add reply number

src/models/esmm/diary_model.py

@@ -7,7 +7,10 @@ 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",
-    "topic_num", "favor_num", "vote_num", "topic_seven_click_num", "topic_thirty_click_num"
+    "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", "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

@@ -7,11 +7,18 @@ from ..utils import common_elements, nth_element
 
 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", "favor_num", "vote_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"
+    "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_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", "topic_seven_click_num", "topic_thirty_click_num", "seven_transform_num",
+    "thirty_transform_num"
 ]
-INT_COLUMNS = ["active_days", "topic_num", "favor_num", "vote_num", "topic_seven_click_num", "topic_thirty_click_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/train_diary.py

@@ -23,6 +23,12 @@ def main():
 
     # os.environ["CUDA_VISIBLE_DEVICES"] = "-1"
 
+    diary_train_columns = set(diary_fe.INT_COLUMNS + diary_fe.FLOAT_COLUMNS + diary_fe.CATEGORICAL_COLUMNS)
+    diary_predict_columns = set(PREDICTION_ALL_COLUMNS)
+    print(diary_predict_columns.difference(diary_train_columns))
+    print(diary_train_columns.difference(diary_predict_columns))
+    assert diary_predict_columns == diary_train_columns
+
     # dataset_path = Path("~/data/cvr_data").expanduser()  # local
     dataset_path = Path("/srv/apps/node2vec_git/cvr_data/")  # server
     diary_df, diary_click_df, diary_conversion_df = diary_fe.read_csv_data(dataset_path)
@@ -57,7 +63,10 @@ def main():
     # 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))
-    tf.estimator.train_and_evaluate(model, train_spec, eval_spec)
+    res = tf.estimator.train_and_evaluate(model, train_spec, eval_spec)
+    print("@@@@@@@@@@")
+    print(res)
+    print("@@@@@@@@@@")
 
     model_export_path = str(Path("~/data/models/diary").expanduser())
     save_path = model_export(model, all_features, model_export_path)
@@ -65,12 +74,6 @@ def main():
     # TODO save model
     # set_essm_model_save_path("diary", save_path)
 
-    diary_train_columns = set(diary_fe.INT_COLUMNS + diary_fe.FLOAT_COLUMNS + diary_fe.CATEGORICAL_COLUMNS)
-    diary_predict_columns = set(PREDICTION_ALL_COLUMNS)
-    print(diary_predict_columns.difference(diary_train_columns))
-    print(diary_train_columns.difference(diary_predict_columns))
-    assert diary_predict_columns == diary_train_columns
-
     print("============================================================")
     # save_path = str(Path("~/Desktop/models/1596012827").expanduser())  # local
     # save_path = "/home/gmuser/data/models/diary/1596083349"  # server

src/train_tractate.py

@@ -21,11 +21,17 @@ def main():
 
     tf.compat.v1.logging.set_verbosity(tf.compat.v1.logging.INFO)
 
-    # data_path = Path("~/data/cvr_data").expanduser()  # local
-    data_path = Path("/srv/apps/node2vec_git/cvr_data/")  # server
-    tractate_df, tractate_click_df, tractate_conversion_df = tractate_fe.read_csv_data(data_path)
+    tractate_train_columns = set(tractate_fe.INT_COLUMNS + tractate_fe.FLOAT_COLUMNS + tractate_fe.CATEGORICAL_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(data_path)
+    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")
@@ -60,12 +66,6 @@ def main():
     print("save to: " + save_path)
     set_essm_model_save_path("tractate", save_path)
 
-    tractate_train_columns = set(tractate_fe.INT_COLUMNS + tractate_fe.FLOAT_COLUMNS + tractate_fe.CATEGORICAL_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
-
     print("============================================================")
 
     # # save_path = str(Path("~/data/models/tractate/1596089465").expanduser())  # local