Modularity
模塊度(Modularity)是一種評估社區(qū)網(wǎng)絡結(jié)構(gòu)的指標,用來評估社區(qū)內(nèi)部連接相對于社區(qū)之間連接的緊密程度,通常模塊度為0.3以上表示社區(qū)劃分質(zhì)量較為合適。Modularity組件能夠輸出圖的模塊度。
配置組件
方法一:可視化方式
在Designer工作流頁面添加Modularity組件,并在界面右側(cè)配置相關參數(shù):
參數(shù)類型 | 參數(shù) | 描述 |
字段設置 | 源頂點列 | 邊表的起點所在列。 |
起始點標簽列 | 邊表起點的群組。 | |
目標頂點列 | 邊表的終點所在列。 | |
目標點標簽列 | 邊表終點的群組。 | |
執(zhí)行調(diào)優(yōu) | 進程數(shù) | 作業(yè)并行執(zhí)行的節(jié)點數(shù)。數(shù)字越大并行度越高,但是框架通訊開銷會增大。 |
進程內(nèi)存 | 單個作業(yè)可使用的最大內(nèi)存量,單位:MB,默認值為4096。 如果實際使用內(nèi)存超過該值,會拋出 |
方法二:PAI命令方式
使用PAI命令配置Modularity組件參數(shù)。您可以使用SQL腳本組件進行PAI命令調(diào)用,詳情請參見場景4:在SQL腳本組件中執(zhí)行PAI命令。
PAI -name Modularity
-project algo_public
-DinputEdgeTableName=Modularity_func_test_edge
-DfromVertexCol=flow_out_id
-DfromGroupCol=group_out_id
-DtoVertexCol=flow_in_id
-DtoGroupCol=group_in_id
-DoutputTableName=Modularity_func_test_result;
參數(shù) | 是否必選 | 默認值 | 描述 |
inputEdgeTableName | 是 | 無 | 輸入邊表名。 |
inputEdgeTablePartitions | 否 | 全表讀入 | 輸入邊表的分區(qū)。 |
fromVertexCol | 是 | 無 | 輸入邊表的起點所在列。 |
fromGroupCol | 是 | 無 | 輸入邊表起點的群組。 |
toVertexCol | 是 | 無 | 輸入邊表的終點所在列。 |
toGroupCol | 是 | 無 | 輸入邊表終點的群組。 |
outputTableName | 是 | 無 | 輸出表名。 |
outputTablePartitions | 否 | 無 | 輸出表的分區(qū)。 |
lifecycle | 否 | 無 | 輸出表的生命周期。 |
workerNum | 否 | 未設置 | 作業(yè)并行執(zhí)行的節(jié)點數(shù)。數(shù)字越大并行度越高,但是框架通訊開銷會增大。 |
workerMem | 否 | 4096 | 單個worker可使用的最大內(nèi)存量,單位:MB,默認值為4096。 如果實際使用內(nèi)存超過該值,會拋出 |
splitSize | 否 | 64 | 數(shù)據(jù)切分的大小,單位:MB。 |
使用示例
步驟中SQL腳本組件均去勾選使用Script模式和是否由系統(tǒng)添加Create Table語句。
添加SQL腳本組件,輸入以下SQL語句生成訓練數(shù)據(jù)。
drop table if exists Modularity_func_test_edge; create table Modularity_func_test_edge as select * from ( select '1' as flow_out_id,'3' as group_out_id,'2' as flow_in_id,'3' as group_in_id union all select '1' as flow_out_id,'3' as group_out_id,'3' as flow_in_id,'3' as group_in_id union all select '1' as flow_out_id,'3' as group_out_id,'4' as flow_in_id,'3' as group_in_id union all select '2' as flow_out_id,'3' as group_out_id,'3' as flow_in_id,'3' as group_in_id union all select '2' as flow_out_id,'3' as group_out_id,'4' as flow_in_id,'3' as group_in_id union all select '3' as flow_out_id,'3' as group_out_id,'4' as flow_in_id,'3' as group_in_id union all select '4' as flow_out_id,'3' as group_out_id,'6' as flow_in_id,'7' as group_in_id union all select '5' as flow_out_id,'7' as group_out_id,'6' as flow_in_id,'7' as group_in_id union all select '5' as flow_out_id,'7' as group_out_id,'7' as flow_in_id,'7' as group_in_id union all select '5' as flow_out_id,'7' as group_out_id,'8' as flow_in_id,'7' as group_in_id union all select '6' as flow_out_id,'7' as group_out_id,'7' as flow_in_id,'7' as group_in_id union all select '6' as flow_out_id,'7' as group_out_id,'8' as flow_in_id,'7' as group_in_id union all select '7' as flow_out_id,'7' as group_out_id,'8' as flow_in_id,'7' as group_in_id )tmp ;
對應的數(shù)據(jù)結(jié)構(gòu)圖:
添加SQL腳本組件,輸入以下PAI命令進行訓練,并和步驟 1中添加的組件連線。
drop table if exists ${o1}; PAI -name Modularity -project algo_public -DinputEdgeTableName=Modularity_func_test_edge -DfromVertexCol=flow_out_id -DfromGroupCol=group_out_id -DtoVertexCol=flow_in_id -DtoGroupCol=group_in_id -DoutputTableName=${o1};
運行此工作流。運行完成后右擊步驟 2中添加的組件,選擇查看數(shù)據(jù) > SQL腳本的輸出,查看訓練結(jié)果。
| val | | ------------------- | | 0.42307692766189575 |