增加特征

tensnsorflow/multi.py

@@ -33,6 +33,10 @@ def multi_hot(df,column,n):
 
 
 def feature_engineer():
+    # TODO 删除下面的测试写入
+    df = spark.sql("select y,z from esmm_train_data limit 60")
+    df.write.format("avro").save(path=path + "tr", mode="overwrite")
+
     db = pymysql.connect(host='172.16.40.158', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test')
     sql = "select max(stat_date) from esmm_train_data"
     validate_date = con_sql(db, sql)[0].values.tolist()[0]
@@ -54,8 +58,6 @@ def feature_engineer():
 
     df = spark.sql(sql)
 
-    df.write.format("avro").save(path=path + "tr", mode="overwrite")
-
     url = "jdbc:mysql://172.16.30.143:3306/zhengxing"
     jdbcDF = spark.read.format("jdbc").option("driver", "com.mysql.jdbc.Driver").option("url", url) \
         .option("dbtable", "api_service").option("user", 'work').option("password", 'BJQaT9VzDcuPBqkd').load()