add printer

src/main.py

@@ -14,7 +14,7 @@ from sklearn.model_selection import train_test_split
 from models.esmm.fe import (click_feature_engineering, device_feature_engineering, diary_feature_engineering,
                             get_device_dict_from_redis, get_diary_dict_from_redis, join_features, read_csv_data)
 from models.esmm.input_fn import build_features, esmm_input_fn
-from models.esmm.model import esmm_model_fn, model_export, model_predict2
+from models.esmm.model import esmm_model_fn, model_export, model_predict_diary
 
 # tf.compat.v1.enable_eager_execution()
 
@@ -94,7 +94,7 @@ def main():
 
     for i in range(2):
         time_1 = timeit.default_timer()
-        model_predict2(random.sample(device_ids, 1)[0], random.sample(diary_ids, 200), device_dict, diary_dict, predict_fn)
+        model_predict_diary(random.sample(device_ids, 1)[0], random.sample(diary_ids, 200), device_dict, diary_dict, predict_fn)
         total_1 = (timeit.default_timer() - time_1)
         print("total prediction cost {:.5f}s".format(total_1), "\n")
 

src/models/esmm/fe.py

@@ -319,9 +319,11 @@ def device_diary_fe(device_id, diary_ids, device_dict, diary_dict):
     device_info["device_sp"] = nth_element(device_sp, 0)
     device_info["device_p"] = nth_element(device_p, 0)
     diary_lst = []
+    diary_ids_res = []
     for id in diary_ids:
         diary_info = diary_dict.get(id, {}).copy()
         if diary_info:
+            diary_ids_res.append(diary_info.get("card_id", "-1"))
             diary_fd = diary_info.get("first_demands", [])
             diary_sd = diary_info.get("second_demands", [])
             diary_fs = diary_info.get("first_solutions", [])
@@ -367,4 +369,4 @@ def device_diary_fe(device_id, diary_ids, device_dict, diary_dict):
             diary_lst.append(diary_info)
     total_1 = (timeit.default_timer() - time_1)
     print("join device diary cost {:.5f}s".format(total_1))
-    return device_info, diary_lst
+    return device_info, diary_lst, diary_ids_res

src/models/esmm/model.py

@@ -95,9 +95,9 @@ def _bytes_feature(value):
     return tf.train.Feature(bytes_list=tf.train.BytesList(value=[value]))
 
 
-def model_predict2(device_id, diary_ids, device_dict, diary_dict, predict_fn):
+def model_predict_diary(device_id, diary_ids, device_dict, diary_dict, predict_fn):
     time_1 = timeit.default_timer()
-    device_info, diary_lst = device_diary_fe(device_id, diary_ids, device_dict, diary_dict)
+    device_info, diary_lst, diary_ids_res = device_diary_fe(device_id, diary_ids, device_dict, diary_dict)
     int_columns = [
         "active_type", "active_days", "card_id", "is_pure_author", "is_have_reply", "is_have_pure_reply", "content_level",
         "topic_num", "favor_num", "vote_num"
@@ -134,7 +134,9 @@ def model_predict2(device_id, diary_ids, device_dict, diary_dict, predict_fn):
         diary_ids.append(i.get("card_id", "-1"))
     print(predictions)
     print(predictions["output"].tolist())
+    print(diary_ids_res)
     print(diary_ids)
+    print(len(predictions["output"].tolist()), len(diary_ids), len(diary_ids_res))
     total_1 = (timeit.default_timer() - time_1)
     print("prediction cost {:.5f}s".format(total_1))
     return predictions