私はいくつかの欠損値（市、州）を持つデータフレーム（DF1）を持っている

Question

欠損値を埋めるためにdplyrを使用した：

SiteID City   StateBasedIn Lat Lon Var1 Var2 
4227  Richmond  KY   -39 -113 6 0 
4987  Nashville  TN   -33 -97 7 0 
4000  Newark  NJ   -39 -95 8 0 
4925  Miami   FL   -40 -99 0 0 
4437  Montgomery AL   -32 -117 4 1 
4053  Jonesboro  AR   -30 -98 8 1 

df1 <- structure(list(SiteID = c(4227L, 4987L, 4000L, 4925L, 4437L, 
4053L, 4482L, 4037L, 4020L, 1787L, 2805L, 3025L, 3027L, 3028L, 
3029L, 3030L, 3031L, 3033L), City = structure(c(10L, 7L, 8L, 
5L, 6L, 4L, 2L, 9L, 3L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = c("", 
"Arcata", "Jackson", "Jonesboro", "Miami", "Montgomery", "Nashville", 
"Newark", "Portland", "Richmond"), class = "factor"), StateBasedIn = structure(c(6L, 
10L, 8L, 5L, 2L, 3L, 4L, 9L, 7L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
1L, 1L), .Label = c("", "AL", "AR", "CA", "FL", "KY", "MS", "NJ", 
"OR", "TN"), class = "factor"), Lat = c(-39L, -33L, -39L, -40L, 
-32L, -30L, -38L, -31L, -35L, -38L, -30L, -39L, -38L, -32L, -39L, 
-31L, -38L, -34L), Lon = c(-113L, -97L, -95L, -99L, -117L, -98L, 
-98L, -95L, -112L, -120L, -114L, -81L, -117L, -90L, -109L, -115L, 
-81L, -104L), Var1 = c(6L, 7L, 8L, 0L, 4L, 8L, 1L, 8L, 0L, 3L, 
3L, 7L, 4L, 8L, 0L, 8L, 1L, 3L), Var2 = c(0L, 0L, 0L, 0L, 1L, 
1L, 1L, 1L, 1L, 0L, 1L, 1L, 0L, 0L, 1L, 0L, 1L, 0L)), .Names = c("SiteID", 
"City", "StateBasedIn", "Lat", "Lon", "Var1", "Var2"), class = "data.frame", row.names = c(NA, 
-18L)) 

そして、私はそれらの値を記入したいと思います（参加を通じて？）

SiteID  City   StateBasedIn 
1787   Lusby  MD 
2805   Springdale AR 
3025   Saukville WI 
3027   Saukville WI 
3028   Saukville WI 
3029   Saukville WI 

df2 <- structure(list(SiteID = c(1787L, 2805L, 3025L, 3027L, 3028L, 
3029L, 3030L, 3031L, 3033L), City = structure(c("Lusby", "Springdale", 
"Saukville", "Saukville", "Saukville", "Saukville", "Saukville", 
"Mequon", "Mequon"), .Dim = c(9L, 1L)), StateBasedIn = structure(c("MD", 
"AR", "WI", "WI", "WI", "WI", "WI", "WI", "WI"), .Dim = c(9L, 
1L))), row.names = c(NA, -9L), class = "data.frame", .Names = c("SiteID", 
"City", "StateBasedIn")) 

したがって、基本的に、私はDF1の情報の全てを保持し、入力します：同じ列の3を持っている、すべてではないがDF1にある列の別のデータフレーム（DF2）と合併することによってでdf2から利用可能な欠損値。私はすべてのdplyrオプションにあまり慣れていないので、別の 'join'オプションを試しましたが、運はありませんでした。私は基本パッケージに 'merge'を使用しようとしましたが、まだ成功しませんでした。これを行う別の方法がありますか（好ましくはdplyrで）？

Answer 1

このソリューションはあまりスタイリッシュではありませんが、少なくとも解決策です。中

library(dplyr) 
library(magrittr) 

aux <- df1 %>% 
    # filter missing values 
    filter(City == "") %>% 
    # delete City and StateBasedIn so that the columns 
    # are not duplicates after the join 
    select(-c(City, StateBasedIn)) %>% 
    # inner join with the second dataframe 
    inner_join(df2, by = "SiteID") %>% 
    # change order of the columns 
    select(SiteID, City, StateBasedIn, Lat, Lon, Var1, Var2) 

df1 %<>% 
    # filter all rows which values are not missing 
    filter(City != "") %>% 
    # bind the auxiliary dataframe 
    rbind(aux) 

結果：フェリックスの答えの

SiteID  City StateBasedIn Lat Lon Var1 Var2 
1 4227 Richmond   KY -39 -113 6 0 
2 4987 Nashville   TN -33 -97 7 0 
3 4000  Newark   NJ -39 -95 8 0 
4 4925  Miami   FL -40 -99 0 0 
5 4437 Montgomery   AL -32 -117 4 1 
6 4053 Jonesboro   AR -30 -98 8 1 
7 4482  Arcata   CA -38 -98 1 1 
8 4037 Portland   OR -31 -95 8 1 
9 4020 Jackson   MS -35 -112 0 1 
10 1787  Lusby   MD -38 -120 3 0 
11 2805 Springdale   AR -30 -114 3 1 
12 3025 Saukville   WI -39 -81 7 1 
13 3027 Saukville   WI -38 -117 4 0 
14 3028 Saukville   WI -32 -90 8 0 
15 3029 Saukville   WI -39 -109 0 1 
16 3030 Saukville   WI -31 -115 8 0 
17 3031  Mequon   WI -38 -81 1 1 
18 3033  Mequon   WI -34 -104 3 0 

Answer 2

少し簡易版。

まず、characterにfactorを変更することで、データを修復、2つ目から明らか行列削除：今すぐ仕事を

str(df1) 
# 'data.frame': 18 obs. of 7 variables: 
# $ SiteID  : int 4227 4987 4000 4925 4437 4053 4482 4037 4020 1787 ... 
# $ City  : Factor w/ 10 levels "","Arcata","Jackson",..: 10 7 8 5 6 4 2 9 3 1 ... 
# $ StateBasedIn: Factor w/ 10 levels "","AL","AR","CA",..: 6 10 8 5 2 3 4 9 7 1 ... 
# $ Lat   : int -39 -33 -39 -40 -32 -30 -38 -31 -35 -38 ... 
# $ Lon   : int -113 -97 -95 -99 -117 -98 -98 -95 -112 -120 ... 
# $ Var1  : int 6 7 8 0 4 8 1 8 0 3 ... 
# $ Var2  : int 0 0 0 0 1 1 1 1 1 0 ... 
str(df2) 
# 'data.frame': 9 obs. of 3 variables: 
# $ SiteID  : int 1787 2805 3025 3027 3028 3029 3030 3031 3033 
# $ City  : chr [1:9, 1] "Lusby" "Springdale" "Saukville" "Saukville" ... 
# $ StateBasedIn: chr [1:9, 1] "MD" "AR" "WI" "WI" ... 

df1 <- mutate_if(df1, is.factor, as.character) 
df2[] <- lapply(df2, as.vector) 

を：

library(dplyr) 
df1 %>% 
    left_join(select(df2, SiteID, cty = City, st = StateBasedIn), by = "SiteID") %>% 
    mutate(
    City   = ifelse(nzchar(City), City, cty), 
    StateBasedIn = ifelse(grepl("[^\\s]", StateBasedIn), StateBasedIn, st) 
) %>% 
    select(-cty, -st) 
# SiteID  City StateBasedIn Lat Lon Var1 Var2 
# 1 4227 Richmond   KY -39 -113 6 0 
# 2 4987 Nashville   TN -33 -97 7 0 
# 3 4000  Newark   NJ -39 -95 8 0 
# 4 4925  Miami   FL -40 -99 0 0 
# 5 4437 Montgomery   AL -32 -117 4 1 
# 6 4053 Jonesboro   AR -30 -98 8 1 
# 7 4482  Arcata   CA -38 -98 1 1 
# 8 4037 Portland   OR -31 -95 8 1 
# 9 4020 Jackson   MS -35 -112 0 1 
# 10 1787  Lusby   MD -38 -120 3 0 
# 11 2805 Springdale   AR -30 -114 3 1 
# 12 3025 Saukville   WI -39 -81 7 1 
# 13 3027 Saukville   WI -38 -117 4 0 
# 14 3028 Saukville   WI -32 -90 8 0 
# 15 3029 Saukville   WI -39 -109 0 1 
# 16 3030 Saukville   WI -31 -115 8 0 
# 17 3031  Mequon   WI -38 -81 1 1 
# 18 3033  Mequon   WI -34 -104 3 0 

私がチェックするには、2つの異なる方法を含め空のフィールドの場合は、あなたの例が便利であるかどうかは不明です。 nzchar（空または空ではない）またはgrepl("[^\\s]",...)（空白ではないもの）のいずれかを簡単に使用できます。 （一部のデータがまた...チェックでis.naが必要になる場合があります）

Answer 3

あなたはかなり簡潔な解決策を一緒に入れてreplaceと​​3210とともに、dplyrからfull_joinを使用することができます。

library(dplyr) 
library(purrr) 

# Cleaning from r2evans (if you want to keep it to dplyr just use r2evans lapply method 

df1 <- mutate_if(df1, is.factor, as.character) 
df2 <- dmap(df2, as.vector) 

full_join(df1, df2, by = "SiteID") %>% 
    mutate_at(vars(matches("City","StateBased")), funs(replace(., . == "", NA))) %>% 
    mutate(City = coalesce(City.y, City.x), 
     StateBasedIn = coalesce(StateBasedIn.y, StateBasedIn.x)) %>% 
    select(-contains("."))