update tractate model

src/models/esmm/diary_model.py

@@ -92,7 +92,6 @@ _int_columns = [
     "business_second_skip_num",
     "service_price",
     "service_sold_num",
-    "recommend_service_price",
 ]
 _float_columns = [
     "one_ctr",
@@ -179,6 +178,7 @@ _categorical_columns = [
     "service_city",
     "recommend_service_id",
     "recommend_service_city",
+    "recommend_service_price",
     "device_fd2",
     "device_sd2",
     "device_fs2",

src/train_tractate.py

@@ -22,71 +22,69 @@ def main():
 
     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,
-    #                                  tractate_fe.CROSS_COLUMNS)
-    # params = {"feature_columns": all_features, "hidden_units": [360, 200, 80, 2], "learning_rate": 0.2}
-    # 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 = 0.7
-    # # session_config.inter_op_parallelism_threads = 1
-    # # session_config.intra_op_parallelism_threads = 1
-    # 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=12000)
-    # 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])
-    # ctr_auc = str(res[0]["ctr_auc"])
-    # ctcvr_auc = str(res[0]["ctcvr_auc"])
-    # print("ctr_auc: " + ctr_auc)
-    # print("ctcvr_auc: " + ctcvr_auc)
-    # print("@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@")
+    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,
+                                     tractate_fe.CROSS_COLUMNS)
+    params = {"feature_columns": all_features, "hidden_units": [360, 200, 80, 2], "learning_rate": 0.2}
+    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 = 0.7
+    # session_config.inter_op_parallelism_threads = 1
+    # session_config.intra_op_parallelism_threads = 1
+    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])
+    ctr_auc = str(res[0]["ctr_auc"])
+    ctcvr_auc = str(res[0]["ctcvr_auc"])
+    print("ctr_auc: " + ctr_auc)
+    print("ctcvr_auc: " + ctcvr_auc)
+    print("@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@")
     total_time = "{:.2f}".format((time.time() - time_begin) / 60)
 
-    # 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)
-    # # record_esmm_auc_to_db("tractate", ctr_auc, ctcvr_auc, total_time, save_path)
-    # 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)
+    set_essm_model_save_path("tractate", save_path)
+    record_esmm_auc_to_db("tractate", ctr_auc, ctcvr_auc, total_time, save_path)
+    print("============================================================")
 
-    # save_path = get_essm_model_save_path("tractate")
-    # print("load path: " + save_path)
+    save_path = get_essm_model_save_path("tractate")
+    print("load path: " + save_path)
 
-    # save_path = str(Path("~/data/models/tractate/1598236893").expanduser())  # local
+    save_path = str(Path("~/data/models/tractate/1598236893").expanduser())  # local
     save_path = "/data/files/models/tractate/1599128140"  # server
     predict_fn = tf.contrib.predictor.from_saved_model(save_path)