service feature

pyrightconfig.json

+{
+  "executionEnvironments": [{ "root": "src" }]
+}

src/models/esmm/diary_model.py

@@ -87,6 +87,11 @@ _int_columns = [
     "first_positions_num",
     "second_positions_num",
     "projects_num",
+    "is_related_service",
+    "effect_second_skip_num",
+    "business_second_skip_num",
+    "service_price",
+    "service_sold_num",
 ]
 _float_columns = [
     "one_ctr",
@@ -121,13 +126,55 @@ _float_columns = [
     "sixty_browse_duration_avg",
     "ninety_browse_duration_avg",
     "history_browse_duration_avg",
+    "effect_second_skip_rate",
+    "business_second_skip_rate",
 ]
 _categorical_columns = [
-    "device_id", "past_consume_ability_history", "potential_consume_ability_history", "price_sensitive_history", "device_fd",
-    "device_sd", "device_fs", "device_ss", "device_fp", "device_sp", "device_p", "content_fd", "content_sd", "content_fs",
-    "content_ss", "content_fp", "content_sp", "content_p", "fd1", "fd2", "fd3", "sd1", "sd2", "sd3", "fs1", "fs2", "fs3", "ss1",
-    "ss2", "ss3", "fp1", "fp2", "fp3", "sp1", "sp2", "sp3", "p1", "p2", "p3", "click_diary_id1", "click_diary_id2",
-    "click_diary_id3", "click_diary_id4", "click_diary_id5"
+    "device_id",
+    "past_consume_ability_history",
+    "potential_consume_ability_history",
+    "price_sensitive_history",
+    "device_fd",
+    "device_sd",
+    "device_fs",
+    "device_ss",
+    "device_fp",
+    "device_sp",
+    "device_p",
+    "content_fd",
+    "content_sd",
+    "content_fs",
+    "content_ss",
+    "content_fp",
+    "content_sp",
+    "content_p",
+    "fd1",
+    "fd2",
+    "fd3",
+    "sd1",
+    "sd2",
+    "sd3",
+    "fs1",
+    "fs2",
+    "fs3",
+    "ss1",
+    "ss2",
+    "ss3",
+    "fp1",
+    "fp2",
+    "fp3",
+    "sp1",
+    "sp2",
+    "sp3",
+    "p1",
+    "p2",
+    "p3",
+    "click_diary_id1",
+    "click_diary_id2",
+    "click_diary_id3",
+    "click_diary_id4",
+    "click_diary_id5",
+    "service_city",
 ]
 
 PREDICTION_ALL_COLUMNS = _int_columns + _float_columns + _categorical_columns

src/models/esmm/fe/device_fe.py

 import pandas as pd
 from utils.cache import redis_db_client
 
-# "channel_first", "city_first", "model_first",
 DIARY_DEVICE_COLUMNS = [
-    "device_id", "active_type", "active_days", "past_consume_ability_history", "potential_consume_ability_history",
-    "price_sensitive_history", "first_demands", "second_demands", "first_solutions", "second_solutions", "first_positions",
-    "second_positions", "projects", "click_diary_id1", "click_diary_id2", "click_diary_id3", "click_diary_id4", "click_diary_id5"
+    "device_id",
+    "active_type",
+    "active_days",
+    "past_consume_ability_history",
+    "potential_consume_ability_history",
+    "price_sensitive_history",
+    "first_demands",
+    "second_demands",
+    "first_solutions",
+    "second_solutions",
+    "first_positions",
+    "second_positions",
+    "projects",
+    "click_diary_id1",
+    "click_diary_id2",
+    "click_diary_id3",
+    "click_diary_id4",
+    "click_diary_id5",
 ]
 
 TRACTATE_DEVICE_COLUMNS = [
-    "device_id", "active_type", "active_days", "channel_first", "city_first", "model_first", "past_consume_ability_history",
-    "potential_consume_ability_history", "price_sensitive_history", "first_demands", "second_demands", "first_solutions",
-    "second_solutions", "first_positions", "second_positions", "projects", "click_tractate_id1", "click_tractate_id2",
-    "click_tractate_id3", "click_tractate_id4", "click_tractate_id5"
+    "device_id",
+    "active_type",
+    "active_days",
+    "channel_first",
+    "city_first",
+    "model_first",
+    "past_consume_ability_history",
+    "potential_consume_ability_history",
+    "price_sensitive_history",
+    "first_demands",
+    "second_demands",
+    "first_solutions",
+    "second_solutions",
+    "first_positions",
+    "second_positions",
+    "projects",
+    "click_tractate_id1",
+    "click_tractate_id2",
+    "click_tractate_id3",
+    "click_tractate_id4",
+    "click_tractate_id5",
 ]
 
 

src/models/esmm/fe/diary_fe.py

@@ -124,6 +124,14 @@ DIARY_COLUMNS = [
     "first_positions_num",
     "second_positions_num",
     "projects_num",
+    "is_related_service",
+    "effect_second_skip_num",
+    "business_second_skip_num",
+    "effect_second_skip_rate",
+    "business_second_skip_rate",
+    "service_price",
+    "service_sold_num",
+    "service_city",
 ]
 INT_COLUMNS = [
     "active_days",
@@ -201,6 +209,10 @@ INT_COLUMNS = [
     "first_positions_num",
     "second_positions_num",
     "projects_num",
+    "effect_second_skip_num",
+    "business_second_skip_num",
+    "service_price",
+    "service_sold_num",
 ]
 FLOAT_COLUMNS = [
     "one_ctr",
@@ -235,14 +247,62 @@ FLOAT_COLUMNS = [
     "sixty_browse_duration_avg",
     "ninety_browse_duration_avg",
     "history_browse_duration_avg",
+    "effect_second_skip_rate",
+    "business_second_skip_rate",
 ]
 CATEGORICAL_COLUMNS = [
-    "device_id", "active_type", "past_consume_ability_history", "potential_consume_ability_history", "price_sensitive_history",
-    "card_id", "is_pure_author", "is_have_reply", "is_have_pure_reply", "content_level", "device_fd", "content_fd", "fd1", "fd2",
-    "fd3", "device_sd", "content_sd", "sd1", "sd2", "sd3", "device_fs", "content_fs", "fs1", "fs2", "fs3", "device_ss",
-    "content_ss", "ss1", "ss2", "ss3", "device_fp", "content_fp", "fp1", "fp2", "fp3", "device_sp", "content_sp", "sp1", "sp2",
-    "sp3", "device_p", "content_p", "p1", "p2", "p3", "click_diary_id1", "click_diary_id2", "click_diary_id3", "click_diary_id4",
-    "click_diary_id5"
+    "device_id",
+    "active_type",
+    "past_consume_ability_history",
+    "potential_consume_ability_history",
+    "price_sensitive_history",
+    "card_id",
+    "is_pure_author",
+    "is_have_reply",
+    "is_have_pure_reply",
+    "content_level",
+    "device_fd",
+    "content_fd",
+    "fd1",
+    "fd2",
+    "fd3",
+    "device_sd",
+    "content_sd",
+    "sd1",
+    "sd2",
+    "sd3",
+    "device_fs",
+    "content_fs",
+    "fs1",
+    "fs2",
+    "fs3",
+    "device_ss",
+    "content_ss",
+    "ss1",
+    "ss2",
+    "ss3",
+    "device_fp",
+    "content_fp",
+    "fp1",
+    "fp2",
+    "fp3",
+    "device_sp",
+    "content_sp",
+    "sp1",
+    "sp2",
+    "sp3",
+    "device_p",
+    "content_p",
+    "p1",
+    "p2",
+    "p3",
+    "click_diary_id1",
+    "click_diary_id2",
+    "click_diary_id3",
+    "click_diary_id4",
+    "click_diary_id5",
+    "is_related_service",
+    "service_city",
 ]
 
 
@@ -275,7 +335,7 @@ def get_diary_dict_from_redis():
                 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"]:
+            elif col_name in ["is_pure_author", "is_have_pure_reply", "is_have_reply", "is_related_service"]:
                 if elem == "true":
                     tmp[col_name] = 1
                 else:
@@ -316,6 +376,7 @@ def diary_feature_engineering(df):
     diary_df["is_pure_author"] = diary_df["is_pure_author"].astype(int)
     diary_df["is_have_pure_reply"] = diary_df["is_have_pure_reply"].astype(int)
     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 = diary_df[DIARY_COLUMNS]
 

src/train_diary.py

@@ -61,7 +61,8 @@ 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=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("@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@")
@@ -73,7 +74,8 @@ 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)
+    # TODO save
+    # set_essm_model_save_path("diary", save_path)
     print("============================================================")
 
     # save_path = str(Path("~/Desktop/models/1596012827").expanduser())  # local