435681_zh-CN

liliconcom

JMP > JSL > 多次调用拟合模型（N > 2000）的脚本加速？

您好 JMP 社区，

我的数据集越来越大，而我不久前创建的基本脚本（见下文）从速度的角度来看并没有跟上。

我将非常感谢听到有关如何优化此类脚本以提高速度的想法。 例如，我怀疑像“连接”这样的操作相对较慢，使用矩阵来进行这种类型的操作可能是有意义的。

Names Default to Here (1);

dt = Current Data Table ();

CList = dt << Get Column Names (string);

dtoutl = New Table ("LSM OUTPUT", "invisible");
dtoutp = New Table ("PVal OUTPUT", "invisible");


For (i = 1, i<= 2000, i++,  

 fm = dt << Fit Model(
     Y( Column (i) ),
     Effects( :VISIT, :TREATMENT, :VISIT * :TREATMENT, Column (i+2000) ),
     Personality( "Standard Least Squares" ),
     Emphasis( "Minimal Report" ),
     Run(
      Column (i) << {Summary of Fit( 1 ), Analysis of Variance( 1 ),
      Parameter Estimates( 1 ), Scaled Estimates( 0 ),
      Plot Actual by Predicted( 0 ), Plot Regression( 0 ),
      Plot Residual by Predicted( 0 ), Plot Studentized Residuals( 0 ),
      Plot Effect Leverage( 0 ), Plot Residual by Normal Quantiles( 0 ),
      Box Cox Y Transformation( 0 ), {:VISIT * :TRT01A <<
      {LSMeans Contrast( [0 0 1 -1 0 0, 0 0 0 0 1 -1] )}}}
     )
     
    );
 fmr = report (fm);
 
 table_list = fmr << xpath ("//OutlineBox [text() = 'VISIT*TREATMENT']//TableBox");
 
 temp_lsm = table_list [1];
 temp_pval = table_list [2];
 
 temp_tbl_lsm = temp_lsm << Make into Data Table (invisible (1));
 temp_tbl_pval = temp_pval << Make into Data Table (invisible (1));
 
 temp_tbl_lsm << New column ("ID", character, nominal, << set each value (CList [i]));
 temp_tbl_pval << New column ("ID", character, nominal, << set each value (CList [i]));
 
 fmr << close window;
 
 dtoutl << Concatenate (Data table (temp_tbl_lsm), "Append to First Table");
 Wait (0);
 dtoutp << Concatenate (Data table (temp_tbl_pval), "Append to First Table");
 
 Close (temp_tbl_lsm, NoSave); 
 Close (temp_tbl_pval, NoSave); 
  
 
);


dtoutl << Bring Window to Front;
dtoutp << Bring Window to Front;

欢迎所有反馈。

最好的，

TS

脚本回复：JMP > JSL > 多次调用拟合模型（N > 2000）的脚本加速？

嗨，

 

使 Fit Model 不可见又减少了 8 秒（从 61 秒到 53 秒），用直接分配替换“For Each Row”又减少了 5 秒（53 秒到 48 秒）。

 

杰出的！

最好的，

TS

回复：JMP > JSL > 多次调用拟合模型（N > 2000）的脚本加速？

这些可能会进一步（很可能相当小）提高速度：

 

您很可能会添加不可见以适合模型

fm = dt << Fit Model(
 Y( Column (i) ),
 Effects( :VISIT, :TRT01A, :VISIT * :TRT01A, Column (i-1933) ),
 Personality( "Standard Least Squares" ),
 Emphasis( "Minimal Report" ),
 Run(
  Column (i) << {Summary of Fit( 1 ), Analysis of Variance( 1 ),
  Parameter Estimates( 1 ), Scaled Estimates( 0 ),
  Plot Actual by Predicted( 0 ), Plot Regression( 0 ),
  Plot Residual by Predicted( 0 ), Plot Studentized Residuals( 0 ),
  Plot Effect Leverage( 0 ), Plot Residual by Normal Quantiles( 0 ),
  Box Cox Y Transformation( 0 ), {:VISIT * :TRT01A <<
  {LSMeans Contrast( [0 0 1 -1 0 0, 0 0 0 0 1 -1] )}}}
 ),
 invisible
);

 

此外，如果您使用公式创建列然后立即删除它们，您可以使用 << Set Each value 而不是 Formula 和 Delete Formula

dtoutl << New Column("METAB_ID", Character, Nominal, << Set Each Value(Substitute(:MET_ID, "LOG10 FC ", "")));

 

您也可以用 << Set Each Value 替换 For Each Row （不确定这一点，也不确定这是否会提高速度）：

Column(dtoutp, "LABEL") << Set Each Value(annot_pv[Sequence( 1, N Items (annot_pv), 1, 1 )]);

 

您还可以尝试将数据表保密（至少不可见），直到您需要它们为止。 您可以使用 << New Data View 使私有表可见（今天之前不知道这个）。

 

在不需要它们后立即关闭数据表/报告/窗口。

回复：JMP > JSL > 多次调用拟合模型（N > 2000）的脚本加速？

您好 JMP 社区，

在下面找到最改进的脚本的注释版本，以运行和捕获大量拟合模型分析的输出。

提高运行时间的两个最重要的步骤是：

1. 使用矩阵而不是数据表来聚合分析输出
2. 替换而不是将分析输出数据插入到在主循环之前创建的主矩阵中。

Names Default to Here (1);

st = Today();

dt = Current Data Table ();

lc_path = dt << GetPath;

// START: CAPTURING OUTPUT ANNOTATION TO REBUILD ANNOTATION // 
dts = dt << Summary( Group( :VISIT, :TRT01A ), Freq( "None" ), Weight( "None" ), invisible );
annot_lsm = {};
met_l = {};
annot_pv = {};

CList = dt << Get Column Names (string);

For (j = 1, j <= N Rows (dts), j++,
 insert into (annot_lsm, dts:VISIT [j] || ", " || dts:TRT01A [j]);
);

annot_pv = annot_lsm;

annot_pv = Concat To(annot_pv, {"Estimate","Std Error", "t Ratio", "Prob>|t|", "SS", "Lower 95%", "Upper 95%"});

Close (dts, NoSave);
// END: CAPTURING OUTPUT ANNOTATION TO REBUILD ANNOTATION // 

// START: CREATING EMPTY NASTER MATRICES TO HOLD TTHE OUTPUT OF THE FIT MODEL//
nro_l = 1933*6;
nco_l = 4;

nro_p = 1933 * 13;
nco_p = 2;

mtx_lsm = J(nro_l, nco_l);
mtx_pval = J(nro_p, nco_p);
// END: CREATING EMPTY MASTER MATRICES TO HOLD TTHE OUTPUT OF THE FIT MODEL//

//START MAIN LOOP//
For (i = 3921, i<= 5853, i++,  //5853
 
 //START LINEAR MODEL WITH CUSTGOMIZED CONTRASTS //
 
 fm = dt << Fit Model(
     Y( Column (i) ),
     Effects( :VISIT, :TRT01A, :VISIT * :TRT01A, Column (i-1933) ),
     Personality( "Standard Least Squares" ),
     Emphasis( "Minimal Report" ),
     Run(
      Column (i) << {Summary of Fit( 1 ), Analysis of Variance( 1 ),
      Parameter Estimates( 1 ), Scaled Estimates( 0 ),
      Plot Actual by Predicted( 0 ), Plot Regression( 0 ),
      Plot Residual by Predicted( 0 ), Plot Studentized Residuals( 0 ),
      Plot Effect Leverage( 0 ), Plot Residual by Normal Quantiles( 0 ),
      Box Cox Y Transformation( 0 ), {:VISIT * :TRT01A <<
      {LSMeans Contrast( [0 0 1 -1 0 0, 0 0 0 0 1 -1] )}}}
     )
     
    );
 //END LINEAR MODEL WITH CUSTGOMIZED CONTRASTS //
 
 //START CAPTURE ANALYSIS OUTPUTS FOR EACH RUN//
 fmr = report (fm);
 
 insert into (met_l, CList [i]); //COLLATING THE NAME OF THE COLUMN FOR EACH RUN//
 
 table_list = fmr << xpath ("//OutlineBox [text() = 'VISIT*TRT01A']//TableBox");
 
 temp_lsm = table_list [1]; //POINTER TO LSMEAN + STDERR TABLE//
 temp_pval = table_list [2]; // POINTER TO CONTRAST TABLE //
 
 temp_mtx_lsm = temp_lsm << Get as Matrix; // EXTRACT LSMEAN + STDERR OUTPUT AS A MATRIX //
 temp_mtx_pval = temp_pval << Get as Matrix; // EXTRACT CONTRAST OUTPUT AS A MATRIX //
 
 locr1_l = ((i-3921)*6) + 1; //GENERATE THE TOP ROW BLOCK FOR INSERTION OF LSMEAN + STDERR IN TO THE MASTER MATRIX //
 locr2_l = ((i-3921)*6) + 6; //GENERATE THE BOTTOM ROW BLOCK FOR INSERTION OF LSMEAN + STDERR IN TO THE MASTER MATRIX //
 
 mtx_lsm [locr1_l::locr2_l, 0] = temp_mtx_lsm [0,0]; //REPLACE PLACEHOLDER VALUES IN MASTER MATRIX WITH LOCAL LSMEAN + STDERR OUTPUT DATA FROM EACH RUN //
 
 locr1_p = ((i-3921)*13) + 1; //GENERATE THE TOP ROW BLOCK FOR INSERTION OF CONTRAST IN TO THE MASTER MATRIX //
 locr2_p = ((i-3921)*13) + 13; //GENERATE THE BOTTOM ROW BLOCK FOR INSERTION OF CONTRAST IN TO THE MASTER MATRIX //
 
 mtx_pval [locr1_p::locr2_p, 0] = temp_mtx_pval [0,0]; //REPLACE PLACEHOLDER VALUES IN MASTER MATRIX WITH LOCAL CONTRAST OUTPUT DATA FROM EACH RUN //
 
 fmr << close window; 
);
// START CONVERT MASTER MATRICES INTO TABLES//
dtoutl = as Table (mtx_lsm); 
dtoutp = as Table (mtx_pval);
// END CONVERT MASTER MATRICES INTO TABLES//

//START REBUILD ANNOTATIONS AND REFORMAT FOR LSMEAN + STDERR TABLE//
dtoutl << new column ("COMP", Character, Nominal);
dtoutl << new column ("MET_ID", Character, Nominal);
dtoutl:Col1 << set name ("LSMEAN");
dtoutl:Col2 << set name ("STDERR");
dtoutl:Col3 << set name ("UPPER CI");
dtoutl:Col4 << set name ("LOWER CI");

dtoutl << Begin Data Update;
 For Each Row( dtoutl, :COMP = annot_lsm[Sequence( 1, N Items (annot_lsm), 1, 1 )] );
 For each row( dtoutl, :MET_ID = met_l[Sequence (1,N Items (met_l), 1, 6)] );
dtoutl << End Data Update;

dtoutl << New Column ("METAB_ID", Character, Nominal, Formula (Substitute (:MET_ID, "LOG10 FC ", ""))) ;
dtoutl << New Column ("VISIT", Character, Nominal, Formula (Word (1,:COMP, ",")));
dtoutl << New Column ("ARM", Character, Ordinal, Formula (Word (-1, :COMP, ",")));

dtoutl:METAB_ID << Delete Formula;
dtoutl:ARM << Delete Formula;
dtoutl:VISIT << Delete Formula;
//END REBUILD ANNOTATIONS AND REFORMAT FOR LSMEAN + STDERR TABLE//

//START REBUILD ANNOTATIONS AND REFORMAT FOR CONTRAST TABLE//
dtoutp << new column ("LABEL", Character, Nominal);
dtoutp << new column ("MET_ID", Character, Nominal);

dtoutp << Begin Data Update;
 For Each Row( dtoutp, :LABEL = annot_pv[Sequence( 1, N Items (annot_pv), 1, 1 )] );
 For each row( dtoutp, :MET_ID = met_l[Sequence (1,N items (met_l), 1, 13)] );
dtoutp << End Data Update;

CNAME1 = Column (dtoutp, 3) [3];
CNAME2 = Column (dtoutp, 3) [5];

dtoutp << Select Where (:LABEL == "Prob>|t|");

dtoutp_s = dtoutp << subset (Selected Rows, Output Table Name ("P VAL"));

Close (dtoutp, NoSave);

dtoutp_s << New Column ("METAB_ID", Character, Nominal, Formula (Substitute (:MET_ID, "LOG10 FC ", "")));

dtoutp_s:Col1 << Set Name (CNAME1);
dtoutp_s:Col2 << Set Name (CNAME2);

dtoutp_s_s = dtoutp_s << Stack (Columns (as name(CNAME1), as name (CNAME2)), Output Table Name ("STACK P VAL"));

Close (dtoutp_s, NoSave);

dtoutp_s_s << New Column ("VISIT", Character, Nominal, Formula (Word (1,:Label, ",")));
dtoutp_s_s << New Column ("xARM", Character, Ordinal, Formula (Word (-1, :Label, ",")));
dtoutp_s_s:Data << Set name ("NOM P VAL");

dtoutl << Update(
 With( dtoutp_s_s ),
 Match Columns( :METAB_ID = :METAB_ID, :VISIT = :VISIT ),
 Add Columns from Update Table( :NOM P VAL ),
 Replace Columns in Main Table( None )
);

Close (dtoutp_s_s, NoSave);
//END REBUILD ANNOTATIONS AND REFORMAT FOR CONTRAST TABLE//
dtoutl << Save (substitute (lc_path, dt << get name||".jmp", "LINMOD_OUT_")||char(today())); //

et = Today ();

show (Date Difference (st, et, "second"));

最好的，

TS

回复：JMP > JSL > 多次调用拟合模型（N > 2000）的脚本加速？

凉爽的！ 我认为社区希望看到您为实现目标所做的工作，或者总结一下不同变化的重要性。

@DonMcCormack

回复：JMP > JSL > 多次调用拟合模型（N > 2000）的脚本加速？

你好@Craige_Hales ,

谢谢你的建议。 感谢您推荐的方法，我的速度又提高了 33%。

我仍然需要完善一些调整，但我开始时的总运行时间约为 450 秒，初始更改时降至 91 秒，现在降至 61 秒。

最好的

TS

 

回复：JMP > JSL > 多次调用拟合模型（N > 2000）的脚本加速？

5X 听起来很棒！

 

该平台可能还有一个隐形选项可能会有所帮助。

 

（试试 JSL 分析器，下一个建议可能会离谱。 使用 < 1% 的时间来加快速度是没有意义的……）

 

如果还不够，循环中的最后两个语句可能是下一个要查看的地方。 我认为您的 JSL 正在以越来越大的大小重新分配数组 2000 次。 如果您可以预先分配数组（使用 J(nr,nc,initvalue) 函数）并使用 mtx_lsm[a::b,0] = temp_mtx_lsm[0,0] 之类的内容存储到其中，您将节省一些时间.

 

编辑：这可能是一个 N^2 问题，因为它不仅会重新分配，还会复制数据；从 1000 次运行到 2000 次运行将复制 4 倍（而不是 2 倍）的数据量。

 

回复：JMP > JSL > 多次调用拟合模型（N > 2000）的脚本加速？

您好 JMP 社区，

 

我已经尝试使用矩阵作为容器来聚合分析输出表的长集合，到目前为止，我已经将执行时间加快了约 5 倍（见下文）。 唯一的小不便是我不得不为捕获的输出表重建注释，因为（显然）矩阵不包含文本。

Names Default to Here (1);

st = Today();

dt = Current Data Table ();
dts = dt << Summary( Group( :VISIT, :TRT01A ), Freq( "None" ), Weight( "None" ), invisible );
annot_lsm = {};
met_l = {};
annot_pv = {};

CList = dt << Get Column Names (string);

For (j = 1, j <= N Rows (dts), j++,
 insert into (annot_lsm, dts:VISIT [j] || ", " || dts:TRT01A [j]);
);

annot_pv = annot_lsm;

annot_pv = Concat To(annot_pv, {"Estimate","Std Error", "t Ratio", "Prob>|t|", "SS", "Lower 95%", "Upper 95%"});

Close (dts, NoSave);

mtx_lsm = [];
mtx_pval = [];

For (i = 1, i<= 2000, i++,  //2000

 fm = dt << Fit Model(
     Y( Column (i) ),
     Effects( :VISIT, :TRT01A, :VISIT * :TRT01A, Column (i+2000) ),
     Personality( "Standard Least Squares" ),
     Emphasis( "Minimal Report" ),
     Run(
      Column (i) << {Summary of Fit( 1 ), Analysis of Variance( 1 ),
      Parameter Estimates( 1 ), Scaled Estimates( 0 ),
      Plot Actual by Predicted( 0 ), Plot Regression( 0 ),
      Plot Residual by Predicted( 0 ), Plot Studentized Residuals( 0 ),
      Plot Effect Leverage( 0 ), Plot Residual by Normal Quantiles( 0 ),
      Box Cox Y Transformation( 0 ), {:VISIT * :TRT01A <<
      {LSMeans Contrast( [0 0 1 -1 0 0, 0 0 0 0 1 -1] )}}}
     )
     
    );
 
 fmr = report (fm);
 
 insert into (met_l, CList [i]);
 
 table_list = fmr << xpath ("//OutlineBox [text() = 'VISIT*TRT01A']//TableBox");
 
 temp_lsm = table_list [1];
 temp_pval = table_list [2];
 
 temp_mtx_lsm = temp_lsm << Get as Matrix;
 temp_mtx_pval = temp_pval << Get as Matrix;
 
 fmr << close window;
 
 mtx_lsm = mtx_lsm |/ temp_mtx_lsm;
 mtx_pval = mtx_pval |/ temp_mtx_pval ;
  
);
dtoutl = as Table (mtx_lsm);
dtoutp = as Table (mtx_pval);

dtoutl << new column ("COMP", Character, Nominal);
dtoutl << new column ("MET_ID", Character, Nominal);
dtoutl:Col1 << set name ("LSMEAN");
dtoutl:Col2 << set name ("STDERR");
dtoutl:Col3 << set name ("UPPER CI");
dtoutl:Col4 << set name ("LOWER CI");

dtoutl << Begin Data Update;
 For Each Row( dtoutl, :COMP = annot_lsm[Sequence( 1, N Items (annot_lsm), 1, 1 )] );
 For each row( dtoutl, :MET_ID = met_l[Sequence (1,N Items (met_l), 1, 6)] );
dtoutl << End Data Update;

dtoutp << new column ("LABEL", Character, Nominal);
dtoutp << new column ("MET_ID", Character, Nominal);

dtoutp << Begin Data Update;
 For Each Row( dtoutp, :LABEL = annot_pv[Sequence( 1, N Items (annot_pv), 1, 1 )] );
 For each row( dtoutp, :MET_ID = met_l[Sequence (1,N items (met_l), 1, 13)] );
dtoutp << End Data Update;