R中data.table与dlyr的使用

# 生成实验数据

set.seed(1234)
smalldat <- data.frame(group1 = rep(1:2, each = 5), 
                       group2 = rep(c('a','b'), times = 5), 
                       x = rnorm(10))

# convert to data.frame to data.table
library(data.table)
smalldat <- data.table(smalldat)

# convert aggregated variable into raw data file

# 添加汇总的列
smalldat[, aggGroup1 := mean(x), by = group1]

# aggregate with 2 variables
smalldat[, aggGroup1.2 := mean(x), by = list(group1, group2)]

# 具有相似功能的plyr包的使用
library(plyr)

# create aggregated data
aggdat1 <- ddply(smalldat, .(group1), summarize,
                 aggGroup1plyr = mean(x))
aggdat12 <- ddply(smalldat, .(group1, group2),  summarize,
                  aggGroup1.1plyr = mean(x))

# join back into data

# 类似merge的使用
smalldat <- join(smalldat, aggdat1, by = 'group1')
smalldat <- join(smalldat, aggdat12, by = c('group1', 'group2'))

# print data
smalldat

# 按照某些给定字段去除重复的记录
# Set keys - this sorts the data based on these values
setkeyv(smalldat, c('group1','group2'))

# keep unique observations (I also remove the variable x)
uniqdat <- subset(unique(smalldat), select = -x)

# print data
uniqdat