Plotting Categorical Values Histogram in R - r
I have data from two instruments. One column is a categorical values- status of sensor (1 or 2 or 3), second column is reference value- numerical value. I want to plot a histogram of status of sensor (1 or 2 or 3) for different ranges of reference. For example: when the reference value is 1-5, I want to see a frequency distribution of sensor 1 status (1 or 2 or 3). Similarly for 6-10 of reference data and upto 95-100 of reference value, I want a frequency distributions of sensor status. Any help is appreciated. I am trying to figure out how good the sensor is with respect to the reference. Here is some sample data:
sample_data <-
structure(list(status = c(1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 2, 2, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,
3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,
3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,
3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,
3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,
3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,
3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,
3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,
3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,
3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,
3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,
3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 1, 1,
1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1), conc = c(0.6, 0.6, 3, 1.8,
0.4, 0.4, 0.6, 0.2, 1, 1.8, 2.2, 0.6, 0.6, 0.4, 2.2, 3.2, 0.6,
0.6, 0.4, 0.6, 0.8, 1, 0.6, 0.2, 0.2, 1, 0.4, 0.6, 1, 1.2, 0.4,
0.4, 0.4, 1, 0.4, 0.8, 0.2, 0.4, 0.6, 44.6, 6.8, 11, 600, 131.4,
32.4, 32, 87.6, 102.6, 89.6, 56.4, 57.8, 57.8, 56, 56, 51.4,
54.8, 56.4, 56.4, 56.4, 58.6, 56, 55.6, 54.4, 54.8, 55.8, 54.6,
55.8, 55.6, 54.6, 55, 54.8, 55.4, 56.2, 55, 54.8, 54.2, 55.2,
55.6, 53.8, 56.2, 55, 55.6, 54.2, 54.8, 56, 54, 54, 54.4, 54.6,
54.4, 54.2, 53.8, 53.8, 54.2, 54.4, 55, 54.4, 54.6, 56, 57.4,
54.6, 54.4, 54.6, 55.2, 55.4, 55.2, 54.2, 56, 52.2, 52.6, 53.2,
51, 47.6, 49.2, 49.4, 48.2, 49.2, 49.2, 52.4, 52.4, 53.8, 52.2,
49.2, 53.6, 55.2, 52.8, 53, 48.8, 51.2, 49.4, 49, 47.8, 47.4,
46.8, 50.4, 47.6, 47.2, 48.8, 48.8, 47.6, 47.8, 48.4, 48.2, 46.8,
45, 44.4, 43.4, 44.2, 45.8, 46.8, 47.4, 47.6, 45.4, 44.6, 44.6,
43.6, 44.4, 46.6, 39.8, 43.4, 42.2, 42.4, 40.4, 42.8, 44, 39.8,
41, 39.8, 38.4, 39.6, 40.2, 41, 40, 39.6, 38.6, 40.6, 40, 39.8,
38.6, 39, 38, 37.6, 37.6, 39.6, 37.6, 37.8, 38.8, 39.2, 38.2,
37.8, 35.8, 35.2, 36.2, 36.2, 37.4, 35.8, 35.6, 33.8, 35.2, 35.8,
35.2, 35.2, 35.6, 36.2, 36, 36.2, 36.2, 36, 34.4, 34.2, 34, 34,
34, 35, 34.2, 33.8, 31.2, 33.2, 32.4, 31.8, 32.4, 32.6, 31.8,
31.4, 31.2, 31.8, 30.8, 32.2, 30.8, 31.2, 29.4, 30.6, 30.2, 29.6,
29.8, 30.2, 30.2, 29.4, 30.2, 29.2, 29.8, 30, 30.4, 30.6, 29.8,
29.4, 29.4, 28.8, 28.8, 27.4, 29.4, 29, 28, 28.2, 29.4, 29.2,
28.6, 29.2, 26.8, 25.8, 25.4, 26.4, 25.8, 26, 27, 26, 27.6, 27.2,
27.6, 27.2, 25.8, 25.4, 25.6, 25.4, 26.4, 25.8, 25.2, 25.2, 24.8,
23.4, 24.4, 24, 24.6, 25, 25.2, 26.8, 23.2, 24, 24, 24.2, 23.8,
23.6, 24.6, 23.6, 23.6, 22.6, 23.8, 23.4, 21.4, 23, 21.8, 21.8,
22.6, 22.6, 22.6, 23.4, 23, 22, 24, 21.2, 21.4, 22.2, 22, 21.4,
22, 21.8, 21.6, 21, 21.6, 21.2, 21.6, 21.6, 21.4, 21.2, 21, 21.2,
21.2, 20.8, 21.2, 21.4, 20.6, 20, 20, 20.8, 21, 19.6, 19.2, 19.6,
20.2, 20.2, 20.4, 19.8, 19, 19, 18.8, 19.2, 19.4, 18.6, 18.2,
17.2, 17.8, 18.2, 17.8, 18, 17.4, 17, 16.8, 17.4, 17.8, 18.2,
17.6, 17.8, 17, 16.8, 17, 17.2, 17, 16.4, 17, 17.8, 15.6, 15.8,
17, 15.6, 17.2, 16.6, 16.2, 16.8, 17, 17, 16.8, 15.6, 16.4, 16.6,
15.4, 15.6, 15.4, 14.6, 14.8, 15.4, 14.6, 14.6, 15, 15.8, 15,
15.2, 15.2, 15.2, 14.6, 14.8, 15, 15.2, 14.4, 15, 15, 15, 15.2,
14, 13.8, 14.6, 14.8, 14, 14.2, 14.4, 14.4, 14.2, 14.2, 14.6,
14.4, 13.8, 13.6, 13, 13.6, 13.4, 13.6, 13, 14, 13.6, 12.4, 12.6,
13.6, 13.8, 12.8, 12.8, 12.8, 13.6, 13.2, 13, 13.2, 13.2, 12,
12.2, 11.6, 12.2, 11.8, 12, 12, 11.6, 12.2, 12.8, 14, 11.8, 11.6,
12.8, 11, 11, 11, 11.6, 12, 11.8, 11, 11.4, 11.8, 12, 11.8, 11.6,
11.6, 11.4, 11.2, 11.6, 11, 10.4, 11.2, 11, 10.4, 10, 9.8, 10.4,
11, 11.2, 11, 11.4, 10.8, 10.8, 11, 10.8, 10.4, 10.8, 9.8, 10.2,
10.4, 11.2, 10.6, 10, 9.6, 10.2, 9.6, 9.6, 9.8, 10.2, 10.4, 9.2,
9.8, 9.6, 9.6, 9.2, 9.2, 9.8, 8.6, 9.2, 9.4, 9.2, 9, 9, 9, 9,
9.4, 9.4, 9.4, 9.2, 9.2, 9.6, 8.4, 8.8, 8.6, 8.6, 8.8, 8.6, 8.8,
8.4, 8.8, 8.8, 9, 9, 9, 9, 8.8, 8.2, 9, 8.8, 8.6, 8.2, 8.8, 8.6,
8.6, 8.4, 7.8, 7.8, 8, 8, 8.2, 8.2, 7.8, 8, 8.2, 8.6, 8, 8, 7.6,
7.6, 7.8, 7.6, 7.6, 7.6, 8, 8, 7.6, 7.6, 7.4, 7.6, 7.4, 7.6,
7.8, 7.4, 7.8, 6.8, 6.8, 6.6, 7.2, 7.2, 6.8, 7, 6.4, 6.6, 6.6,
7, 6.6, 6.8, 7, 7.2, 7, 6.8, 6.8, 7, 6.8, 6.8, 6.4, 6.4, 6.4,
6.4, 6.4, 6.6, 6.6, 6.4, 6, 6.8, 6.6, 6.4, 6, 6.4, 5.6, 6.2,
5.8, 6, 6.2, 6.2, 6.2, 6, 6.2, 5.6, 5.6, 5.8, 6, 5.8, 5.8, 5.8,
6, 5.8, 5.8, 5.8, 5.8, 6, 5.8, 5.6, 5.4, 5.8, 5.6, 6, 5.6, 5.6,
6, 5.8, 5.4, 5.4, 5.2, 5.6, 5.6, 5.6, 5.4, 5.4, 5.2, 5.2, 5,
5.2, 5.4, 5, 5.2, 5, 4.8, 5.2, 5, 6, 5.2, 5, 5, 5, 5, 4.8, 4.8,
4.8, 5, 4.4, 4.4, 4.8, 5, 4.8, 5.2, 5, 4.4, 4.6, 5, 4.6, 5, 4.8,
5, 4.4, 4.4, 4.4, 4.6, 4.6, 4.4, 4.4, 4.6, 4.6, 4.6, 4.4, 4.4,
4.6, 4.4, 4.2, 4, 4.4, 4.4, 4.4, 4.2, 4, 4.4, 4.2, 4.4, 4.4,
4.2, 4.2, 4.4, 4.2, 4.2, 4, 4.2, 4, 4, 4.2, 4, 4, 3.6, 4, 4,
3.8, 3.6, 4, 3.8, 4, 3.8, 3.8, 3.8, 4, 3.8, 3.8, 3.8, 4, 4, 3.6,
3.6, 4, 3.8, 3.8, 3.6, 3.6, 3.8, 3.8, 3.6, 3.8, 3.6, 3.6, 3.4,
3.6, 3.8, 3.4, 3.6, 3.6, 3.8, 3.4, 3.6, 3.6, 3.6, 3.6, 3.2, 3.4,
3.4, 3.4, 3.2, 3.6, 3.4, 3.2, 3.4, 3.4, 3.4, 3.2, 3.2, 3.2, 3.4,
3.2, 3.2, 3, 3.2, 3.4, 3.4, 3.2, 3.2, 3.2, 3.2, 3.2, 3, 3, 3.2,
3.2, 2.8, 3.2, 3.2, 3, 3, 2.8, 2.8, 3, 3, 3, 3, 3, 2.8, 3, 3,
2.8, 2.8, 2.8, 2.8, 2.8, 3, 2.8, 3, 2.6, 3.2, 2.8, 2.6, 2.8,
2.8, 2.8, 2.8, 2.6, 2.8, 2.8, 2.4, 2.6, 2.6, 2.6, 2.8, 2.6, 2.2,
2.4, 2.6, 2.4, 2.4, 2.6, 2.4, 2.4, 2.4, 2.4, 2.4, 2.6, 2.4, 2.4,
2.4, 2.4, 2.6, 2.4, 2.6, 2.4, 2.4, 2.4, 2.4, 2.2, 2.4, 2.4, 2.4,
2.4, 2.4, 2.4, 2.4, 2.4, 2.6, 2.2, 2.4, 2.2, 2.2, 2.2, 2.2, 2.4,
2.2, 2.2, 2.2, 2.2, 2.2, 2, 2.2, 2.2, 2.2, 2, 2.4, 2.4, 2.2,
2.2, 2.2, 2.4, 2.2, 2.2, 2.2, 2.2, 2, 2, 2.2, 2.2, 2.2, 2.2,
2.2)), row.names = 18388:19288, class = "data.frame")
First, create the bar chart:
barplot(table(sample_data$sensor4_calcstatus))
Now a table of frequencies:
tbl <- table(cut(sample_data$ref_conc, breaks=seq(0, 100, by=5)), sample_data$sensor4_calcstatus)
tbl
#
# 1 2 3
# (0,5] 281 0 0
# (5,10] 150 17 0
# (10,15] 8 92 0
# (15,20] 0 58 0
# (20,25] 0 36 20
# (25,30] 0 0 43
# (30,35] 2 0 30
# (35,40] 0 0 39
# (40,45] 1 0 18
# (45,50] 0 0 28
# (50,55] 1 1 43
# (55,60] 5 1 22
# (60,65] 0 0 0
# (65,70] 0 0 0
# (70,75] 0 0 0
# (75,80] 0 0 0
# (80,85] 0 0 0
# (85,90] 2 0 0
# (90,95] 0 0 0
# (95,100] 0 0 0
par(mfrow=c(3, 1))
for (i in 1:3) barplot(tbl[, i], space=0, main=paste("Group", i))
Notice that you have two ref_conc values greater than 100: 131.4 and 600.0.
Related
When joining dfs with dplyr e.g. inner_join, keep matching cols from one df only
Example: library(tidyverse) mtcars1 <- mtcars %>% mutate(rn = row_number(), blah = rnorm(n(), 10, 1)) mtcars2 <- mtcars %>% mutate(rn = row_number(), blah2 = rnorm(n(), 5, 1)) mtcars_combined <- mtcars1 %>% inner_join(mtcars2, by = 'rn') mtcars_combined %>% glimpse Rows: 32 Columns: 25 $ mpg.x <dbl> 21.0, 21.0, 22.8, 21.4, 18.7, 18.1, 14.3, 24.4, 22.8, 19.2, 17.8, 16.4, 17.3, 15.2, 10.4, 10.4, 14.7, 32.4, 30.4, … $ cyl.x <dbl> 6, 6, 4, 6, 8, 6, 8, 4, 4, 6, 6, 8, 8, 8, 8, 8, 8, 4, 4, 4, 4, 8, 8, 8, 8, 4, 4, 4, 8, 6, 8, 4 $ disp.x <dbl> 160.0, 160.0, 108.0, 258.0, 360.0, 225.0, 360.0, 146.7, 140.8, 167.6, 167.6, 275.8, 275.8, 275.8, 472.0, 460.0, 44… $ hp.x <dbl> 110, 110, 93, 110, 175, 105, 245, 62, 95, 123, 123, 180, 180, 180, 205, 215, 230, 66, 52, 65, 97, 150, 150, 245, 1… $ drat.x <dbl> 3.90, 3.90, 3.85, 3.08, 3.15, 2.76, 3.21, 3.69, 3.92, 3.92, 3.92, 3.07, 3.07, 3.07, 2.93, 3.00, 3.23, 4.08, 4.93, … $ wt.x <dbl> 2.620, 2.875, 2.320, 3.215, 3.440, 3.460, 3.570, 3.190, 3.150, 3.440, 3.440, 4.070, 3.730, 3.780, 5.250, 5.424, 5.… $ qsec.x <dbl> 16.46, 17.02, 18.61, 19.44, 17.02, 20.22, 15.84, 20.00, 22.90, 18.30, 18.90, 17.40, 17.60, 18.00, 17.98, 17.82, 17… $ vs.x <dbl> 0, 0, 1, 1, 0, 1, 0, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 1 $ am.x <dbl> 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1 $ gear.x <dbl> 4, 4, 4, 3, 3, 3, 3, 4, 4, 4, 4, 3, 3, 3, 3, 3, 3, 4, 4, 4, 3, 3, 3, 3, 3, 4, 5, 5, 5, 5, 5, 4 $ carb.x <dbl> 4, 4, 1, 1, 2, 1, 4, 2, 2, 4, 4, 3, 3, 3, 4, 4, 4, 1, 2, 1, 1, 2, 2, 4, 2, 1, 2, 2, 4, 6, 8, 2 $ rn <int> 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31,… $ blah.x <dbl> 9.652697, 10.497945, 9.402642, 10.134072, 9.645391, 10.177435, 10.691140, 10.800154, 10.005802, 10.681475, 8.91997… $ mpg.y <dbl> 21.0, 21.0, 22.8, 21.4, 18.7, 18.1, 14.3, 24.4, 22.8, 19.2, 17.8, 16.4, 17.3, 15.2, 10.4, 10.4, 14.7, 32.4, 30.4, … $ cyl.y <dbl> 6, 6, 4, 6, 8, 6, 8, 4, 4, 6, 6, 8, 8, 8, 8, 8, 8, 4, 4, 4, 4, 8, 8, 8, 8, 4, 4, 4, 8, 6, 8, 4 $ disp.y <dbl> 160.0, 160.0, 108.0, 258.0, 360.0, 225.0, 360.0, 146.7, 140.8, 167.6, 167.6, 275.8, 275.8, 275.8, 472.0, 460.0, 44… $ hp.y <dbl> 110, 110, 93, 110, 175, 105, 245, 62, 95, 123, 123, 180, 180, 180, 205, 215, 230, 66, 52, 65, 97, 150, 150, 245, 1… $ drat.y <dbl> 3.90, 3.90, 3.85, 3.08, 3.15, 2.76, 3.21, 3.69, 3.92, 3.92, 3.92, 3.07, 3.07, 3.07, 2.93, 3.00, 3.23, 4.08, 4.93, … $ wt.y <dbl> 2.620, 2.875, 2.320, 3.215, 3.440, 3.460, 3.570, 3.190, 3.150, 3.440, 3.440, 4.070, 3.730, 3.780, 5.250, 5.424, 5.… $ qsec.y <dbl> 16.46, 17.02, 18.61, 19.44, 17.02, 20.22, 15.84, 20.00, 22.90, 18.30, 18.90, 17.40, 17.60, 18.00, 17.98, 17.82, 17… $ vs.y <dbl> 0, 0, 1, 1, 0, 1, 0, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 1 $ am.y <dbl> 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1 $ gear.y <dbl> 4, 4, 4, 3, 3, 3, 3, 4, 4, 4, 4, 3, 3, 3, 3, 3, 3, 4, 4, 4, 3, 3, 3, 3, 3, 4, 5, 5, 5, 5, 5, 4 $ carb.y <dbl> 4, 4, 1, 1, 2, 1, 4, 2, 2, 4, 4, 3, 3, 3, 4, 4, 4, 1, 2, 1, 1, 2, 2, 4, 2, 1, 2, 2, 4, 6, 8, 2 $ blah.y <dbl> 6.047953, 4.379261, 4.609405, 4.420695, 6.545795, 4.962723, 5.955824, 5.011969, 5.617293, 4.347312, 3.126674, 4.13… I only joined on one field, rn. Because there are multiple matching field names, they are appended .x and .y. Of course, I could just have joined onto a smaller df with e.g. mtcars_combined <- mtcars1 %>% inner_join(mtcars2 %>% select(rn, blah2), by = 'rn') But, I'd like to know if there's a clever way to tell r to just keep matching fields from the left side and drop any duplicate fields coming from the right?
One approach is to make use of the suffix argument and drop the duplicated cols using select:
library(dplyr)
mtcars1 <- mtcars %>% mutate(rn = row_number(), blah = rnorm(n(), 10, 1))
mtcars2 <- mtcars %>% mutate(rn = row_number(), blah2 = rnorm(n(), 5, 1))
mtcars_combined <- mtcars1 %>% inner_join(mtcars2, by = 'rn', suffix = c("", "_drop"))
mtcars_combined <- select(mtcars_combined, -ends_with("_drop"))
glimpse(mtcars_combined)
#> Rows: 32
#> Columns: 14
#> $ mpg <dbl> 21.0, 21.0, 22.8, 21.4, 18.7, 18.1, 14.3, 24.4, 22.8, 19.2, 1...
#> $ cyl <dbl> 6, 6, 4, 6, 8, 6, 8, 4, 4, 6, 6, 8, 8, 8, 8, 8, 8, 4, 4, 4, 4...
#> $ disp <dbl> 160.0, 160.0, 108.0, 258.0, 360.0, 225.0, 360.0, 146.7, 140.8...
#> $ hp <dbl> 110, 110, 93, 110, 175, 105, 245, 62, 95, 123, 123, 180, 180,...
#> $ drat <dbl> 3.90, 3.90, 3.85, 3.08, 3.15, 2.76, 3.21, 3.69, 3.92, 3.92, 3...
#> $ wt <dbl> 2.620, 2.875, 2.320, 3.215, 3.440, 3.460, 3.570, 3.190, 3.150...
#> $ qsec <dbl> 16.46, 17.02, 18.61, 19.44, 17.02, 20.22, 15.84, 20.00, 22.90...
#> $ vs <dbl> 0, 0, 1, 1, 0, 1, 0, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1...
#> $ am <dbl> 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 0...
#> $ gear <dbl> 4, 4, 4, 3, 3, 3, 3, 4, 4, 4, 4, 3, 3, 3, 3, 3, 3, 4, 4, 4, 3...
#> $ carb <dbl> 4, 4, 1, 1, 2, 1, 4, 2, 2, 4, 4, 3, 3, 3, 4, 4, 4, 1, 2, 1, 1...
#> $ rn <int> 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18...
#> $ blah <dbl> 10.856380, 9.634127, 10.280296, 10.153320, 9.255293, 10.38564...
#> $ blah2 <dbl> 5.724742, 5.740158, 4.743665, 5.337721, 4.239426, 5.989236, 4...
Using a Unique Identifier, Match Row Values with Column Names in R
Master
StoreNumber Online Pressure MON TUE WED ... SUN ...
1 0.2 50 0 0 0 ... 0
2 0.8 20 0 0 0 ... 0
3 1.2 10 0 0 0 ... 0
...
Hours
BranchNumber Day ... Time
1 MON 7.50
1 TUE 6.00
1 WED 8.50
3 MON 2.00
3 TUE 1.00
3 WED 2.50
...
NB There are many branch numbers about 10,500 due to being 7 days in a week so one branch number may occur 7 times for each day of the week, but some may only have 6 or 5 etc.
The idea is I want to populate the days of the week "Mon", "Tue", "Wed"... "Sun" etc in the 'Master' table from the 'Time' data in the 'Hours' Table. The match should check that the StorenNumber matches the BranchNumber...then the day of the week, if there is 'Mon' in the hours table then it should match it to the column 'Mon' in the Master table.
So the output will look something like this
StoreNumber Online Pressure MON TUE WED ... Hours
1 0.2 50 7.50 6.00 8.50 ... 53
2 0.8 20 0 0 0 ... 30
3 1.2 10 2.00 1.00 2.50 ... 20
...
As an example BranchNumber 2 doesnt exist in the Hours table so it should just skip each column and leaves the inputs as 0
I have tried the R based code below but am struggling to get an output...Once running the code I get zero errors but the Master Table remains unchanged and all days of the week columns remain as 0
merged <- Master%>% select(-
c("MON","TUE","WED","THU","FRI","SAT","SUN")) %>%
left_join(
Hours %>% pivot_wider(names_from = Day, values_from =
Time),
by = c("StoreNumber" = "BranchNumber"))
merged <- merged %>% replace(is.na(.),0)
Dput(Master)
Pressure = c(0, 0, 0, 0, 0, 0, 0, 0, 0.23, 0,
0.19, 0, 0, 0, 0.56, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0.42, 0, 0, 0, 0, 0.37, 0, 0, 0.92, 0, 0, 0, 0,
0.04, 0.15, 0.12, 0.12, 0.06, 0.02, 0.19, 0.12, 0.08, 0.15,
0.02, 0.46, 0.25, 0.02, 0.17, 0.06, 0.25, 0.08, 0, 0.08,
0, 0.12, 0.23, 0.02, 0.04, 0.02, 0.15, 0, 0.02, 0.1, 0, 0,
0.04, 0.02, 0.23, 0.48, 0.19, 0.06, 0.02, 0.02, 0.08, 0.13,
0, 0.02, 0.08, 0.06, 0.15, 0.42, 0.06, 0.04, 0.04, 0.44,
0.06, 0.42, 0.06, 0.13, 0.46, 0, 0.81, 0.12, 0.25, 0.5, 0.06,
0.23, 0.02, 0.19, 0.33, 0, 0.06, 0.13, 0.12, 0.27, 0.04,
0.17, 0.13, 0.08, 0.12, 0.1, 0.21, 0.31, 0.17, 0, 0, 0.04,
0.1, 0.29, 0.13, 0.38, 0.15, 0.17, 0.58, 0.02, 0.02, 0.08,
1.15, 0.08, 0.1, 0.4, 0.58, 0.35, 0.12, 0.12, 0.5, 0.17,
0.6, 0.04, 0.06, 0.13, 0.12, 0.06, 0.19, 0.25, 0.06, 0.06,
0.1, 0, 0.29, 0.58, 0.02, 0.08, 1.4, 0.15, 0.21, 0.15, 0.1,
0.02, 0, 0, 0.08, 0, 0.02, 0.23, 0.1, 0.6, 0, 0.08, 0.37,
0, 0.17, 0.21, 0.44, 0.77, 0.33, 0.42, 0, 0.12, 0.12, 0.1,
0.12, 0.06, 0.02, 0.04, 0.17, 0.13, 0.02, 0.12, 0.25, 0.06,
0.04, 0.04, 0.17, 0.17, 0.6, 0.06, 0.37, 0, 0.15, 0.13, 0.08,
0.21, 0, 0.13, 0.02, 0.15, 0, 0.4, 0.23, 0.27, 0.08, 0.1,
0.19, 0.04, 0.02, 0.1, 0.17, 0.85, 0.56, 0, 0.56, 0.56, 0.06,
0.06, 0, 0.21, 0.02, 0.33, 0, 0.04, 0.13, 0.1, 0.12, 0, 0,
0.13, 0.17, 0.08, 0.02, 0.12, 0.06, 0.38, 0.21, 0.1, 0, 0.13,
0.17, 0, 0.1, 0.12, 0.17, 0, 0.42, 0.15, 0.15, 0.42, 0.04,
0.04, 0.69, 0.15, 0, 0, 0.17, 0.4, 0.23, 0.27, 0.04, 0.17,
0.06, 0, 0, 0.06, 0.21, 0.04, 0.29, 0.04, 0.19, 0, 0.19,
0.02, 0.02, 0.29, 0.35, 0.19, 0.23, 0.42, 0.02, 0.35, 0.29,
0.02, 0.17, 0.1, 0.06, 0.17, 0.1, 0.38, 0.02, 0.15, 0.17,
0.29, 0.04, 0.02, 0.38, 0.12, 0.17, 0.02, 0, 0.06, 0.12,
0.08, 0.13, 0.12, 0.1, 0.33, 0.23, 0.29, 0.31, 0.19, 0.17,
0, 0.33, 0.17, 0.38, 0.02, 0.21, 0.17, 0.19, 0.06, 0.29,
0.12, 0.02, 0.15, 0.13, 0.17, 0.25, 0.02, 0.15, 0.65, 0.48,
0.29, 0.02, 0.19, 0.29, 0.27, 0.06, 0.02, 0.29, 0.21, 0.15,
0.12, 0.19, 0.44, 0.1, 0.04, 0.12, 0.15, 0.27, 0.1, 0.15,
0.1, 0.06, 0.15, 0.06, 0.15, 0.13, 0.54, 0.19, 0.04, 0.33,
0.06, 0.25, 0.17, 0.29, 0.12, 0.25, 0.1, 0.31, 0.13, 0.1,
0.1, 0.02, 0.25, 0.02, 0.15, 0.13, 0.29, 0.15, 0.77, 0.1,
0.08, 0.38, 0.4, 0.02, 0.37, 0, 0.12, 0.27, 0.25, 0.46, 0,
0.02, 0.12, 0, 0.27, 0.02, 0, 0.13, 0.04, 0.08, 0.13, 0.25,
0.08, 0.06, 0, 0.06, 0.12, 0.33, 0.15, 0.67, 0.04, 0.31,
0.21, 0.19, 0.25, 0.27, 0.02, 0.1, 0.1, 0.06, 0.44, 0.35,
0.23, 0.1, 0.15, 0.21, 0.08, 0.02, 0.37, 0.27, 0.17, 0.1,
0.04, 0.19, 0.42, 0.27, 0.29, 0.63, 0.54, 0.29, 0.02, 0.44,
0.35, 1.35, 0, 0.4, 0.25, 0.04, 0.02, 0.02, 0.17, 0.19, 0.17,
0.1, 0.42, 0.13, 0.13, 0.1, 0.1, 0.06, 0.04, 0.04, 0.44,
0.06, 0.04, 0.1, 0.21, 0.06, 0.02, 0.19, 0.27, 0.44, 0.02,
0.17, 0.06, 0.02, 0.17, 0.15, 0.15, 0.15, 0.12, 0.02, 0,
0, 0.21, 0.02), Online = c(1.63, 2.6, 0.48, 1.9, 5.27, 1.23,
1.87, 4.56, 3.71, 2.4, 9.62, 1.15, 1.5, 1.96, 2.5, 10.37,
2.62, 7.44, 2.71, 1.48, 16.94, 3.92, 2.9, 4.44, 2.69, 6.04,
2.69, 1.44, 0.52, 0.48, 1.44, 0.85, 4.56, 1.81, 9.25, 3.12,
5.56, 2.33, 4.67, 2.54, 3.73, 1.63, 3.4, 1.9, 1.15, 1.08,
6.27, 2.23, 3.13, 2.02, 0.63, 3.31, 2.96, 4.56, 3.19, 2.62,
6.21, 8.6, 2.23, 2.33, 0.9, 2.6, 0.94, 1.58, 0.85, 3.38,
4.04, 6.46, 3.17, 4.79, 7.92, 6.58, 1.63, 5.88, 5.06, 6.42,
2.69, 4.4, 2.08, 2.81, 3.23, 1.6, 3.08, 5.77, 1.65, 2.56,
3.81, 4.08, 3.65, 5.06, 1.15, 1.15, 1.08, 3.77, 2.75, 2.6,
2.56, 4.37, 4.92, 2.12, 1.58, 0.1, 1.87, 1.44, 4.02, 2.5,
1.29, 2.33, 6.12, 4.62, 1.98, 5.77, 3.19, 0.9, 1.5, 9.77,
7.63, 5.37, 0.79, 1.17, 4.23, 2.81, 4.31, 2.71, 3.4, 6.38,
2.75, 1.23, 4.77, 2.4, 6.04, 0.58, 0.79, 8.08, 2.13, 1.75,
0.87, 2.19, 1.38, 2.54, 2.71, 1.65, 3.5, 1.85, 18.52, 2.08,
0.33, 3.19, 6.69, 1.06, 3.08, 1.81, 1.06, 0.48, 0.85, 3.65,
1.44, 1.63, 1.71, 3.5, 2.12, 9.62, 1.96, 7.48, 1.65, 3.19,
11.04, 1.81, 3.4, 3.73, 6.1, 0.9, 10.31, 4.46, 2.27, 1.17,
0.94, 2.02, 2.75, 6.38, 3.83, 4.98, 3.77, 2.71, 5.63, 1.21,
3.31, 0, 9.35, 5.56, 1.79, 6.15, 1.9, 3.4, 6.52, 0.63, 1.37,
4.25, 1.71, 0.69, 0.75, 1.23, 2.69, 2.02, 1.79, 3.56, 0.75,
0.75, 0.52, 1.21, 1.12, 0.69, 1.79, 4.56, 1.23, 4.83, 5.04,
2.38, 1.23, 5.4, 3.13, 2.62, 1.08, 13.38, 3.52, 5.19, 3.62,
1.08, 4.5, 10.19, 2.33, 4.73, 1.87, 9.4, 11.21, 1.65, 2.29,
2.9, 35.94, 3.19, 2.4, 1.79, 7.58, 5.4, 4.73, 1.21, 1.54,
1.75, 2.98, 2.27, 2.08, 2.08, 4.35, 5.85, 3.12, 1.63, 5.06,
1.65, 4.92, 4.77, 5.06, 5, 5.27, 8.75, 3.56, 5.77, 6.21,
10.13, 6, 7.69, 1.92, 3.81, 7.92, 1.63, 4.29, 3.46, 7.65,
8.35, 1, 6.27, 6.96, 2.17, 14.81, 10.65, 0.04, 2.54, 1.38,
0.85, 5.79, 3.5, 6.6, 6.04, 2.13, 4.04, 5.63, 4.94, 1.27,
2.5, 6.42, 4.83, 4.35, 3.19, 4.1, 1.38, 1.63, 2.4, 6.96,
0.63, 2.12, 8.65, 3.67, 1.9, 2.08, 5.46, 3.71, 1.69, 2.81,
0.6, 2.06, 5.1, 2.87, 5.27, 6.54, 2.56, 0.42, 0.33, 1.12,
1.06, 1.6, 1.37, 2.23, 1.08, 1.75, 0.6, 0.9, 5.1, 2.27, 0.73,
1.33, 1.06, 1.96, 1.98, 3.98, 1.75, 1.87, 9.73, 12, 1.15,
1.23, 3.29, 1.92, 6.06, 4.44, 2.48, 1.37, 5.58, 2.12, 1.81,
1.17, 0.27, 1.6, 4.85, 1.17, 2.48, 1.63, 2.17, 1.71, 4.15,
0.48, 1.44, 1.08, 4.67, 4.56, 0.52, 6.06, 1.63, 2.35, 1.23,
1.96, 14.35, 0.58, 1.54, 1.5, 1.9, 2.54, 2.48, 2.77, 19.6,
3.35, 0.73, 1.69, 1.17, 0.85, 3.23, 0.17, 2.27, 3.71, 2.27,
2.4, 1.37, 1.5, 2.02, 0.12, 0.25, 0.38, 17.13, 2.65, 0.31,
1.85, 3.13, 1.54, 3.38, 2.98, 3.71, 2.23, 4.58, 3.29, 1.02,
7.12, 1.96, 1.85, 0.85, 2.69, 1.81, 1.21, 1.06, 3.13, 1.44,
2.71, 3.4, 3.98, 3.08, 0.9, 5, 0, 0, 0, 0, 0, 2.06, 0.75,
5.25, 2.06, 3.38, 3.04, 7.9, 4.73, 1.44, 10.67, 0.06, 7.42,
2.19, 4.5, 2.44, 3.13, 3.52, 2.75, 0.27, 7.1, 5.63, 0.52,
1.15, 2.48, 2.48, 3.71, 1.6, 1.98, 2.06, 1.5, 4.56, 1.08,
0.25, 1.15, 4.79, 2.6, 4.73, 2.6, 0.15, 0.15, 5.27, 1.21,
5, 1.29, 3.38, 0.85, 2.27, 0, 0.73, 0.38, 0.38, 0.94, 0.38,
2.08, 1.71, 4.29, 0.94, 5.62, 2.23, 0.38, 1.23, 2.06, 0.65,
4.71, 2.19, 3.08, 1.21, 1.38, 2.06, 0.54, 0.81, 1.08, 4.35,
12.6, 8.98, 1.87, 1.58, 0.27, 0.46, 19.65, 0.38, 1.37, 2.06,
1.98, 0.31, 0.46, 0.6, 0.38, 0.31, 3.77, 2.5, 15.56, 5.27,
12.58, 7.33, 11.06, 9.33, 12.79, 15.29, 7.12, 7.23, 14.17,
12.06, 12, 6.54, 6, 15.35, 10.71, 14.69, 6.94, 6.12, 5.73,
7.17, 4.15, 15.77, 7.02, 12.75, 11.56, 8.12, 6.46, 7.12,
9.02, 11.04, 10.79, 10.08, 8.08, 8.21, 9.81, 8.92, 10.73,
10.15, 9.35, 8.62, 6.27, 13.23, 14.02, 14.13, 6.25, 7.37,
6.06, 21.4, 6.63, 7.1, 8.62, 17.29, 8.4, 7.44, 5.77, 10.77,
56.38, 9.77, 11.98, 8.9, 6.06, 5.77, 13.48, 14.23, 8.17,
9.62, 11.62, 6, 12.38, 7.42, 7.23, 5.79, 8.08, 8.35, 4.73,
7.58, 6.15, 6.88, 15.65, 13.02, 7.71, 18.33, 5.69, 4.5, 7.96,
5.35, 21.17, 4.29, 9.17, 13.96, 8.69, 8.5, 12.94, 7.1, 6.15,
19.94, 7.54, 13.9, 11.56, 11.4, 11.31, 19.6, 8.83, 11.19,
9.94, 7.5, 8, 6, 4.85, 6.15, 9.94, 8.02, 11.15, 15.13, 7.06,
10.37, 10.04, 27.02, 8.17, 13.6, 11.04, 11.15, 6.1, 4.37,
7.02, 15.5, 13.15, 7.75, 9.19, 11.48, 8.81, 10.23, 12.1,
5.96, 8.13, 12.48, 8.21, 9.44, 13.15, 9.54, 19.9, 4.71, 4.63,
23.63, 24.31, 10.79, 15.35, 12.79, 10.31, 20.85, 9.02, 15.04,
9.4, 4.63, 11.27, 5.96, 40.12, 8.77, 7.79, 8.27, 7.1, 11.62,
3.81, 5.67, 5.35, 8.6, 7.33, 7.6, 8.87, 17.77, 7.92, 5.9,
6.85, 12.54, 21.08, 15.08, 9.02, 3.98, 11.67, 32.79, 5.21,
5, 6.38, 10.31, 21.35, 18.06, 13.17, 16.52, 17.04, 10.4,
4.29, 21.19, 8.71, 8.75, 14.5, 5, 8.29, 9.19, 19.87, 4.5,
3.87, 6.73, 6.75, 22.87, 8.4, 13.38, 16.79, 3.31, 8.5, 12.48,
6.33, 10.25, 9.87, 6.04, 14.33, 6.04, 5.79, 5.63, 10.73,
13.58, 8.87, 11.88, 9.12, 12.21, 10.08, 7.5, 13.9, 10.92,
8.4, 9.65, 9.25, 13.75, 9.46, 12.33, 10.02, 98.77, 11.21,
5.77, 5.19, 12.9, 10.1, 10.56, 6.12, 6.17, 7.44, 2.08, 0.65,
2.92, 0.42, 4.1, 8.62, 1.37, 2.35, 2.56, 1.15, 2.17, 0.69,
4.02, 1.81, 1.37, 2.87, 3.29, 2.96, 1.42, 2.62, 0.48, 2.35,
5.27, 2.23, 1.38, 3.31, 8.87, 3.25, 2.98, 3.94, 2.13, 1.85,
5.19, 2.9, 2.23, 2.38, 0.9, 2.92, 0.96, 0.75, 2.33, 4.88,
4.08, 3.65, 7.87, 11.35, 2.83, 3.62, 3.12, 4.79, 4.62, 5.27,
5.25, 6, 2.29, 1.44, 1.06, 2.44, 1.42, 2.6, 4.67, 4.1, 1.06,
2.83, 2.87, 1.5, 1.5, 0.87, 0.73, 3.83, 2.71, 0.65, 2.35,
1.37, 4.23, 2.17, 1.81, 2.77, 1.23, 1.96, 1.37, 4.44, 3.35,
1.96, 2.33, 1.33, 1.38, 6.67, 2.75, 1.48, 2.62, 1.65, 2.29,
5, 1.81, 2.08, 1.27, 3.4, 1.42, 2.23, 0.37, 1.69, 2.23, 2.83,
0.69, 4.71, 1.85, 1.23, 2.71, 8.12, 1.87, 2.62, 0.85, 3.12,
4.88, 1.23, 2.13, 0.52, 4.73, 4.31, 1.23, 0.38, 0.48, 0.58,
1.27, 3.31, 12.46, 2.4, 5.13, 2.81, 2.87, 2.44, 6.69, 1.85,
5.1, 2.29, 4.35, 1.6, 3.25, 3.13, 1.98, 1.79, 2.87, 2.33,
4.31, 0.73, 0.46, 2.83, 1.06, 0.73, 3.94, 0.42, 6.48, 2.4,
5.37, 2.71, 3.38, 1.81, 1.87, 5.13, 0.87, 0.9, 3.38, 0.81,
1.06, 0.96, 0.63, 2.87, 1.5, 1.29, 4.1, 1.54, 2.13, 6.42,
3.17, 3.25, 2.44, 3.19, 1.81, 2.4, 3.83, 3.71, 2.71, 3.04,
15.13, 4.73, 3.17, 2.62, 8.69, 7.1, 2.13, 2.02, 1.42, 2.19,
3.44, 3.56, 3.67, 8.17, 0.63, 3.35, 1.9, 0.87, 1.75, 4.4,
7.12, 3.46, 4.56, 2.81, 1.08, 0.81, 2.27, 2.23, 0.94, 4.92,
3.44, 2.87, 2.65, 6.31, 2.5, 1.85, 1.44, 1.71, 1.15, 1.37,
0.31, 2.9, 3.5, 3.17, 0.48, 0.85, 1.65, 3.56, 6.81, 1.17,
0, 4.02, 2.71, 1.96, 3.44, 10.23, 2.98, 2.54, 4.1, 1.65,
2.4, 4.88, 2.75, 1.9, 2.75, 1.69, 5.37, 7.33, 6.06, 4.19,
1.6, 0.75, 6.63, 2.87, 3.77, 1.85, 1.69, 1.6, 4.85, 5.35,
2.65, 2.75, 2.83, 0.42, 4.88, 3.04, 9.44, 11.79, 4.79, 1.5,
3.52, 0.87, 1.71, 1.15, 1.02, 0.87, 3.35, 7.06, 4.19, 0.94,
0.63, 2.06, 4.62, 2.6, 1.29, 3.73, 4.25, 3.87, 4.23, 1.92,
6.15, 2.12, 4.83, 2.35, 2.29, 6.67, 1.38, 1.15, 1.54, 1.92,
1.75, 1.15, 0, 0, 2.96, 1.08, 0.17, 4.98, 3.5, 4.62, 1.65,
0.1, 2.92, 3.77, 1.65, 0, 1.69, 6.04, 3.88, 3.25, 2.44, 2.75,
1.63, 2.6, 3.04, 0.63, 2.06, 0.15, 0.63, 3.35, 1.15, 0.69,
2.5, 2.6, 0.96, 1.27, 3.6, 2.5, 3.77, 0.81, 0.96, 5.96, 1.12,
0.81, 0.85, 1.38, 4.1, 1.63, 1.69, 0.12, 5.62, 2.98, 3.44,
0.87, 3.17, 1.98, 2.92, 9.54, 0.06, 3.88, 0.81, 1.27, 0.46,
1.12, 2.13, 3.83, 8.83, 1.48, 7.23, 0.48, 1.58, 0.54, 3.12,
3.44, 0.54, 0.17, 3.6, 0.33, 0.81, 0.6, 0.37, 1.17, 2.6,
2.92, 1.81, 3.62, 2.98, 2.06, 4.35, 1.69, 0.37, 1.06, 2.23,
1.42, 0.73, 2.06, 1.38, 1.12, 2.19, 1.15, 0.6, 0.31, 3.83,
1.6, 3.98, 2.35, 13.9, 0.37, 1.85, 3.6, 2.19, 4.5, 0.42,
0.27, 4.23, 5.21, 4.04, 1.33, 5.06, 0, 10.35, 3.19, 2.33,
7.17, 0.52, 0.69, 4.04, 8.21, 7.44, 5.69, 3.5, 2.62, 7.42,
1.85, 4.02, 2.27, 16.15, 7.33, 1.42, 12.31, 3.04, 1.17, 3.17,
9.33, 4.71, 4.67, 4.46, 3.87, 0.21, 2.17, 6.73, 11.88, 2.98,
1.29, 15.87, 0.42, 1.6, 2.23, 1.21, 1.33, 2.81, 3.67, 3.13,
4.71, 6.21, 7.15, 1.44, 3.46, 3.04, 1.85, 1.37, 2.69, 3.71,
5.85, 1.12, 16.58, 2.9, 9.46, 4.58, 2.27, 5.15, 3.94, 2.38,
1, 4.52, 0.65, 1.87, 2.02, 0.15, 1.9, 16.31, 2.5, 4.08, 4.08,
5.21, 5.62, 3.62, 2.56, 1.63, 9.87, 0.63, 1.85, 3.19, 9.62,
3.71, 2.06, 4.79, 9.25, 5.96, 1.63, 2.27, 0.37, 2.9, 3.88,
4.08, 5.63, 5.94, 2.27, 3.38, 4.85, 2.4, 2.35, 0.52, 1.29,
3.52, 1.6, 4.77, 22.02, 3.94, 1.33, 1.33, 1.33, 14.63, 1.98,
6.12, 7.9, 1.5, 1.15, 5.85, 0.9, 2.17, 0.81, 2.17, 4.56,
2.23, 6.27, 10.58, 4.5, 7.96, 2.33, 6.25, 2.44, 3.02, 4.31,
6.58, 2.06, 3.5, 5.4, 0.69, 8, 1.71, 1.44, 0.85, 1.69, 7.54,
2.33, 1.37, 2.17, 2.92, 1.65, 1.69, 3.83, 3.35, 0.79, 3.4,
1.81, 0.81, 2.77, 3.12, 6.75, 1.6, 1.69, 2.54, 3.65, 3.65,
12.6, 3.29, 1.44, 1.65, 5.94, 6, 6.38, 1.48, 9.25, 1.21,
8.98, 2.35, 2.19, 2.71, 14.23, 1.69, 8.12, 23.46, 2.77, 1,
2.44, 1.27, 1.9, 6.63, 0.96, 0.87, 6.33, 1.21, 0.73, 5.9,
0.69, 1.81, 3.65, 4.46, 12, 6.21, 3.35, 1.02, 0.46, 0.21,
0.04, 6.04, 2.23, 1.42, 1.63, 1.58, 6.94, 5.35, 2.33, 1.92,
1.12, 8.98, 2.56, 0.87, 2.27, 1.08, 2.19, 10.67, 6.21, 0.38,
1.44, 0.04, 1, 1.21, 7.33, 0), row.names = c(NA,
-1432L), class = "data.frame")
Dput(Hours)
Days = c(8.5, 8.5, 8.5, 8.5, 8.5, 8, 8.5,
8.5, 8.5, 8.5, 8.5, 8, 9, 9, 9, 9, 9, 8, 9, 9, 9, 9, 9, 8,
9, 9, 9, 9, 9, 4, 9.5, 9.5, 9.5, 9.5, 9.5, 4, 9, 9, 9, 9,
9, 8.5, 10, 13, 13, 13, 13, 13, 10, 9, 9, 9, 9, 9, 4, 9.25,
9.25, 9.25, 9.25, 9.25, 3, 8.75, 8.75, 8.75, 8.75, 8.75,
8.25, 8.5, 8.5, 8.5, 8.5, 9, 4, 4, 9, 9, 9, 9, 9, 8, 8.75,
8.75, 8.75, 8.75, 8.75, 4.25, 9, 9, 9, 9, 9, 8.5, 9, 9, 9,
13, 9.5, 9.5, 9.5, 9.5, 9.5, 4, 9, 9, 9, 9, 9, 9.5, 9.5,
9.5, 9.5, 9.5, 9, 9, 9, 9, 9, 8, 8, 8, 8, 8, 4, 9, 9, 9,
9, 9, 9, 9, 8.5, 8.5, 9, 3, 9, 9, 9, 9, 9, 10, 15, 15, 15,
15, 15, 15, 8.5, 8.5, 8.5, 8.5, 8.5, 8.5, 8.5, 8.5, 8.5,
8.5, 7, 10, 15, 15, 15, 15, 15, 15, 11, 11, 11, 11, 11, 9.5,
9.5, 9.5, 9.5, 9.5, 4, 9, 9, 9, 9, 9, 8.5, 9, 9, 9, 9, 9,
9, 9.5, 9.5, 9.5, 9.5, 9.5, 8.5, 8.5, 8.5, 8.5, 8.5, 8.5,
8, 9, 9, 9, 9, 9, 6, 14.5, 14.5, 14.5, 14.5, 14.5, 14.5,
6, 12, 12, 12, 12, 12, 12, 6, 12, 12, 12, 12, 12, 12, 6,
12.5, 12.5, 12.5, 12.5, 12.5, 12.5, 9, 9, 9, 9, 9, 10.5,
10.5, 10.5, 10.5, 10.5, 7.5, 6, 11.5, 11.5, 11.5, 11.5, 11.5,
11.5, 12, 12, 12, 12, 12, 5, 9, 9, 9, 9, 9, 8, 9, 9, 9, 9,
9, 9, 9, 9, 9, 9, 3, 9, 9, 9, 9, 9, 8, 9, 9, 9, 9, 9, 5,
10, 10, 10, 10, 10, 9, 9, 9, 9, 9, 8, 8.5, 8.5, 8.5, 8.5,
8.5, 8, 9.5, 9.5, 9.5, 9.5, 9.5, 3.5, 9, 9, 9, 9, 9, 9, 9,
9, 9, 9, 3.5, 9.5, 9.5, 9.5, 9, 9.5, 8, 9, 9, 9, 9, 9, 9,
9, 9, 9, 9, 9, 9, 9, 9, 9, 8.5, 8.5, 8.5, 8.5, 8.5, 9, 9,
9, 9, 9, 10, 15, 15, 15, 15, 15, 15, 10, 10, 10, 10, 10,
10, 9, 9, 9, 9, 9, 9.5, 9.5, 9.5, 9.5, 9.5, 6, 14, 14, 14,
14, 14, 14, 6, 12, 12, 12, 12, 12, 12, 6, 12, 12, 12, 12,
12, 12, 6, 12, 12, 12, 12, 12, 12, 9, 9, 9, 9, 9, 4, 9, 9,
9, 9, 9, 8, 9.5, 9, 9, 9, 9, 3, 9.5, 9.5, 9.5, 9.5, 9.5,
3.5, 10, 10, 10, 10.5, 10, 4, 11, 11, 12, 11, 12, 10, 10,
10, 10, 10, 6, 10.5, 10.5, 10.5, 10.5, 10.5, 9, 9, 9, 9,
9, 8, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 4, 9.5, 9.5,
9.5, 9.5, 9.5, 9.75, 9.75, 9.75, 9.75, 9.75, 9, 9, 9, 9,
9, 9.25, 9.25, 9.25, 9.25, 9.25, 4, 10.25, 10.25, 10.25,
10.25, 10.25, 6, 9.5, 9.5, 9.5, 9.5, 9.5, 8.5, 8.5, 8.5,
8.5, 8.5, 8.5, 9, 9, 9, 9, 9, 4, 8.5, 8.5, 8.5, 8.5, 8.5,
8.5, 8, 16, 16, 16, 16, 16, 12, 9, 9, 9, 9, 9, 9.5, 9.5,
9.5, 9.5, 9.5, 10, 10, 10, 10, 10, 9, 9, 9, 9, 9, 8, 10.5,
10.5, 10.5, 10.5, 10.5, 10, 11.5, 11.5, 11.5, 10.5, 10.5,
4, 9, 9, 9, 9, 9, 9, 9.5, 9.5, 9.5, 9.5, 9.5, 3, 9.5, 9.5,
9.5, 9.5, 9.5, 3, 9.5, 9.5, 9.5, 9.5, 9.5, 9, 9, 9, 9, 9,
4, 10, 10, 10, 7.5, 10, 9.5, 9.5, 9.5, 9.5, 9.5, 9.5, 9.5,
9.5, 7.5, 9.5, 2.5, 9, 9, 9, 9, 9, 10, 10, 10, 10, 10, 9.5,
9.5, 9.5, 9.5, 9.5, 3, 10.5, 10.5, 10.5, 10.5, 10.5, 9, 9,
9, 9, 9, 6, 13.5, 13.5, 13.5, 13.5, 13.5, 13.5, 9.5, 9.5,
9.5, 4.5, 9.5, 9.5, 9.5, 9.5, 9.5, 9.5, 4, 9.5, 9.5, 9.5,
9.5, 9.5, 3, 9, 9, 9, 9, 9, 4, 10, 10, 10, 10, 10, 4, 9.75,
9.75, 9.75, 9.75, 9.75, 4, 9.75, 9.75, 9.75, 9.75, 9.75,
9.25, 9.25, 9.25, 4, 9.25, 9.5, 9.5, 9.5, 3.5, 9.5, 9.5,
9.5, 9.5, 9.5, 9.5, 9.75, 9.75, 9.75, 4.5, 9.75, 9, 9, 9,
9, 9, 4, 9.25, 9.25, 9.25, 9.25, 9.25, 2.5, 12, 10.5, 10.5,
10.5, 10.5, 9.75, 9.75, 9.75, 9.75, 9.75, 10, 10, 10, 10,
10, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 10, 10, 10, 10, 10, 6,
14.5, 14.5, 14.5, 14.5, 14.5, 14.5, 6, 12, 12, 12, 12, 12,
12, 6, 12, 12, 12, 12, 12, 12, 6, 14.5, 14.5, 14.5, 14.5,
14.5, 14.5, 6, 12, 12, 12, 12, 12, 12, 9.25, 9.25, 9.25,
9.25, 9.25, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 6, 9, 9, 9, 9,
9, 9.5, 9.5, 9.5, 9.5, 9.5, 10, 10, 10, 10, 10, 6, 10.75,
10.75, 10.75, 10.75, 10.75, 10, 10.75, 10.75, 10.75, 10.75,
10.75, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 4, 10, 10, 10, 10, 10,
9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 4, 9, 9, 9, 9, 9, 9, 9, 9,
9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 10, 10, 10, 10, 10, 5,
9, 9, 9, 9, 9, 5, 10, 10, 10, 10, 10, 9, 9, 9, 9, 9, 9, 9,
9, 9, 9, 9.5, 9.5, 9.5, 9.5, 9.5, 9, 9, 4, 9, 9, 9, 9, 9,
9, 9, 10, 10, 10, 10, 10, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9,
9, 9, 9, 9, 4, 9, 9, 9, 9, 9, 6, 14.5, 14.5, 14.5, 14.5,
14.5, 14.5, 6, 14.5, 14.5, 14.5, 14.5, 14.5, 14.5, 6, 14.5,
14.5, 14.5, 14.5, 14.5, 14.5, 6, 12, 12, 12, 12, 12, 12,
6, 12.5, 12.5, 12.5, 12.5, 12.5, 12, 6, 14, 14, 14, 14, 14,
14, 6, 12, 12, 12, 12, 12, 12, 6, 14.5, 14.5, 14.5, 14.5,
14.5, 14.5, 6, 4, 4, 4, 4, 4, 3, 9.75, 9.75, 9.75, 9.75,
9.75, 3.5, 9, 9, 9, 9, 9, 9.5, 9.5, 9.5, 9.5, 9.5, 9.5, 9.5,
9.5, 9.5, 9.5, 9.75, 9.75, 9.75, 9.75, 9.75, 9, 9, 9, 9,
9, 9.5, 9.5, 9.5, 9.5, 9.5, 10, 10, 10, 10, 10, 4, 9, 9,
9, 9, 9, 9, 9, 9, 9, 9, 9.5, 9.5, 9.5, 9.5, 9.5, 11, 11,
11, 11, 11, 9.75, 9.75, 9.75, 9.75, 9.75, 10, 10, 10, 10,
10, 4, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 10, 10, 10, 10, 10,
10, 8, 9, 9, 9, 9, 9, 4, 9, 9, 9, 9, 9, 13.75, 14.5, 14.5,
14.5, 14.5, 14.5, 13.75, 4, 9.5, 9.5, 9.5, 9.5, 9.5, 8.5,
9.5, 9.5, 9.5, 9.5, 9.5, 8, 9.5, 9.5, 9.5, 9.5, 9.5, 8, 9.5,
9.5, 9.5, 9.5, 9.5, 8.5, 8.5, 8.5, 8.5, 8.5, 8.5, 8.5, 9,
9, 9, 9, 9, 8.5, 5, 14, 14, 14, 14, 14, 12, 10.5, 10.5, 10.5,
10.5, 10.5, 4, 10.5, 10.5, 10.5, 10.5, 10.5, 9, 9, 9, 9,
9, 8.5, 9, 9, 9, 9, 9, 8.5, 10, 10, 10, 10, 10, 3, 9, 9,
9, 9, 9, 8, 9, 9, 11, 11, 11, 8, 9, 9, 9, 9, 9, 8.5, 9, 9,
9, 9, 9, 4, 9, 9, 9, 9, 9, 8.5, 9, 9, 9, 9, 9, 4, 9, 9, 9,
9, 9, 9, 5, 9, 9, 12, 12, 12, 8.5, 9, 9, 9, 9, 9, 4, 8.5,
8.5, 8.5, 8.5, 8.5, 4, 8.5, 8.5, 8.5, 8.5, 8.5, 8.5, 8.5,
8.5, 8.5, 8.5, 8.5, 4, 9.5, 9.5, 9.5, 9.5, 9.5, 4, 3, 11,
11, 11, 11, 11, 9, 9.5, 9.5, 9.5, 9.5, 9.5, 5, 9, 9, 9, 9,
9, 8.5, 8.5, 8.5, 8.5, 8.5, 8.5, 4, 8.5, 8.5, 8.5, 8.5, 8.5,
8, 8.5, 8.5, 8.5, 8.5, 8.5, 7.5, 9.5, 9.5, 9.5, 9.5, 9.5,
4, 9.5, 9.5, 9.5, 9.5, 9.5, 8, 8.5, 8.5, 8.5, 8.5, 8.5, 8.5,
4, 9.5, 9.5, 9.5, 9.5, 9.5, 8.5, 9, 9, 9, 9, 9, 8.5, 6, 12.5,
12.5, 12.5, 12.5, 12.5, 11.5, 6, 11.5, 11.5, 11.5, 11.5,
11.5, 12, 6, 12, 12, 12, 12, 12, 12, 6, 12, 12, 12, 13, 13,
12, 6, 12, 12, 12, 12, 12, 12, 6, 15.5, 15.5, 15.5, 15.5,
15.5, 15.5, 9.5, 9.5, 9.5, 9.5, 9.5, 4, 10, 10, 10, 10, 10,
4, 10, 10, 10, 10, 10, 8, 9.5, 9.5, 9.5, 9.5, 9.5, 4, 9,
9, 9, 9, 9, 8, 9.5, 9.5, 9.5, 9.5, 9.5, 8, 9.5, 9.5, 9.5,
9.5, 9.5, 3, 9, 9, 9, 9, 9, 7, 4, 9.5, 9.5, 9.5, 9.5, 9.5,
8.5, 13, 12.5, 12.5, 12.5, 12.5, 12.5, 13, 9.5, 9.5, 9.5,
9.5, 9.5, 8, 9, 9, 9, 9, 9, 8.5, 10.5, 10.5, 10.5, 10.5,
10.5, 9.5, 9.5, 9.5, 9.5, 9.5, 8, 10.5, 10.5, 10.5, 10.5,
10.5, 8, 9, 9, 9, 9, 9, 4, 10, 10, 10, 10, 10, 8, 10, 10,
10, 10, 10, 8, 9.5, 9.5, 9.5, 9.5, 9.5, 4, 9.5, 9.5, 9.5,
9, 9.5, 4, 10, 10, 10, 10, 10, 8, 10, 11, 10, 10, 10, 10,
10, 10, 10, 10, 9.5, 9.5, 9.5, 9.5, 9.5, 4, 10.5, 10.5, 10.5,
10.5, 10.5, 8, 10.25, 10.25, 10.25, 10.25, 10.25, 9.5, 9.5,
9.5, 9.5, 9.5, 10, 10, 10, 10, 10, 4, 9.5, 9.5, 9.5, 9, 9.5,
4, 10, 10, 10, 10, 10, 4, 10, 10, 10, 10, 10, 8.5, 9, 9,
9, 9, 9, 4, 6, 14.5, 14.5, 14.5, 14.5, 14.5, 14.5, 6, 16,
16, 16, 16, 16, 15, 6, 14.5, 14.5, 14.5, 14.5, 14.5, 14.5,
6, 14.5, 14.5, 14.5, 14.5, 14.5, 14.5, 6, 14.5, 14.5, 14.5,
14.5, 14.5, 14.5, 6, 13.5, 13.5, 13.5, 13.5, 13.5, 13.5,
6, 4, 4, 4, 4, 4, 3, 9.5, 9.5, 9.5, 9.5, 9.5, 8, 9, 9, 9,
9, 9, 8.5, 9.5, 9.5, 9.5, 9.5, 9.5, 4, 9, 9, 9, 9, 9, 4,
9.5, 9.5, 9.5, 9.5, 9.5, 4, 9, 9, 9, 9, 9, 4, 10.5, 10.5,
10.5, 10.5, 10.5, 8.5, 9.75, 9.75, 9.75, 9.75, 9.75, 4, 10,
10, 10, 10, 10, 9, 9, 9, 9, 9, 8, 9, 9, 9, 9, 9, 10, 10,
10, 10, 10, 8.5, 9.5, 9.5, 9.5, 9.5, 9.5, 9.25, 9.25, 9.25,
9.25, 9.25, 4, 9, 9, 9, 9, 9, 9.5, 9.5, 9.5, 9.5, 9.5, 13,
14.5, 14.5, 14.5, 14.5, 14.5, 14.5, 10, 10, 10, 10, 10, 13,
14.5, 14.5, 14.5, 14.5, 14.5, 14.5, 10, 10, 10, 10, 10, 9,
10, 10, 10, 10, 10, 4, 9.5, 9.5, 9.5, 9.5, 9.5, 8.5, 9.5,
9.5, 9.5, 9.5, 9.5, 3, 9.5, 9.5, 9.5, 9.5, 9.5, 8.25, 10,
10, 10, 10, 10, 4, 9.5, 9.5, 9.5, 9.5, 9.5, 8.5, 9.5, 9.5,
9.5, 9.5, 9.5, 8.5, 9.75, 9.75, 9.75, 9.75, 9.75, 4, 9, 9,
9, 9, 9, 4, 9.5, 9.5, 9.5, 9.5, 9.5, 4, 6, 14.5, 14.5, 14.5,
14.5, 14.5, 14.5, 6, 14.5, 14.5, 14.5, 14.5, 14.5, 14.5,
6, 12, 12, 12, 12, 12, 12, 6, 14.5, 14.5, 14.5, 14.5, 14.5,
14.5, 6, 14, 14, 14, 14, 14, 14, 6, 14.5, 14.5, 14.5, 14.5,
14.5, 14.5, 6, 14.5, 14.5, 14.5, 14.5, 14.5, 14.5, 9, 9,
9, 9, 9, 7, 6, 9.5, 9.5, 9.5, 10.5, 10.5, 8, 8.5, 8.5, 8.5,
8.5, 8.5, 8.5, 10, 10, 10, 10, 10, 9.5, 9.5, 9.5, 9.5, 9.5,
3, 9.5, 9.5, 9.5, 9.5, 9.5, 4, 9, 9, 9, 9, 9, 8, 9.5, 9.25,
9.25, 9.25, 9.5, 8.5, 10, 10, 10, 10, 10, 10, 10, 10, 10,
10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 9, 9, 9, 9, 9,
4, 10, 10, 10, 10, 10, 8.5, 8.5, 8.5, 8.5, 8.5, 10, 10, 10,
10, 10, 9.5, 9.5, 9.5, 9.5, 9.5, 9, 9, 9, 9, 9, 8.5, 10,
10, 10, 10, 10, 8.5, 10.25, 10.25, 10.25, 10.25, 10.25, 4,
9, 9, 9, 9, 9, 5, 9.75, 9.75, 9.75, 9.75, 9.75, 4, 9, 9,
9, 9, 9, 8.5, 9, 9, 9, 9, 9, 8, 10, 10, 10, 10, 10, 9.5,
9.5, 9.5, 9.5, 9.5, 8.5, 9.75, 9.75, 9.75, 9.75, 9.75, 4,
8.5, 8.5, 8.5, 8.5, 8.5, 8.5, 10, 10, 10, 10, 10, 9.5, 9.5,
9.5, 9.5, 9.5, 4, 10, 10, 10, 10, 10, 4, 9.5, 9.5, 9.5, 9.5,
9.5, 8, 10, 10, 10, 10, 10, 6, 12, 12, 12, 12, 12, 12, 6,
14.5, 14.5, 14.5, 14.5, 14.5, 14.5, 6, 12, 12, 12, 12, 12,
11, 6, 16, 16, 16, 16, 16, 15, 6, 12, 12, 12, 12, 12, 12,
6, 12, 12, 12, 12, 12, 11, 6, 16, 16, 16, 16, 16, 15, 10.25,
10.25, 10.25, 10.25, 10.25, 4, 10.5, 10.5, 9.5, 9.5, 9.5,
4, 10, 10, 10, 10, 10, 4, 9, 9, 9, 9, 9, 8, 9, 9, 9, 9, 9,
4, 8, 15.5, 15.5, 15.5, 15.5, 15.5, 14.5, 9.5, 9.5, 9.5,
9.5, 9.5, 9.5, 9.5, 9.5, 9.5, 9.5, 10, 10, 10, 10, 10, 9,
9, 9, 9, 9, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 8.5,
9.5, 9.5, 9.5, 9.5, 9.5, 9.5, 9.5, 9.5, 9.5, 9.5, 4.5, 10,
10, 10, 10, 10, 8.5, 9, 9, 9, 9, 9, 4, 10.5, 10.5, 10.5,
10.5, 10.5, 8.5, 8.5, 8.5, 8.5, 8.5, 8, 9, 9, 9, 9, 9, 8,
10.5, 10.5, 10.5, 12, 10.5, 10, 10.5, 10, 10.5, 10, 10, 10,
10, 10.5, 10, 9.5, 9.5, 9.5, 9.5, 9.5, 8, 10, 10, 10, 10,
10, 10.5, 10.5, 10.5, 10.5, 10.5, 8, 9, 9, 9, 9, 9, 8, 10,
10, 10, 10, 10, 3.5, 10, 10, 10, 10, 10, 8, 10, 10, 10, 10,
10, 4, 10, 10, 10, 10, 10, 5, 9, 9, 9, 9, 9, 8.5, 9.5, 9.5,
9.5, 9.5, 9.5, 8, 10, 10, 10, 10, 10, 10.75, 10.75, 10.75,
11.75, 10.75, 9.5, 9.5, 9.5, 9.5, 9.5, 4, 6, 14.5, 14.5,
14.5, 14.5, 14.5, 14.5, 6, 14.5, 14.5, 14.5, 14.5, 14.5,
14.5, 6, 14.5, 14.5, 14.5, 14.5, 14.5, 14.5, 6, 12, 12, 12,
13, 13, 12, 6, 14.5, 14.5, 14.5, 14.5, 14.5, 14.5, 10.5,
10.5, 10.5, 10.5, 10.5, 8.5, 10, 10, 10, 10, 10, 4, 10.75,
9.75, 10, 9.75, 9.75, 9.5, 9.5, 9.5, 9.5, 9.5, 8, 9.5, 9.5,
9.5, 9.5, 9.5, 8.5, 10.5, 10.5, 8.5, 10.5, 10.5, 10, 10,
10, 10, 10, 10, 10, 10, 10, 10, 8.5, 10, 10, 10, 10, 10,
8.5, 11.5, 11.5, 11.5, 11.5, 11.5, 10, 10, 10, 10, 10, 8.5,
10, 10, 10, 10, 10, 4, 10, 10, 10, 10, 10, 9, 9, 9, 9, 9,
8.5, 8.5, 8.5, 8.5, 8.5, 8.5, 10, 10, 10, 10, 10, 9, 9, 9,
8, 9, 9.5, 9.5, 9.5, 9.5, 9.5, 12, 13, 13, 13, 13, 13, 13,
10.5, 10.5, 10, 10.5, 10.5, 9, 9, 9, 9, 9, 4, 10, 10, 10,
10, 10, 8.5, 10, 10, 10, 10, 10, 8.5, 10, 10, 10, 10, 10,
3, 10, 10, 10, 10, 10, 4, 10.5, 10.5, 10.5, 11.5, 10.5, 10,
10, 10, 10, 10, 10, 10, 10.5, 10.5, 10, 8.5, 10.5, 10.5,
10.5, 10.5, 10.5, 4, 6, 14.5, 14.5, 14.5, 14.5, 14.5, 14.5,
6, 12, 12, 12, 12, 12, 12, 6, 14.5, 14.5, 14.5, 14.5, 14.5,
14.5, 6, 13, 13, 13, 13, 13, 13, 6, 14.5, 14.5, 14.5, 14.5,
14.5, 14.5, 9.75, 9.5, 9.75, 9.5, 9.75, 4, 11.25, 9.75, 9.75,
9.75, 9.75, 11.5, 10, 10, 10, 10, 10, 15, 15, 15, 15, 15,
15, 10, 10, 10, 10, 10, 9.5, 9.5, 9.5, 9.5, 9.5, 4, 10.5,
10.5, 10.5, 10.5, 10.5, 8.5, 13.5, 14.5, 14.5, 14.5, 14.5,
14.5, 14.5, 10, 10, 10, 11, 10, 8.5, 8.5, 8.5, 8.5, 8.5,
8.5, 8.5, 9.5, 9.5, 9.5, 9.5, 9.5, 8, 9, 9, 9, 9, 9, 4, 10,
10, 10, 10, 10, 10.5, 10.5, 10.5, 10, 10, 8.5, 9.5, 9.5,
9.5, 9.5, 9.5, 4, 10, 10, 10, 10, 10, 8.5, 9, 9, 9, 9, 9,
4, 9.5, 9.5, 9.5, 9.5, 9.5, 4, 7, 13, 13, 13, 13, 13, 13,
10.5, 11, 10.5, 10.5, 10.5, 4, 7, 11, 11, 11, 11, 11, 9,
9.5, 9.5, 9.5, 9.5, 9.5, 8.5, 9, 9, 9, 9, 9, 8.5, 11, 11,
11, 11, 11, 9, 7, 13, 13, 13, 13, 13, 13, 9.5, 9.5, 9.5,
9.5, 9.5, 8.5, 10, 10, 10, 10, 10, 9.5, 9.5, 9.5, 9.5, 9.5,
4, 9, 9, 9, 9, 9, 8.5, 9, 9, 9, 9, 9, 8.5, 9, 9, 9, 9, 9,
8.5, 9.5, 9.5, 9.5, 9.5, 9.5, 8.5, 9.5, 9.5, 9.5, 9.5, 9.5,
8, 10, 10, 10, 10, 10, 8.5, 9, 9, 9, 9, 9, 8.5, 9.5, 9.5,
9.5, 9.5, 9.5, 4, 9, 9, 9, 9, 9, 4, 6, 13, 13, 13, 13, 13,
12, 6, 14.5, 14.5, 14.5, 14.5, 14.5, 14.5, 6, 14.5, 14.5,
14.5, 14.5, 14.5, 14.5, 10, 10, 10, 10, 10, 9, 13, 14.5,
14.5, 14.5, 14.5, 14.5, 14.5, 10.5, 10.5, 10.5, 10.5, 10.5,
9.5, 9.5, 9.5, 9.5, 9.5, 8.5, 10, 10, 10, 10, 10, 3, 10,
10, 10, 10, 10, 10, 10, 10, 10, 10, 4, 9.75, 9.75, 9.75,
9.75, 9.75, 3, 10, 10, 10, 10, 10, 8.5, 10, 10, 10, 10, 10,
8, 9, 9, 9, 9, 9, 4, 9.5, 9.5, 9.5, 9.5, 9.5, 8, 9, 9, 9,
9, 9, 4, 10, 10, 10, 10, 10, 4, 9, 9, 9, 9, 9, 8, 9.5, 9.5,
9.5, 9.5, 9.5, 4, 12, 12, 12, 12, 12, 12, 12, 9.5, 9.5, 9.5,
9.5, 9.5, 4, 10, 10, 10, 8, 10, 8, 10, 10, 10, 10, 10, 9,
9, 9, 9, 9, 8.5, 10.5, 10.5, 10.5, 10.5, 10.5, 4, 10.5, 10.5,
10.5, 10.5, 10.5, 10, 10, 10, 10, 10, 9.5, 9.5, 9.5, 9.5,
9.5, 4, 9.5, 9.5, 9.5, 9.5, 9.5, 9.5, 9.5, 9.5, 9.5, 9.5,
8, 9, 9, 9, 9, 9, 8, 6, 12, 12, 12, 12, 12, 12, 6, 14.5,
14.5, 14.5, 14.5, 14.5, 14.5, 6, 12.5, 12.5, 12.5, 12.5,
12.5, 12, 6, 14.5, 14.5, 14.5, 14.5, 14.5, 14.5, 6, 14.5,
14.5, 14.5, 14.5, 14.5, 14.5, 9.5, 9.5, 9.5, 9.5, 9.5, 9,
9, 9, 9, 9, 10, 10, 10, 10, 10, 3.5, 8.5, 8.5, 8.5, 8.5,
4, 9, 9, 9, 8.5, 9, 4, 9.5, 9.5, 9.5, 9.5, 9.5, 4, 9.5, 9.5,
8.5)), row.names = c(NA, -8658L), class = "data.frame")
Any help/guidance will be grateful
Many thanks
Maybe this tidyverse solution is close to what you want. But I am no sure where Hours variable comes. You can reshape your data to wide and then merge. Here the code, as days are present in both dataframes you can directly merge like this:
library(tidyverse)
#Code
#First reshape df2
merged <- df1 %>% select(StoreNumber,Online,Pressure) %>%
left_join(
df2 %>% pivot_wider(names_from = Day,values_from=Time),
by = c('StoreNumber'='BranchNumber'))
#Replace zeroes
merged <- merged %>% replace(is.na(.),0)
Output:
StoreNumber Online Pressure MON TUE WED
1 1 0.2 50 7.5 6 8.5
2 2 0.8 20 0.0 0 0.0
3 3 1.2 10 2.0 1 2.5
Some data used:
#Data 1
df1 <- structure(list(StoreNumber = 1:3, Online = c(0.2, 0.8, 1.2),
Pressure = c(50L, 20L, 10L), MON = c(0L, 0L, 0L), TUE = c(0L,
0L, 0L), WED = c(0L, 0L, 0L), SUN = c(0L, 0L, 0L)), class = "data.frame", row.names = c(NA,
-3L))
#Data 2
df2 <- structure(list(BranchNumber = c(1L, 1L, 1L, 3L, 3L, 3L), Day = c("MON",
"TUE", "WED", "MON", "TUE", "WED"), Time = c(7.5, 6, 8.5, 2,
1, 2.5)), class = "data.frame", row.names = c(NA, -6L))
Using glue_sql and DBI::dbExecute can I update set by joining a sql table to a local df?
I would like to update a table in a database within r:
library(tidyverse)
library(dbplyr)
library(DBI)
library(glue)
# create a table with empty field to be updated later
# id field is now 'id'
my_mtcars <- mtcars %>%
rownames_to_column() %>%
rename(id = rowname) %>%
mutate(newfield = NA)
# create a temp db
mtcars_db <- tbl_memdb(my_mtcars)
con <- src_memdb()$con
# query
my_query <- glue_sql("select * from my_mtcars", con = con)
my_initial_data <- dbGetQuery(con, my_query)
Variable my_initial_data is now a dataframe that I got from memdb. It looks like this:
my_initial_data %>% glimpse
Observations: 32
Variables: 13
$ id <chr> "Mazda RX4", "Mazda RX4 Wag", "Datsun 710", "Hornet 4 Drive", "Hornet Sportabout", "Valiant", "Duster 360", "Merc 24…
$ mpg <dbl> 21.0, 21.0, 22.8, 21.4, 18.7, 18.1, 14.3, 24.4, 22.8, 19.2, 17.8, 16.4, 17.3, 15.2, 10.4, 10.4, 14.7, 32.4, 30.4, 33…
$ cyl <dbl> 6, 6, 4, 6, 8, 6, 8, 4, 4, 6, 6, 8, 8, 8, 8, 8, 8, 4, 4, 4, 4, 8, 8, 8, 8, 4, 4, 4, 8, 6, 8, 4
$ disp <dbl> 160.0, 160.0, 108.0, 258.0, 360.0, 225.0, 360.0, 146.7, 140.8, 167.6, 167.6, 275.8, 275.8, 275.8, 472.0, 460.0, 440.…
$ hp <dbl> 110, 110, 93, 110, 175, 105, 245, 62, 95, 123, 123, 180, 180, 180, 205, 215, 230, 66, 52, 65, 97, 150, 150, 245, 175…
$ drat <dbl> 3.90, 3.90, 3.85, 3.08, 3.15, 2.76, 3.21, 3.69, 3.92, 3.92, 3.92, 3.07, 3.07, 3.07, 2.93, 3.00, 3.23, 4.08, 4.93, 4.…
$ wt <dbl> 2.620, 2.875, 2.320, 3.215, 3.440, 3.460, 3.570, 3.190, 3.150, 3.440, 3.440, 4.070, 3.730, 3.780, 5.250, 5.424, 5.34…
$ qsec <dbl> 16.46, 17.02, 18.61, 19.44, 17.02, 20.22, 15.84, 20.00, 22.90, 18.30, 18.90, 17.40, 17.60, 18.00, 17.98, 17.82, 17.4…
$ vs <dbl> 0, 0, 1, 1, 0, 1, 0, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 1
$ am <dbl> 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1
$ gear <dbl> 4, 4, 4, 3, 3, 3, 3, 4, 4, 4, 4, 3, 3, 3, 3, 3, 3, 4, 4, 4, 3, 3, 3, 3, 3, 4, 5, 5, 5, 5, 5, 4
$ carb <dbl> 4, 4, 1, 1, 2, 1, 4, 2, 2, 4, 4, 3, 3, 3, 4, 4, 4, 1, 2, 1, 1, 2, 2, 4, 2, 1, 2, 2, 4, 6, 8, 2
$ newfield <int> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, …
What I would like to do is update the field newfield with values in a local data frame. Is this possible? e.g.
# would like to do something like this:
# (note how I'm joining as local df with one in the db)
my_new_mtcars <- my_mtcars %>% mutate(newfield = 1:nrow(.)) # now newfield is a sequence of numbers
my_update_query <- glue_sql("update my_mtcars
join my_new_mtcars on my_new_mtcars.id = my_mtcars.id
set my_mtcars.newfield = my_new_mtcars.newfield")
Query looks good I think?
my_update_query
<SQL> update my_mtcars
join my_new_mtcars on my_new_mtcars.id = my_mtcars.id
set my_mtcars.newfield = my_new_mtcars.newfield
However, when I try I get an error:
dbExecute(conn = con, statement = my_update_query)
Error: near "join": syntax error
mutate_at & vars: Can I tell r / dplyr to overwrite existing features instead of creating new ones?
[If downvoting feedback would be helpful so I can try to update the post.] library(tidyverse) example_mtcars <- mtcars %>% mutate_at(vars(disp, wt, qsec), funs(as.character(.))) example_mtcars$disp[c(2,4,8)] <- "NULL" example_mtcars$wt[c(10, 12)] <- "NULL" example_mtcars$qsec[c(2,3,4)] <- "NULL" processed_mtcars <- example_mtcars %>% mutate_at(vars(c(disp, wt:qsec)), funs(str_replace(., "NULL", "0"), as.numeric)) The new data frame processed_mtcars has new features where I would like the feature names to be the exact same as example_mtcars but with the transformations applied. > glimpse(processed_mtcars) Observations: 32 Variables: 17 $ mpg <dbl> 21.0, 21.0, 22.8, 21.4, 18.7, 18.1, 14.3, 24.4, 22.8, 19.2, 17.8, 16.4, 17.3, 15.2, 10.4, 10.4, ... $ cyl <dbl> 6, 6, 4, 6, 8, 6, 8, 4, 4, 6, 6, 8, 8, 8, 8, 8, 8, 4, 4, 4, 4, 8, 8, 8, 8, 4, 4, 4, 8, 6, 8, 4 $ disp <chr> "160", "NULL", "108", "NULL", "360", "225", "360", "NULL", "140.8", "167.6", "167.6", "275.8", "... $ hp <dbl> 110, 110, 93, 110, 175, 105, 245, 62, 95, 123, 123, 180, 180, 180, 205, 215, 230, 66, 52, 65, 97... $ drat <dbl> 3.90, 3.90, 3.85, 3.08, 3.15, 2.76, 3.21, 3.69, 3.92, 3.92, 3.92, 3.07, 3.07, 3.07, 2.93, 3.00, ... $ wt <chr> "2.62", "2.875", "2.32", "3.215", "3.44", "3.46", "3.57", "3.19", "3.15", "NULL", "3.44", "NULL"... $ qsec <chr> "16.46", "NULL", "NULL", "NULL", "17.02", "20.22", "15.84", "20", "22.9", "18.3", "18.9", "17.4"... $ vs <dbl> 0, 0, 1, 1, 0, 1, 0, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 1 $ am <dbl> 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1 $ gear <dbl> 4, 4, 4, 3, 3, 3, 3, 4, 4, 4, 4, 3, 3, 3, 3, 3, 3, 4, 4, 4, 3, 3, 3, 3, 3, 4, 5, 5, 5, 5, 5, 4 $ carb <dbl> 4, 4, 1, 1, 2, 1, 4, 2, 2, 4, 4, 3, 3, 3, 4, 4, 4, 1, 2, 1, 1, 2, 2, 4, 2, 1, 2, 2, 4, 6, 8, 2 $ disp_str_replace <chr> "160", "0", "108", "0", "360", "225", "360", "0", "140.8", "167.6", "167.6", "275.8", "275.8", "... $ wt_str_replace <chr> "2.62", "2.875", "2.32", "3.215", "3.44", "3.46", "3.57", "3.19", "3.15", "0", "3.44", "0", "3.7... $ qsec_str_replace <chr> "16.46", "0", "0", "0", "17.02", "20.22", "15.84", "20", "22.9", "18.3", "18.9", "17.4", "17.6",... $ disp_as.numeric <dbl> 160.0, NA, 108.0, NA, 360.0, 225.0, 360.0, NA, 140.8, 167.6, 167.6, 275.8, 275.8, 275.8, 472.0, ... $ wt_as.numeric <dbl> 2.620, 2.875, 2.320, 3.215, 3.440, 3.460, 3.570, 3.190, 3.150, NA, 3.440, NA, 3.730, 3.780, 5.25... $ qsec_as.numeric <dbl> 16.46, NA, NA, NA, 17.02, 20.22, 15.84, 20.00, 22.90, 18.30, 18.90, 17.40, 17.60, 18.00, 17.98, ... Example the second function to funs is as.numeric. However it's referencing the original, untransformed features not the ones where "NULL" has just been replaced with "0". So there are multiple NA values.
Perhaps one of the following is what you're after: example_mtcars %>% mutate_at( vars(c(disp, wt:qsec)), funs(str_replace(., "NULL", "0") %>% as.numeric) ) or this: example_mtcars %>% mutate_at( vars(c(disp, wt:qsec)), funs(str_replace(., "NULL", NA_character_) %>% as.numeric) )
How to set to 0 all values that appeares less than k times in variables within nested df
library(tidyverse)
ex <- structure(list(group = c("Group A", "Group B", "Group C"), data = list(
structure(list(a = c(25.1, 15.1, 28.7, 29.7, 5.3, 3.4, 5.3,
10.1, 2.4, 18, 4.7, 22.1, 9.5, 3.1, 26.5, 5.1, 24, 22.5,
19.4, 22.9, 24.5, 18.2, 7.9, 5.3, 24.7), b = c(95.1, 51,
100, 94.1, 47.3, 0, 50.7, 45.8, 40.7, 49.4, 51.9, 76.4, 26.7,
19.8, 37.4, 59.4, 59.1, 60.2, 26.1, 2.8, 100, 40.7, 56.4,
42.5, 0), c = c(39.9, 42.7, 16.3, 11.1, 56.9, 17.8, 62, 28.1,
43, 44.8, 54.8, 8.7, 5.5, 40.2, 7.7, 60.7, 24.8, 7.5, 3.5,
16.9, 31.6, 45.8, 76.7, 58.6, 15.8), d = c(-2.39999999999999,
28.6, -4.59999999999999, -1.39999999999999, 10.3, 3.1, 23.4,
-43, -36.3, 32.4, 33.1, 9.8, 1.5, -17.6, 16.6, 20.9, 7.8,
-1.7, -23.3, 0, -15, 59.3, -40.2, 46.9, 4.7)), .Names = c("a",
"b", "c", "d"), row.names = c(NA, -25L), class = c("tbl_df",
"tbl", "data.frame")), structure(list(a = c(5, 4.7, 30.3,
14.3, 31.6, 6, 4.9, 23.3, 26.9, 16.9, 27.2, 23.8, 19.9, 28.6,
9.9, 17.4, 14.3, 12.5, 30.4, 30.3, 30, 6, 18, 23.7, 5.1),
b = c(48.9, 41.3, 20.1, 63.7, 85.1, 30.3, 52.8, 49.7,
27.1, 51.6, 21.8, 52.4, 52.5, 59.6, 13.7, 53.1, 69, 66.9,
23.4, 35.4, 45.8, 23.7, 62.9, 90.3, 59.6), c = c(37.4,
18.5, 64.6, 13.5, 7.8, 6.8, 12.7, 8.5, 7.8, 5.4, 14.1,
20.5, 10.9, 10.5, 7.5, 14.7, 6.9, 0.699999999999999,
4.7, 1.9, 11.9, 0.9, 7.2, 9.2, 42.2), d = c(4.9, -3.7,
13.5, 21.9, -2.69999999999999, 6.6, 0.5, -12.3, 38.7,
-25.8, -18, 28.4, 38.3, -3.6, 39.4, 19, 23.4, -38.7,
17, 36.3, -31.7, -9.3, -10.5, 9.7, -10.6)), .Names = c("a",
"b", "c", "d"), row.names = c(NA, -25L), class = c("tbl_df",
"tbl", "data.frame")), structure(list(a = c(29.9, 12.8, 23.9,
26.2, 27.5, 32.6, 33.2, 24.8, 29, 22.6, 4.7, 25.6, 4.7, 13.1,
25.9, 14.5, 23.5, 26.6, 12.8, 24.1, 9.1, 31.9, 24.8, 4.6,
17.9), b = c(63.7, 23.3, 71.2, 46.7, 30.6, 49.3, 14.6, 68.4,
27.9, 49.1, 60.5, 26.4, 56.9, 55.4, 37.9, 40.7, 32.7, 68.5,
42.7, 27.9, 67.5, 43.4, 76.6, 53.3, 26.8), c = c(1.6, 32,
18.6, 14, 0.5, 7.2, 27.3, 8.9, 11, 15.5, 16.7, 16.4, 63.1,
14.7, 6.8, 9, 3.1, 11.7, 11, 11.5, 10.6, 14.9, 7.1, 13.2,
5.1), d = c(-35.4, 21, 12, 1.8, 37.6, 9.2, 17.6, 0, -19.4,
32.6, -32, -3.6, 7.2, -25.7, 9.1, -8, 35.8, 24.8, -13.9,
-21.7, -28.7, 0.200000000000003, -16.9, -26.5, 26.2)), .Names = c("a",
"b", "c", "d"), row.names = c(NA, -25L), class = c("tbl_df",
"tbl", "data.frame"))), h_candidates = list(structure(c(0.17320508075689, 2.37782856461527, 2.94890646051978, 3.35205778704499, 3.66771041547043, 3.95224618679369), .Names = c("0%", "0.01%", "0.02%", "0.03%", "0.04%", "0.05%")), structure(c(0.316227766016836, 2.63452963884554, 3.2327619513522, 3.63593179253957, 3.97743636027027, 4.22137418384109), .Names = c("0%", "0.01%", "0.02%", "0.03%", "0.04%", "0.05%")), structure(c(0.316227766016837, 2.7258026340878, 3.24807635378234, 3.62353418639869, 3.92683078321437, 4.17731971484109), .Names = c("0%", "0.01%", "0.02%", "0.03%", "0.04%", "0.05%"))), assignment = list(
structure(list(`0%` = c(1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11,
12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25),
`0.01%` = c(1, 2, 3, 3, 4, 5, 4, 6, 7, 8, 9, 10, 11,
12, 13, 4, 14, 15, 16, 17, 18, 19, 20, 21, 17), `0.02%` = c(1,
2, 3, 3, 4, 5, 4, 6, 7, 8, 9, 10, 11, 12, 13, 4, 14,
15, 16, 17, 18, 19, 20, 21, 17), `0.03%` = c(1, 2, 3,
3, 4, 5, 4, 6, 7, 8, 9, 10, 11, 12, 13, 4, 10, 14, 15,
16, 17, 18, 19, 9, 16), `0.04%` = c(1, 2, 3, 4, 5, 6,
5, 7, 8, 9, 10, 11, 12, 13, 14, 5, 11, 15, 16, 17, 18,
19, 20, 10, 17)), .Names = c("0%", "0.01%", "0.02%",
"0.03%", "0.04%"), row.names = c(NA, -25L), class = c("tbl_df",
"tbl", "data.frame")), structure(list(`0%` = c(1, 2, 3, 4,
5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20,
21, 22, 23, 24, 25), `0.01%` = c(1, 2, 3, 4, 5, 6, 7, 8,
9, 10, 11, 12, 13, 14, 15, 16, 4, 17, 18, 19, 20, 21, 22,
23, 24), `0.02%` = c(1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12,
13, 14, 15, 13, 4, 16, 17, 9, 18, 19, 14, 20, 21), `0.03%` = c(1,
2, 3, 4, 5, 6, 2, 7, 8, 9, 10, 11, 12, 13, 14, 12, 4, 15,
6, 8, 16, 17, 13, 18, 19), `0.04%` = c(1, 2, 3, 4, 5, 6,
2, 7, 8, 9, 10, 11, 12, 13, 14, 12, 4, 15, 6, 8, 7, 16, 13,
17, 1)), .Names = c("0%", "0.01%", "0.02%", "0.03%", "0.04%"
), row.names = c(NA, -25L), class = c("tbl_df", "tbl", "data.frame"
)), structure(list(`0%` = c(1, 2, 3, 4, 5, 6, 7, 8, 9, 10,
11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25
), `0.01%` = c(1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13,
14, 12, 15, 16, 17, 15, 18, 19, 4, 20, 21, 22), `0.02%` = c(1,
2, 3, 4, 5, 6, 7, 8, 9, 5, 10, 11, 12, 13, 11, 14, 5, 15,
14, 16, 17, 18, 8, 19, 20), `0.03%` = c(1, 2, 3, 4, 5, 6,
7, 3, 8, 9, 10, 11, 12, 10, 11, 13, 5, 14, 13, 8, 10, 4,
3, 13, 6), `0.04%` = c(1, 2, 3, 4, 5, 5, 6, 3, 7, 8, 9, 10,
11, 9, 10, 12, 5, 13, 12, 7, 9, 4, 3, 12, 5)), .Names = c("0%",
"0.01%", "0.02%", "0.03%", "0.04%"), row.names = c(NA, -25L
), class = c("tbl_df", "tbl", "data.frame")))), .Names = c("group", "data", "h_candidates", "assignment"), class = c("tbl_df", "tbl", "data.frame"), row.names = c(NA, -3L))
With the data structured like above I would like to change all values within assignment data.frames that appears less than k times (let's say k = 5) in a column.
So I need a solution that takes subsequent data.frames, then subsequent columns within a data.frame, check which values appears less than 5 times in a column and if there are any just replace them with 0.
At best, the solution would involve tidyverse functions. I think that nested purrr::map, as well as dplyr::mutate are needed here, but don't know how to count appearances within a column and replace the values then.
You can use purrr::map() to loop over the list column with the dataframes,
and then purrr::modify() to loop over each column in each dataframe. Then
it's just a matter of defining a function that counts occurences of values in
a vector, and replaces them if the count is less than k:
library(tidyverse)
ex %>%
mutate(assignment = map(assignment, modify, function(x, k) {
n <- table(x)[as.character(x)]
replace(x, n < k, 0)
}, k = 5))
#> # A tibble: 3 x 4
#> group data h_candidates assignment
#> <chr> <list> <list> <list>
#> 1 Group A <tibble [25 x 4]> <dbl [6]> <tibble [25 x 5]>
#> 2 Group B <tibble [25 x 4]> <dbl [6]> <tibble [25 x 5]>
#> 3 Group C <tibble [25 x 4]> <dbl [6]> <tibble [25 x 5]>
We can also define a couple of helper functions to make this more readable:
# Replace elements in x given by f(x) with val
replace_if <- function(x, f, val, ...) {
replace(x, f(x, ...), val)
}
appears_less_than <- function(x, k) {
table(x)[as.character(x)] < k
}
Combining these two functions gets what we are after:
replace_if(c(1, 1, 2, 3), appears_less_than, k = 2, 0)
#> [1] 1 1 0 0
Now all that remains is to put the pieces together:
res <- ex %>%
mutate(assignment = map(assignment, modify, replace_if,
appears_less_than, k = 3, 0))
As #thothal mentioned, there aren't any values in your data that occur more
than 4 times in your data, but with k = 3 we can have a look at the result
(to illustrate, just the 3rd dataframe in assignment):
res %>% pluck("assignment", 3)
#> # A tibble: 25 x 5
#> `0%` `0.01%` `0.02%` `0.03%` `0.04%`
#> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 0 0 0 0 0
#> 2 0 0 0 0 0
#> 3 0 0 0 3 3
#> 4 0 0 0 0 0
#> 5 0 0 5 0 5
#> 6 0 0 0 0 5
#> 7 0 0 0 0 0
#> 8 0 0 0 3 3
#> 9 0 0 0 0 0
#> 10 0 0 5 0 0
#> # ... with 15 more rows
Finally, we could also use a scoped mutate_at() to further reduce some of
the excess syntax:
ex %>%
mutate_at(vars(assignment), map, modify,
replace_if, appears_less_than, k = 3, 0)
Created on 2018-08-08 by the reprex package (v0.2.0.9000).
This should do the trick: library(tidyverse) ex %>% mutate( assignment = map(assignment, ~ rowid_to_column(.x, "id") %>% gather(key, value, -id) %>% group_by(key) %>% add_count(value) %>% mutate(value = ifelse(n < 5, 0, n)) %>% select(-n) %>% spread(key, value) %>% select(-id) ) ) Note in your example there is no single value appearing more than 4 times. Explanation You map over all assignment data.frames For each data.frame you first add an id column (needed for gather/spread) Then you gather all columns butidinto akey(former column names)value` (the values) pair For each group of former columns (now in key) you add a counter of the values in value Then you replace occurrences which appear less than 5 times by 0 You remove n (the counter) spread the data back into the original format Remove the id column