修改测试文件

tensnsorflow/multi.py

@@ -171,9 +171,10 @@ def get_predict(date,value_map,app_list_map,level2_map,level3_map):
     native_pre.write.format("avro").save(path="/recommend/pre_native", mode="overwrite")
 
     spark.createDataFrame(rdd.filter(lambda x: x[6] == 0)
-                                   .map(lambda x: (x[0], x[1], x[2],x[9],x[10],x[11],x[12],x[13],x[14],x[15],
+                                   .map(lambda x: (x[0], x[1], x[2],x[7],x[8],x[9],x[10],x[11],x[12],
+                                                   x[13],x[14],x[15],
                                                    x[16],x[17],x[18],x[19],x[20],x[21],x[22],x[23]))) \
-        .toDF("app_list", "level2_ids", "level3_ids","ucity_id",
+        .toDF("app_list", "level2_ids", "level3_ids","y","z","ucity_id",
              "ccity_name", "device_type","manufacturer", "channel", "time", "hospital_id",
               "treatment_method", "price_min", "price_max", "treatment_time", "maintain_time",
               "recover_time", "top","stat_date").write.format("avro").save(path="/recommend/native", mode="overwrite")
@@ -185,9 +186,10 @@ def get_predict(date,value_map,app_list_map,level2_map,level3_map):
     nearby_pre.write.format("avro").save(path="/recommend/pre_nearby", mode="overwrite")
 
     spark.createDataFrame(rdd.filter(lambda x: x[6] == 1)
-                          .map(lambda x: (x[0], x[1], x[2], x[9], x[10], x[11], x[12], x[13], x[14], x[15],
+                          .map(lambda x: (x[0], x[1], x[2], x[7], x[8], x[9], x[10], x[11], x[12],
+                                          x[13], x[14], x[15],
                                           x[16], x[17], x[18], x[19], x[20], x[21], x[22], x[23]))) \
-        .toDF("app_list", "level2_ids", "level3_ids", "ucity_id",
+        .toDF("app_list", "level2_ids", "level3_ids","y","z", "ucity_id",
                "ccity_name", "device_type", "manufacturer", "channel", "time", "hospital_id",
               "treatment_method", "price_min", "price_max", "treatment_time", "maintain_time",
               "recover_time","top","stat_date").write.format("avro").save(path="/recommend/nearby", mode="overwrite")
@@ -228,13 +230,13 @@ if __name__ == '__main__':
         .set("spark.driver.maxResultSize", "8g")
 
     spark = SparkSession.builder.config(conf=sparkConf).enableHiveSupport().getOrCreate()
-    # ti = pti.TiContext(spark)
-    # ti.tidbMapDatabase("jerry_test")
-    # spark.sparkContext.setLogLevel("WARN")
-    # validate_date, value_map, app_list_map, leve2_map, leve3_map = feature_engineer()
-    # get_predict(validate_date, value_map, app_list_map, leve2_map, leve3_map)
+    ti = pti.TiContext(spark)
+    ti.tidbMapDatabase("jerry_test")
+    spark.sparkContext.setLogLevel("WARN")
+    validate_date, value_map, app_list_map, leve2_map, leve3_map = feature_engineer()
+    get_predict(validate_date, value_map, app_list_map, leve2_map, leve3_map)
+
 
-    test()