514558_zh-CN

liliconcom

优化循环

你好，

我有一些 JSL 代码需要很长时间才能针对较大的数据集执行。

该代码在 for 循环中运行 for 循环以计算条带的平均偏移量。 我正在寻找一种更快的方法来做到这一点。

有没有办法让处理更快？ 当前脚本大约需要 20 分钟才能完成循环

 

这是下面的脚本：

Names Default To Here( 1 );

dt1 =Data table( "Reference data table.jmp" );
dt2 = Current data table(); /// Select Data table.jmp
Col_List1 = dt2 << Get Column Names( "String" );

For( c = 1, c <= N Col( dt2 ) -1, c++,
 theMatrix = [];
 name = Column( Col_List1[c] ) << Get name;
 if (Contains( Col_List1[c], "Currents" )| Contains( Col_List1[c], "Voltage" )| Contains( Col_List1[c], "Resistance" ),
 For( r = 1, r <= N Rows( dt2 ), r++,
  mean = dt1:Mean[dt1 << Get Rows Where( :Tests == name )];
  measure = mean - Col Mean( If( dt2:Strips == dt2:Strips[r], Column( dt2, c ), . ) );
  theMatrix = theMatrix || Column( dt2, c )[r] + measure;
 );
 Column( dt2, c ) << Set Values( theMatrix );
););

 

脚本Re: 优化循环

我看到问题的两个地方是

mean = dt1:Mean[dt1 << Get Rows Where( :Tests == name )];

和

measure = mean - Col Mean( If( dt2:Strips == dt2:Strips[r], Column( dt2, c ), . ) );

这是解决这些问题的方法 检查它们，看看答案是否正确

Names Default To Here( 1 );
start=today();
dt1 =Data table( "Reference data table.jmp" );
dt2 = Current data table(); /// Select Data table.jmp

For(i=1,i<=nrows(dt1),i++,
 theTest = dt1:Tests[i];
 try(column(dt2,theTest) << set property("TheMean", dt1:mean[i]));
);

Col_List1 = dt2 << Get Column Names( "String" );

For( c = 1, c <= N Col( dt2 ) -1, c++,
 theMatrix = [];
 name = Column( Col_List1[c] ) << Get name;
 if (Contains( Col_List1[c], "Currents" )| Contains( Col_List1[c], "Voltage" )| Contains( Col_List1[c], "Resistance" ),
 //For( r = 1, r <= N Rows( dt2 ), r++,
 For Each Row( r=row();
  //mean = dt1:Mean[dt1 << Get Rows Where( :Tests == name )];
  mean = column(dt2,col_list1[c]) << get property("theMean");
  //measure = mean - Col Mean( If( dt2:Strips == dt2:Strips[r], Column( dt2, c ), . ) );
  measure = mean - Col Mean(as Column( dt2, c ),:Strips);
  theMatrix = theMatrix || Column( dt2, c )[r] + measure;
 );
 Column( dt2, c ) << Set Values( theMatrix );
););
show((start-today())/60);

 

Re: 优化循环

@杰克史密斯12 ，我不确定条件是什么dt2:Strips == dt2Strips[r]应该解决，但它可能没有做你想做的事。

 

没有任何测试数据要测试，这就是我将如何开始优化它——主要是采用 dt1 << 获取行位置（：测试 == 名称）在循环之外。

 

Names Default to Here( 1 );

dt1 = Data Table( "Reference Data Table.jmp" );
dt2 = Current Data Table();

col list1 = dt2 << Get Column Names( "String" );

Summation( c = 1, N Col( dt2 ) - 1,  //summation is faster that For() if you don't need to use Break() or Continue()
 values = [];
 name = Column( dt2, c ) << Get Name;
 If( Contains( name, "Currents" ) | Contains( name, "Voltage" ) | Contains( name, "Resistance" ),
  rows = dt1 << Get Rows Where( :tests == name );  // As Constant() prevents JMP from doing a lookup per row
  col = Column( dt2, c );
  col mean = Col Mean( col );
  For Each Row( dt2,
   mean = dt1:Mean[rows];
   measure = mean - If( dt2:Strips == dt2:Strips /* always true */, col mean, 0 );
   values |/= col[] + measure  // append value to
  );
  col << Set Values( values )
 );
 0 // summation needs to end in a numeric
)

Re: 优化循环

谢谢吉姆。 它就像魅力一样

Re: 优化循环

你好@txnelson ,

您建议的逻辑存在一些问题。 如果参考数据表不包含主数据表中的测试，它将从这些测试中删除行值。 我只是为了抵消参考数据表中的测试。 任何帮助将非常感激

 

我附上了下面的数据表。 我只想抵消参考表中指定的测试

 

Re: 优化循环

如果未设置列属性“theMean”，我修改了您的代码以绕过处理

Names Default To Here( 1 );
start = Today();
dt1 = Data Table( "Reference data table.jmp" );
dt2 = Current Data Table(); /// Select Data table.jmp

For( i = 1, i <= N Rows( dt1 ), i++,
 theTest = dt1:Tests[i];
 Try( Column( dt2, theTest ) << set property( "TheMean", dt1:mean[i] ) );
);

Col_List1 = dt2 << Get Column Names( "String" );

For( c = 1, c <= N Col( dt2 ) - 1, c++,
 theMatrix = [];
 name = Column( Col_List1[c] ) << Get name;
 If( Contains( Col_List1[c], "Currents" ) | Contains( Col_List1[c], "Voltage" ) | Contains( Col_List1[c], "Resistance" ), 
 //For( r = 1, r <= N Rows( dt2 ), r++,
  mean = .;
  Try( mean = Column( dt2, col_list1[c] ) << get property( "theMean" ) );
  // Don't process if a value for theMean does not exist
  If( Is Missing( mean ) == 0,
   For Each Row(
    r = Row();
  //mean = dt1:Mean[dt1 << Get Rows Where( :Tests == name )];
  
    //measure = mean - Col Mean( If( dt2:Strips == dt2:Strips[r], Column( dt2, c ), . ) );
    measure = mean - Col Mean( As Column( dt2, c ), :Strips );
    theMatrix = theMatrix || Column( dt2, c )[r] + measure;
   );
   Column( dt2, c ) << Set Values( theMatrix );
  );
 );
);
Show( (start - Today()) / 60 );

Re: 优化循环

非常感谢吉姆。