5.3.1.3 個別列の選択例

OREdplyrパッケージのdistinctおよびarrange関数の例。

例5-72 個別列の選択

df <- data.frame(
  x = sample(10, 100, rep = TRUE),
  y = sample(10, 100, rep = TRUE)
)
DF <- ore.push(df)
nrow(DF)
nrow(distinct(DF))
arrange(distinct(DF, x), x)
arrange(distinct(DF, y), y)

# Use distinct on computed variables
arrange(distinct(DF, diff = abs(x - y)), diff)

この例のリスト

R> df <- data.frame(
+   x = sample(10, 100, rep = TRUE),
+   y = sample(10, 100, rep = TRUE)
+ )
R> DF <- ore.push(df)
R> nrow(DF)
[1] 100
R> nrow(distinct(DF))
[1] 66
R> arrange(distinct(DF, x), x)
    x
1   1
2   2
3   3
4   4
5   5
6   6
7   7
8   8
9   9
10 10
R> arrange(distinct(DF, y), y)
    y
1   1
2   2
3   3
4   4
5   5
6   6
7   7
8   8
9   9
R> 
R> # Use distinct on computed variables
R> arrange(distinct(DF, diff = abs(x - y)), diff)
   diff
1     0
2     1
3     2
4     3
5     4
6     5
7     6
8     7
9     8
10    9