train diar

src/train_diary.py

@@ -19,73 +19,70 @@ from utils.cache import get_essm_model_save_path, set_essm_model_save_path
 def main():
     time_begin = time.time()
 
-    # tf.compat.v1.logging.set_verbosity(tf.compat.v1.logging.INFO)
-
-    # # os.environ["CUDA_VISIBLE_DEVICES"] = "-1"
-
-    # diary_train_columns = set(diary_fe.INT_COLUMNS + diary_fe.FLOAT_COLUMNS + diary_fe.CATEGORICAL_COLUMNS)
-    # print("features: " + str(len(diary_train_columns)))
-    # diary_predict_columns = set(PREDICTION_ALL_COLUMNS)
-    # print(diary_predict_columns.difference(diary_train_columns))
-    # print(diary_train_columns.difference(diary_predict_columns))
-    # assert diary_predict_columns == diary_train_columns
-
-    # # dataset_path = Path("~/data/cvr_data").expanduser()  # local
-    # dataset_path = Path("/srv/apps/node2vec_git/cvr_data/")  # server
-    # diary_df, diary_click_df, diary_conversion_df = diary_fe.read_csv_data(dataset_path)
-    # # print(diary_df.sample(1))
-    # diary_df = diary_fe.diary_feature_engineering(diary_df)
-    # # print(diary_df.sample(1))
-    # device_df = device_fe.read_csv_data(dataset_path)
-    # # print(diary_df.sample(1))
-    # device_df = device_fe.device_feature_engineering(device_df, "diary")
-    # # print(device_df.sample(1))
-    # cc_df = click_fe.click_feature_engineering(diary_click_df, diary_conversion_df)
-    # # print(cc_df.sample(1))
-    # df = diary_fe.join_features(device_df, diary_df, cc_df)
-    # # print(df.sample(1))
-    # # print(df.dtypes)
-
-    # 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 = fe.build_features(df, diary_fe.INT_COLUMNS, diary_fe.FLOAT_COLUMNS, diary_fe.CATEGORICAL_COLUMNS)
-    # params = {"feature_columns": all_features, "hidden_units": [64, 32], "learning_rate": 0.1}
-    # model_path = str(Path("/data/files/model_tmp/diary/").expanduser())
-    # if os.path.exists(model_path):
-    #     shutil.rmtree(model_path)
-
-    # session_config = tf.compat.v1.ConfigProto()
-    # session_config.gpu_options.allow_growth = True
-    # session_config.gpu_options.per_process_gpu_memory_fraction = 0.9
-    # estimator_config = tf.estimator.RunConfig(session_config=session_config)
-
-    # model = tf.estimator.Estimator(model_fn=esmm_model_fn, params=params, model_dir=model_path, config=estimator_config)
-    # # TODO 50000
-    # train_spec = tf.estimator.TrainSpec(input_fn=lambda: esmm_input_fn(train_df, shuffle=True), max_steps=15000)
-    # eval_spec = tf.estimator.EvalSpec(input_fn=lambda: esmm_input_fn(val_df, shuffle=False))
-    # res = tf.estimator.train_and_evaluate(model, train_spec, eval_spec)
-    # print("@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@")
-    # print(res[0])
-    # print("ctr_auc: " + str(res[0]["ctr_auc"]))
-    # print("ctcvr_auc: " + str(res[0]["ctcvr_auc"]))
-    # print("@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@")
-
-    # model_export_path = str(Path("/data/files/models/diary").expanduser())
-    # save_path = model_export(model, all_features, model_export_path)
-    # print("save to: " + save_path)
-    # # TODO save
-    # # set_essm_model_save_path("diary", save_path)
-    # print("============================================================")
+    tf.compat.v1.logging.set_verbosity(tf.compat.v1.logging.INFO)
+
+    # os.environ["CUDA_VISIBLE_DEVICES"] = "-1"
+
+    diary_train_columns = set(diary_fe.INT_COLUMNS + diary_fe.FLOAT_COLUMNS + diary_fe.CATEGORICAL_COLUMNS)
+    print("features: " + str(len(diary_train_columns)))
+    diary_predict_columns = set(PREDICTION_ALL_COLUMNS)
+    print(diary_predict_columns.difference(diary_train_columns))
+    print(diary_train_columns.difference(diary_predict_columns))
+    assert diary_predict_columns == diary_train_columns
+
+    # dataset_path = Path("~/data/cvr_data").expanduser()  # local
+    dataset_path = Path("/srv/apps/node2vec_git/cvr_data/")  # server
+    diary_df, diary_click_df, diary_conversion_df = diary_fe.read_csv_data(dataset_path)
+    # print(diary_df.sample(1))
+    diary_df = diary_fe.diary_feature_engineering(diary_df)
+    # print(diary_df.sample(1))
+    device_df = device_fe.read_csv_data(dataset_path)
+    # print(diary_df.sample(1))
+    device_df = device_fe.device_feature_engineering(device_df, "diary")
+    # print(device_df.sample(1))
+    cc_df = click_fe.click_feature_engineering(diary_click_df, diary_conversion_df)
+    # print(cc_df.sample(1))
+    df = diary_fe.join_features(device_df, diary_df, cc_df)
+    # print(df.sample(1))
+    # print(df.dtypes)
+
+    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 = fe.build_features(df, diary_fe.INT_COLUMNS, diary_fe.FLOAT_COLUMNS, diary_fe.CATEGORICAL_COLUMNS)
+    params = {"feature_columns": all_features, "hidden_units": [64, 32], "learning_rate": 0.1}
+    model_path = str(Path("/data/files/model_tmp/diary/").expanduser())
+    if os.path.exists(model_path):
+        shutil.rmtree(model_path)
+
+    session_config = tf.compat.v1.ConfigProto()
+    session_config.gpu_options.allow_growth = True
+    session_config.gpu_options.per_process_gpu_memory_fraction = 0.9
+    estimator_config = tf.estimator.RunConfig(session_config=session_config)
+
+    model = tf.estimator.Estimator(model_fn=esmm_model_fn, params=params, model_dir=model_path, config=estimator_config)
+    train_spec = tf.estimator.TrainSpec(input_fn=lambda: esmm_input_fn(train_df, shuffle=True), max_steps=50000)
+    eval_spec = tf.estimator.EvalSpec(input_fn=lambda: esmm_input_fn(val_df, shuffle=False))
+    res = tf.estimator.train_and_evaluate(model, train_spec, eval_spec)
+    print("@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@")
+    print(res[0])
+    print("ctr_auc: " + str(res[0]["ctr_auc"]))
+    print("ctcvr_auc: " + str(res[0]["ctcvr_auc"]))
+    print("@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@")
+
+    model_export_path = str(Path("/data/files/models/diary").expanduser())
+    save_path = model_export(model, all_features, model_export_path)
+    print("save to: " + save_path)
+    set_essm_model_save_path("diary", save_path)
+    print("============================================================")
 
     # save_path = str(Path("~/Desktop/models/1596012827").expanduser())  # local
     # save_path = "/data/files/models/diary/1597390452"  # server
 
     # tf.saved_model.load
 
-    # TODO
-    save_path = get_essm_model_save_path("diary")
-    print("load path: " + save_path)
+    # save_path = get_essm_model_save_path("diary")
+    # print("load path: " + save_path)
     predict_fn = tf.contrib.predictor.from_saved_model(save_path)
 
     device_dict = device_fe.get_device_dict_from_redis()