update tractate fe

3c6c69fa · 赵威 · 39ea1b4f · 3c6c69fa · 3c6c69fa · 3c6c69fa
Commit 3c6c69fa authored Aug 14, 2020 by 赵威
Show whitespace changes
Inline Side-by-side

Showing with 180 additions and 25 deletions

tractate_fe.py src/models/esmm/fe/tractate_fe.py +154 -21

tractate_model.py src/models/esmm/tractate_model.py +24 -0

train_tractate.py src/train_tractate.py +2 -4

No files found.
--- a/src/models/esmm/fe/tractate_fe.py
+++ b/src/models/esmm/fe/tractate_fe.py
@@ -6,30 +6,163 @@ from utils.cache import redis_db_client
 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",
+    "card_id",
-    "reply_pure_num", "one_reply_user_num", "three_reply_user_num", "seven_reply_user_num", "fifteen_reply_user_num",
+    "is_pure_author",
-    "thirty_reply_user_num", "sixty_reply_user_num", "ninety_reply_user_num", "history_reply_user_num", "one_reply_num",
+    "is_have_pure_reply",
-    "three_reply_num", "seven_reply_num", "fifteen_reply_num", "thirty_reply_num", "sixty_reply_num", "ninety_reply_num",
+    "is_have_reply",
-    "history_reply_num", "one_click_num", "three_click_num", "seven_click_num", "fifteen_click_num", "thirty_click_num",
+    "content_level",
-    "sixty_click_num", "ninety_click_num", "history_click_num", "one_precise_exposure_num", "three_precise_exposure_num",
+    "show_tag_id",
-    "seven_precise_exposure_num", "fifteen_precise_exposure_num", "thirty_precise_exposure_num", "sixty_precise_exposure_num",
+    "reply_num",
-    "ninety_precise_exposure_num", "history_precise_exposure_num", "one_vote_user_num", "three_vote_user_num",
+    "reply_pure_num",
-    "seven_vote_user_num", "fifteen_vote_user_num", "thirty_vote_user_num", "sixty_vote_user_num", "ninety_vote_user_num",
+    "one_reply_user_num",
-    "history_vote_user_num", "one_ctr", "three_ctr", "seven_ctr", "fifteen_ctr", "thirty_ctr", "sixty_ctr", "ninety_ctr",
+    "three_reply_user_num",
-    "history_ctr", "first_demands", "second_demands", "first_solutions", "second_solutions", "first_positions",
+    "seven_reply_user_num",
-    "second_positions", "projects"
+    "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_browse_user_num",
+    "three_browse_user_num",
+    "seven_browse_user_num",
+    "fifteen_browse_user_num",
+    "thirty_browse_user_num",
+    "sixty_browse_user_num",
+    "ninety_browse_user_num",
+    "history_browse_user_num",
+    "one_vote_pure_rate",
+    "three_vote_pure_rate",
+    "seven_vote_pure_rate",
+    "fifteen_vote_pure_rate",
+    "thirty_vote_pure_rate",
+    "sixty_vote_pure_rate",
+    "ninety_vote_pure_rate",
+    "history_vote_pure_rate",
+    "one_reply_pure_rate",
+    "three_reply_pure_rate",
+    "seven_reply_pure_rate",
+    "fifteen_reply_pure_rate",
+    "thirty_reply_pure_rate",
+    "sixty_reply_pure_rate",
+    "ninety_reply_pure_rate",
+    "history_reply_pure_rate",
+    "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", "one_reply_user_num", "three_reply_user_num", "seven_reply_user_num",
+    "active_days",
-    "fifteen_reply_user_num", "thirty_reply_user_num", "sixty_reply_user_num", "ninety_reply_user_num", "history_reply_user_num",
+    "reply_num",
-    "one_reply_num", "three_reply_num", "seven_reply_num", "fifteen_reply_num", "thirty_reply_num", "sixty_reply_num",
+    "reply_pure_num",
-    "ninety_reply_num", "history_reply_num", "one_click_num", "three_click_num", "seven_click_num", "fifteen_click_num",
+    "one_reply_user_num",
-    "thirty_click_num", "sixty_click_num", "ninety_click_num", "history_click_num", "one_precise_exposure_num",
+    "three_reply_user_num",
-    "three_precise_exposure_num", "seven_precise_exposure_num", "fifteen_precise_exposure_num", "thirty_precise_exposure_num",
+    "seven_reply_user_num",
-    "sixty_precise_exposure_num", "ninety_precise_exposure_num", "history_precise_exposure_num", "one_vote_user_num",
+    "fifteen_reply_user_num",
-    "three_vote_user_num", "seven_vote_user_num", "fifteen_vote_user_num", "thirty_vote_user_num", "sixty_vote_user_num",
+    "thirty_reply_user_num",
-    "ninety_vote_user_num", "history_vote_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_browse_user_num",
+    "three_browse_user_num",
+    "seven_browse_user_num",
+    "fifteen_browse_user_num",
+    "thirty_browse_user_num",
+    "sixty_browse_user_num",
+    "ninety_browse_user_num",
+    "history_browse_user_num",
+    "one_vote_pure_rate",
+    "three_vote_pure_rate",
+    "seven_vote_pure_rate",
+    "fifteen_vote_pure_rate",
+    "thirty_vote_pure_rate",
+    "sixty_vote_pure_rate",
+    "ninety_vote_pure_rate",
+    "history_vote_pure_rate",
+    "one_reply_pure_rate",
+    "three_reply_pure_rate",
+    "seven_reply_pure_rate",
+    "fifteen_reply_pure_rate",
+    "thirty_reply_pure_rate",
+    "sixty_reply_pure_rate",
+    "ninety_reply_pure_rate",
+    "history_reply_pure_rate",
 ]
 FLOAT_COLUMNS = ["one_ctr", "three_ctr", "seven_ctr", "fifteen_ctr", "thirty_ctr", "sixty_ctr", "ninety_ctr", "history_ctr"]
 CATEGORICAL_COLUMNS = [

--- a/src/models/esmm/tractate_model.py
+++ b/src/models/esmm/tractate_model.py
@@ -55,6 +55,30 @@ _int_columns = [
    "sixty_vote_user_num",
    "ninety_vote_user_num",
    "history_vote_user_num",
+    "one_browse_user_num",
+    "three_browse_user_num",
+    "seven_browse_user_num",
+    "fifteen_browse_user_num",
+    "thirty_browse_user_num",
+    "sixty_browse_user_num",
+    "ninety_browse_user_num",
+    "history_browse_user_num",
+    "one_vote_pure_rate",
+    "three_vote_pure_rate",
+    "seven_vote_pure_rate",
+    "fifteen_vote_pure_rate",
+    "thirty_vote_pure_rate",
+    "sixty_vote_pure_rate",
+    "ninety_vote_pure_rate",
+    "history_vote_pure_rate",
+    "one_reply_pure_rate",
+    "three_reply_pure_rate",
+    "seven_reply_pure_rate",
+    "fifteen_reply_pure_rate",
+    "thirty_reply_pure_rate",
+    "sixty_reply_pure_rate",
+    "ninety_reply_pure_rate",
+    "history_reply_pure_rate",
 ]
 _float_columns = ["one_ctr", "three_ctr", "seven_ctr", "fifteen_ctr", "thirty_ctr", "sixty_ctr", "ninety_ctr", "history_ctr"]
 _categorical_columns = [

--- a/src/train_tractate.py
+++ b/src/train_tractate.py
@@ -58,8 +58,7 @@ 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)
-    # TODO 50000
+    train_spec = tf.estimator.TrainSpec(input_fn=lambda: esmm_input_fn(train_df, shuffle=True), max_steps=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("@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@")
@@ -71,8 +70,7 @@ 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)
-    # TODO save model
+    set_essm_model_save_path("tractate", save_path)
-    # set_essm_model_save_path("tractate", save_path)
    print("============================================================")
    # # save_path = str(Path("~/data/models/tractate/1596089465").expanduser())  # local