def process(
self, sparse_data: StackedAssociativeArray
) -> Tuple[str, str, List[str]]:
lengths_blob = sparse_data.lengths
keys_blob = sparse_data.keys
values_blob = sparse_data.values
MISSING_SCALAR = C2.NextBlob("MISSING_SCALAR")
missing_value = 0.0 if self.set_missing_value_to_zero else MISSING_VALUE
workspace.FeedBlob(MISSING_SCALAR,
np.array([missing_value], dtype=np.float32))
C2.net().GivenTensorFill([], [MISSING_SCALAR],
shape=[],
values=[missing_value])
parameters: List[str] = [MISSING_SCALAR]
assert len(self.sorted_features) > 0, "Sorted features is empty"
dense_input = C2.NextBlob("dense_input")
dense_input_presence = C2.NextBlob("dense_input_presence")
C2.net().SparseToDenseMask(
[keys_blob, values_blob, MISSING_SCALAR, lengths_blob],
[dense_input, dense_input_presence],
mask=self.sorted_features,
return_presence_mask=True,
)
if self.set_missing_value_to_zero:
dense_input_presence = C2.And(
C2.GT(dense_input, -1e-4, broadcast=1),
C2.LT(dense_input, 1e-4, broadcast=1),
)
return dense_input, dense_input_presence, parameters
def preprocess_blob(self, blob, normalization_parameters):
"""
Takes in a blob and its normalization parameters. Outputs a tuple
whose first element is a blob containing the normalized input blob
and whose second element contains all the parameter blobs used to
create it.
Call this from a CPU context and ensure the input blob exists in it.
"""
parameters: List[str] = []
ZERO = self._store_parameter(parameters, "ZERO",
np.array([0], dtype=np.float32))
MISSING_U = self._store_parameter(
parameters, "MISSING_U",
np.array([MISSING_VALUE + 1e-4], dtype=np.float32))
MISSING_L = self._store_parameter(
parameters, "MISSING_L",
np.array([MISSING_VALUE - 1e-4], dtype=np.float32))
is_empty_l = C2.GT(blob, MISSING_L, broadcast=1)
is_empty_u = C2.LT(blob, MISSING_U, broadcast=1)
is_empty = C2.And(is_empty_l, is_empty_u)
for i in range(len(normalization_parameters) - 1):
if (normalization_parameters[i].feature_type !=
normalization_parameters[i + 1].feature_type):
raise Exception(
"Only one feature type is allowed per call to preprocess_blob!"
)
feature_type = normalization_parameters[0].feature_type
if feature_type == identify_types.BINARY:
TOLERANCE = self._store_parameter(parameters, "TOLERANCE",
np.array(1e-3, dtype=np.float32))
is_gt_zero = C2.GT(blob,
C2.Add(ZERO, TOLERANCE, broadcast=1),
broadcast=1)
is_lt_zero = C2.LT(blob,
C2.Sub(ZERO, TOLERANCE, broadcast=1),
broadcast=1)
bool_blob = C2.Or(is_gt_zero, is_lt_zero)
blob = C2.Cast(bool_blob, to=caffe2_pb2.TensorProto.FLOAT)
elif feature_type == identify_types.PROBABILITY:
blob = C2.Logit(C2.Clip(blob, min=0.01, max=0.99))
elif feature_type == identify_types.ENUM:
for parameter in normalization_parameters:
possible_values = parameter.possible_values
for x in possible_values:
if x < 0:
logger.fatal(
"Invalid enum possible value for feature: " +
str(x) + " " + str(parameter.possible_values))
raise Exception(
"Invalid enum possible value for feature " + blob +
": " + str(x) + " " +
str(parameter.possible_values))
int_blob = C2.Cast(blob, to=core.DataType.INT32)
# Batch one hot transform with MISSING_VALUE as a possible value
feature_lengths = [
len(p.possible_values) + 1 for p in normalization_parameters
]
feature_lengths_blob = self._store_parameter(
parameters,
"feature_lengths_blob",
np.array(feature_lengths, dtype=np.int32),
)
feature_values = [
x for p in normalization_parameters
for x in p.possible_values + [int(MISSING_VALUE)]
]
feature_values_blob = self._store_parameter(
parameters,
"feature_values_blob",
np.array(feature_values, dtype=np.int32),
)
one_hot_output = C2.BatchOneHot(int_blob, feature_lengths_blob,
feature_values_blob)
flattened_one_hot = C2.FlattenToVec(one_hot_output)
# Remove missing values with a mask
cols_to_include = [[1] * len(p.possible_values) + [0]
for p in normalization_parameters]
cols_to_include = [x for col in cols_to_include for x in col]
mask = self._store_parameter(
parameters, "mask", np.array(cols_to_include, dtype=np.int32))
zero_vec = C2.ConstantFill(one_hot_output,
value=0,
dtype=caffe2_pb2.TensorProto.INT32)
repeated_mask_bool = C2.Cast(C2.Add(zero_vec, mask, broadcast=1),
to=core.DataType.BOOL)
flattened_repeated_mask = C2.FlattenToVec(repeated_mask_bool)
flattened_one_hot_proc = C2.NextBlob("flattened_one_hot_proc")
flattened_one_hot_proc_indices = C2.NextBlob(
"flattened_one_hot_proc_indices")
C2.net().BooleanMask(
[flattened_one_hot, flattened_repeated_mask],
[flattened_one_hot_proc, flattened_one_hot_proc_indices],
)
one_hot_shape = C2.Shape(one_hot_output)
shape_delta = self._store_parameter(
parameters,
"shape_delta",
np.array([0, len(normalization_parameters)], dtype=np.int64),
)
target_shape = C2.Sub(one_hot_shape, shape_delta, broadcast=1)
output_int_blob = C2.NextBlob("output_int_blob")
output_int_blob_old_shape = C2.NextBlob(
"output_int_blob_old_shape")
C2.net().Reshape(
[flattened_one_hot_proc, target_shape],
[output_int_blob, output_int_blob_old_shape],
)
output_blob = C2.Cast(output_int_blob, to=core.DataType.FLOAT)
return output_blob, parameters
elif feature_type == identify_types.QUANTILE:
# This transformation replaces a set of values with their quantile.
# The quantile boundaries are provided in the normalization params.
quantile_sizes = [
len(norm.quantiles) for norm in normalization_parameters
]
num_boundaries_blob = self._store_parameter(
parameters,
"num_boundaries_blob",
np.array(quantile_sizes, dtype=np.int32),
)
quantile_values = np.array([], dtype=np.float32)
quantile_labels = np.array([], dtype=np.float32)
for norm in normalization_parameters:
quantile_values = np.append(
quantile_values, np.array(norm.quantiles,
dtype=np.float32))
# TODO: Fix this: the np.unique is making this part not true.
quantile_labels = np.append(
quantile_labels,
np.arange(len(norm.quantiles), dtype=np.float32) /
float(len(norm.quantiles)),
)
quantiles = np.vstack([quantile_values, quantile_labels]).T
quantiles_blob = self._store_parameter(parameters,
"quantiles_blob", quantiles)
quantile_blob = C2.Percentile(blob, quantiles_blob,
num_boundaries_blob)
blob = quantile_blob
elif (feature_type == identify_types.CONTINUOUS
or feature_type == identify_types.BOXCOX):
boxcox_shifts = []
boxcox_lambdas = []
means = []
stddevs = []
for norm in normalization_parameters:
if feature_type == identify_types.BOXCOX:
assert (norm.boxcox_shift is not None
and norm.boxcox_lambda is not None)
boxcox_shifts.append(norm.boxcox_shift)
boxcox_lambdas.append(norm.boxcox_lambda)
means.append(norm.mean)
stddevs.append(norm.stddev)
if feature_type == identify_types.BOXCOX:
boxcox_shift_blob = self._store_parameter(
parameters,
"boxcox_shift",
np.array(boxcox_shifts, dtype=np.float32),
)
boxcox_lambda_blob = self._store_parameter(
parameters,
"boxcox_shift",
np.array(boxcox_lambdas, dtype=np.float32),
)
blob = C2.BatchBoxCox(blob, boxcox_lambda_blob,
boxcox_shift_blob)
means_blob = self._store_parameter(
parameters, "means_blob", np.array([means], dtype=np.float32))
stddevs_blob = self._store_parameter(
parameters, "stddevs_blob",
np.array([stddevs], dtype=np.float32))
blob = C2.Sub(blob, means_blob, broadcast=1, axis=0)
blob = C2.Div(blob, stddevs_blob, broadcast=1, axis=0)
if self.clip_anomalies:
blob = C2.Clip(blob, min=-3.0, max=3.0)
else:
raise NotImplementedError(
"Invalid feature type: {}".format(feature_type))
zeros = C2.ConstantFill(blob, value=0.)
output_blob = C2.Where(is_empty, zeros, blob)
return output_blob, parameters