test features

eda/esmm/Model_pipline/train.py

@@ -64,7 +64,8 @@ def input_fn(filenames, batch_size=32, num_epochs=1, perform_shuffle=False):
             "tag4_list": tf.VarLenFeature(tf.int64),
             "tag5_list": tf.VarLenFeature(tf.int64),
             "tag6_list": tf.VarLenFeature(tf.int64),
-            "tag7_list": tf.VarLenFeature(tf.int64)
+            "tag7_list": tf.VarLenFeature(tf.int64),
+            "number": tf.VarLenFeature(tf.int64)
         }
         parsed = tf.parse_single_example(record, features)
         y = parsed.pop('y')
@@ -131,6 +132,7 @@ def model_fn(features, labels, mode, params):
     tag5_list = features['tag5_list']
     tag6_list = features['tag6_list']
     tag7_list = features['tag7_list']
+    number = features['features']
 
     if FLAGS.task_type != "infer":
         y = labels['y']
@@ -153,6 +155,7 @@ def model_fn(features, labels, mode, params):
         # x_concat = tf.reshape(embedding_id,shape=[-1, common_dims])  # None * (F * K)
         x_concat = tf.concat([tf.reshape(embedding_id, shape=[-1, common_dims]), app_id, level2, level3, tag1,
                               tag2, tag3, tag4, tag5, tag6, tag7], axis=1)
+        number1 = tf.reshape(number,shape=[-1])
 
     with tf.name_scope("CVR_Task"):
         if mode == tf.estimator.ModeKeys.TRAIN:
@@ -197,8 +200,9 @@ def model_fn(features, labels, mode, params):
         pctr = tf.sigmoid(y_ctr)
         pcvr = tf.sigmoid(y_cvr)
         pctcvr = pctr*pcvr
+        sample_id = number1
 
-    predictions={"pcvr": pcvr, "pctr": pctr, "pctcvr": pctcvr}
+    predictions={"pcvr": pcvr, "pctr": pctr, "pctcvr": pctcvr, "sample_id": sample_id}
     export_outputs = {tf.saved_model.signature_constants.DEFAULT_SERVING_SIGNATURE_DEF_KEY: tf.estimator.export.PredictOutput(predictions)}
     # Provide an estimator spec for `ModeKeys.PREDICT`
     if mode == tf.estimator.ModeKeys.PREDICT: