def get_clean_prices(symbols=None,
dataobj=dataobj,
start=None,
end=None,
market_sym='$SPX',
reset_cache=True):
start = util.normalize_date(start or datetime.date(2008, 1, 1))
end = util.normalize_date(end or datetime.date(2009, 12, 31))
symbols = normalize_symbols(symbols)
symbols += [market_sym]
print "Calculating timestamps for {0} SP500 symbols".format(len(symbols))
ldt_timestamps = du.getNYSEdays(start, end, datetime.timedelta(hours=16))
ls_keys = ['open', 'high', 'low', 'close', 'volume', 'actual_close']
print "Retrieving data for {0} SP500 symbols between {1} and {2}.".format(len(symbols), start, end)
ldf_data = dataobj.get_data(ldt_timestamps, symbols, ls_keys, )
d_data = dict(zip(ls_keys, ldf_data))
for s_key in ls_keys:
print 'cleaning nans from the column {0}'.format(repr(s_key))
d_data[s_key] = d_data[s_key].fillna(method='ffill')
d_data[s_key] = d_data[s_key].fillna(method='bfill')
d_data[s_key] = d_data[s_key].fillna(1.0)
return d_data
def price_dataframe(symbols='sp5002012',
start=datetime.datetime(2008, 1, 1),
end=datetime.datetime(2009, 12, 31),
price_type='actual_close',
cleaner=clean_dataframe,
):
"""Retrieve the prices of a list of equities as a DataFrame (columns = symbols)
Arguments:
symbols (list of str): Ticker symbols like "GOOG", "AAPL", etc
e.g. ["AAPL", " slv ", GLD", "GOOG", "$SPX", "XOM", "msft"]
start (datetime): The date at the start of the period being analyzed.
end (datetime): The date at the end of the period being analyzed.
Yahoo data stops at 2013/1/1
"""
if isinstance(price_type, basestring):
price_type = [price_type]
start = util.normalize_date(start or datetime.date(2008, 1, 1))
end = util.normalize_date(end or datetime.date(2009, 12, 31))
symbols = normalize_symbols(symbols)
t = du.getNYSEdays(start, end, datetime.timedelta(hours=16))
df = clean_dataframes(dataobj.get_data(t, symbols, price_type))
if not df or len(df) > 1:
return cleaner(df)
else:
return cleaner(df[0])
def get_clean_prices(symbols=None,
dataobj=dataobj,
start=None,
end=None,
market_sym='$SPX',
reset_cache=True):
start = util.normalize_date(start or datetime.date(2008, 1, 1))
end = util.normalize_date(end or datetime.date(2009, 12, 31))
symbols = normalize_symbols(symbols)
symbols += [market_sym]
print "Calculating timestamps for {0} SP500 symbols".format(len(symbols))
ldt_timestamps = du.getNYSEdays(start, end, datetime.timedelta(hours=16))
ls_keys = ['open', 'high', 'low', 'close', 'volume', 'actual_close']
print "Retrieving data for {0} SP500 symbols between {1} and {2}.".format(
len(symbols), start, end)
ldf_data = dataobj.get_data(
ldt_timestamps,
symbols,
ls_keys,
)
d_data = dict(zip(ls_keys, ldf_data))
for s_key in ls_keys:
print 'cleaning nans from the column {0}'.format(repr(s_key))
d_data[s_key] = d_data[s_key].fillna(method='ffill')
d_data[s_key] = d_data[s_key].fillna(method='bfill')
d_data[s_key] = d_data[s_key].fillna(1.0)
return d_data
def symbols_bollinger(symbols='sp5002012',
start=datetime.datetime(2008, 1, 1),
end=datetime.datetime(2009, 12, 31),
price_type='adjusted_close',
cleaner=clean_dataframe,
window=20,
sigma=1.):
"""Calculate the Bolinger for a list or set of symbols
Example:
>>> symbols_bollinger(["AAPL", "GOOG", "IBM", "MSFT"], '10-12-01', '10-12-30')[-5:] # doctest: +NORMALIZE_WHITESPACE
GOOG AAPL IBM MSFT
2010-12-23 16:00:00 1.298178 1.185009 1.177220 1.237684
2010-12-27 16:00:00 1.073603 1.371298 0.590403 0.932911
2010-12-28 16:00:00 0.745548 1.436278 0.863406 0.812844
2010-12-29 16:00:00 0.874885 1.464894 2.096242 0.752602
2010-12-30 16:00:00 0.634661 0.793493 1.959324 0.498395
"""
symbols = normalize_symbols(symbols)
prices = price_dataframe(symbols,
start=start,
end=end,
price_type=price_type,
cleaner=cleaner)
return frame_bollinger(prices, window=window, sigma=sigma, plot=False)
def price_dataframe(
symbols='sp5002012',
start=datetime.datetime(2008, 1, 1),
end=datetime.datetime(2009, 12, 31),
price_type='actual_close',
cleaner=clean_dataframe,
):
"""Retrieve the prices of a list of equities as a DataFrame (columns = symbols)
Arguments:
symbols (list of str): Ticker symbols like "GOOG", "AAPL", etc
e.g. ["AAPL", " slv ", GLD", "GOOG", "$SPX", "XOM", "msft"]
start (datetime): The date at the start of the period being analyzed.
end (datetime): The date at the end of the period being analyzed.
Yahoo data stops at 2013/1/1
"""
if isinstance(price_type, basestring):
price_type = [price_type]
start = util.normalize_date(start or datetime.date(2008, 1, 1))
end = util.normalize_date(end or datetime.date(2009, 12, 31))
symbols = normalize_symbols(symbols)
t = du.getNYSEdays(start, end, datetime.timedelta(hours=16))
df = clean_dataframes(dataobj.get_data(t, symbols, price_type))
if not df or len(df) > 1:
return cleaner(df)
else:
return cleaner(df[0])
def symbol_bollinger(symbol='GOOG',
start=datetime.datetime(2008, 1, 1), end=datetime.datetime(2009, 12, 31), price_type='close', cleaner=clean_dataframe,
window=20, sigma=1.):
"""Calculate the Bolinger indicator value
>>> symbol_bollinger("goog", '2008-1-1', '2008-2-1')[-1] # doctest: +ELLIPSIS, +NORMALIZE_WHITESPACE
-1.8782...
"""
symbols = normalize_symbols(symbol)
prices = price_dataframe(symbols, start=start, end=end, price_type=price_type, cleaner=cleaner)
return series_bollinger(prices[symbols[0]], window=window, sigma=sigma, plot=False)
def symbols_bollinger(symbols='sp5002012',
start=datetime.datetime(2008, 1, 1), end=datetime.datetime(2009, 12, 31), price_type='adjusted_close', cleaner=clean_dataframe,
window=20, sigma=1.):
"""Calculate the Bolinger for a list or set of symbols
Example:
>>> symbols_bollinger(["AAPL", "GOOG", "IBM", "MSFT"], '10-12-01', '10-12-30')[-5:] # doctest: +NORMALIZE_WHITESPACE
GOOG AAPL IBM MSFT
2010-12-23 16:00:00 1.298178 1.185009 1.177220 1.237684
2010-12-27 16:00:00 1.073603 1.371298 0.590403 0.932911
2010-12-28 16:00:00 0.745548 1.436278 0.863406 0.812844
2010-12-29 16:00:00 0.874885 1.464894 2.096242 0.752602
2010-12-30 16:00:00 0.634661 0.793493 1.959324 0.498395
"""
symbols = normalize_symbols(symbols)
prices = price_dataframe(symbols, start=start, end=end, price_type=price_type, cleaner=cleaner)
return frame_bollinger(prices, window=window, sigma=sigma, plot=False)
def symbol_bollinger(symbol='GOOG',
start=datetime.datetime(2008, 1, 1),
end=datetime.datetime(2009, 12, 31),
price_type='close',
cleaner=clean_dataframe,
window=20,
sigma=1.):
"""Calculate the Bolinger indicator value
>>> symbol_bollinger("goog", '2008-1-1', '2008-2-1')[-1] # doctest: +ELLIPSIS, +NORMALIZE_WHITESPACE
-1.8782...
"""
symbols = normalize_symbols(symbol)
prices = price_dataframe(symbols,
start=start,
end=end,
price_type=price_type,
cleaner=cleaner)
return series_bollinger(prices[symbols[0]],
window=window,
sigma=sigma,
plot=False)
def portfolio_prices(
symbols=("AAPL", "GLD", "GOOG", "$SPX", "XOM", "msft"),
start=datetime.datetime(2005, 1, 1),
end=datetime.datetime(2011, 12, 31), # data stops at 2013/1/1
normalize=True,
allocation=None,
price_type='actual_close',
):
"""Calculate the Sharpe Ratio and other performance metrics for a portfolio
Arguments:
symbols (list of str): Ticker symbols like "GOOG", "AAPL", etc
start (datetime): The date at the start of the period being analyzed.
end (datetime): The date at the end of the period being analyzed.
normalize (bool): Whether to normalize prices to 1 at the start of the time series.
allocation (list of float): The portion of the portfolio allocated to each equity.
"""
symbols = normalize_symbols(symbols)
start = util.normalize_date(start)
end = util.normalize_date(end)
if allocation is None:
allocation = [1. / len(symbols)] * len(symbols)
if len(allocation) < len(symbols):
allocation = list(allocation) + [1. / len(symbols)
] * (len(symbols) - len(allocation))
total = np.sum(allocation.sum)
allocation = np.array([(float(a) / total) for a in allocation])
timestamps = du.getNYSEdays(start, end, datetime.timedelta(hours=16))
ls_keys = [price_type]
ldf_data = da.get_data(timestamps, symbols, ls_keys)
d_data = dict(zip(ls_keys, ldf_data))
na_price = d_data[price_type].values
if normalize:
na_price /= na_price[0, :]
na_price *= allocation
return np.sum(na_price, axis=1)
def portfolio_prices(
symbols=("AAPL", "GLD", "GOOG", "$SPX", "XOM", "msft"),
start=datetime.datetime(2005, 1, 1),
end=datetime.datetime(2011, 12, 31), # data stops at 2013/1/1
normalize=True,
allocation=None,
price_type='actual_close',
):
"""Calculate the Sharpe Ratio and other performance metrics for a portfolio
Arguments:
symbols (list of str): Ticker symbols like "GOOG", "AAPL", etc
start (datetime): The date at the start of the period being analyzed.
end (datetime): The date at the end of the period being analyzed.
normalize (bool): Whether to normalize prices to 1 at the start of the time series.
allocation (list of float): The portion of the portfolio allocated to each equity.
"""
symbols = normalize_symbols(symbols)
start = util.normalize_date(start)
end = util.normalize_date(end)
if allocation is None:
allocation = [1. / len(symbols)] * len(symbols)
if len(allocation) < len(symbols):
allocation = list(allocation) + [1. / len(symbols)] * (len(symbols) - len(allocation))
total = np.sum(allocation.sum)
allocation = np.array([(float(a) / total) for a in allocation])
timestamps = du.getNYSEdays(start, end, datetime.timedelta(hours=16))
ls_keys = [price_type]
ldf_data = da.get_data(timestamps, symbols, ls_keys)
d_data = dict(zip(ls_keys, ldf_data))
na_price = d_data[price_type].values
if normalize:
na_price /= na_price[0, :]
na_price *= allocation
return np.sum(na_price, axis=1)