删除部分轻医美标签词

eda/smart_rank/dist_update_user_history_order_tags.py

@@ -17,6 +17,7 @@ import numpy as np
 import pandas as pd
 from pyspark.sql.functions import lit
 from pyspark.sql.functions import concat_ws
+from tool import *
 
 
 def send_email(app,id,e):
@@ -52,6 +53,25 @@ def send_email(app,id,e):
         print('error')
 
 
+def get_hot_search_words_tag():
+    try:
+        hot_search = """
+                        SELECT a.keywords,
+                               b.id,
+                               b.tag_type
+                        FROM api_hot_search_words a
+                        LEFT JOIN api_tag b ON a.keywords=b.name
+                        WHERE a.is_delete=0
+                          AND b.tag_type+0<'4'+0
+                          AND b.is_online=1
+                        ORDER BY a.sorted DESC LIMIT 10
+                        """
+        mysql_results = get_data_by_mysql('172.16.30.141', 3306, 'work', 'BJQaT9VzDcuPBqkd', 'zhengxing', hot_search)
+        return mysql_results
+    except Exception as e:
+        print(e)
+        return []
+
 def get_user_history_order_service_tag(user_id):
     try:
         if user_id:
@@ -139,6 +159,7 @@ if __name__ == '__main__':
         redis_client.hmset(hot_search_words_portrait_portrait_key3, hot_search_words_portrait3_dict)
 
         # rdd
+        spark.sparkContext.addPyFile("/srv/apps/ffm-baseline_git/eda/smart_rank/tool.py")
         sparkConf = SparkConf().set("spark.hive.mapred.supports.subdirectories", "true") \
             .set("spark.hadoop.mapreduce.input.fileinputformat.input.dir.recursive", "true") \
             .set("spark.tispark.plan.allow_index_double_read", "false") \