def _load_raw_yahoo_data(indexes=None, stocks=None, start=None, end=None):
"""Load closing prices from yahoo finance.
:Optional:
indexes : dict (Default: {'SPX': '^SPY'})
Financial indexes to load.
stocks : list (Default: ['AAPL', 'GE', 'IBM', 'MSFT',
'XOM', 'AA', 'JNJ', 'PEP', 'KO'])
Stock closing prices to load.
start : datetime (Default: datetime(1993, 1, 1, 0, 0, 0, 0, pytz.utc))
Retrieve prices from start date on.
end : datetime (Default: datetime(2002, 1, 1, 0, 0, 0, 0, pytz.utc))
Retrieve prices until end date.
:Note:
This is based on code presented in a talk by Wes McKinney:
http://wesmckinney.com/files/20111017/notebook_output.pdf
"""
assert indexes is not None or stocks is not None, """
must specify stocks or indexes"""
if start is None:
start = pd.datetime(1990, 1, 1, 0, 0, 0, 0, pytz.utc)
if start is not None and end is not None:
assert start < end, "start date is later than end date."
data = OrderedDict()
if stocks is not None:
for stock in stocks:
logger.info('Loading stock: {}'.format(stock))
stock_pathsafe = stock.replace(os.path.sep, '--')
cache_filename = "{stock}-{start}-{end}.csv".format(
stock=stock_pathsafe,
start=start,
end=end).replace(':', '-')
cache_filepath = get_cache_filepath(cache_filename)
if os.path.exists(cache_filepath):
stkd = pd.DataFrame.from_csv(cache_filepath)
else:
stkd = DataReader(stock, 'yahoo', start, end).sort_index()
stkd.to_csv(cache_filepath)
data[stock] = stkd
if indexes is not None:
for name, ticker in iteritems(indexes):
logger.info('Loading index: {} ({})'.format(name, ticker))
stkd = DataReader(ticker, 'yahoo', start, end).sort_index()
data[name] = stkd
return data
评论列表
文章目录