Code
library(tidyverse)汇总表格
Code
head(mtcars) mpg cyl disp hp drat wt qsec vs am gear carb
Mazda RX4 21.0 6 160 110 3.90 2.620 16.46 0 1 4 4
Mazda RX4 Wag 21.0 6 160 110 3.90 2.875 17.02 0 1 4 4
Datsun 710 22.8 4 108 93 3.85 2.320 18.61 1 1 4 1
Hornet 4 Drive 21.4 6 258 110 3.08 3.215 19.44 1 0 3 1
Hornet Sportabout 18.7 8 360 175 3.15 3.440 17.02 0 0 3 2
Valiant 18.1 6 225 105 2.76 3.460 20.22 1 0 3 1按照1个变量hp汇总。算了观察数量row_record,drat总数,drat总数占比
Code
mtcars %>% group_by(hp) %>% summarise(row_record=n(),total_drat=sum(drat)) %>%
mutate(total_drat_share = round(total_drat / sum(total_drat),2))# A tibble: 22 × 4
hp row_record total_drat total_drat_share
<dbl> <int> <dbl> <dbl>
1 52 1 4.93 0.04
2 62 1 3.69 0.03
3 65 1 4.22 0.04
4 66 2 8.16 0.07
5 91 1 4.43 0.04
6 93 1 3.85 0.03
7 95 1 3.92 0.03
8 97 1 3.7 0.03
9 105 1 2.76 0.02
10 109 1 4.11 0.04
# … with 12 more rows只保留前3组
Code
mtcars %>% mutate(new_hp=as.factor(hp) %>%fct_lump_n(3, other_level = "Other")) %>%
group_by(new_hp) %>% summarise(row_record=n()) %>% arrange(desc(row_record))# A tibble: 4 × 2
new_hp row_record
<fct> <int>
1 Other 23
2 110 3
3 175 3
4 180 3只保留出现过2次以及以上的
Code
mtcars %>% mutate(new_hp=as.factor(hp) %>%fct_lump_min(2, other_level = "Other")) %>%
group_by(new_hp) %>% summarise(row_record=n(),total_wt=sum(wt)) %>% arrange(desc(row_record))# A tibble: 8 × 3
new_hp row_record total_wt
<fct> <int> <dbl>
1 Other 15 47.2
2 110 3 8.71
3 175 3 10.1
4 180 3 11.6
5 66 2 4.14
6 123 2 6.88
7 150 2 6.96
8 245 2 7.41Code
mtcars %>% add_count(hp, wt = drat)%>% add_count(hp) mpg cyl disp hp drat wt qsec vs am gear carb n nn
1 21.0 6 160.0 110 3.90 2.620 16.46 0 1 4 4 10.88 3
2 21.0 6 160.0 110 3.90 2.875 17.02 0 1 4 4 10.88 3
3 22.8 4 108.0 93 3.85 2.320 18.61 1 1 4 1 3.85 1
4 21.4 6 258.0 110 3.08 3.215 19.44 1 0 3 1 10.88 3
5 18.7 8 360.0 175 3.15 3.440 17.02 0 0 3 2 9.85 3
6 18.1 6 225.0 105 2.76 3.460 20.22 1 0 3 1 2.76 1
7 14.3 8 360.0 245 3.21 3.570 15.84 0 0 3 4 6.94 2
8 24.4 4 146.7 62 3.69 3.190 20.00 1 0 4 2 3.69 1
9 22.8 4 140.8 95 3.92 3.150 22.90 1 0 4 2 3.92 1
10 19.2 6 167.6 123 3.92 3.440 18.30 1 0 4 4 7.84 2
11 17.8 6 167.6 123 3.92 3.440 18.90 1 0 4 4 7.84 2
12 16.4 8 275.8 180 3.07 4.070 17.40 0 0 3 3 9.21 3
13 17.3 8 275.8 180 3.07 3.730 17.60 0 0 3 3 9.21 3
14 15.2 8 275.8 180 3.07 3.780 18.00 0 0 3 3 9.21 3
15 10.4 8 472.0 205 2.93 5.250 17.98 0 0 3 4 2.93 1
16 10.4 8 460.0 215 3.00 5.424 17.82 0 0 3 4 3.00 1
17 14.7 8 440.0 230 3.23 5.345 17.42 0 0 3 4 3.23 1
18 32.4 4 78.7 66 4.08 2.200 19.47 1 1 4 1 8.16 2
19 30.4 4 75.7 52 4.93 1.615 18.52 1 1 4 2 4.93 1
20 33.9 4 71.1 65 4.22 1.835 19.90 1 1 4 1 4.22 1
21 21.5 4 120.1 97 3.70 2.465 20.01 1 0 3 1 3.70 1
22 15.5 8 318.0 150 2.76 3.520 16.87 0 0 3 2 5.91 2
23 15.2 8 304.0 150 3.15 3.435 17.30 0 0 3 2 5.91 2
24 13.3 8 350.0 245 3.73 3.840 15.41 0 0 3 4 6.94 2
25 19.2 8 400.0 175 3.08 3.845 17.05 0 0 3 2 9.85 3
26 27.3 4 79.0 66 4.08 1.935 18.90 1 1 4 1 8.16 2
27 26.0 4 120.3 91 4.43 2.140 16.70 0 1 5 2 4.43 1
28 30.4 4 95.1 113 3.77 1.513 16.90 1 1 5 2 3.77 1
29 15.8 8 351.0 264 4.22 3.170 14.50 0 1 5 4 4.22 1
30 19.7 6 145.0 175 3.62 2.770 15.50 0 1 5 6 9.85 3
31 15.0 8 301.0 335 3.54 3.570 14.60 0 1 5 8 3.54 1
32 21.4 4 121.0 109 4.11 2.780 18.60 1 1 4 2 4.11 1