dplry_bug.R

library(dplyr)

## 
## Attaching package: 'dplyr'
## 
## The following objects are masked from 'package:stats':
## 
##     filter, lag
## 
## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

df <- data.frame(
  V1 = c(rep("a",5), rep("b",5)),
  V2 = rep(c(1:5), 2),
  V3 = c(101:110),
  stringsAsFactors = TRUE
)

match <- data.frame(
  V1 = c("a", "b"),
  V2 = c(3, 4),
  V4 = c(99,99),
  stringsAsFactors = TRUE
)



inner_join(df,match) #This has the two matching records

## Joining by: c("V1", "V2")

##   V1 V2  V3 V4
## 1  a  3 103 99
## 2  b  4 109 99

left_join(match,df)

## Joining by: c("V1", "V2")

##   V1 V2 V4  V3
## 1  a  3 99 103
## 2  b  4 99 109

df$V1<-as.character(df$V1)
inner_join(df,match) #This has only 1 record, but does not give any warning

## Joining by: c("V1", "V2")

##   V1 V2  V3 V4
## 1  a  4 104 99

left_join(match,df) #This produces the same result, Why does it match on 'a' but not on 'b'?

## Joining by: c("V1", "V2")

##   V1 V2 V4  V3
## 1  a  3 99  NA
## 2  b  4 99 104

sessionInfo()

## R version 3.1.0 (2014-04-10)
## Platform: x86_64-apple-darwin10.8.0 (64-bit)
## 
## locale:
## [1] en_US.UTF-8/en_US.UTF-8/en_US.UTF-8/C/en_US.UTF-8/en_US.UTF-8
## 
## attached base packages:
## [1] stats     graphics  grDevices utils     datasets  methods   base     
## 
## other attached packages:
## [1] dplyr_0.2
## 
## loaded via a namespace (and not attached):
##  [1] assertthat_0.1   digest_0.6.4     evaluate_0.5.5   formatR_0.10    
##  [5] htmltools_0.2.4  knitr_1.6        parallel_3.1.0   Rcpp_0.11.2     
##  [9] rmarkdown_0.2.49 stringr_0.6.2    tools_3.1.0