def getHistoricData(symbols, **options):
'''
get data from Yahoo finance and return pandas dataframe
Will get OHLCV data frame if sinle symbol is provided.
If many symbols are provided, it will return a wide panel
Parameters
------------
symbols: Yahoo finanance symbol or a list of symbols
sDate: start date (y,m,d)
eDate: end date (y,m,d)
adjust : T/[F] adjust data based on adj_close
'''
assert isinstance(
symbols,
(list, str)), 'Input must be a string symbol or a list of symbols'
if isinstance(symbols, str):
return getSymbolData(symbols, **options)
else:
data = {}
print 'Downloading data:'
p = ProgressBar(len(symbols))
for idx, symbol in enumerate(symbols):
p.animate(idx + 1)
data[symbol] = getSymbolData(symbol, verbose=False, **options)
return WidePanel(data)
def _check(frame):
dense_frame = frame.to_dense()
wp = WidePanel.from_dict({"foo": frame})
from_dense_lp = wp.to_long()
from_sparse_lp = spm.stack_sparse_frame(frame)
self.assert_(np.array_equal(from_dense_lp.values, from_sparse_lp.values))
def load(self, dataFile):
"""load data from HDF"""
if os.path.exists(dataFile):
store = HDFStore(dataFile)
symbols = [str(s).strip('/') for s in store.keys()]
data = dict(zip(symbols, [store[symbol] for symbol in symbols]))
self.wp = WidePanel(data)
store.close()
else:
raise IOError('Data file does not exist')
def downloadData(self,symbols='all'):
''' get data from yahoo '''
if symbols == 'all':
symbols = self.symbols
#store = HDFStore(self.dataFile)
for idx,symbol in enumerate(symbols):
print 'Downloading %s [%i/%i]' % (symbol,idx+1,len(symbols))
try:
df = getHistoricData(symbol,self.startDate)
print 'Got %i samples' % len(df)
if self.autoAdjust:
df = _adjust(df,removeOrig=True)
if len(self.symbols)==0:
self.wp = WidePanel({symbol:df})
else:
self.wp[symbol] = df
except Exception,e:
print e
def downloadData(self, symbols='all'):
''' get data from yahoo '''
if symbols == 'all':
symbols = self.symbols
#store = HDFStore(self.dataFile)
p = ProgressBar(len(symbols))
for idx, symbol in enumerate(symbols):
try:
df = getHistoricData(symbol, self.startDate, verbose=False)
if self.autoAdjust:
df = _adjust(df, removeOrig=True)
if len(self.symbols) == 0:
self.wp = WidePanel({symbol: df})
else:
self.wp[symbol] = df
except Exception, e:
print e
p.animate(idx + 1)
def __init__(self, autoAdjust=True):
self.startDate = (2008, 1, 1)
self.autoAdjust = autoAdjust
self.wp = WidePanel()
def test_to_dense(self):
dwp = self.panel.to_dense()
dwp2 = WidePanel.from_dict(self.data_dict)
assert_panel_equal(dwp, dwp2)
def test_dense_to_sparse(self):
wp = WidePanel.from_dict(self.data_dict)
dwp = wp.to_sparse()
self.assert_(isinstance(dwp['ItemA']['A'], SparseSeries))