update field

src/main.py

@@ -30,7 +30,7 @@ def main():
     print(b.size)
 
     device_df, diary_df, click_df, conversion_df = read_csv_data(Path("~/data/cvr_data/"))
-    device_df = device_feature_engineering(device_df)
+    # device_df = device_feature_engineering(device_df)
     diary_df = diary_feature_engineering(diary_df)
     print(diary_df.sample(1))
     # cc_df = click_feature_engineering(click_df, conversion_df)

src/models/esmm/fe.py

@@ -86,9 +86,9 @@ 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 [])
 
-    diary_df["is_pure_author"] = diary_df["is_pure_author"].replace(str_bool_map)
-    diary_df["is_have_pure_reply"] = diary_df["is_have_pure_reply"].replace(str_bool_map)
-    diary_df["is_have_reply"] = diary_df["is_have_reply"].replace(str_bool_map)
+    diary_df["is_pure_author"] = diary_df["is_pure_author"].map(str_bool_map)
+    diary_df["is_have_pure_reply"] = diary_df["is_have_pure_reply"].map(str_bool_map)
+    diary_df["is_have_reply"] = diary_df["is_have_reply"].map(str_bool_map)
 
     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)