[Predator] Move ``SingleFeatureScore`` to LLM.

appengine/findit/crash/loglinear/feature.py

 # Copyright 2016 The Chromium Authors. All rights reserved.
 # Use of this source code is governed by a BSD-style license that can be
 # found in the LICENSE file.
 
 from collections import namedtuple
 import math
 
 import libs.math.logarithms as lmath
 
 
@@ skipping 120 matching lines @@
     thinks the ``y`` should be blamed or should not be depends on the sign
     of the value and the sign of the weight given to this feature.) As
     special cases, a value of negative infinity means "do not blame this
     ``y`` no matter what any other features say", and a value of positive
     infinity means "definitely blame this ``y`` no matter what any other
     features say". Both of those special values should be used sparingly,
     since they override the model's ability to combine multiple sources of
     information and decide the cuplrit based on all the evidence together.
     """
     raise NotImplementedError()
+
+
+class FeatureFunction(object):
+  """Given a dict of scalar-valued functions, return an dict-valued function.
+
+  Properties:
+    fs (iterable of functions): A collection of curried functions
+    ``X -> Y -> dict(FeatureValue)``. That is, given a particular ``x`` they
+    return a function ``Y -> dict(FeatureValue)``. N.B. each function should
+    have a name property.

[wrengr, 2017/01/12 19:09:09]

The input functions don't return a dict(FV), they just return one FV. With that
change, this entire description is exactly the description of what the
``Feature`` class is capturing. For the current interface, the collection of
inputs is either:

(a) a dict of X->Y->FV functions. The key gives the name, and we will
automatically convert the raw function into a Feature under the covers.

(b) an iterable of Feature objects. Here we use an iterable so we can't get the
name form there; thus we require a Feature object since that specifies both the
X->Y->FV and the name.

Pick one or the other and run with it.

[Sharu Jiang, 2017/01/13 01:08:34]

Oops, I will stick to the option (b).

+  """
+  def __init__(self, fs):
+    self._fs = fs
+
+  def __call__(self, x):
+    """Fuction mapping ``X -> Y -> dict(A.name to A).

[wrengr, 2017/01/12 19:09:09]

The ``A`` should be ``FeatureValue`` here as well

[Sharu Jiang, 2017/01/13 01:08:34]

Done.

+
+    Returns:
+      A function ``X -> Y -> dict(A.name to A)`` where for all ``x``, ``y``, and

[wrengr, 2017/01/12 19:09:09]

ditto

[Sharu Jiang, 2017/01/13 01:08:34]

Done.

+     for a feature f in fs, we have
+      ``FeatureFunction(fs)(x)(y)[f.name] == f(x)(y)``.
+    """
+    name_to_fx = {f.name: f(x) for f in self._fs}
+    return lambda y: {name: fx(y) for name, fx in name_to_fx.iteritems()}