add printer

src/main.py

@@ -20,36 +20,36 @@ 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)
+    # 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)
+    # 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)
+    # all_features = build_features(df)
 
-    params = {"feature_columns": all_features, "hidden_units": [64, 32], "learning_rate": 0.1}
-    model_path = str(Path("~/data/model_tmp/").expanduser())
-    if os.path.exists(model_path):
-        shutil.rmtree(model_path)
-    model = tf.estimator.Estimator(model_fn=esmm_model_fn, params=params, model_dir=model_path)
+    # params = {"feature_columns": all_features, "hidden_units": [64, 32], "learning_rate": 0.1}
+    # model_path = str(Path("~/data/model_tmp/").expanduser())
+    # if os.path.exists(model_path):
+    #     shutil.rmtree(model_path)
+    # model = tf.estimator.Estimator(model_fn=esmm_model_fn, params=params, model_dir=model_path)
 
-    print("train")
-    model.train(input_fn=lambda: esmm_input_fn(train_df, shuffle=True), steps=5000)
-    metrics = model.evaluate(input_fn=lambda: esmm_input_fn(val_df, False), steps=5000)
-    print("metrics: " + str(metrics))
+    # print("train")
+    # model.train(input_fn=lambda: esmm_input_fn(train_df, shuffle=True), steps=5000)
+    # metrics = model.evaluate(input_fn=lambda: esmm_input_fn(val_df, False), steps=5000)
+    # print("metrics: " + str(metrics))
 
-    model_export_path = str(Path("~/data/models/").expanduser())
-    save_path = model_export(model, all_features, model_export_path)
-    print("save to: " + save_path)
+    # model_export_path = str(Path("~/data/models/").expanduser())
+    # 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)
+    # predict_fn = tf.contrib.predictor.from_saved_model(save_path)
 
     # for i in range(10):
     #     test_300 = test_df.sample(300)
@@ -63,13 +63,18 @@ def main():
 
     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)
+
+    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)
+    # 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()))

src/models/esmm/model.py

@@ -113,6 +113,6 @@ def model_predict(inputs, predict_fn):
     time_1 = timeit.default_timer()
     predictions = predict_fn({"examples": examples})
     total_1 = (timeit.default_timer() - time_1)
-    print("prediction cost {:.5f} s".format(total_1))
+    print("prediction cost {:.5f}s".format(total_1))
     # print(predictions)
     return predictions