tag numbers for diary

src/models/esmm/diary_model.py

@@ -72,6 +72,13 @@ _int_columns = [
     "sixty_browse_user_num",
     "ninety_browse_user_num",
     "history_browse_user_num",
+    "first_demands_num",
+    "second_demands_num",
+    "first_solutions_num",
+    "second_solutions_num",
+    "first_positions_num",
+    "second_positions_num",
+    "projects_num",
 ]
 _float_columns = [
     "one_ctr",

src/models/esmm/fe/diary_fe.py

@@ -101,6 +101,13 @@ DIARY_COLUMNS = [
     "first_positions",
     "second_positions",
     "projects",
+    "first_demands_num",
+    "second_demands_num",
+    "first_solutions_num",
+    "second_solutions_num",
+    "first_positions_num",
+    "second_positions_num",
+    "projects_num",
 ]
 INT_COLUMNS = [
     "active_days",
@@ -163,6 +170,13 @@ INT_COLUMNS = [
     "sixty_browse_user_num",
     "ninety_browse_user_num",
     "history_browse_user_num",
+    "first_demands_num",
+    "second_demands_num",
+    "first_solutions_num",
+    "second_solutions_num",
+    "first_positions_num",
+    "second_positions_num",
+    "projects_num",
 ]
 FLOAT_COLUMNS = [
     "one_ctr",
@@ -226,6 +240,9 @@ def get_diary_dict_from_redis():
                     "second_positions", "projects"
             ]:
                 tmp[col_name] = elem.split(",")
+                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"]:
                 if elem == "true":
                     tmp[col_name] = 1
@@ -256,6 +273,14 @@ def diary_feature_engineering(df):
     diary_df["second_positions"] = diary_df["second_positions"].apply(lambda d: d if isinstance(d, list) else [])
     diary_df["projects"] = diary_df["projects"].apply(lambda d: d if isinstance(d, list) else [])
 
+    df["first_demands_num"] = df["first_demands"].apply(lambda d: len(d))
+    df["second_demands_num"] = df["second_demands"].apply(lambda d: len(d))
+    df["first_solutions_num"] = df["first_solutions"].apply(lambda d: len(d))
+    df["second_solutions_num"] = df["second_solutions"].apply(lambda d: len(d))
+    df["first_positions_num"] = df["first_positions"].apply(lambda d: len(d))
+    df["second_positions_num"] = df["second_positions"].apply(lambda d: len(d))
+    df["projects_num"] = df["projects"].apply(lambda d: len(d))
+
     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)