bug fix

eda/esmm/Model_pipline/dist_predict.py

@@ -143,7 +143,7 @@ def input_fn(filenames, batch_size=32, num_epochs=1, perform_shuffle=False):
 
 def main():
     # dt_dir = (date.today() + timedelta(-1)).strftime('%Y%m%d')
-    model_dir = "hdfs://172.16.32.4:8020/strategy/esmm/model_ckpt/DeepCvrMTL/"
+    model_dir = "hdfs:///172.16.32.4:8020/strategy/esmm/model_ckpt/DeepCvrMTL/"
     te_files = ["hdfs://172.16.32.4:8020/strategy/esmm/nearby/part-r-00000"]
     model_params = {
         "field_size": 15,
@@ -175,15 +175,15 @@ def test_map(x):
 
 
 if __name__ == "__main__":
-    sparkConf = SparkConf().set("spark.hive.mapred.supports.subdirectories", "true") \
-        .set("spark.hadoop.mapreduce.input.fileinputformat.input.dir.recursive", "true") \
-        .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", "8g").set("spark.sql.avro.compression.codec","snappy")
-    spark = SparkSession.builder.config(conf=sparkConf).enableHiveSupport().getOrCreate()
-    spark.sparkContext.setLogLevel("WARN")
+    # sparkConf = SparkConf().set("spark.hive.mapred.supports.subdirectories", "true") \
+    #     .set("spark.hadoop.mapreduce.input.fileinputformat.input.dir.recursive", "true") \
+    #     .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", "8g").set("spark.sql.avro.compression.codec","snappy")
+    # spark = SparkSession.builder.config(conf=sparkConf).enableHiveSupport().getOrCreate()
+    # spark.sparkContext.setLogLevel("WARN")
 
     path = "hdfs://172.16.32.4:8020/strategy/esmm/"
     # df = spark.read.format("tfrecords").load(path+"nearby/part-r-00000")