def _read_matrix(group):
index = _read_index(group, 'index')
columns = _read_index(group, 'columns')
values = group.values[:]
objects = None
if hasattr(group, 'obj_columns'):
obj_columns = _read_index(group, 'columns')
obj_values = group.obj_values[:]
objects = DataMatrix(obj_values, index=index, columns=obj_columns)
return DataMatrix(values, index=index, columns=columns, objects=objects)
def __init__(self, models):
self.models = models
self.names = sorted(models.keys())
mod = self.models.values()[0]
self.pred_like = DataMatrix(dict(
(k, v.pred_like) for k, v in models.iteritems()),
index=mod.dates)
def getQuotes(symbol, start, end):
quotes = fin.quotes_historical_yahoo(symbol, start, end)
dates, open, close, high, low, volume = zip(*quotes)
data = {
'open': open,
'close': close,
'high': high,
'low': low,
'volume': volume
}
dates = Index([datetime.fromordinal(int(d)) for d in dates])
return DataMatrix(data, index=dates)
def __init__(self, phi):
self.phi = phi
self.p = len(phi)
(self.modulus, self.frequency, self.wavelength,
self.H) = self._compute_decomp()
self.result = DataMatrix(
{
'wavelength': self.wavelength,
'modulus': self.modulus,
'frequency': self.frequency
},
columns=['modulus', 'wavelength', 'frequency'])
# Set start and end dates
t = map(int, sys.argv[1].split('-'))
startday = dt.datetime(t[2], t[0], t[1])
t = map(int, sys.argv[2].split('-'))
endday = dt.datetime(t[2], t[0], t[1])
# Get desired timestamps
timeofday = dt.timedelta(hours=16)
timestamps = du.getNYSEdays(startday, endday, timeofday)
# Get the data from the data store
dataobj = da.DataAccess('Norgate')
historic = dataobj.get_data(timestamps, symbols, "close")
# Setup the allocation table
alloc_val = random.random()
alloc = DataMatrix(index=[historic.index[0]],
data=[alloc_val],
columns=symbols)
for date in range(1, len(historic.index)):
alloc_val = 1 #random.random()
alloc = alloc.append(
DataMatrix(index=[historic.index[date]],
data=[alloc_val],
columns=[symbols[0]]))
alloc['_CASH'] = 1 - alloc[symbols[0]]
# Dump to pkl file
output = open(sys.argv[3], "wb")
cPickle.dump(alloc, output)
ibm['hi-lo spread'] = ibm['high'] - ibm['low']
# Aggregate monthly
def toMonthly(frame, how):
offset = BMonthEnd()
return frame.groupby(offset.rollforward).aggregate(how)
msftMonthly = toMonthly(msft, np.mean)
ibmMonthly = toMonthly(ibm, np.mean)
# Statistics
stdev = DataMatrix({'MSFT': msft.std(), 'IBM': ibm.std()})
# Arithmetic
ratios = ibm / msft
# Works with different indices
ratio = ibm / ibmMonthly
monthlyRatio = ratio.reindex(ibmMonthly.index)
# Ratio relative to past month average
filledRatio = ibm / ibmMonthly.reindex(ibm.index, fillMethod='pad')
'close' : close,
'high' : high,
'low' : low,
'volume' : volume
}
dates = Index([datetime.fromordinal(int(d)) for d in dates])
return DataMatrix(data, index=dates)
msft = getQuotes('MSFT', startDate, endDate)
aapl = getQuotes('AAPL', startDate, endDate)
goog = getQuotes('GOOG', startDate, endDate)
ibm = getQuotes('IBM', startDate, endDate)
px = DataMatrix({'MSFT' : msft['close'],
'IBM' : ibm['close'],
'GOOG' : goog['close'],
'AAPL' : aapl['close']})
returns = px / px.shift(1) - 1
# Select dates
subIndex = ibm.index[(ibm['close'] > 95) & (ibm['close'] < 100)]
msftOnSameDates = msft.reindex(subIndex)
# Insert columns
msft['hi-lo spread'] = msft['high'] - msft['low']
ibm['hi-lo spread'] = ibm['high'] - ibm['low']
# Aggregate monthly
