mirror of
https://github.com/wassname/catalyst.git
synced 2026-06-29 00:37:43 +08:00
Scott Sanderson
49bb8264dc
- Added test coverage for grouped and masked top/bottom. - Added test coverage for grouped rank on datetime factors. - Fixed an issue where grouped rank would fail on datetime inputs because unary-negative isn't defined for datetimes. We now instead directly invoke a function from rank.pyx that does the normalizations as neeeded. - Fixed an issue where GroupedRowTransform assumed that it produced the same dtype as its input. This isn't true for rank() of a datetime-dtype factor. GroupedRowTransform now takes a required dtype parameter. - Similarly, fixed an issue where GroupedRowTransform assumed that its missing_value was the same as its parent's, which isn't true for rank() of a datetime-dtype factor. GroupedRowTransform now takes a required dtype parameter. - Fixed an issue where Factor.demean() and Factor.zscore() weren't properly cached because their static_identity included a closure that was dynamically generated on each invocation. They both now always use a function defined at module scope.
52 lines
1.8 KiB
Python
52 lines
1.8 KiB
Python
import numpy as np
|
|
|
|
|
|
def naive_grouped_rowwise_apply(data,
|
|
group_labels,
|
|
func,
|
|
func_args=(),
|
|
out=None):
|
|
"""
|
|
Simple implementation of grouped row-wise function application.
|
|
|
|
Parameters
|
|
----------
|
|
data : ndarray[ndim=2]
|
|
Input array over which to apply a grouped function.
|
|
group_labels : ndarray[ndim=2, dtype=int64]
|
|
Labels to use to bucket inputs from array.
|
|
Should be the same shape as array.
|
|
func : function[ndarray[ndim=1]] -> function[ndarray[ndim=1]]
|
|
Function to apply to pieces of each row in array.
|
|
func_args : tuple
|
|
Additional positional arguments to provide to each row in array.
|
|
out : ndarray, optional
|
|
Array into which to write output. If not supplied, a new array of the
|
|
same shape as ``data`` is allocated and returned.
|
|
|
|
Example
|
|
-------
|
|
>>> data = np.array([[1., 2., 3.],
|
|
... [2., 3., 4.],
|
|
... [5., 6., 7.]])
|
|
>>> labels = np.array([[0, 0, 1],
|
|
... [0, 1, 0],
|
|
... [1, 0, 2]])
|
|
>>> naive_grouped_rowwise_apply(data, labels, lambda row: row - row.min())
|
|
array([[ 0., 1., 0.],
|
|
[ 0., 0., 2.],
|
|
[ 0., 0., 0.]])
|
|
>>> naive_grouped_rowwise_apply(data, labels, lambda row: row / row.sum())
|
|
array([[ 0.33333333, 0.66666667, 1. ],
|
|
[ 0.33333333, 1. , 0.66666667],
|
|
[ 1. , 1. , 1. ]])
|
|
"""
|
|
if out is None:
|
|
out = np.empty_like(data)
|
|
|
|
for (row, label_row, out_row) in zip(data, group_labels, out):
|
|
for label in np.unique(label_row):
|
|
locs = (label_row == label)
|
|
out_row[locs] = func(row[locs], *func_args)
|
|
return out
|