Add a transform_fn into DenseFeat (#309)

* Add transform_fn for DenseFeat

Author: workingloong

deepctr/feature_column.py

@@ -87,11 +87,21 @@ def __hash__(self):
         return self.name.__hash__()
 
 
-class DenseFeat(namedtuple('DenseFeat', ['name', 'dimension', 'dtype'])):
+class DenseFeat(namedtuple('DenseFeat', ['name', 'dimension', 'dtype', 'transform_fn'])):
+    """ Dense feature
+    Args:
+        name: feature name,
+        dimension: dimension of the feature, default = 1.
+        dtype: dtype of the feature, default="float32".
+        transform_fn: If not None, a function that can be used to transfrom
+        values of the feature.  the function takes the input Tensor as its
+        argument, and returns the output Tensor. 
+        (e.g. lambda x: (x - 3.0) / 4.2).
+    """
     __slots__ = ()
 
-    def __new__(cls, name, dimension=1, dtype="float32"):
-        return super(DenseFeat, cls).__new__(cls, name, dimension, dtype)
+    def __new__(cls, name, dimension=1, dtype="float32", transform_fn=None):
+        return super(DenseFeat, cls).__new__(cls, name, dimension, dtype, transform_fn)
 
     def __hash__(self):
         return self.name.__hash__()

deepctr/inputs.py

@@ -9,7 +9,7 @@
 from collections import defaultdict
 from itertools import chain
 
-from tensorflow.python.keras.layers import Embedding
+from tensorflow.python.keras.layers import Embedding, Lambda
 from tensorflow.python.keras.regularizers import l2
 
 from .layers.sequence import SequencePoolingLayer, WeightedSequenceLayer
@@ -138,7 +138,11 @@ def get_dense_input(features, feature_columns):
         filter(lambda x: isinstance(x, fc_lib.DenseFeat), feature_columns)) if feature_columns else []
     dense_input_list = []
     for fc in dense_feature_columns:
-        dense_input_list.append(features[fc.name])
+        if fc.transform_fn is None:
+            dense_input_list.append(features[fc.name])
+        else:
+            transform_result = Lambda(fc.transform_fn)(features[fc.name])
+            dense_input_list.append(transform_result)
     return dense_input_list
 
 

tests/utils.py

@@ -52,7 +52,15 @@ def get_test_data(sample_size=1000, embedding_size=4, sparse_feature_num=1, dens
             SparseFeat(prefix + 'sparse_feature_' + str(i), dim, embedding_size, use_hash=hash_flag, dtype=tf.int32,group_name=group_name))
 
     for i in range(dense_feature_num):
-        feature_columns.append(DenseFeat(prefix + 'dense_feature_' + str(i), 1, dtype=tf.float32))
+        transform_fn = lambda x: (x - 0.0)/ 1.0
+        feature_columns.append(
+            DenseFeat(
+                prefix + 'dense_feature_' + str(i),
+                1,
+                dtype=tf.float32,
+                transform_fn=transform_fn
+            )
+        )
     for i, mode in enumerate(sequence_feature):
         dim = np.random.randint(1, 10)
         maxlen = np.random.randint(1, 10)