add printer

src/main.py

@@ -20,17 +20,17 @@ from models.esmm.model import esmm_model_fn, model_export, model_predict
 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)
 
@@ -49,33 +49,34 @@ def main():
     # save_path = model_export(model, all_features, model_export_path)
     # print("save to: " + save_path)
 
-    # predict_fn = tf.contrib.predictor.from_saved_model(save_path)
-
-    # for i in range(10):
-    #     test_300 = test_df.sample(300)
-    #     model_predict(test_300, predict_fn)
-
-    print("==============================")
-    device_id = "861601036552944"
-    diary_ids = [
-        "16195283", "16838351", "17161073", "17297878", "17307484", "17396235", "16418737", "16995481", "17312201", "12237988"
-    ]
-
-    df = get_device_df_from_redis()
-    df2 = get_diary_df_from_redis()
-    redis_device_df = device_feature_engineering(df)
-    redis_diary_df = diary_feature_engineering(df2, from_redis=True)
-    print(list(redis_diary_df["card_id"].values)[:10])
-
-    time_1 = timeit.default_timer()
-    res = join_device_diary(device_id, diary_ids, redis_device_df, redis_diary_df)
-    print(len(res))
-    print(res.sample(1), "\n")
-    print(res.sample(1))
-
-    # model_predict(res, predict_fn)
-    total_1 = (timeit.default_timer() - time_1)
-    print("prediction total cost {:.5f}s".format(total_1))
+    save_path = "/home/gmuser/data/models/1595317247"
+    predict_fn = tf.contrib.predictor.from_saved_model(save_path)
+
+    for i in range(10):
+        test_300 = test_df.sample(300)
+        model_predict(test_300, predict_fn)
+
+    # print("==============================")
+    # device_id = "861601036552944"
+    # diary_ids = [
+    #     "16195283", "16838351", "17161073", "17297878", "17307484", "17396235", "16418737", "16995481", "17312201", "12237988"
+    # ]
+
+    # df = get_device_df_from_redis()
+    # df2 = get_diary_df_from_redis()
+    # redis_device_df = device_feature_engineering(df)
+    # redis_diary_df = diary_feature_engineering(df2, from_redis=True)
+    # diary_ids = list(redis_diary_df["card_id"].values)[:300]
+
+    # time_1 = timeit.default_timer()
+    # res = join_device_diary(device_id, diary_ids, redis_device_df, redis_diary_df)
+    # print(len(res))
+    # print(res.sample(1), "\n")
+    # print(res.sample(1))
+
+    # # model_predict(res, predict_fn)
+    # total_1 = (timeit.default_timer() - time_1)
+    # print("prediction total cost {:.5f}s".format(total_1))
 
     total_time = (time.time() - time_begin) / 60
     print("cost {:.2f} mins at {}".format(total_time, datetime.now()))