pickle file

src/main.py

@@ -37,17 +37,17 @@ def time_cost(func):
 def main():
     time_begin = time.time()
 
-    device_df, diary_df, click_df, conversion_df = read_csv_data(Path("~/data/cvr_data/"))
-    # print(diary_df.sample(1))
-    device_df = device_feature_engineering(device_df)
-    # print(device_df.sample(1))
-    diary_df = diary_feature_engineering(diary_df)
-    # print(diary_df.sample(1))
-    cc_df = click_feature_engineering(click_df, conversion_df)
-    df = join_features(device_df, diary_df, cc_df)
-
-    train_df, test_df = train_test_split(df, test_size=0.2)
-    train_df, val_df = train_test_split(train_df, test_size=0.2)
+    # device_df, diary_df, click_df, conversion_df = read_csv_data(Path("~/data/cvr_data/"))
+    # # print(diary_df.sample(1))
+    # device_df = device_feature_engineering(device_df)
+    # # print(device_df.sample(1))
+    # diary_df = diary_feature_engineering(diary_df)
+    # # print(diary_df.sample(1))
+    # cc_df = click_feature_engineering(click_df, conversion_df)
+    # df = join_features(device_df, diary_df, cc_df)
+
+    # train_df, test_df = train_test_split(df, test_size=0.2)
+    # train_df, val_df = train_test_split(train_df, test_size=0.2)
 
     # all_features = build_features(df)
     # params = {"feature_columns": all_features, "hidden_units": [64, 32], "learning_rate": 0.1}
@@ -68,11 +68,13 @@ def main():
     save_path = "/home/gmuser/data/models/1595317247"
 
     # save_path = str(Path("~/Desktop/models/1595297428").expanduser())
-    filename = save_path + "/saved_model.pb"
+    filename = save_path
 
     # tf.saved_model.load
 
-    predict_fn = tf.contrib.predictor.from_saved_model(filename)
+    predict_fn = tf.contrib.predictor.from_saved_model(save_path)
+    res = pickle.dumps(predict_fn)
+    print(res)
 
     # for i in range(5):
     #     test_300 = test_df.sample(300)
@@ -84,17 +86,17 @@ def main():
     #     "16195283", "16838351", "17161073", "17297878", "17307484", "17396235", "16418737", "16995481", "17312201", "12237988"
     # ]
 
-    device_dict = get_device_dict_from_redis()
-    diary_dict = get_diary_dict_from_redis()
+    # device_dict = get_device_dict_from_redis()
+    # diary_dict = get_diary_dict_from_redis()
 
-    device_ids = list(device_dict.keys())[:20]
-    diary_ids = list(diary_dict.keys())
+    # device_ids = list(device_dict.keys())[:20]
+    # diary_ids = list(diary_dict.keys())
 
-    for i in range(2):
-        time_1 = timeit.default_timer()
-        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")
+    # for i in range(2):
+    #     time_1 = timeit.default_timer()
+    #     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")
 
     total_time = (time.time() - time_begin) / 60
     print("total cost {:.2f} mins at {}".format(total_time, datetime.now()))