add test

tensnsorflow/test.py

-import time
-from pyspark.context import SparkContext
-from pyspark.conf import SparkConf
-
-conf = SparkConf().setMaster("spark://10.30.181.88:7077").setAppName("My app")
-sc = SparkContext(conf=conf)
-sc.setLogLevel("WARN")
-for i in range(1,100):
-    print(i)
-    time.sleep(5)
\ No newline at end of file
+import pandas as pd
+import pymysql
+
+
+def con_sql(db,sql):
+    cursor = db.cursor()
+    try:
+        cursor.execute(sql)
+        result = cursor.fetchall()
+        df = pd.DataFrame(list(result))
+    except Exception:
+        print("发生异常", Exception)
+        df = pd.DataFrame()
+    finally:
+        db.close()
+    return df
+
+
+
+def exp():
+    db = pymysql.connect(host='10.66.157.22', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test')
+    sql = "select native_queue from esmm_device_diary_queue where device_id = '358035085192742'"
+    cursor = db.cursor()
+    cursor.execute(sql)
+    result = cursor.fetchone()[0]
+    native = tuple(result.split(","))
+    db = pymysql.connect(host='10.66.157.22', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_prod')
+    sql = "select diary_id,level1_ids,level2_ids,level3_ids from esmm_diary_feat where diary_id in {}".format(native)
+    df = con_sql(db,sql)
+    n = df.shape[0]
+    one = df[1].unique()
+    one_map = {}
+    for i in one:
+        one_map[i] = df.loc[df[1]==i].shape[0]/n
+    print(sorted(one_map.items(),key = lambda x:x[1]))
+    two = df[2].unique()
+    two_map = {}
+
+    for i in two:
+        two_map[i] = df.loc[df[2] == i].shape[0] / n
+    print(sorted(two_map.items(), key=lambda x: x[1]))
+
+
+
+
+if __name__ == "__main__":
+    exp()
+
+