R 如何连接（合并）数据帧（内部、外部、左侧、右侧）
给定两个数据帧：R 如何连接（合并）数据帧（内部、外部、左侧、右侧）,r,join,merge,dataframe,r-faq,R,Join,Merge,Dataframe,R Faq,给定两个数据帧： df1 = data.frame(CustomerId = c(1:6), Product = c(rep("Toaster", 3), rep("Radio", 3))) df2 = data.frame(CustomerId = c(2, 4, 6), State = c(rep("Alabama", 2), rep("Ohio", 1))) df1 # CustomerId Product # 1 Toaster # 2 Toa
df1 = data.frame(CustomerId = c(1:6), Product = c(rep("Toaster", 3), rep("Radio", 3)))
df2 = data.frame(CustomerId = c(2, 4, 6), State = c(rep("Alabama", 2), rep("Ohio", 1)))
df1
# CustomerId Product
# 1 Toaster
# 2 Toaster
# 3 Toaster
# 4 Radio
# 5 Radio
# 6 Radio
df2
# CustomerId State
# 2 Alabama
# 4 Alabama
# 6 Ohio
和df1
的一个示例：df2
仅返回左表在右表中具有匹配键的行
和df1
的一个示例：df2
返回两个表中的所有行，以及左侧的联接记录，这些记录在右侧表中具有匹配的键
和df1df2
返回左表中的所有行，以及右表中具有匹配键的所有行
和df1df2
返回右表中的所有行，以及左表中具有匹配键的所有行
额外积分：
如何执行SQL样式的select语句？在下面的示例中，我们可以使用SQL样式的select语句。我会在这里偷一对： 合并方法 由于键的名称相同，因此进行内部联接的短方法是merge（）： 可以使用“all”关键字创建完整的内部联接（两个表中的所有记录）： df1和df2的左外连接：
merge(df1,df2, all.x=TRUE)
merge(df1,df2, all.y=TRUE)
merge(df1,df2, all.x=TRUE)
merge(df1,df2, all.y=TRUE)
df1[,"State"]<-df2[df1[ ,"Product"], "State"]
df1[，“State”]使用merge
函数及其可选参数：
内部联接：merge（df1，df2）
适用于这些示例，因为R会通过通用变量名自动联接帧，但您很可能希望指定merge（df1，df2，by=“CustomerId”）
，以确保仅匹配所需的字段。如果匹配变量在不同的数据帧中具有不同的名称，则还可以使用by.x
和by.y
参数
外部联接：合并（x=df1，y=df2，by=“CustomerId”，all=TRUE）
左外：合并（x=df1，y=df2，by=“CustomerId”，all.x=TRUE）
右侧外部：合并（x=df1，y=df2，by=“CustomerId”，all.y=TRUE）
交叉连接：合并（x=df1，y=df2，by=NULL）
与内部联接一样，您可能希望显式地将“CustomerId”作为匹配变量传递给R。我认为，几乎总是最好明确地声明要合并的标识符；如果输入data.frames发生意外更改，并且以后更容易读取，则会更安全
通过给by
一个向量，例如by=c（“CustomerId”、“OrderId”）
，可以在多个列上进行合并
如果要合并的列名不相同，您可以指定，例如，by.x=“CustomerId\u in_df1”，by.y=“CustomerId\u in_df2”
其中CustomerId\u in_df1
是第一个数据帧中的列名，CustomerId\u in_in_df2
是第二个数据帧中的列名。（如果需要在多个列上合并，这些也可以是向量。）我建议签出，它允许您用SQL表达这些操作
library(sqldf)
## inner join
df3 <- sqldf("SELECT CustomerId, Product, State
FROM df1
JOIN df2 USING(CustomerID)")
## left join (substitute 'right' for right join)
df4 <- sqldf("SELECT CustomerId, Product, State
FROM df1
LEFT JOIN df2 USING(CustomerID)")
库（sqldf）
##内连接
df3对于内部联接，有一种data.table方法，它非常节省时间和内存（对于一些较大的data.frames来说是必需的）：
stackoverflow上记录的数据表：
另一个选项是包中的join
函数
类型的选项：内部
，左侧
，右侧
，完整
从？join
：与merge
不同，[join
]保留x的顺序，无论使用何种联接类型。2014年新增：
特别是如果您还对一般的数据操作感兴趣（包括排序、筛选、子集设置、汇总等），那么一定要看看dplyr
，它附带了各种功能，所有这些功能都是专门为方便您处理数据框和某些其他数据库类型而设计的。它甚至提供了一个非常复杂的SQL接口，甚至还提供了一个将（大多数）SQL代码直接转换为R的函数
dplyr包中的四个连接相关功能（引用）：
内部联接（x，y，by=NULL，copy=FALSE，…）
：从
x，其中y中有匹配的值，以及x和y中的所有列左联合（x，y，by=NULL，copy=FALSE，…）
：从x返回所有行，从x和y返回所有列semi_join（x，y，by=NULL，copy=FALSE，…）
：返回x中存在匹配值的所有行
y、 只保留x的列
反联接（x，y，by=NULL，copy=FALSE，…）
：返回x的所有行
其中y中没有匹配的值，只保留x中的列
一切都非常详细
选择列可以通过选择（df，“列”）
完成。如果这还不够SQL，那么有一个SQL（）
函数，您可以按原样输入SQL代码，它将执行您指定的操作，就像您一直在R中编写一样（有关更多信息，请参阅）。例如，如果应用正确，sql（“SELECT*FROM hflights”）
将从“hflights”dplyr表（一个“tbl”）中选择所有列。您也可以使用Hadley Wickham的Aweasome包进行连接
library(dplyr)
#make sure that CustomerId cols are both type numeric
#they ARE not using the provided code in question and dplyr will complain
df1$CustomerId <- as.numeric(df1$CustomerId)
df2$CustomerId <- as.numeric(df2$CustomerId)
过滤联接：过滤掉df1中的行，不修改列
dplyr自0.4以来实现了所有这些联接，包括外部联接
，但值得注意的是在0.4之前的前几个版本中，它不提供外部联接
，并且作为
merge(dt1, dt2)
library(plyr)
join(df1, df2,
type = "inner")
# CustomerId Product State
# 1 2 Toaster Alabama
# 2 4 Radio Alabama
# 3 6 Radio Ohio
library(dplyr)
#make sure that CustomerId cols are both type numeric
#they ARE not using the provided code in question and dplyr will complain
df1$CustomerId <- as.numeric(df1$CustomerId)
df2$CustomerId <- as.numeric(df2$CustomerId)
#inner
inner_join(df1, df2)
#left outer
left_join(df1, df2)
#right outer
right_join(df1, df2)
#alternate right outer
left_join(df2, df1)
#full join
full_join(df1, df2)
semi_join(df1, df2) #keep only observations in df1 that match in df2.
anti_join(df1, df2) #drops all observations in df1 that match in df2.
df1 = data.frame(CustomerId = c(1:6), Product = c(rep("Toaster", 3), rep("Radio", 3)))
df2 = data.frame(CustomerId = c(2L, 4L, 7L), State = c(rep("Alabama", 2), rep("Ohio", 1))) # one value changed to show full outer join
library(data.table)
dt1 = as.data.table(df1)
dt2 = as.data.table(df2)
setkey(dt1, CustomerId)
setkey(dt2, CustomerId)
# right outer join keyed data.tables
dt1[dt2]
setkey(dt1, NULL)
setkey(dt2, NULL)
# right outer join unkeyed data.tables - use `on` argument
dt1[dt2, on = "CustomerId"]
# left outer join - swap dt1 with dt2
dt2[dt1, on = "CustomerId"]
# inner join - use `nomatch` argument
dt1[dt2, nomatch=NULL, on = "CustomerId"]
# anti join - use `!` operator
dt1[!dt2, on = "CustomerId"]
# inner join - using merge method
merge(dt1, dt2, by = "CustomerId")
# full outer join
merge(dt1, dt2, by = "CustomerId", all = TRUE)
# see ?merge.data.table arguments for other cases
# inner
Unit: seconds
expr min lq mean median uq max neval
base 111.66266 111.66266 111.66266 111.66266 111.66266 111.66266 1
sqldf 624.88388 624.88388 624.88388 624.88388 624.88388 624.88388 1
dplyr 51.91233 51.91233 51.91233 51.91233 51.91233 51.91233 1
DT 10.40552 10.40552 10.40552 10.40552 10.40552 10.40552 1
# left
Unit: seconds
expr min lq mean median uq max
base 142.782030 142.782030 142.782030 142.782030 142.782030 142.782030
sqldf 613.917109 613.917109 613.917109 613.917109 613.917109 613.917109
dplyr 49.711912 49.711912 49.711912 49.711912 49.711912 49.711912
DT 9.674348 9.674348 9.674348 9.674348 9.674348 9.674348
# right
Unit: seconds
expr min lq mean median uq max
base 122.366301 122.366301 122.366301 122.366301 122.366301 122.366301
sqldf 611.119157 611.119157 611.119157 611.119157 611.119157 611.119157
dplyr 50.384841 50.384841 50.384841 50.384841 50.384841 50.384841
DT 9.899145 9.899145 9.899145 9.899145 9.899145 9.899145
# full
Unit: seconds
expr min lq mean median uq max neval
base 141.79464 141.79464 141.79464 141.79464 141.79464 141.79464 1
dplyr 94.66436 94.66436 94.66436 94.66436 94.66436 94.66436 1
DT 21.62573 21.62573 21.62573 21.62573 21.62573 21.62573 1
df1 <- data.frame(CustomerId=1:6,Product=c(rep('Toaster',3L),rep('Radio',3L)));
df2 <- data.frame(CustomerId=c(2L,4L,6L,7L),State=c(rep('Alabama',2L),'Ohio','Texas'));
df1[names(df2)[-1L]] <- df2[match(df1[,1L],df2[,1L]),-1L];
df1;
## CustomerId Product State
## 1 1 Toaster <NA>
## 2 2 Toaster Alabama
## 3 3 Toaster <NA>
## 4 4 Radio Alabama
## 5 5 Radio <NA>
## 6 6 Radio Ohio
library(microbenchmark);
library(data.table);
library(sqldf);
library(plyr);
library(dplyr);
solSpecs <- list(
merge=list(testFuncs=list(
inner=function(df1,df2,key) merge(df1,df2,key),
left =function(df1,df2,key) merge(df1,df2,key,all.x=T),
right=function(df1,df2,key) merge(df1,df2,key,all.y=T),
full =function(df1,df2,key) merge(df1,df2,key,all=T)
)),
data.table.unkeyed=list(argSpec='data.table.unkeyed',testFuncs=list(
inner=function(dt1,dt2,key) dt1[dt2,on=key,nomatch=0L,allow.cartesian=T],
left =function(dt1,dt2,key) dt2[dt1,on=key,allow.cartesian=T],
right=function(dt1,dt2,key) dt1[dt2,on=key,allow.cartesian=T],
full =function(dt1,dt2,key) merge(dt1,dt2,key,all=T,allow.cartesian=T) ## calls merge.data.table()
)),
data.table.keyed=list(argSpec='data.table.keyed',testFuncs=list(
inner=function(dt1,dt2) dt1[dt2,nomatch=0L,allow.cartesian=T],
left =function(dt1,dt2) dt2[dt1,allow.cartesian=T],
right=function(dt1,dt2) dt1[dt2,allow.cartesian=T],
full =function(dt1,dt2) merge(dt1,dt2,all=T,allow.cartesian=T) ## calls merge.data.table()
)),
sqldf.unindexed=list(testFuncs=list( ## note: must pass connection=NULL to avoid running against the live DB connection, which would result in collisions with the residual tables from the last query upload
inner=function(df1,df2,key) sqldf(paste0('select * from df1 inner join df2 using(',paste(collapse=',',key),')'),connection=NULL),
left =function(df1,df2,key) sqldf(paste0('select * from df1 left join df2 using(',paste(collapse=',',key),')'),connection=NULL),
right=function(df1,df2,key) sqldf(paste0('select * from df2 left join df1 using(',paste(collapse=',',key),')'),connection=NULL) ## can't do right join proper, not yet supported; inverted left join is equivalent
##full =function(df1,df2,key) sqldf(paste0('select * from df1 full join df2 using(',paste(collapse=',',key),')'),connection=NULL) ## can't do full join proper, not yet supported; possible to hack it with a union of left joins, but too unreasonable to include in testing
)),
sqldf.indexed=list(testFuncs=list( ## important: requires an active DB connection with preindexed main.df1 and main.df2 ready to go; arguments are actually ignored
inner=function(df1,df2,key) sqldf(paste0('select * from main.df1 inner join main.df2 using(',paste(collapse=',',key),')')),
left =function(df1,df2,key) sqldf(paste0('select * from main.df1 left join main.df2 using(',paste(collapse=',',key),')')),
right=function(df1,df2,key) sqldf(paste0('select * from main.df2 left join main.df1 using(',paste(collapse=',',key),')')) ## can't do right join proper, not yet supported; inverted left join is equivalent
##full =function(df1,df2,key) sqldf(paste0('select * from main.df1 full join main.df2 using(',paste(collapse=',',key),')')) ## can't do full join proper, not yet supported; possible to hack it with a union of left joins, but too unreasonable to include in testing
)),
plyr=list(testFuncs=list(
inner=function(df1,df2,key) join(df1,df2,key,'inner'),
left =function(df1,df2,key) join(df1,df2,key,'left'),
right=function(df1,df2,key) join(df1,df2,key,'right'),
full =function(df1,df2,key) join(df1,df2,key,'full')
)),
dplyr=list(testFuncs=list(
inner=function(df1,df2,key) inner_join(df1,df2,key),
left =function(df1,df2,key) left_join(df1,df2,key),
right=function(df1,df2,key) right_join(df1,df2,key),
full =function(df1,df2,key) full_join(df1,df2,key)
)),
in.place=list(testFuncs=list(
left =function(df1,df2,key) { cns <- setdiff(names(df2),key); df1[cns] <- df2[match(df1[,key],df2[,key]),cns]; df1; },
right=function(df1,df2,key) { cns <- setdiff(names(df1),key); df2[cns] <- df1[match(df2[,key],df1[,key]),cns]; df2; }
))
);
getSolTypes <- function() names(solSpecs);
getJoinTypes <- function() unique(unlist(lapply(solSpecs,function(x) names(x$testFuncs))));
getArgSpec <- function(argSpecs,key=NULL) if (is.null(key)) argSpecs$default else argSpecs[[key]];
initSqldf <- function() {
sqldf(); ## creates sqlite connection on first run, cleans up and closes existing connection otherwise
if (exists('sqldfInitFlag',envir=globalenv(),inherits=F) && sqldfInitFlag) { ## false only on first run
sqldf(); ## creates a new connection
} else {
assign('sqldfInitFlag',T,envir=globalenv()); ## set to true for the one and only time
}; ## end if
invisible();
}; ## end initSqldf()
setUpBenchmarkCall <- function(argSpecs,joinType,solTypes=getSolTypes(),env=parent.frame()) {
## builds and returns a list of expressions suitable for passing to the list argument of microbenchmark(), and assigns variables to resolve symbol references in those expressions
callExpressions <- list();
nms <- character();
for (solType in solTypes) {
testFunc <- solSpecs[[solType]]$testFuncs[[joinType]];
if (is.null(testFunc)) next; ## this join type is not defined for this solution type
testFuncName <- paste0('tf.',solType);
assign(testFuncName,testFunc,envir=env);
argSpecKey <- solSpecs[[solType]]$argSpec;
argSpec <- getArgSpec(argSpecs,argSpecKey);
argList <- setNames(nm=names(argSpec$args),vector('list',length(argSpec$args)));
for (i in seq_along(argSpec$args)) {
argName <- paste0('tfa.',argSpecKey,i);
assign(argName,argSpec$args[[i]],envir=env);
argList[[i]] <- if (i%in%argSpec$copySpec) call('copy',as.symbol(argName)) else as.symbol(argName);
}; ## end for
callExpressions[[length(callExpressions)+1L]] <- do.call(call,c(list(testFuncName),argList),quote=T);
nms[length(nms)+1L] <- solType;
}; ## end for
names(callExpressions) <- nms;
callExpressions;
}; ## end setUpBenchmarkCall()
harmonize <- function(res) {
res <- as.data.frame(res); ## coerce to data.frame
for (ci in which(sapply(res,is.factor))) res[[ci]] <- as.character(res[[ci]]); ## coerce factor columns to character
for (ci in which(sapply(res,is.logical))) res[[ci]] <- as.integer(res[[ci]]); ## coerce logical columns to integer (works around sqldf quirk of munging logicals to integers)
##for (ci in which(sapply(res,inherits,'POSIXct'))) res[[ci]] <- as.double(res[[ci]]); ## coerce POSIXct columns to double (works around sqldf quirk of losing POSIXct class) ----- POSIXct doesn't work at all in sqldf.indexed
res <- res[order(names(res))]; ## order columns
res <- res[do.call(order,res),]; ## order rows
res;
}; ## end harmonize()
checkIdentical <- function(argSpecs,solTypes=getSolTypes()) {
for (joinType in getJoinTypes()) {
callExpressions <- setUpBenchmarkCall(argSpecs,joinType,solTypes);
if (length(callExpressions)<2L) next;
ex <- harmonize(eval(callExpressions[[1L]]));
for (i in seq(2L,len=length(callExpressions)-1L)) {
y <- harmonize(eval(callExpressions[[i]]));
if (!isTRUE(all.equal(ex,y,check.attributes=F))) {
ex <<- ex;
y <<- y;
solType <- names(callExpressions)[i];
stop(paste0('non-identical: ',solType,' ',joinType,'.'));
}; ## end if
}; ## end for
}; ## end for
invisible();
}; ## end checkIdentical()
testJoinType <- function(argSpecs,joinType,solTypes=getSolTypes(),metric=NULL,times=100L) {
callExpressions <- setUpBenchmarkCall(argSpecs,joinType,solTypes);
bm <- microbenchmark(list=callExpressions,times=times);
if (is.null(metric)) return(bm);
bm <- summary(bm);
res <- setNames(nm=names(callExpressions),bm[[metric]]);
attr(res,'unit') <- attr(bm,'unit');
res;
}; ## end testJoinType()
testAllJoinTypes <- function(argSpecs,solTypes=getSolTypes(),metric=NULL,times=100L) {
joinTypes <- getJoinTypes();
resList <- setNames(nm=joinTypes,lapply(joinTypes,function(joinType) testJoinType(argSpecs,joinType,solTypes,metric,times)));
if (is.null(metric)) return(resList);
units <- unname(unlist(lapply(resList,attr,'unit')));
res <- do.call(data.frame,c(list(join=joinTypes),setNames(nm=solTypes,rep(list(rep(NA_real_,length(joinTypes))),length(solTypes))),list(unit=units,stringsAsFactors=F)));
for (i in seq_along(resList)) res[i,match(names(resList[[i]]),names(res))] <- resList[[i]];
res;
}; ## end testAllJoinTypes()
testGrid <- function(makeArgSpecsFunc,sizes,overlaps,solTypes=getSolTypes(),joinTypes=getJoinTypes(),metric='median',times=100L) {
res <- expand.grid(size=sizes,overlap=overlaps,joinType=joinTypes,stringsAsFactors=F);
res[solTypes] <- NA_real_;
res$unit <- NA_character_;
for (ri in seq_len(nrow(res))) {
size <- res$size[ri];
overlap <- res$overlap[ri];
joinType <- res$joinType[ri];
argSpecs <- makeArgSpecsFunc(size,overlap);
checkIdentical(argSpecs,solTypes);
cur <- testJoinType(argSpecs,joinType,solTypes,metric,times);
res[ri,match(names(cur),names(res))] <- cur;
res$unit[ri] <- attr(cur,'unit');
}; ## end for
res;
}; ## end testGrid()
## OP's example, supplemented with a non-matching row in df2
argSpecs <- list(
default=list(copySpec=1:2,args=list(
df1 <- data.frame(CustomerId=1:6,Product=c(rep('Toaster',3L),rep('Radio',3L))),
df2 <- data.frame(CustomerId=c(2L,4L,6L,7L),State=c(rep('Alabama',2L),'Ohio','Texas')),
'CustomerId'
)),
data.table.unkeyed=list(copySpec=1:2,args=list(
as.data.table(df1),
as.data.table(df2),
'CustomerId'
)),
data.table.keyed=list(copySpec=1:2,args=list(
setkey(as.data.table(df1),CustomerId),
setkey(as.data.table(df2),CustomerId)
))
);
## prepare sqldf
initSqldf();
sqldf('create index df1_key on df1(CustomerId);'); ## upload and create an sqlite index on df1
sqldf('create index df2_key on df2(CustomerId);'); ## upload and create an sqlite index on df2
checkIdentical(argSpecs);
testAllJoinTypes(argSpecs,metric='median');
## join merge data.table.unkeyed data.table.keyed sqldf.unindexed sqldf.indexed plyr dplyr in.place unit
## 1 inner 644.259 861.9345 923.516 9157.752 1580.390 959.2250 270.9190 NA microseconds
## 2 left 713.539 888.0205 910.045 8820.334 1529.714 968.4195 270.9185 224.3045 microseconds
## 3 right 1221.804 909.1900 923.944 8930.668 1533.135 1063.7860 269.8495 218.1035 microseconds
## 4 full 1302.203 3107.5380 3184.729 NA NA 1593.6475 270.7055 NA microseconds
makeArgSpecs.singleIntegerKey.optionalOneToOne <- function(size,overlap) {
com <- as.integer(size*overlap);
argSpecs <- list(
default=list(copySpec=1:2,args=list(
df1 <- data.frame(id=sample(size),y1=rnorm(size),y2=rnorm(size)),
df2 <- data.frame(id=sample(c(if (com>0L) sample(df1$id,com) else integer(),seq(size+1L,len=size-com))),y3=rnorm(size),y4=rnorm(size)),
'id'
)),
data.table.unkeyed=list(copySpec=1:2,args=list(
as.data.table(df1),
as.data.table(df2),
'id'
)),
data.table.keyed=list(copySpec=1:2,args=list(
setkey(as.data.table(df1),id),
setkey(as.data.table(df2),id)
))
);
## prepare sqldf
initSqldf();
sqldf('create index df1_key on df1(id);'); ## upload and create an sqlite index on df1
sqldf('create index df2_key on df2(id);'); ## upload and create an sqlite index on df2
argSpecs;
}; ## end makeArgSpecs.singleIntegerKey.optionalOneToOne()
## cross of various input sizes and key overlaps
sizes <- c(1e1L,1e3L,1e6L);
overlaps <- c(0.99,0.5,0.01);
system.time({ res <- testGrid(makeArgSpecs.singleIntegerKey.optionalOneToOne,sizes,overlaps); });
## user system elapsed
## 22024.65 12308.63 34493.19
plotRes <- function(res,titleFunc,useFloor=F) {
solTypes <- setdiff(names(res),c('size','overlap','joinType','unit')); ## derive from res
normMult <- c(microseconds=1e-3,milliseconds=1); ## normalize to milliseconds
joinTypes <- getJoinTypes();
cols <- c(merge='purple',data.table.unkeyed='blue',data.table.keyed='#00DDDD',sqldf.unindexed='brown',sqldf.indexed='orange',plyr='red',dplyr='#00BB00',in.place='magenta');
pchs <- list(inner=20L,left='<',right='>',full=23L);
cexs <- c(inner=0.7,left=1,right=1,full=0.7);
NP <- 60L;
ord <- order(decreasing=T,colMeans(res[res$size==max(res$size),solTypes],na.rm=T));
ymajors <- data.frame(y=c(1,1e3),label=c('1ms','1s'),stringsAsFactors=F);
for (overlap in unique(res$overlap)) {
x1 <- res[res$overlap==overlap,];
x1[solTypes] <- x1[solTypes]*normMult[x1$unit]; x1$unit <- NULL;
xlim <- c(1e1,max(x1$size));
xticks <- 10^seq(log10(xlim[1L]),log10(xlim[2L]));
ylim <- c(1e-1,10^((if (useFloor) floor else ceiling)(log10(max(x1[solTypes],na.rm=T))))); ## use floor() to zoom in a little more, only sqldf.unindexed will break above, but xpd=NA will keep it visible
yticks <- 10^seq(log10(ylim[1L]),log10(ylim[2L]));
yticks.minor <- rep(yticks[-length(yticks)],each=9L)*1:9;
plot(NA,xlim=xlim,ylim=ylim,xaxs='i',yaxs='i',axes=F,xlab='size (rows)',ylab='time (ms)',log='xy');
abline(v=xticks,col='lightgrey');
abline(h=yticks.minor,col='lightgrey',lty=3L);
abline(h=yticks,col='lightgrey');
axis(1L,xticks,parse(text=sprintf('10^%d',as.integer(log10(xticks)))));
axis(2L,yticks,parse(text=sprintf('10^%d',as.integer(log10(yticks)))),las=1L);
axis(4L,ymajors$y,ymajors$label,las=1L,tick=F,cex.axis=0.7,hadj=0.5);
for (joinType in rev(joinTypes)) { ## reverse to draw full first, since it's larger and would be more obtrusive if drawn last
x2 <- x1[x1$joinType==joinType,];
for (solType in solTypes) {
if (any(!is.na(x2[[solType]]))) {
xy <- spline(x2$size,x2[[solType]],xout=10^(seq(log10(x2$size[1L]),log10(x2$size[nrow(x2)]),len=NP)));
points(xy$x,xy$y,pch=pchs[[joinType]],col=cols[solType],cex=cexs[joinType],xpd=NA);
}; ## end if
}; ## end for
}; ## end for
## custom legend
## due to logarithmic skew, must do all distance calcs in inches, and convert to user coords afterward
## the bottom-left corner of the legend will be defined in normalized figure coords, although we can convert to inches immediately
leg.cex <- 0.7;
leg.x.in <- grconvertX(0.275,'nfc','in');
leg.y.in <- grconvertY(0.6,'nfc','in');
leg.x.user <- grconvertX(leg.x.in,'in');
leg.y.user <- grconvertY(leg.y.in,'in');
leg.outpad.w.in <- 0.1;
leg.outpad.h.in <- 0.1;
leg.midpad.w.in <- 0.1;
leg.midpad.h.in <- 0.1;
leg.sol.w.in <- max(strwidth(solTypes,'in',leg.cex));
leg.sol.h.in <- max(strheight(solTypes,'in',leg.cex))*1.5; ## multiplication factor for greater line height
leg.join.w.in <- max(strheight(joinTypes,'in',leg.cex))*1.5; ## ditto
leg.join.h.in <- max(strwidth(joinTypes,'in',leg.cex));
leg.main.w.in <- leg.join.w.in*length(joinTypes);
leg.main.h.in <- leg.sol.h.in*length(solTypes);
leg.x2.user <- grconvertX(leg.x.in+leg.outpad.w.in*2+leg.main.w.in+leg.midpad.w.in+leg.sol.w.in,'in');
leg.y2.user <- grconvertY(leg.y.in+leg.outpad.h.in*2+leg.main.h.in+leg.midpad.h.in+leg.join.h.in,'in');
leg.cols.x.user <- grconvertX(leg.x.in+leg.outpad.w.in+leg.join.w.in*(0.5+seq(0L,length(joinTypes)-1L)),'in');
leg.lines.y.user <- grconvertY(leg.y.in+leg.outpad.h.in+leg.main.h.in-leg.sol.h.in*(0.5+seq(0L,length(solTypes)-1L)),'in');
leg.sol.x.user <- grconvertX(leg.x.in+leg.outpad.w.in+leg.main.w.in+leg.midpad.w.in,'in');
leg.join.y.user <- grconvertY(leg.y.in+leg.outpad.h.in+leg.main.h.in+leg.midpad.h.in,'in');
rect(leg.x.user,leg.y.user,leg.x2.user,leg.y2.user,col='white');
text(leg.sol.x.user,leg.lines.y.user,solTypes[ord],cex=leg.cex,pos=4L,offset=0);
text(leg.cols.x.user,leg.join.y.user,joinTypes,cex=leg.cex,pos=4L,offset=0,srt=90); ## srt rotation applies *after* pos/offset positioning
for (i in seq_along(joinTypes)) {
joinType <- joinTypes[i];
points(rep(leg.cols.x.user[i],length(solTypes)),ifelse(colSums(!is.na(x1[x1$joinType==joinType,solTypes[ord]]))==0L,NA,leg.lines.y.user),pch=pchs[[joinType]],col=cols[solTypes[ord]]);
}; ## end for
title(titleFunc(overlap));
readline(sprintf('overlap %.02f',overlap));
}; ## end for
}; ## end plotRes()
titleFunc <- function(overlap) sprintf('R merge solutions: single-column integer key, 0..1:0..1 cardinality, %d%% overlap',as.integer(overlap*100));
plotRes(res,titleFunc,T);
makeArgSpecs.assortedKey.optionalManyToMany <- function(size,overlap,uniquePct=75) {
## number of unique keys in df1
u1Size <- as.integer(size*uniquePct/100);
## (roughly) divide u1Size into bases, so we can use expand.grid() to produce the required number of unique key values with repetitions within individual key columns
## use ceiling() to ensure we cover u1Size; will truncate afterward
u1SizePerKeyColumn <- as.integer(ceiling(u1Size^(1/3)));
## generate the unique key values for df1
keys1 <- expand.grid(stringsAsFactors=F,
idCharacter=replicate(u1SizePerKeyColumn,paste(collapse='',sample(letters,sample(4:12,1L),T))),
idInteger=sample(u1SizePerKeyColumn),
idLogical=sample(c(F,T),u1SizePerKeyColumn,T)
##idPOSIXct=as.POSIXct('2016-01-01 00:00:00','UTC')+sample(u1SizePerKeyColumn)
)[seq_len(u1Size),];
## rbind some repetitions of the unique keys; this will prepare one side of the many-to-many relationship
## also scramble the order afterward
keys1 <- rbind(keys1,keys1[sample(nrow(keys1),size-u1Size,T),])[sample(size),];
## common and unilateral key counts
com <- as.integer(size*overlap);
uni <- size-com;
## generate some unilateral keys for df2 by synthesizing outside of the idInteger range of df1
keys2 <- data.frame(stringsAsFactors=F,
idCharacter=replicate(uni,paste(collapse='',sample(letters,sample(4:12,1L),T))),
idInteger=u1SizePerKeyColumn+sample(uni),
idLogical=sample(c(F,T),uni,T)
##idPOSIXct=as.POSIXct('2016-01-01 00:00:00','UTC')+u1SizePerKeyColumn+sample(uni)
);
## rbind random keys from df1; this will complete the many-to-many relationship
## also scramble the order afterward
keys2 <- rbind(keys2,keys1[sample(nrow(keys1),com,T),])[sample(size),];
##keyNames <- c('idCharacter','idInteger','idLogical','idPOSIXct');
keyNames <- c('idCharacter','idInteger','idLogical');
## note: was going to use raw and complex type for two of the non-key columns, but data.table doesn't seem to fully support them
argSpecs <- list(
default=list(copySpec=1:2,args=list(
df1 <- cbind(stringsAsFactors=F,keys1,y1=sample(c(F,T),size,T),y2=sample(size),y3=rnorm(size),y4=replicate(size,paste(collapse='',sample(letters,sample(4:12,1L),T)))),
df2 <- cbind(stringsAsFactors=F,keys2,y5=sample(c(F,T),size,T),y6=sample(size),y7=rnorm(size),y8=replicate(size,paste(collapse='',sample(letters,sample(4:12,1L),T)))),
keyNames
)),
data.table.unkeyed=list(copySpec=1:2,args=list(
as.data.table(df1),
as.data.table(df2),
keyNames
)),
data.table.keyed=list(copySpec=1:2,args=list(
setkeyv(as.data.table(df1),keyNames),
setkeyv(as.data.table(df2),keyNames)
))
);
## prepare sqldf
initSqldf();
sqldf(paste0('create index df1_key on df1(',paste(collapse=',',keyNames),');')); ## upload and create an sqlite index on df1
sqldf(paste0('create index df2_key on df2(',paste(collapse=',',keyNames),');')); ## upload and create an sqlite index on df2
argSpecs;
}; ## end makeArgSpecs.assortedKey.optionalManyToMany()
sizes <- c(1e1L,1e3L,1e5L); ## 1e5L instead of 1e6L to respect more heavy-duty inputs
overlaps <- c(0.99,0.5,0.01);
solTypes <- setdiff(getSolTypes(),'in.place');
system.time({ res <- testGrid(makeArgSpecs.assortedKey.optionalManyToMany,sizes,overlaps,solTypes); });
## user system elapsed
## 38895.50 784.19 39745.53
titleFunc <- function(overlap) sprintf('R merge solutions: character/integer/logical key, 0..*:0..* cardinality, %d%% overlap',as.integer(overlap*100));
plotRes(res,titleFunc,F);
merge(df1, df2)
# V1 V2
# 1 B 2
# 2 C 3
dplyr::intersect(df1, df2)
# V1 V2
# 1 B 2
# 2 C 3
data.table::fintersect(setDT(df1), setDT(df2))
# V1 V2
# 1: B 2
# 2: C 3
df1 <- data.frame(V1 = LETTERS[1:4], V2 = 1:4)
df2 <- data.frame(V1 = LETTERS[2:3], V2 = 2:3)
sales = data.frame(
CustomerId = c(1, 1, 1, 3, 4, 6),
Year = 2000:2005,
Product = c(rep("Toaster", 3), rep("Radio", 3))
)
cust = data.frame(
CustomerId = c(1, 1, 4, 6),
Year = c(2001L, 2002L, 2002L, 2002L),
State = state.name[1:4]
)
sales
# CustomerId Year Product
# 1 2000 Toaster
# 1 2001 Toaster
# 1 2002 Toaster
# 3 2003 Radio
# 4 2004 Radio
# 6 2005 Radio
cust
# CustomerId Year State
# 1 2001 Alabama
# 1 2002 Alaska
# 4 2002 Arizona
# 6 2002 Arkansas
sales$State <- cust$State[ match(sales$CustomerId, cust$CustomerId) ]
# CustomerId Year Product State
# 1 2000 Toaster Alabama
# 1 2001 Toaster Alabama
# 1 2002 Toaster Alabama
# 3 2003 Radio <NA>
# 4 2004 Radio Arizona
# 6 2005 Radio Arkansas
# cleanup for the next example
sales$State <- NULL
library(data.table)
setDT(sales); setDT(cust)
sales[, State := cust[sales, on=.(CustomerId, Year), x.State]]
# CustomerId Year Product State
# 1: 1 2000 Toaster <NA>
# 2: 1 2001 Toaster Alabama
# 3: 1 2002 Toaster Alaska
# 4: 3 2003 Radio <NA>
# 5: 4 2004 Radio <NA>
# 6: 6 2005 Radio <NA>
# cleanup for next example
sales[, State := NULL]
sales[, State := cust[sales, on=.(CustomerId, Year), roll=TRUE, x.State]]
# CustomerId Year Product State
# 1: 1 2000 Toaster <NA>
# 2: 1 2001 Toaster Alabama
# 3: 1 2002 Toaster Alaska
# 4: 3 2003 Radio <NA>
# 5: 4 2004 Radio Arizona
# 6: 6 2005 Radio Arkansas