我有一个ID，年和月为单位的数据框。我需要按年份和月份分组，并从该分组中获取唯一的ID。我想将唯一ID与上一年，月份组，添加的ID和减去的ID进行比较。
那种在黑暗中射击的方法，但我尝试了以下方法，但不起作用：
connections <- df %>%
group_by(year, month) %>%
arrange(year, month) %>%
diff_data(unique(as.vector(~ID)), lag(unique(as.vector(~ID))))
样本数据
df <- data.frame(ID=c("A1", "A2", "A3", "A1", "A2","A4", "A1", "A4", "A5"),
year= c(2010, 2010, 2010, 2011, 2011, 2011, 2012, 2012, 2012),
month= c(1, 2, 3, 1, 2, 3, 1, 2, 3))
答案 0 :(得分：0)
First会在月份和年份都进行class stack1 {
private:
int num1[SIZE/2]; int top1;
public:
void push1(int data)
{
if (is_full1());
else
{
num1[top1] = data;
top1++;
}
}
int pop1(void)
{
if(is_empty1());
else
{
top1--;
return num1[top1];
}
}
int is_empty1(void)
{
if(top1 == 0)
{
return 1;
}else
{
return 0;
}
}
int is_full1(void)
{
if(top1 == SIZE)
{
return 1;
}else
{
return 0;
}
}
stack1()
{
top1 = 0; num1[SIZE/2] = {0};
} };
class stack2 {
private:
int num2[SIZE/2]; int top2; public:
void push2(int data)
{
if (is_full2());
else
{
num2[top2] = data;
top2++;
}
}
int pop2(void)
{
if(is_empty2());
else
{
top2--;
return num2[top2];
}
}
int is_empty2(void)
{
if(top2 == 0)
{
return 1;
}else
{
return 0;
}
}
int is_full2(void)
{
if(top2 == SIZE)
{
return 1;
}else
{
return 0;
}
}
stack2()
{
top2 = 0; num2[SIZE/2] = {0};
} };
class operation: public stack2, public stack1 {
private:
int answer;
int a;
int b;
int num_cnt;
int ans;
int from_st1;
int from_st2;
public:
int c;
int oper(void)
{
answer = 0;
a = 0;
b = 0;
num_cnt = 0;
ans = 0;
c = 0;
stack1 st1;
stack2 st2;
while(!st1.is_empty1())
{
from_st1 = st1.pop1();
if(from_st1 == plus)
{
st2.push2(from_st1);
}else if(from_st1 == minus)
{
st2.push2(from_st1);
}else if(from_st1 == mult)
{
st2.push2(from_st1);
}else if (from_st1 == divide)
{
st2.push2(from_st1);
}else if(num_cnt == 1)
{
num_cnt = 0;
if(ans == 0)
{
answer = b;
ans++;
}
a = from_st1;
from_st2 = st2.pop2();
if(from_st2 == plus)
{
c = a+answer;
}else if(from_st2 == minus)
{
c = a-answer;
}else if(from_st2 == mult)
{
c = a*answer;
}else if(from_st2 == divide)
{
c = a/answer;
}
}else
{
b = from_st1;
}
num_cnt++;
}
return c;
}
operation()
{
answer = 0;
a = 0;
b = 0;
num_cnt = 0;
ans = 0;
from_st1 = 0;
from_st2 = 0;
} };
。在这种方法中，将列出每月添加和删除的所有ID，并获得aggregate来计算每月添加和删除的数量。
length输出
library(tidyverse)
df %>%
aggregate(ID ~ year + month, ., unique, drop = FALSE) %>%
group_by(month) %>%
arrange(year) %>%
mutate(addedID = mapply(setdiff, ID, lag(ID), SIMPLIFY = FALSE),
num_addedID = lapply(addedID, length),
deletedID = mapply(setdiff, lag(ID), ID, SIMPLIFY = FALSE),
num_deletedID = lapply(deletedID, function(x) length(na.omit(x)))) %>%
ungroup() %>%
arrange(month, year) %>%
as.data.frame()
数据
year month ID addedID num_addedID deletedID num_deletedID
1 2010 1 A1 A1 1 NA 0
2 2011 1 A1 0 0
3 2012 1 A1 0 0
4 2010 2 A3 A3 1 NA 0
5 2011 2 A2 A2 1 A3 1
6 2012 2 A4 A4 1 A2 1
7 2010 3 A3 A3 1 NA 0
8 2011 3 A4 A4 1 A3 1
9 2012 3 A5 A5 1 A4 1