update feature

spark/featureEng.py

@@ -112,6 +112,7 @@ def addItemFeatures(samples,itemDF,dataVocab,multiVocab):
     samples = samples.join(staticFeatures, on=['itemid'], how='left')
 
     print("连续特征处理...")
+    # todo 分桶比较耗时，可以考虑做非线性转换
     # 连续特征处理
     pipelineStage = []
     # Normalization

train/train_service.py

@@ -14,7 +14,7 @@ import utils.configUtils as configUtils
 ITEM_NUMBER_COLUMNS = ["item_"+c for c in ["smart_rank2"]]
 embedding_columns = ["itemid","userid"] + ["item_"+c for c in ["doctor_id","hospital_id"]]
 multi_columns = ["tags_v3","first_demands","second_demands","first_solutions","second_solutions","first_positions","second_positions"]
-one_hot_columns = ["item_"+c for c in ["service_type","doctor_type","doctor_famous","hospital_city_tag_id","hospital_type","hospital_is_high_quality"]]
+one_hot_columns = ["user_os"] + ["item_"+c for c in ["service_type","doctor_type","doctor_famous","hospital_city_tag_id","hospital_type","hospital_is_high_quality"]]
 # history_columns = ["userRatedHistory"]
 
 # 数据加载