update trace price type

src/models/esmm/diary_model.py

@@ -174,7 +174,11 @@ _categorical_columns = [
     "click_diary_id3",
     "click_diary_id4",
     "click_diary_id5",
+    "service_id",
     "service_city",
+    "recommend_service_id",
+    "recommend_service_city",
+    "recommend_service_price",
     "device_fd2",
     "device_sd2",
     "device_fs2",

src/models/esmm/fe/diary_fe.py

@@ -129,9 +129,13 @@ DIARY_COLUMNS = [
     "business_second_skip_num",
     "effect_second_skip_rate",
     "business_second_skip_rate",
+    "service_id",
     "service_price",
     "service_sold_num",
     "service_city",
+    "recommend_service_id",
+    "recommend_service_city",
+    "recommend_service_price",
 ]
 INT_COLUMNS = [
     "active_days",
@@ -302,7 +306,11 @@ CATEGORICAL_COLUMNS = [
     "click_diary_id4",
     "click_diary_id5",
     "is_related_service",
+    "service_id",
     "service_city",
+    "recommend_service_id",
+    "recommend_service_city",
+    "recommend_service_price",
     "device_fd2",
     "device_sd2",
     "device_fs2",
@@ -415,7 +423,14 @@ def diary_feature_engineering(df):
     diary_df["is_have_reply"] = diary_df["is_have_reply"].astype(int)
 
     diary_df["is_related_service"] = diary_df["is_related_service"].astype(int)
+    diary_df["service_id"] = diary_df["service_id"].astype(str)
+    diary_df["recommend_service_id"] = diary_df["recommend_service_id"].astype(str)
+    diary_df["recommend_service_price"] = diary_df["recommend_service_price"].astype(str)
+
+    diary_df["service_id"] = diary_df["service_city"].fillna("-1")
     diary_df["service_city"] = diary_df["service_city"].fillna("")
+    diary_df["recommend_service_id"] = diary_df["recommend_service_id"].fillna("-1")
+    diary_df["recommend_service_city"] = diary_df["recommend_service_city"].fillna("")
 
     diary_df = diary_df[DIARY_COLUMNS]
 

src/models/esmm/fe/tractate_fe.py

@@ -407,13 +407,14 @@ def tractate_feature_engineering(tractate_df):
     df["is_have_pure_reply"] = df["is_have_pure_reply"].astype(int)
     df["is_have_reply"] = df["is_have_reply"].astype(int)
     df["show_tag_id"] = df["show_tag_id"].astype(str)
-    df["service_id"] = df["service_id"].astype(str)
-    df["recommend_service_id"] = df["recommend_service_id"].astype(str)
 
     df["is_related_service"] = df["is_related_service"].astype(int)
-    df["service_city"] = df["service_city"].fillna("")
+    df["service_id"] = df["service_id"].astype(str)
+    df["recommend_service_id"] = df["recommend_service_id"].astype(str)
+    df["recommend_service_price"] = df["recommend_service_price"].astype(str)
 
     df["service_id"] = df["service_city"].fillna("-1")
+    df["service_city"] = df["service_city"].fillna("")
     df["recommend_service_id"] = df["recommend_service_id"].fillna("-1")
     df["recommend_service_city"] = df["recommend_service_city"].fillna("")
 

src/online_prediction.py

@@ -46,6 +46,12 @@ if __name__ == "__main__":
     tractate_dict = tractate_fe.get_tractate_dict_from_redis()
     print("redis data: " + str(len(device_dict)) + " " + str(len(diary_dict)) + " " + str(len(tractate_dict)))
 
+    # device_ids = list(device_dict.keys())[:20]
+    # tractate_ids = list(tractate_dict.keys())[:20]
+
+    # print(device_dict[device_ids[0]], "\n")
+    # print(tractate_dict[tractate_ids[0]], "\n")
+
     diary_save_path = get_essm_model_save_path("diary")
     if not diary_save_path:
         diary_save_path = "/data/files/models/diary/1597390452"

src/train_diary.py

@@ -65,7 +65,8 @@ def main():
     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)
+    # TODO 50000
+    train_spec = tf.estimator.TrainSpec(input_fn=lambda: esmm_input_fn(train_df, shuffle=True), max_steps=13000)
     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("@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@")
@@ -80,8 +81,9 @@ def main():
     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)
-    record_esmm_auc_to_db("diary", ctr_auc, ctcvr_auc, total_time, save_path)
+    # TODO save model
+    # set_essm_model_save_path("diary", save_path)
+    # record_esmm_auc_to_db("diary", ctr_auc, ctcvr_auc, total_time, save_path)
     print("============================================================")
 
     # save_path = str(Path("~/Desktop/models/1596012827").expanduser())  # local

src/train_tractate.py

@@ -63,7 +63,7 @@ def main():
 
     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)
+    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("@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@")
@@ -87,7 +87,7 @@ def main():
     # print("load path: " + save_path)
 
     # save_path = str(Path("~/data/models/tractate/1598236893").expanduser())  # local
-    # save_path = "/data/files/models/tractate/1598254242"  # server
+    save_path = "/data/files/models/tractate/1599123885"  # server
     predict_fn = tf.contrib.predictor.from_saved_model(save_path)
 
     device_dict = device_fe.get_device_dict_from_redis()