Merge branch 'fe' into 'offic'

Fe

See merge request !21

src/models/esmm/diary_model.py

@@ -87,11 +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",
+    # "is_related_service",
+    # "effect_second_skip_num",
+    # "business_second_skip_num",
+    # "service_price",
+    # "service_sold_num",
 ]
 _float_columns = [
     "one_ctr",
@@ -126,8 +126,8 @@ _float_columns = [
     "sixty_browse_duration_avg",
     "ninety_browse_duration_avg",
     "history_browse_duration_avg",
-    "effect_second_skip_rate",
-    "business_second_skip_rate",
+    # "effect_second_skip_rate",
+    # "business_second_skip_rate",
 ]
 _categorical_columns = [
     "device_id",
@@ -174,25 +174,25 @@ _categorical_columns = [
     "click_diary_id3",
     "click_diary_id4",
     "click_diary_id5",
-    "service_id",
-    "service_city",
-    "recommend_service_id",
-    "recommend_service_city",
-    "recommend_service_price",
-    "device_fd2",
-    "device_sd2",
-    "device_fs2",
-    "device_ss2",
-    "device_fp2",
-    "device_sp2",
-    "device_p2",
-    "device_fd3",
-    "device_sd3",
-    "device_fs3",
-    "device_ss3",
-    "device_fp3",
-    "device_sp3",
-    "device_p3",
+    # "service_id",
+    # "service_city",
+    # "recommend_service_id",
+    # "recommend_service_city",
+    # "recommend_service_price",
+    # "device_fd2",
+    # "device_sd2",
+    # "device_fs2",
+    # "device_ss2",
+    # "device_fp2",
+    # "device_sp2",
+    # "device_p2",
+    # "device_fd3",
+    # "device_sd3",
+    # "device_fs3",
+    # "device_ss3",
+    # "device_fp3",
+    # "device_sp3",
+    # "device_p3",
 ]
 
 PREDICTION_ALL_COLUMNS = _int_columns + _float_columns + _categorical_columns

src/models/esmm/fe/diary_fe.py

@@ -124,18 +124,18 @@ 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_id",
-    "service_price",
-    "service_sold_num",
-    "service_city",
-    "recommend_service_id",
-    "recommend_service_city",
-    "recommend_service_price",
+    # "is_related_service",
+    # "effect_second_skip_num",
+    # "business_second_skip_num",
+    # "effect_second_skip_rate",
+    # "business_second_skip_rate",
+    # "service_id",
+    # "service_price",
+    # "service_sold_num",
+    # "service_city",
+    # "recommend_service_id",
+    # "recommend_service_city",
+    # "recommend_service_price",
 ]
 INT_COLUMNS = [
     "active_days",
@@ -213,10 +213,10 @@ INT_COLUMNS = [
     "first_positions_num",
     "second_positions_num",
     "projects_num",
-    "effect_second_skip_num",
-    "business_second_skip_num",
-    "service_price",
-    "service_sold_num",
+    # "effect_second_skip_num",
+    # "business_second_skip_num",
+    # "service_price",
+    # "service_sold_num",
 ]
 FLOAT_COLUMNS = [
     "one_ctr",
@@ -251,8 +251,8 @@ FLOAT_COLUMNS = [
     "sixty_browse_duration_avg",
     "ninety_browse_duration_avg",
     "history_browse_duration_avg",
-    "effect_second_skip_rate",
-    "business_second_skip_rate",
+    # "effect_second_skip_rate",
+    # "business_second_skip_rate",
 ]
 CATEGORICAL_COLUMNS = [
     "device_id",
@@ -305,26 +305,26 @@ CATEGORICAL_COLUMNS = [
     "click_diary_id3",
     "click_diary_id4",
     "click_diary_id5",
-    "is_related_service",
-    "service_id",
-    "service_city",
-    "recommend_service_id",
-    "recommend_service_city",
-    "recommend_service_price",
-    "device_fd2",
-    "device_sd2",
-    "device_fs2",
-    "device_ss2",
-    "device_fp2",
-    "device_sp2",
-    "device_p2",
-    "device_fd3",
-    "device_sd3",
-    "device_fs3",
-    "device_ss3",
-    "device_fp3",
-    "device_sp3",
-    "device_p3",
+    # "is_related_service",
+    # "service_id",
+    # "service_city",
+    # "recommend_service_id",
+    # "recommend_service_city",
+    # "recommend_service_price",
+    # "device_fd2",
+    # "device_sd2",
+    # "device_fs2",
+    # "device_ss2",
+    # "device_fp2",
+    # "device_sp2",
+    # "device_p2",
+    # "device_fd3",
+    # "device_sd3",
+    # "device_fs3",
+    # "device_ss3",
+    # "device_fp3",
+    # "device_sp3",
+    # "device_p3",
 ]
 CROSS_COLUMNS = [
     ["device_fd", "content_fd"],
@@ -334,20 +334,20 @@ CROSS_COLUMNS = [
     ["device_fp", "content_fp"],
     ["device_sp", "content_sp"],
     ["device_p", "content_p"],
-    ["device_fd2", "content_fd"],
-    ["device_sd2", "content_sd"],
-    ["device_fs2", "content_fs"],
-    ["device_ss2", "content_ss"],
-    ["device_fp2", "content_fp"],
-    ["device_sp2", "content_sp"],
-    ["device_p2", "content_p"],
-    ["device_fd3", "content_fd"],
-    ["device_sd3", "content_sd"],
-    ["device_fs3", "content_fs"],
-    ["device_ss3", "content_ss"],
-    ["device_fp3", "content_fp"],
-    ["device_sp3", "content_sp"],
-    ["device_p3", "content_p"],
+    # ["device_fd2", "content_fd"],
+    # ["device_sd2", "content_sd"],
+    # ["device_fs2", "content_fs"],
+    # ["device_ss2", "content_ss"],
+    # ["device_fp2", "content_fp"],
+    # ["device_sp2", "content_sp"],
+    # ["device_p2", "content_p"],
+    # ["device_fd3", "content_fd"],
+    # ["device_sd3", "content_sd"],
+    # ["device_fs3", "content_fs"],
+    # ["device_ss3", "content_ss"],
+    # ["device_fp3", "content_fp"],
+    # ["device_sp3", "content_sp"],
+    # ["device_p3", "content_p"],
 ]
 
 
@@ -422,15 +422,15 @@ def diary_feature_engineering(df):
     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["service_id"] = diary_df["service_id"].astype(str)
-    diary_df["recommend_service_id"] = diary_df["recommend_service_id"].astype(str)
-    diary_df["recommend_service_price"] = diary_df["recommend_service_price"].astype(str)
+    # diary_df["is_related_service"] = diary_df["is_related_service"].astype(int)
+    # diary_df["service_id"] = diary_df["service_id"].astype(str)
+    # diary_df["recommend_service_id"] = diary_df["recommend_service_id"].astype(str)
+    # diary_df["recommend_service_price"] = diary_df["recommend_service_price"].astype(str)
 
-    diary_df["service_id"] = diary_df["service_id"].fillna("-1")
-    diary_df["service_city"] = diary_df["service_city"].fillna("")
-    diary_df["recommend_service_id"] = diary_df["recommend_service_id"].fillna("-1")
-    diary_df["recommend_service_city"] = diary_df["recommend_service_city"].fillna("")
+    # diary_df["service_id"] = diary_df["service_id"].fillna("-1")
+    # diary_df["service_city"] = diary_df["service_city"].fillna("")
+    # diary_df["recommend_service_id"] = diary_df["recommend_service_id"].fillna("-1")
+    # diary_df["recommend_service_city"] = diary_df["recommend_service_city"].fillna("")
 
     diary_df = diary_df[DIARY_COLUMNS]
 
@@ -463,21 +463,21 @@ def join_features(device_df, diary_df, cc_df):
     df["device_sp"] = df["second_positions_x"].apply(lambda x: nth_element(x, 0))
     df["device_p"] = df["projects_x"].apply(lambda x: nth_element(x, 0))
 
-    df["device_fd2"] = df["first_demands_x"].apply(lambda x: nth_element(x, 1))
-    df["device_sd2"] = df["second_demands_x"].apply(lambda x: nth_element(x, 1))
-    df["device_fs2"] = df["first_solutions_x"].apply(lambda x: nth_element(x, 1))
-    df["device_ss2"] = df["second_solutions_x"].apply(lambda x: nth_element(x, 1))
-    df["device_fp2"] = df["first_positions_x"].apply(lambda x: nth_element(x, 1))
-    df["device_sp2"] = df["second_positions_x"].apply(lambda x: nth_element(x, 1))
-    df["device_p2"] = df["projects_x"].apply(lambda x: nth_element(x, 1))
+    # df["device_fd2"] = df["first_demands_x"].apply(lambda x: nth_element(x, 1))
+    # df["device_sd2"] = df["second_demands_x"].apply(lambda x: nth_element(x, 1))
+    # df["device_fs2"] = df["first_solutions_x"].apply(lambda x: nth_element(x, 1))
+    # df["device_ss2"] = df["second_solutions_x"].apply(lambda x: nth_element(x, 1))
+    # df["device_fp2"] = df["first_positions_x"].apply(lambda x: nth_element(x, 1))
+    # df["device_sp2"] = df["second_positions_x"].apply(lambda x: nth_element(x, 1))
+    # df["device_p2"] = df["projects_x"].apply(lambda x: nth_element(x, 1))
 
-    df["device_fd3"] = df["first_demands_x"].apply(lambda x: nth_element(x, 2))
-    df["device_sd3"] = df["second_demands_x"].apply(lambda x: nth_element(x, 2))
-    df["device_fs3"] = df["first_solutions_x"].apply(lambda x: nth_element(x, 2))
-    df["device_ss3"] = df["second_solutions_x"].apply(lambda x: nth_element(x, 2))
-    df["device_fp3"] = df["first_positions_x"].apply(lambda x: nth_element(x, 2))
-    df["device_sp3"] = df["second_positions_x"].apply(lambda x: nth_element(x, 2))
-    df["device_p3"] = df["projects_x"].apply(lambda x: nth_element(x, 2))
+    # df["device_fd3"] = df["first_demands_x"].apply(lambda x: nth_element(x, 2))
+    # df["device_sd3"] = df["second_demands_x"].apply(lambda x: nth_element(x, 2))
+    # df["device_fs3"] = df["first_solutions_x"].apply(lambda x: nth_element(x, 2))
+    # df["device_ss3"] = df["second_solutions_x"].apply(lambda x: nth_element(x, 2))
+    # df["device_fp3"] = df["first_positions_x"].apply(lambda x: nth_element(x, 2))
+    # df["device_sp3"] = df["second_positions_x"].apply(lambda x: nth_element(x, 2))
+    # df["device_p3"] = df["projects_x"].apply(lambda x: nth_element(x, 2))
 
     df["content_fd"] = df["first_demands_y"].apply(lambda x: nth_element(x, 0))
     df["content_sd"] = df["second_demands_y"].apply(lambda x: nth_element(x, 0))
@@ -566,20 +566,20 @@ def device_diary_fe(device_id, diary_ids, device_dict, diary_dict):
     device_info["device_fp"] = nth_element(device_fp, 0)
     device_info["device_sp"] = nth_element(device_sp, 0)
     device_info["device_p"] = nth_element(device_p, 0)
-    device_info["device_fd2"] = nth_element(device_fd, 1)
-    device_info["device_sd2"] = nth_element(device_sd, 1)
-    device_info["device_fs2"] = nth_element(device_fs, 1)
-    device_info["device_ss2"] = nth_element(device_ss, 1)
-    device_info["device_fp2"] = nth_element(device_fp, 1)
-    device_info["device_sp2"] = nth_element(device_sp, 1)
-    device_info["device_p2"] = nth_element(device_p, 1)
-    device_info["device_fd3"] = nth_element(device_fd, 2)
-    device_info["device_sd3"] = nth_element(device_sd, 2)
-    device_info["device_fs3"] = nth_element(device_fs, 2)
-    device_info["device_ss3"] = nth_element(device_ss, 2)
-    device_info["device_fp3"] = nth_element(device_fp, 2)
-    device_info["device_sp3"] = nth_element(device_sp, 2)
-    device_info["device_p3"] = nth_element(device_p, 2)
+    # device_info["device_fd2"] = nth_element(device_fd, 1)
+    # device_info["device_sd2"] = nth_element(device_sd, 1)
+    # device_info["device_fs2"] = nth_element(device_fs, 1)
+    # device_info["device_ss2"] = nth_element(device_ss, 1)
+    # device_info["device_fp2"] = nth_element(device_fp, 1)
+    # device_info["device_sp2"] = nth_element(device_sp, 1)
+    # device_info["device_p2"] = nth_element(device_p, 1)
+    # device_info["device_fd3"] = nth_element(device_fd, 2)
+    # device_info["device_sd3"] = nth_element(device_sd, 2)
+    # device_info["device_fs3"] = nth_element(device_fs, 2)
+    # device_info["device_ss3"] = nth_element(device_ss, 2)
+    # device_info["device_fp3"] = nth_element(device_fp, 2)
+    # device_info["device_sp3"] = nth_element(device_sp, 2)
+    # device_info["device_p3"] = nth_element(device_p, 2)
     diary_lst = []
     diary_ids_res = []
     for id in diary_ids: