wassname/catalyst
1
0
Fork 0
mirror of https://github.com/wassname/catalyst.git synced 2026-06-29 07:22:00 +08:00
Code Issues Packages Projects Releases Wiki Activity

DOC: More docs updates.

Browse Source
This commit is contained in:
Scott Sanderson
2015-10-06 06:00:06 -04:00
parent f109dbbd1d
commit 7d760f64d7
3 changed files with 64 additions and 49 deletions
Download Patch File Download Diff File Expand all files Collapse all files
zipline/pipeline/factors/factor.py
+57 -48
View File
@@ -101,6 +101,7 @@ def binary_operator(op):
)
raise BadBinaryOperator(op, self, other)
binary_operator.__doc__ = "Binary Operator: '%s'" % op
return binary_operator
@@ -159,6 +160,8 @@ def unary_operator(op):
)
else:
return NumExprFactor("{op}x_0".format(op=op), (self,))
unary_operator.__doc__ = "Unary Operator: '%s'" % op
return unary_operator
@@ -183,8 +186,7 @@ def function_application(func):
class Factor(Term):
"""
A transformation yielding a timeseries of scalar values associated with an
Asset.
Pipeline API expression producing numerically-valued outputs.
"""
dtype = float64
@@ -230,9 +232,6 @@ class Factor(Term):
Parameters
----------
ranks : zipline.pipeline.factor.Rank
A new factor that will compute the sorted indices of the data
produced by `self`.
method : str, {'ordinal', 'min', 'max', 'dense', 'average'}
The method used to assign ranks to tied elements. See
`scipy.stats.rankdata` for a full description of the semantics for
@@ -243,7 +242,9 @@ class Factor(Term):
Returns
-------
ranks : zipline.pipeline.factor.Rank
ranks : zipline.pipeline.factors.Rank
A new factor that will compute the ranking of the data produced by
`self`.
Notes
-----
@@ -258,7 +259,7 @@ class Factor(Term):
--------
scipy.stats.rankdata
zipline.lib.rank
zipline.pipeline.factor.Rank
zipline.pipeline.factors.Rank
"""
return Rank(self if ascending else -self, method=method, mask=mask)
@@ -270,10 +271,12 @@ class Factor(Term):
----------
N : int
Number of assets passing the returned filter each day.
mask : zipline.pipeline.Filter
Filter to apply as a mask before computing top values.
Returns
-------
filter : zipline.pipeline.Filter
filter : zipline.pipeline.filters.Filter
"""
return self.rank(ascending=False, mask=mask) <= N
@@ -285,6 +288,8 @@ class Factor(Term):
----------
N : int
Number of assets passing the returned filter each day.
mask : zipline.pipeline.filters.Filter
Filter to apply as a mask before computing bottom values.
Returns
-------
@@ -350,7 +355,7 @@ class Rank(SingleInputMixin, Factor):
Parameters
----------
factor : zipline.pipeline.factor.Factor
factor : zipline.pipeline.factors.Factor
The factor on which to compute ranks.
method : str, {'average', 'min', 'max', 'dense', 'ordinal'}
The method used to assign ranks to tied elements. See
@@ -360,7 +365,7 @@ class Rank(SingleInputMixin, Factor):
See Also
--------
scipy.stats.rankdata : Underlying ranking algorithm.
zipline.factor.Factor.rank : Method-style interface to same functionality.
zipline.factors.Factor.rank : Method-style interface to same functionality.
Notes
-----
@@ -433,7 +438,7 @@ class Rank(SingleInputMixin, Factor):
class CustomFactor(RequiredWindowLengthMixin, CustomTermMixin, Factor):
"""
'''
Base class for user-defined Factors.
Parameters
@@ -451,16 +456,16 @@ class CustomFactor(RequiredWindowLengthMixin, CustomTermMixin, Factor):
Notes
-----
Users implementing their own Factors should subclass CustomFactor and
implement a method named `compute` with the following signature:
implement a method named `compute` with the following signature::
def compute(self, today, assets, out, *inputs):
...
On each simulation date, `compute` will be called with the current date, an
array of sids, an output array, and an input array for each expression
passed as `inputs` to the CustomFactor constructor.
On each simulation date, ``compute`` will be called with the current date,
an array of sids, an output array, and an input array for each expression
passed as inputs to the CustomFactor constructor.
The specific types of the values passed to `compute` are as follows:
The specific types of the values passed to `compute` are as follows::
today : np.datetime64[ns]
Row label for the last row of all arrays passed as `inputs`.
@@ -472,7 +477,7 @@ class CustomFactor(RequiredWindowLengthMixin, CustomTermMixin, Factor):
*inputs : tuple of np.array
Raw data arrays corresponding to the values of `self.inputs`.
`compute` functions should expect to be passed NaN values for dates on
``compute`` functions should expect to be passed NaN values for dates on
which no data was available for an asset. This may include dates on which
an asset did not yet exist.
@@ -484,48 +489,52 @@ class CustomFactor(RequiredWindowLengthMixin, CustomTermMixin, Factor):
Examples
--------
class TenDayRange(CustomFactor):
'''
Computes the difference between the highest high in the last 10 days
and the lowest low.
A CustomFactor with pre-declared defaults::
Pre-declares high and low as default inputs and `window_length` as 10.
'''
class TenDayRange(CustomFactor):
"""
Computes the difference between the highest high in the last 10
days and the lowest low.
inputs = [USEquityPricing.high, USEquityPricing.low]
window_length = 10
Pre-declares high and low as default inputs and `window_length` as
10.
"""
def compute(self, today, assets, out, highs, lows):
from numpy import nanmin, nanmax
inputs = [USEquityPricing.high, USEquityPricing.low]
window_length = 10
highest_highs = nanmax(axis=0)
lowest_lows = nanmin(axis=0)
out[:] = highest_highs - lowest_lows
def compute(self, today, assets, out, highs, lows):
from numpy import nanmin, nanmax
highest_highs = nanmax(axis=0)
lowest_lows = nanmin(axis=0)
out[:] = highest_highs - lowest_lows
class MedianValue(CustomFactor):
'''
Computes the median value of an arbitrary single input over an
arbitrary window..
# Doesn't require passing inputs or window_length because they're
# pre-declared as defaults for the TenDayRange class.
ten_day_range = TenDayRange()
Does not declare any defaults, so values for `window_length` and
`inputs` must be passed explicitly on every construction.
'''
A CustomFactor without defaults::
def compute(self, today, assets, out, data):
from numpy import nanmedian
out[:} = data.nanmedian(axis=0)
class MedianValue(CustomFactor):
"""
Computes the median value of an arbitrary single input over an
arbitrary window..
Does not declare any defaults, so values for `window_length` and
`inputs` must be passed explicitly on every construction.
"""
# Doesn't require passing inputs or window_length because they're
# pre-declared as defaults for the TenDayRange class.
ten_day_range = TenDayRange()
def compute(self, today, assets, out, data):
from numpy import nanmedian
out[:} = data.nanmedian(axis=0)
# Values for `inputs` and `window_length` must be passsed explitly to
# MedianValue.
median_close_10 = MedianValue([USEquityPricing.close], window_length=10)
median_low_15 = MedianValue([USEquityPricing.low], window_length=15)
"""
# Values for `inputs` and `window_length` must be passsed explitly to
# MedianValue.
median_close10 = MedianValue([USEquityPricing.close], window_length=10)
median_low15 = MedianValue([USEquityPricing.low], window_length=15)
'''
ctx = nullctx()
def _validate(self):
zipline/pipeline/filters/filter.py
+1 -1
View File
@@ -83,7 +83,7 @@ def binary_operator(op):
class Filter(Term):
"""
A boolean predicate on a universe of Assets.
Pipeline API expression producing boolean-valued outputs.
"""
dtype = bool_
zipline/pipeline/term.py
+6
View File
@@ -273,6 +273,12 @@ class CustomTermMixin(object):
window_length=window_length,
)
def __init__(self, inputs=NotSpecified, window_length=NotSpecified):
return super(CustomTermMixin, self).__init__(
inputs=inputs,
window_length=window_length,
)
def compute(self, today, assets, out, *arrays):
"""
Override this method with a function that writes a value into `out`.