working but very slow

scratchpad.py

@@ -1,5 +1,7 @@
+import time
 import sys
 import json
+from typing import Dict
 from cassandra.cluster import Cluster
 
 sys.path.append("config/db")
@@ -14,19 +16,14 @@ session = cluster.connect(config['cassandra_keyspace'])
 print(f"Connection OK")
 
 result = session.execute("SELECT * FROM clusters")
-print(result.all())
 
+map = dict()
 
-"""
+for e in result.all():
-sc = pyspark.SparkContext('spark://osboxes:7077')
+    if(e[1] not in map):
+        map[e[1]] = []
     
-data = sc.parallelize(list("aaa bbb cc dd e f"))
+    map[e[1]].append(e[0])
-counts = data \
-    .map(lambda x: (x, 1)) \
-    .reduceByKey(add) \
-    .sortBy(lambda x: x[1], ascending=False) \
-    .collect()
 
-for (word, count) in counts:
+for key in map:
-    print("{}: {}".format(word, count))
+    print(sorted(map[key]))
-"""

src/spark/main.py

@@ -4,11 +4,13 @@ import json
 from sqlite3 import Row
 from typing import Iterable, List
 
-from pyspark import RDD
-
 from pyspark.sql import SparkSession, DataFrame, Row
 from pyspark.sql import functions as F
 
+import time
+start = time.time()
+
+
 config = json.load(open("./settings.json"))
 debug = config['debug']
 
@@ -63,17 +65,21 @@ class Master:
             .toDF(["tx_group", "index"])
 
     def rewrite_cluster_parent(self, cluster_roots: Iterable[str], new_cluster_root: str) -> None:
-        sqlstr = f"""
+        cluster_rewrite = self.spark \
-            UPDATE {self.CLUSTERS_TABLE} 
+            .table(self.CLUSTERS_TABLE) \
-            SET parent='{new_cluster_root}' 
+            .where(F.col('parent').isin(cluster_roots)) \
-            WHERE parent IN ({','.join(map(lambda r: f"'{r}'", cluster_roots))})"""
+            .select('address') \
+            .rdd \
+            .map(lambda addr: (addr['address'], new_cluster_root)) \
+            .toDF(['address', 'parent']) \
         
         if(debug):
-            print("UPDATE SQL")
+            print("REWRITE JOB")
-            print(sqlstr)
+            cluster_rewrite.show(truncate=False, vertical=True)
             print()
 
-        self.spark.sql(sqlstr)
+        cluster_rewrite.writeTo(self.CLUSTERS_TABLE).append()
+        
         
 # end class Master
 
@@ -104,7 +110,7 @@ for i in range(0, tx_addr_groups.count()):
 
     if(debug):
         print("KNOWN CLUSTERS")
-        cluster_addr_groups.show(truncate=False)
+        cluster_addr_groups.show(truncate=True)
         print()
 
     tx_addrs: Iterable[str] = tx_groups_indexed \
@@ -129,7 +135,7 @@ for i in range(0, tx_addr_groups.count()):
         print("cluster_tx_mapping")
         cluster_tx_mapping \
             .toDF(['cluster', 'tx']) \
-            .show(truncate=False)
+            .show(truncate=True)
         print()
 
 
@@ -145,7 +151,7 @@ for i in range(0, tx_addr_groups.count()):
 
 
     if(len(matched_roots) == 0):
-        new_root = master.insertNewCluster(tx_addrs)
+        master.insertNewCluster(tx_addrs)
     elif(len(matched_roots) == 1):
         master.insertNewCluster(tx_addrs, matched_roots[0])
     else:
@@ -153,4 +159,7 @@ for i in range(0, tx_addr_groups.count()):
         master.insertNewCluster(tx_addrs, matched_roots[0])
 
     if(debug):
-        print("==============")
+        print("======================================================================")
+
+end = time.time()
+print("ELAPSED TIME:", end-start)