change test file

ctr-56.py

@@ -89,11 +89,19 @@ def rate2file():
         f.write(line)
 
 
+def get_time():
+    db = pymysql.connect(host='172.16.40.158', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test')
+    sql = "select dur_time from cost_time"
+    cursor = db.cursor()
+    cursor.execute(sql)
+    result = cursor.fetchall()
+    df = pd.DataFrame(list(result))
+    db.close()
+    return df
+
+
 if __name__ == "__main__":
-    DIRECTORY_PATH = "/data/ffm/"
-    date = get_yesterday_date()
-    black = get_black_user()
-    device_id = get_data()
-    temp_data = ctr()
-    data = ctr_all()
-    rate2file()
+    DIRECTORY_PATH = "/home/gmuser/"
+    df = get_time()
+    df.to_csv( DIRECTORY_PATH+"hello.csv",index = None)
+

tensnsorflow/test.py

@@ -13,8 +13,8 @@ def test():
         conf = SparkConf().setAppName("My App").set("spark.io.compression.codec", "lzf")
         sc = SparkContext(conf = conf)
         spark = SparkSession.builder.enableHiveSupport().getOrCreate()
-        # ti = pti.TiContext(spark)
-        # ti.tidbMapDatabase("jerry_test")
+        ti = pti.TiContext(spark)
+        ti.tidbMapDatabase("jerry_test")
 
         spark = SparkSession.builder.appName("hello test").enableHiveSupport().getOrCreate()
 
@@ -24,11 +24,11 @@ def test():
         spark.sql("CREATE TEMPORARY FUNCTION json_map AS 'brickhouse.udf.json.JsonMapUDF'")
         spark.sql("CREATE TEMPORARY FUNCTION is_json AS 'com.gmei.hive.common.udf.UDFJsonFormatCheck'")
 
-        # hive_context.sql("SET mapreduce.job.queuename=data")
-        # hive_context.sql("SET mapred.input.dir.recursive=true")
-        # hive_context.sql("SET hive.mapred.supports.subdirectories=true")
-        sql = "select user_id from online.tl_hdfs_maidian_view where partition_date = '20190412' limit 10"
-        spark.sql(sql).show(6)
+        sql = """select cl_id as device_id,params["business_id"] as cid_id,
+        (params["out"]-params["in"]) as dur_time from online.bl_hdfs_maidian_updates where action="page_view" 
+        and params["page_name"]="diary_detail" and partition_date = '20190801'
+       """
+        df = spark.sql(sql)