printer

src/main_portrait.py

@@ -35,7 +35,7 @@ def user_portrait_scan_info(device_dict, diary_dict, predict_fn):
 
 def offline_predict(device_id, device_dict, diary_dict, predict_fn):
     diary_ids = user_portrait_tag3_get_candidate_unread_list(device_id, "diary")
-    print(diary_ids)
+    print(diary_ids[:10])
     res = model_predict_diary(device_id, diary_ids, device_dict, diary_dict, predict_fn)
     print(res[:10])
     # user_portrait_tag3_write_ctcvr_data(device_id, "diary", res)

src/models/esmm/model.py

@@ -113,6 +113,8 @@ def model_predict_diary(device_id, diary_ids, device_dict, diary_dict, predict_f
         tmp = {}
         tmp.update(device_info)
         tmp.update(diary_info)
+        # TODO
+        print(tmp)
         features = {}
         for col in int_columns:
             features[col] = _int64_feature(int(tmp[col]))
@@ -123,11 +125,15 @@ def model_predict_diary(device_id, diary_ids, device_dict, diary_dict, predict_f
         example = tf.train.Example(features=tf.train.Features(feature=features))
         examples.append(example.SerializeToString())
 
+    # TODO
+    print(examples)
     total_1 = (timeit.default_timer() - time_1)
     print("make example cost {:.5f}s".format(total_1))
 
     time_1 = timeit.default_timer()
     predictions = predict_fn({"examples": examples})
+    # TODO
+    print(predictions)
     res_tuple = sorted(zip(diary_ids_res, predictions["output"].tolist()), key=lambda x: x[1], reverse=True)
     res = []
     for (id, _) in res_tuple: