESEARCH':
data = get_pricing(
set(tickers + [benchmark_symbol, cash_proxy_symbol, risk_free_symbol]),
start_date=start,
end_date = end,
frequency='daily'
)
# repair unusable data
# BE CAREFUL!! dropna doesn't change the Panel's Major Index, so NA may still remain!
# safer to use ffill
for security in data.transpose(2,1,0):
data.transpose(2,1,0)[security] = data.transpose(2,1,0)[security].ffill()
if ENVIRONMENT == 'ZIPLINE':
other_data = load_bars_from_yahoo(
stocks=[benchmark_symbol] + [cash_proxy_symbol],
start=start,
end=end,
adjusted=False) # use this for comparing to Quantopian 'get_pricing'
other_data.transpose(2,1,0).price = other_data.transpose(2,1,0).close # use this for comparing to Quantopian 'get_pricing'
elif ENVIRONMENT == 'RESEARCH':
other_data = get_pricing(
[benchmark_symbol] + [cash_proxy_symbol],
fields='price',
start_date= data.major_axis[0],
end_date = data.major_axis[-1],
frequency='daily',
)
other_data = other_data.ffill()
# need to add benchmark (eg SPY) and cash proxy to data panel
benchmark = other_data[benchmark_symbol]
benchmark_rets = benchmark.pct_change().dropna()
benchmark2 = other_data[cash_proxy_symbol]
benchmark2_rets = benchmark2.pct_change().dropna()
# make sure we have all the data we need
inception_dates = pd.DataFrame([data.transpose(2,1,0)[security].dropna().index[0].date() \
for security in data.transpose(2,1,0)], \
index=data.transpose(2,1,0).items, columns=['inception'])
inception_dates.loc['benchmark'] = benchmark.index[0].date()
inception_dates.loc['benchmark2'] = benchmark2.index[0].date()
print(inception_dates)
print()
# check that the end dates coincide
end_dates = pd.DataFrame([data.transpose(2,1,0)[security].dropna().index[-1].date() \
for security in data.transpose(2,1,0)], \
index=data.transpose(2,1,0).items, columns=['end_date'])
end_dates.loc['benchmark'] = benchmark.index[-1].date()
end_dates.loc['benchmark2'] = benchmark2.index[-1].date()
print(end_dates)
# this will ensure that the strat and end dates are aligned
data = data[:,inception_dates.values.max(): end_dates.values.min(),:]
benchmark_rets = benchmark_rets[inception_dates.values.max(): end_dates.values.min()]
benchmark2_rets = benchmark2_rets[inception_dates.values.max(): end_dates.values.min()]
print ('\n\nBACKTEST DATA IS FROM {} UNTIL {} \n*************************************************'
.format(inception_dates.values.max(), end_dates.values.min()))
# DATA FROM ZIPLINE LOAD_YAHOO_BARS DIFFERS FROM RESEARCH ENVIRONMENT!
data.items = ['open_price', 'high', 'low', 'close_price', 'volume', 'price']
print ('\n\n{}'.format(data))
return data
plt.show()
# Note: this if-block should be removed if running
# this algorithm on quantopian.com
if __name__ == '__main__':
from datetime import datetime
import pytz
from zipline.algorithm import TradingAlgorithm
from zipline.utils.factory import load_bars_from_yahoo
# Set the simulation start and end dates.
start = datetime(2011, 1, 1, 0, 0, 0, 0, pytz.utc)
end = datetime(2013, 1, 1, 0, 0, 0, 0, pytz.utc)
# Load price data from yahoo.
data = load_bars_from_yahoo(
stocks=['AAPL'],
indexes={},
start=start,
end=end,
)
# Create and run the algorithm.
algo = TradingAlgorithm(initialize=initialize, handle_data=handle_data)
results = algo.run(data)
# Plot the portfolio and asset data.
analyze(results=results)
self.order(sym, -q)
self.sell_plot[sym].append(self.day_count)
elif self.portfolio.positions[sym].amount < 0:
if sym_price <= self.stops[sym][
0] or sym_price >= self.stops[sym][1]:
print day, ' Exit Short ', sym
q = self.portfolio.positions[sym].amount
self.order(sym, -q)
self.buy_plot[sym].append(self.day_count)
self.day_count += 1
if __name__ == '__main__':
start = datetime(2012, 1, 1, 0, 0, 0, 0, pytz.utc)
end = datetime(2013, 01, 01, 0, 0, 0, 0, pytz.utc)
data = load_bars_from_yahoo(stocks=feed, indexes={}, start=start, end=end)
sector_rs = sector_rs()
results = sector_rs.run(data)
###########################################################################
# Generate metrics
print 'Generating Risk Report...........'
print 'Using S&P500 as benchmark........'
start = results.first_valid_index().replace(tzinfo=pytz.utc)
end = results.last_valid_index().replace(tzinfo=pytz.utc)
env = trading.SimulationParameters(start, end)
returns_risk = create_returns_from_list(results.returns, env)
algo_returns = RiskMetricsBase(start, end,
returns_risk).algorithm_period_returns
print day,' Exit Long ',sym
q = self.portfolio.positions[sym].amount
self.order(sym,-q)
self.sell_plot[sym].append(self.day_count)
elif self.portfolio.positions[sym].amount < 0:
if sym_price <= self.stops[sym][0] or sym_price >= self.stops[sym][1]:
print day,' Exit Short ',sym
q = self.portfolio.positions[sym].amount
self.order(sym,-q)
self.buy_plot[sym].append(self.day_count)
self.day_count += 1
if __name__ == '__main__':
start = datetime(2012, 1, 1, 0, 0, 0, 0, pytz.utc)
end = datetime(2013, 01, 01, 0, 0, 0, 0, pytz.utc)
data = load_bars_from_yahoo(stocks=feed, indexes={}, start=start, end=end)
sector_rs = sector_rs()
results = sector_rs.run(data)
###########################################################################
# Generate metrics
print 'Generating Risk Report...........'
print 'Using S&P500 as benchmark........'
start = results.first_valid_index().replace(tzinfo=pytz.utc)
end = results.last_valid_index().replace(tzinfo=pytz.utc)
env = trading.SimulationParameters(start, end)
returns_risk = create_returns_from_list(results.returns, env)
algo_returns = RiskMetricsBase(start, end, returns_risk).algorithm_period_returns
benchmark_returns = RiskMetricsBase(start, end, returns_risk).benchmark_period_returns
def analyze(context, perf):
fig = plt.figure()
ax1 = fig.add_subplot(211)
perf.portfolio_value.plot(ax=ax1)
ax1.set_ylabel("portfolio value in $")
ax2 = fig.add_subplot(212)
perf[eqSymbol].plot(ax=ax2)
perf[["mc_price"]].plot(ax=ax2)
ax2.set_ylabel("price in $")
plt.legend(loc=0)
plt.show()
if __name__ == "__main__":
# Load data manually from Yahoo! finance
eqSymbol = "YHOO"
start = datetime(2010, 1, 1, 0, 0, 0, 0, pytz.utc)
end = datetime(2014, 1, 1, 0, 0, 0, 0, pytz.utc)
data = load_bars_from_yahoo(stocks=[eqSymbol], start=start, end=end)
# Create algorithm object
algo_obj = MonteCarloTradingAlgorithm()
# Run algorithm
perf_manual = algo_obj.run(data)
# print(perf_manual)
# print(perf_manual.ending_value[-1])
["2009-06-08", sid(7041), 1],
["2009-06-08", sid(1900), 1],
["2012-09-24", sid(22802), 0],
["2012-09-24", sid(7792), 1],
["2013-09-23", sid(700), 0],
["2013-09-23", sid(3735), 0],
["2013-09-23", sid(20088), 1],
["2013-09-23", sid(35920), 1],
["2015-03-18", sid(6653), 0],
["2015-03-18", sid(24), 1]
]
# Load data manually from Yahoo! finance
start = datetime(2011, 1, 1, 0, 0, 0, 0, pytz.utc)
end = datetime(2012, 1, 1, 0, 0, 0, 0, pytz.utc)
data = load_bars_from_yahoo(stocks=['SPY'], start=start, end=end)
def get_dow(dow_constituents):
date = datetime.date()
ret = []
for equity in dow_constituents:
if equity[0] > date:
break
if equity[2] == 1:
ret.append(equity[1])
elif equity[2] == 0:
ret.remove(equity[1])
else:
raise Exception('unknown membership')
return ret
print weights
# ### Backtesting on real market data
# This is all very interesting but not very applied. We next demonstrate how you can create a simple algorithm in [`zipline`](http://github.com/quantopian/zipline) -- the open-source backtester that powers [Quantopian](https://www.quantopian.com) -- to test this optimization on actual historical stock data.
#
# First, lets load in some historical data using [Quantopian](https://www.quantopian.com)'s data (if we are running in the [Quantopian Research Platform](http://blog.quantopian.com/quantopian-research-your-backtesting-data-meets-ipython-notebook/), or the `load_bars_from_yahoo()` function from `zipline`.
# In[5]:
from zipline.utils.factory import load_bars_from_yahoo
end = pd.Timestamp.utcnow()
start = end - 2500 * pd.tseries.offsets.BDay()
data = load_bars_from_yahoo(stocks=['IBM', 'GLD', 'XOM', 'AAPL',
'MSFT', 'TLT', 'SHY'],
start=start, end=end)
# In[9]:
data.loc[:, :, 'price'].iplot(filename='prices', yTitle='price in $', world_readable=True, asDates=True)
# Next, we'll create a `zipline` algorithm by defining two functions -- `initialize()` which is called once before the simulation starts, and `handle_data()` which is called for every trading bar. We then instantiate the algorithm object.
#
# If you are confused about the syntax of `zipline`, check out the [tutorial](http://nbviewer.ipython.org/github/quantopian/zipline/blob/master/docs/notebooks/tutorial.ipynb).
# In[14]:
import zipline
