mirror of
https://github.com/wassname/catalyst.git
synced 2026-07-06 05:14:38 +08:00
Joe Jevnik
59c8e371a2
Adds the data bundle concept which makes it easy for users to register loading functions to build out minute and daily data along with an assets db and adjustments db. By default we have provided a `quandl` bundle which pulls from the public domain WIKI dataset. Users may register new bundles by decorating an ingest function with `zipline.data.bundles.register(<name>)`. This also provides a `yahoo_equities` function for creating an ingestion function that will load a static set of assets from yahoo. The cli is now structured as a couple of subcommands and has been changed to `python -m zipline`. The old behavior of `run_algo.py` has been moved to the `run` subcommand. This is almost entirely the same except that it now takes the name of the data bundle to use, defaulting to `quandl`. The next subcommand is `ingest` which takes the name of a data bundle to ingest. This will run the loading machinery and write the data to a specified location that `run` can find. There is also a `clean` subcommand which deletes the data that was written with `ingest`. Extensions have also been added to zipline. This is an experimental feature where users can provide an extra set of python files to run at the start of the process. These can be used to configure aspects of zipline. Right now the only thing that is supported in an extension file is the registration of a new data bundle.
80 lines
1.9 KiB
Python
80 lines
1.9 KiB
Python
#!/usr/bin/env python
|
|
"""
|
|
Script for rebuilding the samples for the Yahoo tests.
|
|
"""
|
|
from textwrap import dedent
|
|
|
|
import numpy as np
|
|
import pandas as pd
|
|
|
|
from zipline.testing import test_resource_path, write_compressed
|
|
from zipline.utils.tradingcalendar import trading_days
|
|
|
|
|
|
def zipfile_path(symbol, ext):
|
|
return test_resource_path('yahoo_samples', symbol + ext + '.gz')
|
|
|
|
|
|
def pricing_for_sid(sid):
|
|
modifier = {
|
|
'Low': 0,
|
|
'Open': 1,
|
|
'Close': 2,
|
|
'High': 3,
|
|
'Volume': 0,
|
|
}
|
|
|
|
def column(name):
|
|
return np.arange(252) + 1 + sid * 10000 + modifier[name] * 1000
|
|
|
|
return pd.DataFrame(
|
|
data={
|
|
'Date': trading_days[
|
|
(trading_days >= pd.Timestamp('2014')) &
|
|
(trading_days < pd.Timestamp('2015'))
|
|
],
|
|
'Open': column('Open'),
|
|
'High': column('High'),
|
|
'Low': column('Low'),
|
|
'Close': column('Close'),
|
|
'Volume': column('Volume'),
|
|
'Adj Close': 0,
|
|
},
|
|
columns=[
|
|
'Date', 'Open', 'High', 'Low', 'Close', 'Volume', 'Adj Close',
|
|
],
|
|
).to_csv(index=False, date_format='%Y-%m-%d').encode('ascii')
|
|
|
|
|
|
def adjustments_for_sid(sid):
|
|
"""This is not exactly a csv... thanks yahoo.
|
|
"""
|
|
return dedent(
|
|
"""\
|
|
Date,Dividends
|
|
DIVIDEND, 20140403,0.{p1}00000
|
|
SPLIT, 20140703,{p2}:1
|
|
DIVIDEND, 20141002,0.{p2}00000
|
|
STARTDATE, 20140102
|
|
ENDDATE, 20141231
|
|
TOTALSIZE, 2
|
|
""".format(p1=sid + 1, p2=sid + 2),
|
|
).encode('ascii')
|
|
|
|
|
|
def main():
|
|
symbols = 'AAPL', 'IBM', 'MSFT'
|
|
|
|
for sid, symbol in enumerate(symbols):
|
|
write_compressed(
|
|
zipfile_path(symbol, '.csv'),
|
|
pricing_for_sid(sid),
|
|
)
|
|
write_compressed(
|
|
zipfile_path(symbol, '.adjustments'),
|
|
adjustments_for_sid(sid),
|
|
)
|
|
|
|
if __name__ == '__main__':
|
|
main()
|