修改测试文件

tensnsorflow/multi.py

@@ -36,7 +36,7 @@ def feature_engineer():
     validate_date = con_sql(db, sql)[0].values.tolist()[0]
     print("validate_date:" + validate_date)
     temp = datetime.datetime.strptime(validate_date, "%Y-%m-%d")
-    start = (temp - datetime.timedelta(days=3)).strftime("%Y-%m-%d")
+    start = (temp - datetime.timedelta(days=1)).strftime("%Y-%m-%d")
     print(start)
 
     sparkConf = SparkConf().set("spark.hive.mapred.supports.subdirectories", "true") \
@@ -44,8 +44,8 @@ def feature_engineer():
         .set("spark.tispark.plan.allow_index_double_read", "false") \
         .set("spark.tispark.plan.allow_index_read", "true") \
         .set("spark.sql.extensions", "org.apache.spark.sql.TiExtensions") \
-        .set("spark.tispark.pd.addresses", "172.16.40.158:2379").set("spark.io.compression.codec", "lzf")\
-        .set("spark.driver.maxResultSize", "4g")
+        .set("spark.tispark.pd.addresses", "172.16.40.158:2379").set("spark.io.compression.codec", "lzf")
+        # .set("spark.driver.maxResultSize", "4g")
 
     spark = SparkSession.builder.config(conf=sparkConf).enableHiveSupport().getOrCreate()
     ti = pti.TiContext(spark)
@@ -118,11 +118,12 @@ def feature_engineer():
                    value_map[x[13]], value_map[x[14]], value_map[x[15]], value_map[x[16]],
                    value_map[x[17]], x[18], x[19]))
 
-    print("test.count",test.count())
-    print("train count",train.count())
+    # print("test.count",test.count())
+    # print("train count",train.count())
 
     spark.createDataFrame(test).write.csv('/recommend/va', mode='overwrite', header=True)
     spark.createDataFrame(train).write.csv('/recommend/tr', mode='overwrite', header=True)
+    print("done")
 
     return validate_date,value_map,app_list_map,leve2_map,leve3_map