mirror of
https://github.com/wassname/catalyst.git
synced 2026-06-28 19:47:13 +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.
121 lines
3.4 KiB
Python
Executable File
121 lines
3.4 KiB
Python
Executable File
#!/usr/bin/env python
|
|
from code import InteractiveConsole
|
|
import readline # noqa
|
|
import shutil
|
|
import tarfile
|
|
|
|
import click
|
|
import numpy as np
|
|
import pandas as pd
|
|
|
|
from zipline import examples, run_algorithm
|
|
from zipline.testing import test_resource_path, tmp_dir
|
|
from zipline.utils.cache import dataframe_cache
|
|
|
|
banner = """
|
|
Please verify that the new perfomance is more correct than the old performance.
|
|
|
|
To do this, please inspect `new` and `old` which are mappings from the name of
|
|
the example to the results.
|
|
|
|
If you are sure that the new results are more correct, or that the difference
|
|
is acceptable, please call `correct()`. Otherwise, call `incorrect()`.
|
|
|
|
Note
|
|
----
|
|
Remember to run this with the other supported versions of pandas!
|
|
"""
|
|
|
|
|
|
def eof(*args, **kwargs):
|
|
raise EOFError()
|
|
|
|
|
|
@click.command()
|
|
@click.pass_context
|
|
def main(ctx):
|
|
"""Rebuild the perf data for test_examples
|
|
"""
|
|
example_path = test_resource_path('example_data.tar.gz')
|
|
with tmp_dir() as d:
|
|
with tarfile.open(example_path) as tar:
|
|
tar.extractall(d.path)
|
|
|
|
mods = (
|
|
(e, getattr(examples, e))
|
|
for e in dir(examples)
|
|
if not e.startswith('_')
|
|
)
|
|
|
|
new_perf_path = d.getpath(
|
|
'example_data/new_perf/%s' % pd.__version__.replace('.', '-'),
|
|
)
|
|
c = dataframe_cache(
|
|
new_perf_path,
|
|
serialization='pickle:2',
|
|
)
|
|
with c:
|
|
for name, mod in mods:
|
|
c[name] = run_algorithm(
|
|
handle_data=mod.handle_data,
|
|
initialize=mod.initialize,
|
|
before_trading_start=getattr(
|
|
mod, 'before_trading_start', None,
|
|
),
|
|
analyze=getattr(mod, 'analyze', None),
|
|
bundle='test',
|
|
environ={
|
|
'ZIPLINE_ROOT': d.getpath('example_data/root'),
|
|
},
|
|
**mod._test_args()
|
|
)
|
|
|
|
correct_called = [False]
|
|
|
|
console = None
|
|
|
|
def _exit(*args, **kwargs):
|
|
console.raw_input = eof
|
|
|
|
def correct():
|
|
correct_called[0] = True
|
|
_exit()
|
|
|
|
expected_perf_path = d.getpath(
|
|
'example_data/expected_perf/%s' %
|
|
pd.__version__.replace('.', '-'),
|
|
)
|
|
|
|
# allow users to run some analysis to make sure that the new
|
|
# results check out
|
|
console = InteractiveConsole({
|
|
'correct': correct,
|
|
'exit': _exit,
|
|
'incorrect': _exit,
|
|
'new': c,
|
|
'np': np,
|
|
'old': dataframe_cache(
|
|
expected_perf_path,
|
|
serialization='pickle',
|
|
),
|
|
'pd': pd,
|
|
})
|
|
console.interact(banner)
|
|
|
|
if not correct_called[0]:
|
|
ctx.fail(
|
|
'`correct()` was not called! This means that the new'
|
|
' results will not be written',
|
|
)
|
|
|
|
# move the new results to the expected path
|
|
shutil.rmtree(expected_perf_path)
|
|
shutil.copytree(new_perf_path, expected_perf_path)
|
|
|
|
with tarfile.open(example_path, 'w|gz') as tar:
|
|
tar.add(d.getpath('example_data'), 'example_data')
|
|
|
|
|
|
if __name__ == '__main__':
|
|
main()
|