mirror of
https://github.com/wassname/catalyst.git
synced 2026-06-29 01:41:38 +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
2.0 KiB
Python
80 lines
2.0 KiB
Python
#
|
|
# Copyright 2013 Quantopian, Inc.
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
import math
|
|
|
|
from numpy import isnan
|
|
|
|
|
|
def tolerant_equals(a, b, atol=10e-7, rtol=10e-7, equal_nan=False):
|
|
"""Check if a and b are equal with some tolerance.
|
|
|
|
Parameters
|
|
----------
|
|
a, b : float
|
|
The floats to check for equality.
|
|
atol : float, optional
|
|
The absolute tolerance.
|
|
rtol : float, optional
|
|
The relative tolerance.
|
|
equal_nan : bool, optional
|
|
Should NaN compare equal?
|
|
|
|
See Also
|
|
--------
|
|
numpy.isclose
|
|
|
|
Notes
|
|
-----
|
|
This function is just a scalar version of numpy.isclose for performance.
|
|
See the docstring of ``isclose`` for more information about ``atol`` and
|
|
``rtol``.
|
|
"""
|
|
if equal_nan and isnan(a) and isnan(b):
|
|
return True
|
|
return math.fabs(a - b) <= (atol + rtol * math.fabs(b))
|
|
|
|
|
|
try:
|
|
# fast versions
|
|
import bottleneck as bn
|
|
nanmean = bn.nanmean
|
|
nanstd = bn.nanstd
|
|
nansum = bn.nansum
|
|
nanmax = bn.nanmax
|
|
nanmin = bn.nanmin
|
|
nanargmax = bn.nanargmax
|
|
nanargmin = bn.nanargmin
|
|
except ImportError:
|
|
# slower numpy
|
|
import numpy as np
|
|
nanmean = np.nanmean
|
|
nanstd = np.nanstd
|
|
nansum = np.nansum
|
|
nanmax = np.nanmax
|
|
nanmin = np.nanmin
|
|
nanargmax = np.nanargmax
|
|
nanargmin = np.nanargmin
|
|
|
|
|
|
def round_if_near_integer(a, epsilon=1e-4):
|
|
"""
|
|
Round a to the nearest integer if that integer is within an epsilon
|
|
of a.
|
|
"""
|
|
if abs(a - round(a)) <= epsilon:
|
|
return round(a)
|
|
else:
|
|
return a
|