fix error when linear_feature_columns is empty in tf1.12

Author: shenweichen

deepctr/feature_column.py

@@ -180,9 +180,8 @@ def get_linear_logit(features, feature_columns, units=1, use_bias=False, seed=10
         elif len(dense_input_list) > 0:
             dense_input = concat_func(dense_input_list)
             linear_logit = Linear(l2_reg, mode=1, use_bias=use_bias, seed=seed)(dense_input)
-        else:
-            # raise NotImplementedError
-            return add_func([])
+        else:   #empty feature_columns
+            return Lambda(lambda x: tf.constant([[0.0]]))(features.values()[0])
         linear_logit_list.append(linear_logit)
 
     return concat_func(linear_logit_list)

examples/run_classification_criteo.py

@@ -25,9 +25,9 @@
 
     # 2.count #unique features for each sparse field,and record dense feature field name
 
-    fixlen_feature_columns = [SparseFeat(feat, vocabulary_size=data[feat].max() + 1,embedding_dim=4 )
-                           for i,feat in enumerate(sparse_features)] + [DenseFeat(feat, 1,)
-                          for feat in dense_features]
+    fixlen_feature_columns = [SparseFeat(feat, vocabulary_size=data[feat].max() + 1, embedding_dim=4)
+                              for i, feat in enumerate(sparse_features)] + [DenseFeat(feat, 1, )
+                                                                            for feat in dense_features]
 
     dnn_feature_columns = fixlen_feature_columns
     linear_feature_columns = fixlen_feature_columns
@@ -37,8 +37,8 @@
     # 3.generate input data for model
 
     train, test = train_test_split(data, test_size=0.2, random_state=2020)
-    train_model_input = {name:train[name] for name in feature_names}
-    test_model_input = {name:test[name] for name in feature_names}
+    train_model_input = {name: train[name] for name in feature_names}
+    test_model_input = {name: test[name] for name in feature_names}
 
     # 4.Define Model,train,predict and evaluate
     model = DeepFM(linear_feature_columns, dnn_feature_columns, task='binary')

tests/models/DCN_test.py

@@ -25,6 +25,18 @@ def test_DCN(cross_num, hidden_size, sparse_feature_num, cross_parameterization)
     check_model(model, model_name, x, y)
 
 
+def test_DCN_2():
+    model_name = "DCN"
+
+    sample_size = SAMPLE_SIZE
+    x, y, feature_columns = get_test_data(sample_size, sparse_feature_num=3,
+                                          dense_feature_num=2)
+
+    model = DCN([], feature_columns, cross_num=1, cross_parameterization=cross_parameterization,
+                dnn_hidden_units=8, dnn_dropout=0.5)
+    check_model(model, model_name, x, y)
+
+
 @pytest.mark.parametrize(
     'cross_num,hidden_size,sparse_feature_num',
     [(1, (8,), 3)