change test file

tensnsorflow/feature_engineering.py

@@ -40,19 +40,19 @@ def get_map():
     db = pymysql.connect(host='172.16.40.158', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test')
     sql = "select app_list from device_app_list"
     a = time.time()
-    apps_number, app_list_map = get_list(db,sql,1)
+    apps_number, app_list_map = get_list(db,sql,16)
     print("applist")
     print((time.time()-a)/60)
     db = pymysql.connect(host='172.16.40.158', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test')
     sql = "select level2_ids from diary_feat"
     b = time.time()
-    leve2_number, leve2_map = get_list(db, sql, 1+apps_number)
+    leve2_number, leve2_map = get_list(db, sql, 16+apps_number)
     print("leve2")
     print((time.time() - b) / 60)
     db = pymysql.connect(host='172.16.40.158', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test')
     sql = "select level3_ids from diary_feat"
     c = time.time()
-    leve3_number, leve3_map = get_list(db, sql, 1+leve2_number+apps_number)
+    leve3_number, leve3_map = get_list(db, sql, 16+leve2_number+apps_number)
     print((time.time() - c) / 60)
     return apps_number, app_list_map,leve2_number, leve2_map,leve3_number, leve3_map
 
@@ -276,14 +276,14 @@ def get_predict(date,value_map,app_list_map,leve2_map,leve3_map):
                                              app_list_func(x[10], leve2_map), app_list_func(x[11], leve2_map),
                                              app_list_func(x[12], leve2_map), app_list_func(x[13], leve2_map),
                                              app_list_func(x[14], leve2_map), app_list_func(x[15], leve2_map),
-                                             [value_map.get(date, 299999), value_map.get(x[16], 299998),
-                                              value_map.get(x[17], 299997), value_map.get(x[18], 299996),
-                                              value_map.get(x[19], 299995), value_map.get(x[20], 299994),
-                                              value_map.get(x[21], 299993), value_map.get(x[22], 299992),
-                                              value_map.get(x[23], 299991), value_map.get(x[24], 299990),
-                                              value_map.get(x[25], 299989), value_map.get(x[26], 299988),
-                                              value_map.get(x[27], 299987), value_map.get(x[28], 299986),
-                                              value_map.get(x[29], 299985)
+                                             [value_map.get(date,1), value_map.get(x[16],2),
+                                              value_map.get(x[17],3), value_map.get(x[18], 4),
+                                              value_map.get(x[19], 5), value_map.get(x[20], 6),
+                                              value_map.get(x[21], 7), value_map.get(x[22], 8),
+                                              value_map.get(x[23], 9), value_map.get(x[24], 10),
+                                              value_map.get(x[25], 11), value_map.get(x[26], 12),
+                                              value_map.get(x[27], 13), value_map.get(x[28], 14),
+                                              value_map.get(x[29], 15)
                                               ]))
 
     rdd.persist(storageLevel= StorageLevel.MEMORY_AND_DISK)
@@ -321,9 +321,6 @@ def get_predict(date,value_map,app_list_map,leve2_map,leve3_map):
     print("nearby tfrecord done")
 
 
-
-
-
 if __name__ == '__main__':
     sparkConf = SparkConf().set("spark.hive.mapred.supports.subdirectories", "true") \
         .set("spark.hadoop.mapreduce.input.fileinputformat.input.dir.recursive", "true") \