try get data from redis

src/models/esmm/fe/tractate_fe.py

@@ -224,6 +224,8 @@ def get_tractate_dict_from_redis():
                     "second_positions", "projects"
             ]:
                 tmp[col_name] = elem.split(",")
+                if "" in tmp[col_name]:
+                    tmp[col_name].remove("")
                 tmp[col_name + "_num"] = len(tmp[col_name])
             elif col_name in ["is_pure_author", "is_have_pure_reply", "is_have_reply"]:
                 if elem == "true":

src/train_tractate.py

@@ -13,70 +13,71 @@ from models.esmm.fe import click_fe, device_fe, fe, tractate_fe
 from models.esmm.input_fn import esmm_input_fn
 from models.esmm.model import esmm_model_fn, model_export
 from models.esmm.tractate_model import (PREDICTION_ALL_COLUMNS, model_predict_tractate)
-from utils.cache import set_essm_model_save_path
+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)
-
-    tractate_train_columns = set(tractate_fe.INT_COLUMNS + tractate_fe.FLOAT_COLUMNS + tractate_fe.CATEGORICAL_COLUMNS)
-    print("features: " + str(len(tractate_train_columns)))
-    tractate_predict_columns = set(PREDICTION_ALL_COLUMNS)
-    print(tractate_predict_columns.difference(tractate_train_columns))
-    print(tractate_train_columns.difference(tractate_predict_columns))
-    assert tractate_predict_columns == tractate_train_columns
-
-    # dataset_path = Path("~/data/cvr_data").expanduser()  # local
-    dataset_path = Path("/srv/apps/node2vec_git/cvr_data/")  # server
-    tractate_df, tractate_click_df, tractate_conversion_df = tractate_fe.read_csv_data(dataset_path)
-    tractate_df = tractate_fe.tractate_feature_engineering(tractate_df)
-    device_df = device_fe.read_csv_data(dataset_path)
-    device_df = device_fe.device_feature_engineering(device_df, "tractate")
-    # print(device_df.columns)
-    # print(device_df.dtypes, "\n")
-
-    cc_df = click_fe.click_feature_engineering(tractate_click_df, tractate_conversion_df)
-    df = tractate_fe.join_features(device_df, tractate_df, cc_df)
-    # for i in df.columns:
-    #     print(i)
-    # 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, tractate_fe.INT_COLUMNS, tractate_fe.FLOAT_COLUMNS, tractate_fe.CATEGORICAL_COLUMNS)
-    params = {"feature_columns": all_features, "hidden_units": [64, 32], "learning_rate": 0.1}
-    model_path = str(Path("/data/files/model_tmp/tractate/").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=20000)
-    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/tractate/").expanduser())
-    save_path = model_export(model, all_features, model_export_path)
-    print("save to: " + save_path)
-    # TODO save model
-    # set_essm_model_save_path("tractate", save_path)
-    print("============================================================")
-
+    # tf.compat.v1.logging.set_verbosity(tf.compat.v1.logging.INFO)
+
+    # tractate_train_columns = set(tractate_fe.INT_COLUMNS + tractate_fe.FLOAT_COLUMNS + tractate_fe.CATEGORICAL_COLUMNS)
+    # print("features: " + str(len(tractate_train_columns)))
+    # tractate_predict_columns = set(PREDICTION_ALL_COLUMNS)
+    # print(tractate_predict_columns.difference(tractate_train_columns))
+    # print(tractate_train_columns.difference(tractate_predict_columns))
+    # assert tractate_predict_columns == tractate_train_columns
+
+    # # dataset_path = Path("~/data/cvr_data").expanduser()  # local
+    # dataset_path = Path("/srv/apps/node2vec_git/cvr_data/")  # server
+    # tractate_df, tractate_click_df, tractate_conversion_df = tractate_fe.read_csv_data(dataset_path)
+    # tractate_df = tractate_fe.tractate_feature_engineering(tractate_df)
+    # device_df = device_fe.read_csv_data(dataset_path)
+    # device_df = device_fe.device_feature_engineering(device_df, "tractate")
+    # # print(device_df.columns)
+    # # print(device_df.dtypes, "\n")
+
+    # cc_df = click_fe.click_feature_engineering(tractate_click_df, tractate_conversion_df)
+    # df = tractate_fe.join_features(device_df, tractate_df, cc_df)
+    # # for i in df.columns:
+    # #     print(i)
+    # # 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, tractate_fe.INT_COLUMNS, tractate_fe.FLOAT_COLUMNS, tractate_fe.CATEGORICAL_COLUMNS)
+    # params = {"feature_columns": all_features, "hidden_units": [64, 32], "learning_rate": 0.1}
+    # model_path = str(Path("/data/files/model_tmp/tractate/").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=20000)
+    # 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/tractate/").expanduser())
+    # save_path = model_export(model, all_features, model_export_path)
+    # print("save to: " + save_path)
+    # # TODO save model
+    # # set_essm_model_save_path("tractate", save_path)
+    # print("============================================================")
+
+    save_path = get_essm_model_save_path("diary")
+    print("load path: " + save_path)
     # # save_path = str(Path("~/data/models/tractate/1596089465").expanduser())  # local
-    # save_path = "/data/files/models/tractate/1597390051"  # server
     predict_fn = tf.contrib.predictor.from_saved_model(save_path)
 
     device_dict = device_fe.get_device_dict_from_redis()