valores únicos/distintos por grupo en una trama de datos

Question

Digamos que tengo el siguiente cuadro de datos:

> myvec 
    name order_no 
1 Amy  12 
2 Jack  14 
3 Jack  16 
4 Dave  11 
5 Amy  12 
6 Jack  16 
7 Tom  19 
8 Larry  22 
9 Tom  19 
10 Dave  11 
11 Jack  17 
12 Tom  20 
13 Amy  23 
14 Jack  16 

Quiero contar el número de distintos valores para cada order_noname. Debe producir el siguiente resultado:

name number_of_distinct_orders 
Amy  2 
Jack 3 
Dave 1 
Tom  2 
Larry 1 

¿Cómo puedo hacer eso?

Answer 1

Esto debe hacer el truco:

ddply(myvec,~name,summarise,number_of_distinct_orders=length(unique(order_no))) 

Esto requiere paquete plyr.

Answer 2

Esto también podría funcionar, pero es menos elocuente que la solución plyr:

x <- sapply(split(myvec, myvec$name), function(x) length(unique(x[, 2]))) 
data.frame(names=names(x), number_of_distinct_orders=x, row.names = NULL) 

Answer 3

Ésta es una solución sencilla con la función aggregate:

aggregate(order_no ~ name, myvec, function(x) length(unique(x))) 

Answer 4

sólo puede utilizar el incorporado en R funciones tapply con length

tapply(myvec$order_no, myvec$name, FUN = function(x) length(unique(x))) 

Answer 5

Un enfoque data.table

library(data.table) 
DT <- data.table(myvec) 

DT[, .(number_of_distinct_orders = length(unique(order_no))), by = name] 

---

data.table v> = 1.9.5 ha construido en función de uniqueN ahora

DT[, .(number_of_distinct_orders = uniqueN(order_no)), by = name] 

Answer 6

Un dato.enfoque mesa

train[,lapply(.SD,uniqueN),by=group_1] 

Answer 7

En dplyr puede usar n_distinct a "contar el número de valores únicos":

library(dplyr) 
myvec %>% 
    group_by(name) %>% 
    summarise(n_distinct(order_no)) 

Answer 8

Aquí es una solución con sqldf

library("sqldf") 

myvec <- read.table(header=TRUE, text= 
" name order_no 
1 Amy  12 
2 Jack  14 
3 Jack  16 
4 Dave  11 
5 Amy  12 
6 Jack  16 
7 Tom  19 
8 Larry  22 
9 Tom  19 
10 Dave  11 
11 Jack  17 
12 Tom  20 
13 Amy  23 
14 Jack  16") 
sqldf("SELECT name,COUNT(distinct(order_no)) as number_of_distinct_orders FROM myvec GROUP BY name") 
# > sqldf("SELECT name,COUNT(distinct(order_no)) as number_of_distinct_orders FROM myvec GROUP BY name") 
# name number_of_distinct_orders 
# 1 Amy       2 
# 2 Dave       1 
# 3 Jack       3 
# 4 Larry       1 
# 5 Tom       2 

Answer 9

myvec %>%group_by(name)%>%summarise(Numberofoder=length(unique(order_no))) 

Answer 10

Usando table :

library(magrittr) 
myvec %>% unique %>% '['(1) %>% table %>% as.data.frame %>% 
    setNames(c("name","number_of_distinct_orders")) 

# name number_of_distinct_orders 
# 1 Amy       2 
# 2 Dave       1 
# 3 Jack       3 
# 4 Larry       1 
# 5 Tom       2 

Answer 11

my.1 <- table(myvec) 

my.1[my.1 != 0] <- 1 

rowSums(my.1) 

Answer 12

Aquí es un punto de referencia de la solución de @ David Arenburg there, así como un resumen de algunas de las soluciones incluidas en este documento (@mnel, @Sven Hohenstein, @Henrik):

library(dplyr) 
library(data.table) 
library(microbenchmark) 
library(tidyr) 
library(ggplot2) 

df <- mtcars 
DT <- as.data.table(df) 
DT_32k <- rbindlist(replicate(1e3, mtcars, simplify = FALSE)) 
df_32k <- as.data.frame(DT_32k) 
DT_32M <- rbindlist(replicate(1e6, mtcars, simplify = FALSE)) 
df_32M <- as.data.frame(DT_32M) 
bench <- microbenchmark(
    base_32 = aggregate(hp ~ cyl, df, function(x) length(unique(x))), 
    base_32k = aggregate(hp ~ cyl, df_32k, function(x) length(unique(x))), 
    base_32M = aggregate(hp ~ cyl, df_32M, function(x) length(unique(x))), 
    dplyr_32 = summarise(group_by(df, cyl), count = n_distinct(hp)), 
    dplyr_32k = summarise(group_by(df_32k, cyl), count = n_distinct(hp)), 
    dplyr_32M = summarise(group_by(df_32M, cyl), count = n_distinct(hp)), 
    data.table_32 = DT[, .(count = uniqueN(hp)), by = cyl], 
    data.table_32k = DT_32k[, .(count = uniqueN(hp)), by = cyl], 
    data.table_32M = DT_32M[, .(count = uniqueN(hp)), by = cyl], 
    times = 10 
) 

Resultados:

print(bench) 

# Unit: microseconds 
#   expr   min   lq   mean  median   uq   max neval cld 
#   base_32  816.153  1064.817 1.231248e+03 1.134542e+03  1263.152  2430.191 10 a 
#  base_32k 38045.080 38618.383 3.976884e+04 3.962228e+04 40399.740 42825.633 10 a 
#  base_32M 35065417.492 35143502.958 3.565601e+07 3.534793e+07 35802258.435 37015121.086 10 d 
#  dplyr_32  2211.131  2292.499 1.211404e+04 2.370046e+03  2656.419 99510.280 10 a 
#  dplyr_32k  3796.442  4033.207 4.434725e+03 4.159054e+03  4857.402  5514.646 10 a 
#  dplyr_32M 1536183.034 1541187.073 1.580769e+06 1.565711e+06 1600732.034 1733709.195 10 b 
# data.table_32  403.163  413.253 5.156662e+02 5.197515e+02  619.093  628.430 10 a 
# data.table_32k  2208.477  2374.454 2.494886e+03 2.448170e+03  2557.604  3085.508 10 a 
# data.table_32M 2011155.330 2033037.689 2.074020e+06 2.052079e+06 2078231.776 2189809.835 10 c 

Parcela:

as_tibble(bench) %>% 
    group_by(expr) %>% 
    summarise(time = median(time)) %>% 
    separate(expr, c("framework", "nrow"), "_", remove = FALSE) %>% 
    mutate(nrow = recode(nrow, "32" = 32, "32k" = 32e3, "32M" = 32e6), 
     time = time/1e3) %>% 
    ggplot(aes(nrow, time, col = framework)) + 
    geom_line() + 
    scale_x_log10() + 
    scale_y_log10() + ylab("microseconds") 

información de la sesión:

sessionInfo() 
# R version 3.4.1 (2017-06-30) 
# Platform: x86_64-pc-linux-gnu (64-bit) 
# Running under: Linux Mint 18 
# 
# Matrix products: default 
# BLAS: /usr/lib/atlas-base/atlas/libblas.so.3.0 
# LAPACK: /usr/lib/atlas-base/atlas/liblapack.so.3.0 
# 
# locale: 
# [1] LC_CTYPE=fr_FR.UTF-8  LC_NUMERIC=C    LC_TIME=fr_FR.UTF-8  
# [4] LC_COLLATE=fr_FR.UTF-8  LC_MONETARY=fr_FR.UTF-8 LC_MESSAGES=fr_FR.UTF-8 
# [7] LC_PAPER=fr_FR.UTF-8  LC_NAME=C     LC_ADDRESS=C    
# [10] LC_TELEPHONE=C    LC_MEASUREMENT=fr_FR.UTF-8 LC_IDENTIFICATION=C  
# 
# attached base packages: 
# [1] stats  graphics grDevices utils  datasets methods base  
# 
# other attached packages: 
# [1] ggplot2_2.2.1   tidyr_0.6.3   bindrcpp_0.2   stringr_1.2.0   
# [5] microbenchmark_1.4-2.1 data.table_1.10.4  dplyr_0.7.1   
# 
# loaded via a namespace (and not attached): 
# [1] Rcpp_0.12.11  compiler_3.4.1 plyr_1.8.4  bindr_0.1  tools_3.4.1  digest_0.6.12 
# [7] tibble_1.3.3  gtable_0.2.0  lattice_0.20-35 pkgconfig_2.0.1 rlang_0.1.1  Matrix_1.2-10 
# [13] mvtnorm_1.0-6 grid_3.4.1  glue_1.1.1  R6_2.2.2   survival_2.41-3 multcomp_1.4-6 
# [19] TH.data_1.0-8 magrittr_1.5  scales_0.4.1  codetools_0.2-15 splines_3.4.1 MASS_7.3-47  
# [25] assertthat_0.2.0 colorspace_1.3-2 labeling_0.3  sandwich_2.3-4 stringi_1.1.5 lazyeval_0.2.0 
# [31] munsell_0.4.3 zoo_1.8-0