add features for tractate

src/models/esmm/diary_model.py

@@ -9,13 +9,14 @@ _int_columns = [
     "active_type", "active_days", "card_id", "is_pure_author", "is_have_reply", "is_have_pure_reply", "content_level",
     "topic_num", "favor_num", "favor_pure_num", "vote_num", "reply_num", "reply_pure_num", "one_reply_user_num",
     "three_reply_user_num", "seven_reply_user_num", "fifteen_reply_user_num", "thirty_reply_user_num", "sixty_reply_user_num",
-    "ninety_reply_user_num", "history_reply_user_num", "one_click_num", "three_click_num", "seven_click_num", "fifteen_click_num",
-    "thirty_click_num", "sixty_click_num", "ninety_click_num", "history_click_num", "one_precise_exposure_num",
-    "three_precise_exposure_num", "seven_precise_exposure_num", "fifteen_precise_exposure_num", "thirty_precise_exposure_num",
-    "sixty_precise_exposure_num", "ninety_precise_exposure_num", "history_precise_exposure_num", "one_vote_user_num",
-    "three_vote_user_num", "seven_vote_user_num", "fifteen_vote_user_num", "thirty_vote_user_num", "sixty_vote_user_num",
-    "ninety_vote_user_num", "history_vote_user_num", "topic_seven_click_num", "topic_thirty_click_num", "seven_transform_num",
-    "thirty_transform_num"
+    "ninety_reply_user_num", "history_reply_user_num", "one_reply_num", "three_reply_num", "seven_reply_num", "fifteen_reply_num",
+    "thirty_reply_num", "sixty_reply_num", "ninety_reply_num", "history_reply_num", "one_click_num", "three_click_num",
+    "seven_click_num", "fifteen_click_num", "thirty_click_num", "sixty_click_num", "ninety_click_num", "history_click_num",
+    "one_precise_exposure_num", "three_precise_exposure_num", "seven_precise_exposure_num", "fifteen_precise_exposure_num",
+    "thirty_precise_exposure_num", "sixty_precise_exposure_num", "ninety_precise_exposure_num", "history_precise_exposure_num",
+    "one_vote_user_num", "three_vote_user_num", "seven_vote_user_num", "fifteen_vote_user_num", "thirty_vote_user_num",
+    "sixty_vote_user_num", "ninety_vote_user_num", "history_vote_user_num", "topic_seven_click_num", "topic_thirty_click_num",
+    "seven_transform_num", "thirty_transform_num"
 ]
 _float_columns = ["one_ctr", "three_ctr", "seven_ctr", "fifteen_ctr", "thirty_ctr", "sixty_ctr", "ninety_ctr", "history_ctr"]
 _categorical_columns = [

src/models/esmm/fe/diary_fe.py

@@ -9,25 +9,28 @@ DIARY_COLUMNS = [
     "card_id", "is_pure_author", "is_have_reply", "is_have_pure_reply", "content_level", "topic_num", "topic_seven_click_num",
     "topic_thirty_click_num", "seven_transform_num", "thirty_transform_num", "favor_num", "favor_pure_num", "vote_num",
     "reply_num", "reply_pure_num", "one_reply_user_num", "three_reply_user_num", "seven_reply_user_num", "fifteen_reply_user_num",
-    "thirty_reply_user_num", "sixty_reply_user_num", "ninety_reply_user_num", "history_reply_user_num", "one_click_num",
-    "three_click_num", "seven_click_num", "fifteen_click_num", "thirty_click_num", "sixty_click_num", "ninety_click_num",
-    "history_click_num", "one_precise_exposure_num", "three_precise_exposure_num", "seven_precise_exposure_num",
-    "fifteen_precise_exposure_num", "thirty_precise_exposure_num", "sixty_precise_exposure_num", "ninety_precise_exposure_num",
-    "history_precise_exposure_num", "one_vote_user_num", "three_vote_user_num", "seven_vote_user_num", "fifteen_vote_user_num",
-    "thirty_vote_user_num", "sixty_vote_user_num", "ninety_vote_user_num", "history_vote_user_num", "one_ctr", "three_ctr",
-    "seven_ctr", "fifteen_ctr", "thirty_ctr", "sixty_ctr", "ninety_ctr", "history_ctr", "first_demands", "second_demands",
-    "first_solutions", "second_solutions", "first_positions", "second_positions", "projects"
+    "thirty_reply_user_num", "sixty_reply_user_num", "ninety_reply_user_num", "history_reply_user_num", "one_reply_num",
+    "three_reply_num", "seven_reply_num", "fifteen_reply_num", "thirty_reply_num", "sixty_reply_num", "ninety_reply_num",
+    "history_reply_num", "one_click_num", "three_click_num", "seven_click_num", "fifteen_click_num", "thirty_click_num",
+    "sixty_click_num", "ninety_click_num", "history_click_num", "one_precise_exposure_num", "three_precise_exposure_num",
+    "seven_precise_exposure_num", "fifteen_precise_exposure_num", "thirty_precise_exposure_num", "sixty_precise_exposure_num",
+    "ninety_precise_exposure_num", "history_precise_exposure_num", "one_vote_user_num", "three_vote_user_num",
+    "seven_vote_user_num", "fifteen_vote_user_num", "thirty_vote_user_num", "sixty_vote_user_num", "ninety_vote_user_num",
+    "history_vote_user_num", "one_ctr", "three_ctr", "seven_ctr", "fifteen_ctr", "thirty_ctr", "sixty_ctr", "ninety_ctr",
+    "history_ctr", "first_demands", "second_demands", "first_solutions", "second_solutions", "first_positions",
+    "second_positions", "projects"
 ]
 INT_COLUMNS = [
     "active_days", "topic_num", "favor_num", "favor_pure_num", "vote_num", "reply_num", "reply_pure_num", "one_reply_user_num",
     "three_reply_user_num", "seven_reply_user_num", "fifteen_reply_user_num", "thirty_reply_user_num", "sixty_reply_user_num",
-    "ninety_reply_user_num", "history_reply_user_num", "one_click_num", "three_click_num", "seven_click_num", "fifteen_click_num",
-    "thirty_click_num", "sixty_click_num", "ninety_click_num", "history_click_num", "topic_seven_click_num",
-    "topic_thirty_click_num", "one_precise_exposure_num", "three_precise_exposure_num", "seven_precise_exposure_num",
-    "fifteen_precise_exposure_num", "thirty_precise_exposure_num", "sixty_precise_exposure_num", "ninety_precise_exposure_num",
-    "history_precise_exposure_num", "one_vote_user_num", "three_vote_user_num", "seven_vote_user_num", "fifteen_vote_user_num",
-    "thirty_vote_user_num", "sixty_vote_user_num", "ninety_vote_user_num", "history_vote_user_num", "seven_transform_num",
-    "thirty_transform_num"
+    "ninety_reply_user_num", "history_reply_user_num", "one_reply_num", "three_reply_num", "seven_reply_num", "fifteen_reply_num",
+    "thirty_reply_num", "sixty_reply_num", "ninety_reply_num", "history_reply_num", "one_click_num", "three_click_num",
+    "seven_click_num", "fifteen_click_num", "thirty_click_num", "sixty_click_num", "ninety_click_num", "history_click_num",
+    "topic_seven_click_num", "topic_thirty_click_num", "one_precise_exposure_num", "three_precise_exposure_num",
+    "seven_precise_exposure_num", "fifteen_precise_exposure_num", "thirty_precise_exposure_num", "sixty_precise_exposure_num",
+    "ninety_precise_exposure_num", "history_precise_exposure_num", "one_vote_user_num", "three_vote_user_num",
+    "seven_vote_user_num", "fifteen_vote_user_num", "thirty_vote_user_num", "sixty_vote_user_num", "ninety_vote_user_num",
+    "history_vote_user_num", "seven_transform_num", "thirty_transform_num"
 ]
 FLOAT_COLUMNS = ["one_ctr", "three_ctr", "seven_ctr", "fifteen_ctr", "thirty_ctr", "sixty_ctr", "ninety_ctr", "history_ctr"]
 CATEGORICAL_COLUMNS = [

src/models/esmm/fe/tractate_fe.py

@@ -7,11 +7,30 @@ from ..utils import common_elements, nth_element
 
 TRACTATE_COLUMNS = [
     "card_id", "is_pure_author", "is_have_pure_reply", "is_have_reply", "content_level", "show_tag_id", "reply_num",
-    "reply_pure_num", "one_ctr", "three_ctr", "seven_ctr", "fifteen_ctr", "thirty_ctr", "sixty_ctr", "ninety_ctr", "history_ctr",
-    "first_demands", "second_demands", "first_solutions", "second_solutions", "first_positions", "second_positions", "projects"
+    "reply_pure_num", "one_reply_user_num", "three_reply_user_num", "seven_reply_user_num", "fifteen_reply_user_num",
+    "thirty_reply_user_num", "sixty_reply_user_num", "ninety_reply_user_num", "history_reply_user_num", "one_reply_num",
+    "three_reply_num", "seven_reply_num", "fifteen_reply_num", "thirty_reply_num", "sixty_reply_num", "ninety_reply_num",
+    "history_reply_num", "one_click_num", "three_click_num", "seven_click_num", "fifteen_click_num", "thirty_click_num",
+    "sixty_click_num", "ninety_click_num", "history_click_num", "one_precise_exposure_num", "three_precise_exposure_num",
+    "seven_precise_exposure_num", "fifteen_precise_exposure_num", "thirty_precise_exposure_num", "sixty_precise_exposure_num",
+    "ninety_precise_exposure_num", "history_precise_exposure_num", "one_vote_user_num", "three_vote_user_num",
+    "seven_vote_user_num", "fifteen_vote_user_num", "thirty_vote_user_num", "sixty_vote_user_num", "ninety_vote_user_num",
+    "history_vote_user_num", "one_ctr", "three_ctr", "seven_ctr", "fifteen_ctr", "thirty_ctr", "sixty_ctr", "ninety_ctr",
+    "history_ctr", "first_demands", "second_demands", "first_solutions", "second_solutions", "first_positions",
+    "second_positions", "projects"
 ]
 
-INT_COLUMNS = ["active_days", "reply_num", "reply_pure_num"]
+INT_COLUMNS = [
+    "active_days", "reply_num", "reply_pure_num", "one_reply_user_num", "three_reply_user_num", "seven_reply_user_num",
+    "fifteen_reply_user_num", "thirty_reply_user_num", "sixty_reply_user_num", "ninety_reply_user_num", "history_reply_user_num",
+    "one_reply_num", "three_reply_num", "seven_reply_num", "fifteen_reply_num", "thirty_reply_num", "sixty_reply_num",
+    "ninety_reply_num", "history_reply_num", "one_click_num", "three_click_num", "seven_click_num", "fifteen_click_num",
+    "thirty_click_num", "sixty_click_num", "ninety_click_num", "history_click_num", "one_precise_exposure_num",
+    "three_precise_exposure_num", "seven_precise_exposure_num", "fifteen_precise_exposure_num", "thirty_precise_exposure_num",
+    "sixty_precise_exposure_num", "ninety_precise_exposure_num", "history_precise_exposure_num", "one_vote_user_num",
+    "three_vote_user_num", "seven_vote_user_num", "fifteen_vote_user_num", "thirty_vote_user_num", "sixty_vote_user_num",
+    "ninety_vote_user_num", "history_vote_user_num"
+]
 FLOAT_COLUMNS = ["one_ctr", "three_ctr", "seven_ctr", "fifteen_ctr", "thirty_ctr", "sixty_ctr", "ninety_ctr", "history_ctr"]
 CATEGORICAL_COLUMNS = [
     "device_id", "active_type", "past_consume_ability_history", "potential_consume_ability_history", "price_sensitive_history",

src/models/esmm/tractate_model.py

@@ -6,8 +6,55 @@ from .fe.tractate_fe import device_tractate_fe
 from .model import _bytes_feature, _float_feature, _int64_feature
 
 _int_columns = [
-    "active_type", "active_days", "card_id", "is_pure_author", "is_have_reply", "is_have_pure_reply", "content_level",
-    "reply_num", "reply_pure_num"
+    "active_type",
+    "active_days",
+    "card_id",
+    "is_pure_author",
+    "is_have_reply",
+    "is_have_pure_reply",
+    "content_level",
+    "reply_num",
+    "reply_pure_num",
+    "one_reply_user_num",
+    "three_reply_user_num",
+    "seven_reply_user_num",
+    "fifteen_reply_user_num",
+    "thirty_reply_user_num",
+    "sixty_reply_user_num",
+    "ninety_reply_user_num",
+    "history_reply_user_num",
+    "one_reply_num",
+    "three_reply_num",
+    "seven_reply_num",
+    "fifteen_reply_num",
+    "thirty_reply_num",
+    "sixty_reply_num",
+    "ninety_reply_num",
+    "history_reply_num",
+    "one_click_num",
+    "three_click_num",
+    "seven_click_num",
+    "fifteen_click_num",
+    "thirty_click_num",
+    "sixty_click_num",
+    "ninety_click_num",
+    "history_click_num",
+    "one_precise_exposure_num",
+    "three_precise_exposure_num",
+    "seven_precise_exposure_num",
+    "fifteen_precise_exposure_num",
+    "thirty_precise_exposure_num",
+    "sixty_precise_exposure_num",
+    "ninety_precise_exposure_num",
+    "history_precise_exposure_num",
+    "one_vote_user_num",
+    "three_vote_user_num",
+    "seven_vote_user_num",
+    "fifteen_vote_user_num",
+    "thirty_vote_user_num",
+    "sixty_vote_user_num",
+    "ninety_vote_user_num",
+    "history_vote_user_num",
 ]
 _float_columns = ["one_ctr", "three_ctr", "seven_ctr", "fifteen_ctr", "thirty_ctr", "sixty_ctr", "ninety_ctr", "history_ctr"]
 _categorical_columns = [
@@ -20,6 +67,7 @@ _categorical_columns = [
 
 PREDICTION_ALL_COLUMNS = _int_columns + _float_columns + _categorical_columns
 
+
 def model_predict_tractate(device_id, tractate_ids, device_dict, tractate_dict, predict_fn):
     try:
         time_1 = timeit.default_timer()

src/train_tractate.py

@@ -58,7 +58,8 @@ 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=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("@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@")
@@ -69,7 +70,8 @@ def main():
     model_export_path = str(Path("~/data/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)
+    # TODO save model
+    # set_essm_model_save_path("tractate", save_path)
     print("@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@")
 
     print("============================================================")