665502_zh-CN

liliconcom

在循环中使用设置每个值、具有相同列名的表和 col 统计函数的组合时出现错误

这已报告给 JMP 支持人员，他们已将其作为错误提交给开发 (00049239)。 似乎至少在 JMP16.2 和 JMP17.0 中会发生

 

需要注意的是，在使用上述组合（设置每个值、循环和列统计函数）时，JMP 存在相当严重的错误。 所发生的情况是，在将数据添加到不同的表时，JMP 确实使用了错误表中的数据。 一种解决方法是在 << Set Each Value (<< Set Each Value(Col Rank(Row(), dt:name))) 中提供表首选项。

 

你似乎需要（根据我相当快的测试）：

1. 具有相同列名的数据表
2. 循环那些
3. 使用 << Set Each Value 设置列中的值
4. 使用的公式应使用Col统计函数和byVar（很可能这在两个表中必须具有相同的名称）

 

下面是一些测试用例

Names Default To Here(1);
// https://www.jmp.com/support/help/en/17.0/#page/jmp/scoping-operators.shtml#

// Initialize data
test_tables = {};
dt = Open("$SAMPLE_DATA/Big Class.jmp");
dt << New Column("REAL NAME RANK", Numeric, Continuous, Formula(Col Rank(Row(), :NAME)));
Column(dt, "age") << Set Modeling Type("Continuous");
Insert Into(test_tables, dt);
dt = Open("$SAMPLE_DATA/Students1.jmp");
dt << Sort(By(:name), Replace Table, Order(Ascending)); // sort to create worse scenario
dt << New Column("REAL NAME RANK", Numeric, Continuous, Formula(Col Rank(Row(), :NAME)));
Column(dt, "age") << Set Modeling Type("Continuous");
Insert Into(test_tables, dt);
/*
dt = Open("$SAMPLE_DATA/Students2.jmp");
dt << Sort(By(:name), Replace Table, Order(Ascending)); // sort to create worse scenario
dt << New Column("REAL NAME RANK", Numeric, Continuous, Formula(Col Rank(Row(), :NAME)));
Column(dt, "age") << Set Modeling Type("Continuous");
Insert Into(test_tables, dt);
*/

// use idx 1 to skip first table
min_idx = 0;

// without reversing we will run out of index as we are using wrong table
// but if we reverse we will get worse outcome (in my opinion) as we end up with wrong data
reverse_tableorder = 0; 


If(reverse_tableorder,
 test_tables = Reverse(test_tables);
);

For Each({dt, idx}, test_tables,
 // works
 // dt << New Column("COPY", Character, Nominal, << Set Each Value(:NAME));
 // dt << New Column("MULTI", Numeric, Continuous, << Set Each Value(:age * :age));

 If(idx > 0, // if the column isn't created to first table seems to work fine?
  // Doesn't work (// old table used due to some col function optimizations when using byVar?)
  Try(
   dt << New Column("RANK", Numeric, Continuous, << Set Each Value(Col Rank(Row(), :NAME)));
  ,
   show(exception_msg);
  );

  Try(
   new_col = dt << New Column("RANK_SEPARATE", Numeric, Continuous);
   new_col << Set Each Value(Col Rank(:Row(), :name));
  ,
   show(exception_msg);
  );

  Try(
   new_col = dt << New Column("SUM", Numeric, Continuous, << Set Each Value(Col Sum(1)));
  ,
   show(exception_msg);
  );

  Try(
   new_col = dt << New Column("SUM_WITH_GROUP", Numeric, Continuous, << Set Each Value(Col Sum(1, :name)));
  ,
   show(exception_msg);
  );

  Try( // with reverse_tableorder = 1, :age is taken from correct table BUT the group sizes from wrong? 
  // KATIE -> 72 (6*12) and not 11+12+12+13+14+15 -> 77
   new_col = dt << New Column("SUM_OF_COL", Numeric, Continuous);
   new_col << Set Each Value(Col Sum(:age, :name));
  ,
   show(exception_msg);
  );

  // workaround
  dt << New Column("RANK_WITH_REF", Numeric, Continuous, << Set Each Value(
   Col Rank(Row(), dt:NAME)
  ));
 );
);

自动化和脚本编写