Mirrors
/
the-algorithm
mirror of https://github.com/twitter/the-algorithm.git
2
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Function TFModelInitializerBuilder._set_discretized_features refactored with the following changes: 

removes a pair of brackets, making the intent slightly clearer
 Convert for loop into dictionary comprehension (dict-comprehension)
This commit is contained in:
Jhv 2023-04-04 21:28:36 +08:00
parent d1cab28a10
commit d2da7e56ab
1 changed files with 68 additions and 67 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

135
src/python/twitter/deepbird/projects/timelines/scripts/models/earlybird/lolly/tf_model_initializer_builder.py
View File

@ -3,89 +3,90 @@ from .parsers import LollyModelFeaturesParser
class TFModelInitializerBuilder:
def __init__(self, model_features_parser=LollyModelFeaturesParser()):
self._model_features_parser = model_features_parser
def __init__(self, model_features_parser=LollyModelFeaturesParser()):
self._model_features_parser = model_features_parser
def build(self, lolly_model_reader):
'''
:param lolly_model_reader: LollyModelReader instance
:return: tf_model_initializer dictionary of the following format:
{
"features": {
"bias": 0.0,
"binary": {
# (feature name : feature weight) pairs
"feature_name_1": 0.0,
...
"feature_nameN": 0.0
},
"discretized": {
# (feature name : index aligned lists of bin_boundaries and weights
"feature_name_1": {
"bin_boundaries": [1, ..., inf],
"weights": [0.0, ..., 0.0]
}
...
"feature_name_K": {
"bin_boundaries": [1, ..., inf],
"weights": [0.0, ..., 0.0]
def build(self, lolly_model_reader):
'''
:param lolly_model_reader: LollyModelReader instance
:return: tf_model_initializer dictionary of the following format:
{
"features": {
"bias": 0.0,
"binary": {
# (feature name : feature weight) pairs
"feature_name_1": 0.0,
...
"feature_nameN": 0.0
},
"discretized": {
# (feature name : index aligned lists of bin_boundaries and weights
"feature_name_1": {
"bin_boundaries": [1, ..., inf],
"weights": [0.0, ..., 0.0]
}
...
"feature_name_K": {
"bin_boundaries": [1, ..., inf],
"weights": [0.0, ..., 0.0]
}
}
}
}
'''
tf_model_initializer = {
"features": {}
}
}
'''
tf_model_initializer = {
"features": {}
}
features = self._model_features_parser.parse(lolly_model_reader)
tf_model_initializer["features"]["bias"] = features["bias"]
self._set_discretized_features(features["discretized"], tf_model_initializer)
features = self._model_features_parser.parse(lolly_model_reader)
tf_model_initializer["features"]["bias"] = features["bias"]
self._set_discretized_features(features["discretized"], tf_model_initializer)
self._dedup_binary_features(features["binary"], features["discretized"])
tf_model_initializer["features"]["binary"] = features["binary"]
self._dedup_binary_features(features["binary"], features["discretized"])
tf_model_initializer["features"]["binary"] = features["binary"]
return tf_model_initializer
return tf_model_initializer
def _set_discretized_features(self, discretized_features, tf_model_initializer):
if len(discretized_features) == 0:
return
def _set_discretized_features(self, discretized_features, tf_model_initializer):
if len(discretized_features) == 0:
return
num_bins = max([len(bins) for bins in discretized_features.values()])
num_bins = max(len(bins) for bins in discretized_features.values())
bin_boundaries_and_weights = {}
for feature_name in discretized_features:
bin_boundaries_and_weights[feature_name] = self._extract_bin_boundaries_and_weights(
discretized_features[feature_name], num_bins)
bin_boundaries_and_weights = {
feature_name: self._extract_bin_boundaries_and_weights(
discretized_features[feature_name], num_bins)
for feature_name in discretized_features
}
tf_model_initializer["features"]["discretized"] = bin_boundaries_and_weights
tf_model_initializer["features"]["discretized"] = bin_boundaries_and_weights
def _dedup_binary_features(self, binary_features, discretized_features):
[binary_features.pop(feature_name) for feature_name in discretized_features]
def _dedup_binary_features(self, binary_features, discretized_features):
[binary_features.pop(feature_name) for feature_name in discretized_features]
def _extract_bin_boundaries_and_weights(self, discretized_feature_buckets, num_bins):
bin_boundary_weight_pairs = []
def _extract_bin_boundaries_and_weights(self, discretized_feature_buckets, num_bins):
bin_boundary_weight_pairs = []
for bucket in discretized_feature_buckets:
bin_boundary_weight_pairs.append([bucket[0], bucket[2]])
for bucket in discretized_feature_buckets:
bin_boundary_weight_pairs.append([bucket[0], bucket[2]])
# The default DBv2 HashingDiscretizer bin membership interval is (a, b]
#
# The Earlybird Lolly prediction engine discretizer bin membership interval is [a, b)
#
# Thus, convert (a, b] to [a, b) by inverting the bin boundaries.
for bin_boundary_weight_pair in bin_boundary_weight_pairs:
if bin_boundary_weight_pair[0] < float("inf"):
bin_boundary_weight_pair[0] *= -1
# The default DBv2 HashingDiscretizer bin membership interval is (a, b]
#
# The Earlybird Lolly prediction engine discretizer bin membership interval is [a, b)
#
# Thus, convert (a, b] to [a, b) by inverting the bin boundaries.
for bin_boundary_weight_pair in bin_boundary_weight_pairs:
if bin_boundary_weight_pair[0] < float("inf"):
bin_boundary_weight_pair[0] *= -1
while len(bin_boundary_weight_pairs) < num_bins:
bin_boundary_weight_pairs.append([float("inf"), float(0)])
while len(bin_boundary_weight_pairs) < num_bins:
bin_boundary_weight_pairs.append([float("inf"), float(0)])
bin_boundary_weight_pairs.sort(key=lambda bin_boundary_weight_pair: bin_boundary_weight_pair[0])
bin_boundary_weight_pairs.sort(key=lambda bin_boundary_weight_pair: bin_boundary_weight_pair[0])
bin_boundaries, weights = list(zip(*bin_boundary_weight_pairs))
bin_boundaries, weights = list(zip(*bin_boundary_weight_pairs))
return {
"bin_boundaries": bin_boundaries,
"weights": weights
}
return {
"bin_boundaries": bin_boundaries,
"weights": weights
}