I am trying to summarize multiple columns. The below is my raw dataset:
neg_sentiment neu_sentiment pos_sentiment age
1 1270 609 594 39
2 374 150 260 77
3 30 23 138 67
4 20 30 138 59
5 78 194 566 70
6 420 275 609 50
7 1233 447 745 57
8 1096 390 1022 43
9 1688 704 888 61
10 667 563 2051 69
My desired output is like below :
new_age pos_sentiment neu sentiment neg_sentiment
<chr> <int> <int> <int>
1 age(old) > 60 1000 1000 500
2 age(young) < 60 1000 1000 500
But I just could summarize for one column.
df_1 %>%
group_by(new_age = c('age(old) > 60', 'age(young) < 60')[(age < 60) + 1]) %>%
summarise(neg_sentiment = sum(neg_sentiment))
Could you help me make the desired output?
The below is dput:
structure(list(neg_sentiment = c(1270L, 374L, 30L, 20L, 78L, 420L, 1233L, 1096L, 1688L, 667L, 260L, 315L, 1060L, 5089L, 647L, 3691L, 3217L, 4155L, 13345L, 6121L, 478L, 2152L, 49863L, 4224L, 267L, 1660L, 1340L, 148L, 2660L, 484L, 2495L, 603L, 379L, 6340L, 951L, 86L, 7389L, 7459L, 1363L, 597L, 12915L, 1642L, 1808L, 352L, 13970L, 2740L, 10351L, 664L), neu_sentiment = c(609L, 150L, 23L, 30L, 194L, 275L, 447L, 390L, 704L, 563L, 197L, 245L, 403L, 2972L, 229L, 1453L, 1012L, 1686L, 4229L, 2429L, 168L, 955L, 18109L,
1889L, 165L, 984L, 664L, 78L, 967L, 198L, 960L, 208L, 190L, 1672L, 562L, 35L, 2840L, 2477L, 473L, 439L, 6102L, 816L, 881L, 238L, 4292L, 1026L, 4705L, 524L), pos_sentiment = c(594L, 260L, 138L, 138L, 566L, 609L, 745L, 1022L, 888L, 2051L, 375L, 582L, 394L, 6480L, 215L, 1254L, 1049L, 1676L, 3404L, 1890L, 177L, 2621L, 28169L, 2111L, 559L, 4103L, 1348L, 354L, 1556L, 528L, 1256L, 252L, 488L, 3661L, 1740L, 57L, 2381L, 2552L, 491L, 1376L, 2002L, 876L, 2214L, 799L, 5522L, 2417L, 4606L, 2010L), age = c(39, 77,
67, 59, 70, 50, 57, 43, 61, 69, 57, 49, 51, 63, 69, 63, 74, 77, 43, 56, 54, 80, 70, 49, 67, 73, 69, 70, 57, 48, 55, 54, 67, 60, 54, 68, 66, 87, 74, 67, 64, 66, 62, 91, 83, 60, 40, 74)), class = "data.frame", row.names = c(NA, -48L))
