我有一份调查电子表格,其中我需要了解特定用户随时间的变化情况。因此,我需要忽略特定列中具有唯一值的所有行。数据如下所示:
Response Date Response_ID Account_ID Q.1
10/20/2011 12:03:43 PM 23655956 1168161 8
10/20/2011 03:52:57 PM 23660161 1168152 0
10/21/2011 10:55:54 AM 23672903 1166121 7
10/23/2011 04:28:16 PM 23694471 1144756 9
10/25/2011 06:30:52 AM 23732674 1167449 7
10/25/2011 07:52:28 AM 23734597 1087618 5
我在Excel VBA中找到了一种方法:
Sub Del_Unique()
Application.ScreenUpdating = False
Columns("B:B").Insert Shift:=xlToRight
Columns("A:A").Copy Destination:=Columns("B:B")
i = Application.CountIf(Range("A:A"), "<>") + 50
If i > 65536 Then i = 65536
Do
If Application.CountIf(Range("B:B"), Range("A" & i)) = 1 Then
Rows(i).Delete
End If
i = i - 1
Loop Until i = 0
Columns("B:B").Delete
Application.ScreenUpdating = True
End Sub
我想在Google Spreadsheets中使用不必更改的脚本。我能得到的最接近的是从范围中检索所有重复的用户ID,但不能将其与该行关联。该代码如下:
function findDuplicatesInSelection() {
var activeRange = SpreadsheetApp.getActiveRange();
var values = activeRange.getValues();
// values that appear at least once
var once = {};
// values that appear at least twice
var twice = {};
// values that appear at least twice, stored in a pretty fashion!
var final = [];
for (var i = 0; i < values.length; i++) {
var inner = values[i];
for (var j = 0; j < inner.length; j++) {
var cell = inner[j];
if (cell == "") continue;
if (once.hasOwnProperty(cell)) {
if (!twice.hasOwnProperty(cell)) {
final.push(cell);
}
twice[cell] = 1;
} else {
once[cell] = 1;
}
}
}
if (final.length == 0) {
Browser.msgBox("No duplicates found");
} else {
Browser.msgBox("Duplicates are: " + final);
}
}
答案 0 :(得分:0)
这可能效率不高,但我认为这就是你想要的:
var ar=[1,3,3,5,6,8,6,6];
console.log("Before:");
display(ar);//1 3 3 5 6 8 6 6
var index=[];
var ar2=[];
for(var a=0;a<ar.length;a++)
{
var duplicate=false;
for(var b=0;b<ar.length;b++)
{
if(ar[a]==ar[b]&&a!=b)
{
duplicate=true;
}
}
if(!duplicate)
{
index.push(a);
}
}
for(var a=0;a<index.length;a++)
{
ar[index[a]]=null;
}
for(var a=0;a<ar.length;a++)
{
if(ar[a]!=null)ar2.push(ar[a]);
}
console.log("After:");
display(ar2);//3 3 6 6 6
function display(x)
{
for(var a=0;a<x.length;a++)console.log(x[a]);
}
小提琴:http://jsfiddle.net/mageek/6AGQ4/
作为功能的较短版本:
var ar=[1,3,3,5,6,8,6,6];
function removeUnique(x)
{
var index=[];
var ar2=[];
for(var a=0;a<ar.length;a++)
{
var duplicate=0;
for(var b=0;b<ar.length;b++)if(ar[a]==ar[b]&&a!=b)duplicate=1;
if(!duplicate)index.push(a);
}
for(var a=0;a<index.length;a++)ar[index[a]]=null;
for(var a=0;a<ar.length;a++)if(ar[a]!=null)ar2.push(ar[a]);
return x;
}
ar=removeUnique(ar);
答案 1 :(得分:0)
我建议选择简单的事情。
这是一个标记重复的简单函数
function flagDuplicate(value, array) {
var duplicateCounter = 0;
for (var i=0; i<array.length; i++){
if (array[i] == value){ // I avoid === in Spreadsheet functions
duplicateCounter++;
}
}
if (duplicateCounter > 1){
return true;
}else{
return false;
}
}
大型表上的函数太多会降低速度。如果它成为问题,您可以随时复制并“仅粘贴值” - 这将保留信息但删除功能。
祝你好运。
注意:当我测试这个时,我注意到在电子表格识别新的自定义函数之前可能需要一段时间(给出错误,如无法找到函数FLAGDUPLICATE)
答案 2 :(得分:0)
您也可以使用数组一次处理整个工作表:
function removeUnique(){
var col = 2 ; // choose the column you want to check for unique elements
var sh = SpreadsheetApp.getActiveSheet();
var ss = SpreadsheetApp.getActiveSpreadsheet();
var data=ss.getDataRange().getValues();// get all data
data.sort(function(x,y){
// var xp = Number(x[col]);// use these to sort on numeric values
// var yp = Number(y[col]);
var xp = x[col];// use these for non-numeric values
var yp = y[col];
Logger.log(xp+' '+yp); // just to check the sort is OK
return xp == yp ? 0 : xp < yp ? -1 : 1;// sort on column col numeric ascending
});
var cc=0;
var newdata = new Array();
for(nn=0;nn<data.length-1;++nn){
if(data[nn+1][col]==data[nn][col]||cc>0){
newdata.push(data[nn]);
++cc;
if(cc>1){cc=0}}
}
ss.getDataRange().clearContent(); // clear the sheet
sh.getRange(1,1,newdata.length,newdata[0].length).setValues(newdata);// paste new values sorted and without unique elements
}
编辑:这是保留所有重复项(工作版)的版本
function removeUnique(){
var col = 2 ; // choose the column you want to check for unique elements
var sh = SpreadsheetApp.getActiveSheet();
var ss = SpreadsheetApp.getActiveSpreadsheet();
var data=ss.getDataRange().getValues();// get all data
data.sort(function(x,y){
// var xp = Number(x[col]);// use these to sort on numeric values
// var yp = Number(y[col]);
var xp = x[col];// use these for non-numeric values
var yp = y[col];
Logger.log(xp+' '+yp); // just to check the sort is OK
return xp == yp ? 0 : xp < yp ? -1 : 1;// sort on column col numeric ascending
});
var newdata = new Array();
for(nn=0;nn<data.length-1;++nn){
if(data[nn+1][col]==data[nn][col]){
newdata.push(data[nn]);
}
}
if(data[nn-1][col]==data[nn][col]){newdata.push(data[nn])}
ss.getDataRange().clearContent(); // clear the sheet
sh.getRange(1,1,newdata.length,newdata[0].length).setValues(newdata);// paste new values sorted and without unique elements
}