R distinct() does not take out duplicates - r

I have been battling with this for a while now. As part of a large for-loop, want to take out some data points to be able to create concave hull around the resulting points (needs a minimum of 4 points). For this I have a line which makes sure that clusters where x or y values are ALL the same value are removed, as well as clusters with less than 4 lines. However, it can also happen that some points (not all) within a cluster are duplicates, causing the cluster to have >=4 lines, but the actual points are not >=4. To take out these duplicates I use distinct(), but sometimes this fails to take out the duplicates, as with the example data frame below. Any idea how to effectively take out these duplicates?
Example data
SP_occ <- structure(list(x = c(-28.212197, -130.758, -15, 47.549999, -29.346937,
-27.794644, -124.8, 47.416698, 47.75, -15.566667, 178.73, -29.344852,
175.432999, 47.75, 87, -10, 55.666668, 46.533, 47, 114.75, -29.356563,
87, 46, -128.296, -9, 154.21667, 47.549999, 47.549999, 87, -72.133301,
-157.89167, -23.055, 87, 46.366665, 55.45, 122.932999, -28.991,
153.216995, -29.35066, -29.122, 47.75, 123.967003, 121.5, 27.4167,
-27.96666, 47.266701, 87, 87, 47.583302, 114.75, -26.610647,
-26.589459, -10, 87, 122.949997, 47.583302, 125.400002, -15.533334,
-25.239904, 45.533, -28.295, 47.416698, 46, 52.0833, 87, 172.932999,
47.75, 5.4629, 121.667, 27.4167, -29.344852, -29.346937, -29.356563,
-9.387, -28.212197, -27.794644, 154.216667, -28.991, -28.991,
-29.35066, -25.239904, -26.610647, -26.589459, -27.96666, -15,
87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 52.0833, 45.533,
46.533, 114.75, -10, -15.533333, -15.566667, 178.73, -9.5, -9.466667,
-9.466667, -9.466667, -9.466667, -9.466667, -9.466667, -8.916667,
-8.916667, -9.083333, 152.756836, 138.74492, -9.321667, 5.4629,
139.416667, 55.666668), y = c(38.659904, -23.931, 55, -38.366699,
38.681605, 39.000465, -24.68, -38.349998, -38.650002, 28.183332,
-38.65, 38.68313, -28.1833, -38.650002, -27, 46, -4.582778, -39.033,
-9, -35, 38.671144, -27, -12, -24.328, 56, -20.85, -38.366699,
-38.9333, -27, 40.966702, 21.391684, 16.5667, -27, -9.416667,
-4.766666, 24.5, 42.497, -20.85, 37.997214, 42.432, -38.583302,
24.0667, -11, -33.3167, 38.962846, -38.950001, -27, -27, -38.966702,
-35, 40.341647, 40.357008, 46, -27, 24.299999, -38.966702, 24.5833,
28.266666, 37.900563, -40.416, 29.891666, -38.349998, -9, -36.5833,
-27, -28.5667, -38.583302, -26.1297, -11, -33.3167, 38.68313,
38.681605, 38.671144, 57.245, 38.659904, 39.000465, -20.85, 42.497,
42.497, 37.997214, 37.900563, 40.341647, 40.357008, 38.962846,
55, -27, -27, -27, -27, -27, -27, -27, -27, -27, -27, -27, -36.5833,
-40.416, -39.033, -35, 46, 28.266667, 28.183333, -38.65, 55.733333,
55.666667, 55.666667, 55.666667, 55.666667, 55.666667, 55.666667,
58.583333, 58.583333, 56.691667, -33.054223, 34.908889, 38.285,
-26.1297, 35.25, -4.582778), cluster = c(1L, 2L, 3L, 4L, 5L,
1L, 6L, 4L, 4L, 7L, 8L, 5L, 9L, 4L, 10L, 11L, 12L, 13L, 14L,
15L, 5L, 10L, 16L, 17L, 18L, 19L, 4L, 4L, 10L, 20L, 21L, 22L,
10L, 23L, 12L, 24L, 25L, 26L, 27L, 25L, 4L, 28L, 29L, 30L, 1L,
4L, 10L, 10L, 4L, 15L, 31L, 31L, 11L, 10L, 24L, 4L, 32L, 7L,
33L, 34L, 35L, 4L, 36L, 37L, 10L, 38L, 4L, 39L, 29L, 30L, 5L,
5L, 5L, 40L, 1L, 1L, 19L, 25L, 25L, 27L, 33L, 31L, 31L, 1L, 3L,
10L, 10L, 10L, 10L, 10L, 10L, 10L, 10L, 10L, 10L, 10L, 37L, 34L,
13L, 15L, 11L, 7L, 7L, 8L, 41L, 41L, 41L, 41L, 41L, 41L, 41L,
42L, 42L, 43L, 44L, 45L, 46L, 39L, 47L, 12L)), row.names = c(1L,
2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 11L, 12L, 13L, 14L, 15L,
16L, 17L, 18L, 19L, 20L, 21L, 22L, 23L, 24L, 25L, 26L, 27L, 28L,
29L, 30L, 31L, 32L, 33L, 34L, 35L, 36L, 37L, 38L, 39L, 40L, 41L,
42L, 43L, 44L, 45L, 46L, 47L, 48L, 49L, 50L, 51L, 52L, 53L, 54L,
55L, 56L, 57L, 58L, 59L, 60L, 61L, 62L, 63L, 64L, 65L, 66L, 67L,
68L, 69L, 70L, 74L, 75L, 76L, 77L, 78L, 79L, 80L, 81L, 82L, 83L,
84L, 85L, 86L, 87L, 88L, 89L, 90L, 91L, 92L, 93L, 94L, 95L, 96L,
97L, 98L, 99L, 100L, 101L, 103L, 105L, 106L, 107L, 108L, 109L,
111L, 112L, 113L, 114L, 115L, 116L, 117L, 118L, 119L, 120L, 123L,
125L, 126L, 135L, 136L, 141L), class = "data.frame")
Code
SP_occ <- SP_occ %>% distinct()
SP_occ <- SP_occ %>% group_by(cluster) %>% filter(!(n_distinct(round(x, 6)) == 1 || n_distinct(round(y, 6)) == 1) && n() >= 4)
SP_occ <- SP_occ[SP_occ$cluster != 0,]
SP_occ$Cluster <- SP_occ %>% group_indices(cluster)
SP_occ <- SP_occ[, c(1,2,4)]


Could you explain which records in your example are the problem you are referring to? After using distinct() there are no remaining exact duplicates in your data. If you want to remove records that are 'almost' identical (very small numerical differences) you could consider doing
SP_occ <- SP_occ %>%
mutate(x = round(x,5),
y = round(y,5)) %>%
distinct()


The result that I get is the DF below. Cluster 2 is made up by 4 points, of which 2 are actually unique.
x y Cluster
1 47.55000 -38.36670 1
2 47.41670 -38.35000 1
3 47.75000 -38.65000 1
4 -15.56667 28.18333 2
5 47.55000 -38.93330 1
6 47.75000 -38.58330 1
7 47.26670 -38.95000 1
8 47.58330 -38.96670 1
9 -15.53333 28.26667 2
10 -15.53333 28.26667 2
11 -15.56667 28.18333 2

Related

Creating scatter plot class or group wise

Im using ggstatsplot's ggscatterstats function to calculate correlation between various clinical parameters and then plotting them. For example
here my variables are age and WBC. This is taking all the data points irrespective of the class they belong. I would like to do the same with each FAB classification that is present in my data.
dat <- merge_clinical_class_TMB %>% select(FAB,AGE,Wbc,Platelet,HB,PB_Blasts,BM_Blasts,TMB_NONSYNONYMOUS)
df2 <- dat
library(ggstatsplot)
ggscatterstats(
df2,
x = AGE,
y = Wbc,
type = "np" # try the "robust" correlation too! It might be even better here
#, marginal.type = "boxplot"
)
My dataframe looks like this
head(df2)
FAB AGE Wbc Platelet HB PB_Blasts BM_Blasts TMB_NONSYNONYMOUS
1 M4 50 17 231 10 88 52 0.3000000
2 M3 61 1 90 10 44 0 0.4333333
3 M3 30 6 114 11 82 6 0.2333333
4 M0 77 92 105 9 67 56 0.4000000
5 M1 46 29 90 9 90 81 0.5666667
6 M1 68 3 63 8 91 55 0.9000000
My data
dput(df2)
structure(list(FAB = structure(c(5L, 4L, 4L, 1L, 2L, 2L, 3L,
3L, 3L, 5L, 3L, 5L, 1L, 5L, 5L, 3L, 3L, 3L, 1L, 2L, 1L, 4L, 6L,
6L, 5L, 3L, 5L, 7L, 5L, 1L, 6L, 5L, 5L, 6L, 5L, 6L, 3L, 3L, 4L,
4L, 5L, 7L, 3L, 3L, 5L, 2L, 5L, 1L, 3L, 6L, 2L, 5L, 2L, 5L, 7L,
3L, 3L, 8L, 6L, 4L, 2L, 2L, 2L, 2L, 3L, 8L, 3L, 2L, 2L, 4L, 6L,
3L, 3L, 3L, 2L, 3L, 2L, 2L, 2L, 3L, 6L, 2L, 1L, 3L, 2L, 5L, 5L,
1L, 2L, 5L, 6L, 6L, 2L, 6L, 4L, 2L, 5L, 2L, 2L, 2L, 1L, 4L, 4L,
1L, 3L, 9L, 6L, 5L, 5L, 1L, 3L, 3L, 5L, 1L, 2L, 2L, 3L, 5L, 1L,
5L, 5L, 6L, 2L, 2L, 2L, 1L, 3L, 3L, 6L, 5L, 2L, 5L, 1L, 2L, 8L,
2L, 3L, 9L, 5L, 2L, 1L, 5L, 3L, 5L, 5L, 1L, 3L, 2L, 5L, 3L, 6L,
5L, 1L, 2L, 2L, 5L, 3L, 5L, 5L, 6L, 5L, 5L, 3L, 5L, 6L, 3L, 2L,
3L, 3L, 2L, 4L, 6L, 4L, 1L, 2L, 6L, 3L, 6L, 2L, 3L, 2L, 4L, 2L,
2L, 4L, 3L, 3L, 4L, 4L, 4L, 3L, 4L, 3L, 6L, 2L, 4L, 2L, 5L, 2L,
4L), .Label = c("M0", "M1", "M2", "M3", "M4", "M5", "M6", "M7",
"nc"), class = "factor"), AGE = c(50L, 61L, 30L, 77L, 46L, 68L,
23L, 64L, 76L, 81L, 25L, 78L, 39L, 49L, 57L, 63L, 62L, 52L, 76L,
64L, 65L, 61L, 44L, 31L, 64L, 33L, 55L, 50L, 64L, 59L, 59L, 77L,
33L, 48L, 35L, 66L, 67L, 51L, 74L, 51L, 64L, 77L, 63L, 37L, 57L,
53L, 62L, 39L, 72L, 66L, 51L, 51L, 18L, 63L, 54L, 75L, 40L, 60L,
76L, 33L, 63L, 53L, 75L, 67L, 66L, 77L, 64L, 76L, 51L, 42L, 51L,
59L, 43L, 45L, 60L, 47L, 68L, 24L, 48L, 73L, 60L, 44L, 71L, 25L,
60L, 57L, 55L, 69L, 42L, 42L, 45L, 50L, 41L, 21L, 50L, 69L, 76L,
70L, 27L, 76L, 65L, 48L, 59L, 69L, 81L, 22L, 61L, 51L, 63L, 61L,
22L, 73L, 49L, 41L, 47L, 54L, 44L, 55L, 83L, 78L, 59L, 57L, 57L,
88L, 43L, 71L, 62L, 75L, 62L, 58L, 65L, 66L, 60L, 35L, 76L, 72L,
35L, 73L, 67L, 70L, 48L, 65L, 41L, 52L, 67L, 58L, 34L, 60L, 55L,
56L, 61L, 31L, 71L, 56L, 57L, 60L, 57L, 58L, 79L, 55L, 34L, 76L,
82L, 67L, 67L, 54L, 53L, 71L, 61L, 30L, 50L, 35L, 29L, 45L, 38L,
81L, 31L, 75L, 67L, 29L, 51L, 40L, 32L, 57L, 25L, 63L, 75L, 25L,
68L, 62L, 25L, 31L, 68L, 45L, 61L, 35L, 22L, 23L, 21L, 53L),
Wbc = c(17L, 1L, 6L, 92L, 29L, 3L, 32L, 117L, 62L, 91L, 34L,
10L, 2L, 57L, 88L, 77L, 75L, 4L, 15L, 1L, 3L, 86L, 9L, 137L,
132L, 3L, 22L, 6L, 3L, 1L, 12L, 40L, 26L, 116L, 53L, 112L,
2L, 42L, 32L, 4L, 2L, 3L, 17L, 19L, 14L, 3L, 119L, 5L, 3L,
79L, 104L, 3L, 35L, 77L, 2L, 8L, 8L, 1L, 4L, 1L, 46L, 2L,
6L, 31L, 3L, 2L, 3L, 34L, 2L, 2L, 15L, 12L, 4L, 29L, 12L,
12L, 60L, 224L, 33L, 2L, 7L, 14L, 5L, 11L, 47L, 5L, 31L,
6L, 11L, 38L, 5L, 7L, 134L, 93L, 3L, 10L, 3L, 48L, 90L, 297L,
1L, 1L, 1L, 2L, 2L, 115L, 35L, 50L, 18L, 62L, 52L, 15L, 12L,
48L, 81L, 13L, 35L, 28L, 78L, 17L, 30L, 99L, 20L, 3L, 172L,
6L, 28L, 98L, 59L, 101L, 68L, 2L, 2L, 43L, 4L, 38L, 34L,
59L, 37L, 1L, 111L, 49L, 43L, 298L, 26L, 47L, 14L, 16L, 114L,
203L, 8L, 133L, 1L, 31L, 3L, 68L, 3L, 20L, 19L, 73L, 20L,
5L, 1L, 15L, 45L, 68L, 88L, 36L, 10L, 23L, 1L, 72L, 1L, 2L,
40L, 12L, 13L, 7L, 46L, 2L, 64L, NA, 5L, 103L, 8L, 1L, 3L,
16L, 29L, 1L, 99L, 2L, 6L, 2L, 3L, 2L, 115L, 27L, 8L, 1L),
Platelet = c(231L, 90L, 114L, 105L, 90L, 63L, 38L, 100L,
32L, 32L, 23L, 98L, 215L, 14L, 56L, 19L, 110L, 22L, 85L,
42L, 16L, 22L, 50L, 42L, 15L, 61L, 65L, 50L, 134L, 102L,
57L, 29L, 111L, 50L, 44L, 34L, 28L, 232L, 42L, 58L, 27L,
86L, 23L, 38L, 76L, 108L, 52L, 175L, 52L, 132L, 23L, 143L,
30L, 41L, 9L, 21L, 95L, 59L, 79L, 38L, 11L, 68L, 22L, 141L,
168L, 70L, 41L, 21L, 25L, 35L, 14L, 20L, 67L, 116L, 45L,
57L, 8L, 34L, 32L, 60L, 93L, 145L, 48L, 33L, 50L, 129L, 9L,
61L, 176L, 12L, 53L, 136L, 40L, 73L, 27L, 12L, 166L, 30L,
87L, 40L, 94L, 52L, 23L, 127L, 39L, 57L, 35L, 21L, 148L,
25L, 149L, 64L, 351L, 71L, 53L, 22L, 35L, 31L, 46L, 85L,
18L, 80L, 62L, 156L, 32L, 50L, 69L, 31L, 20L, 57L, 142L,
37L, 79L, 66L, 21L, 31L, 88L, 11L, 15L, 82L, 53L, 76L, 51L,
68L, 64L, 55L, 40L, 90L, 37L, 45L, 36L, 52L, 86L, 88L, 35L,
174L, 28L, 121L, 131L, 17L, 152L, 52L, 30L, 79L, 79L, 87L,
30L, 44L, 140L, 59L, 58L, 19L, 29L, 156L, 19L, 61L, 36L,
11L, 71L, 13L, 45L, 34L, 39L, 82L, 18L, 43L, 118L, 32L, 73L,
15L, 60L, 208L, 96L, 257L, 61L, 12L, 32L, 23L, 52L, 46L),
HB = c(10L, 10L, 11L, 9L, 9L, 8L, 7L, 10L, 10L, 11L, 11L,
10L, 10L, 8L, 10L, 13L, 11L, 9L, 9L, 8L, 9L, 12L, 8L, 6L,
10L, 7L, 8L, 9L, 11L, 12L, 11L, 10L, 10L, 9L, 8L, 10L, 9L,
13L, 9L, 8L, 12L, 9L, 12L, 9L, 9L, 9L, 11L, 10L, 11L, 12L,
12L, 11L, 9L, 10L, 9L, 9L, 10L, 9L, 10L, 9L, 8L, 9L, 9L,
10L, 12L, 10L, 10L, 8L, 10L, 9L, 11L, 11L, 11L, 8L, 9L, 9L,
9L, 6L, 10L, 10L, 9L, 9L, 8L, 9L, 9L, 7L, 9L, 11L, 12L, 10L,
9L, 10L, 12L, NA, 10L, 7L, 11L, 10L, 9L, 11L, 10L, 9L, 8L,
8L, 10L, 9L, 12L, 11L, 8L, 13L, 11L, 9L, 9L, 12L, 10L, 9L,
10L, 8L, 9L, 9L, 9L, 10L, 9L, 10L, 10L, 9L, 10L, 8L, 7L,
9L, 9L, 8L, 9L, 9L, 8L, 10L, 8L, 9L, 9L, 8L, 9L, 9L, 9L,
9L, 9L, 10L, 9L, 8L, 9L, 10L, 7L, 11L, 11L, 10L, 6L, 8L,
9L, 9L, 10L, 8L, 11L, 10L, 11L, 8L, 9L, 8L, 9L, 8L, 10L,
10L, 10L, 9L, 9L, 12L, 9L, 9L, 11L, 9L, 13L, 9L, 10L, 8L,
9L, 10L, 10L, 11L, 9L, 9L, 10L, 9L, 9L, 11L, 7L, 13L, 14L,
12L, 8L, 12L, 8L, 9L), PB_Blasts = c(88L, 44L, 82L, 67L,
90L, 91L, 59L, 60L, 48L, 98L, 53L, 40L, 75L, 81L, 90L, 57L,
46L, 67L, 74L, 61L, 99L, 73L, 74L, 83L, 72L, 33L, 35L, 70L,
85L, 61L, 95L, 80L, 71L, 83L, 90L, 90L, 50L, 64L, 51L, 93L,
95L, 75L, 80L, 52L, 61L, 72L, 65L, 83L, 45L, 32L, 85L, 73L,
86L, 82L, 30L, 48L, 47L, 58L, 78L, 100L, 81L, 82L, 40L, 89L,
70L, 47L, 80L, 73L, 62L, 88L, 57L, 70L, 40L, 56L, 86L, 37L,
90L, 77L, 75L, 37L, 94L, 86L, 97L, 72L, 87L, 40L, 52L, 60L,
68L, 40L, 95L, 81L, 92L, 90L, 90L, 42L, 37L, 84L, 77L, 99L,
83L, 65L, 79L, 82L, 46L, 94L, 71L, 39L, 62L, 95L, 55L, 11L,
51L, 42L, 77L, 72L, 39L, 69L, 75L, 70L, 75L, 52L, 91L, 33L,
87L, 55L, 72L, 76L, 85L, 79L, 79L, 81L, 50L, 81L, 33L, 88L,
34L, 90L, 69L, 32L, 92L, 90L, 47L, 75L, 30L, 59L, 57L, 62L,
54L, 60L, 89L, 82L, 90L, 90L, 64L, 89L, 43L, 58L, 58L, 97L,
71L, 91L, 53L, 75L, 85L, 67L, 86L, 70L, 43L, 86L, 74L, 87L,
0L, 0L, 86L, 53L, 63L, 41L, 76L, 45L, 85L, 0L, 94L, 6L, 91L,
0L, 2L, 93L, 85L, 82L, 56L, 40L, 48L, 0L, 14L, 90L, 71L,
51L, 91L, 42L), BM_Blasts = c(52L, 0L, 6L, 56L, 81L, 55L,
0L, 0L, 88L, 37L, 87L, 6L, 4L, 48L, 84L, 70L, 53L, 18L, 82L,
5L, 34L, 68L, 5L, 6L, 90L, 0L, 67L, 0L, 22L, 12L, 0L, 2L,
14L, 3L, 18L, 7L, 17L, 79L, 0L, 40L, 0L, 8L, 71L, 33L, 17L,
41L, 65L, 53L, 0L, 11L, 85L, 2L, 90L, 39L, 0L, 54L, 23L,
0L, 0L, 0L, 97L, 42L, 48L, 61L, 6L, 0L, 46L, 55L, 10L, 2L,
0L, 48L, 39L, 37L, 43L, 0L, 91L, 76L, 41L, 16L, 30L, 17L,
54L, 50L, 65L, 0L, 59L, 22L, 51L, 16L, 6L, 10L, 90L, 72L,
0L, 32L, 0L, 49L, 88L, 98L, 0L, 0L, 15L, 0L, 0L, 94L, 55L,
39L, 9L, 86L, 70L, 11L, 5L, 74L, 79L, 90L, 83L, 57L, 74L,
28L, 17L, 4L, 91L, 0L, 91L, 50L, 49L, 80L, 22L, 64L, 84L,
12L, 14L, 86L, 6L, 18L, 40L, 0L, 61L, 6L, 87L, 0L, 62L, 51L,
6L, 72L, 59L, 29L, 24L, 96L, 0L, 53L, 13L, 45L, 61L, 56L,
35L, 10L, 0L, 8L, 58L, 16L, 25L, 10L, 3L, 71L, 52L, 67L,
32L, 88L, 10L, 8L, 0L, 0L, 97L, 7L, 45L, 0L, 49L, 9L, 85L,
0L, 70L, 91L, 7L, 0L, 2L, 0L, 32L, 11L, 71L, 0L, 48L, 0L,
14L, 7L, 90L, 63L, 83L, 29L), TMB_NONSYNONYMOUS = c(0.3,
0.433333333333, 0.233333333333, 0.4, 0.566666666667, 0.9,
0.3, 0.133333333333, 0.4, 0.3, 0.233333333333, 0.5, 0.266666666667,
0, 0.2, 0.4, 0.266666666667, 0.333333333333, 0.4, 0.4, 0.566666666667,
0.0333333333333, 0.166666666667, 0.1, 0.166666666667, 0.266666666667,
0.3, 0.3, 0.466666666667, 0.0666666666667, 0.266666666667,
0.266666666667, 0.0333333333333, 0.1, 0.133333333333, 0.0333333333333,
0.5, 0.6, 0.0333333333333, 0.1, 0.0333333333333, 0.333333333333,
0.433333333333, 0.2, 0.466666666667, 0.2, 0.0333333333333,
0.733333333333, 0.2, 0.233333333333, 0.233333333333, 0.3,
0.133333333333, 0, 0.3, 0.333333333333, 0.333333333333, 0.266666666667,
0.533333333333, 0.2, 0.533333333333, 0.466666666667, 0.533333333333,
0.0333333333333, 0.3, 0.5, 0.333333333333, 0.266666666667,
0.5, 0.333333333333, 0.0666666666667, 0.466666666667, 0.333333333333,
0.266666666667, 0.7, 0.433333333333, 0.166666666667, 0.0666666666667,
0.233333333333, 0.5, 0.0333333333333, 0.2, 0.433333333333,
0.433333333333, 0.4, 0.233333333333, 0.0666666666667, 0.233333333333,
0.466666666667, 0.0666666666667, 0, 0.1, 0.4, 0.1, 0.2, 0.4,
0.433333333333, 0.566666666667, 0.2, 0.0333333333333, 0.533333333333,
0.566666666667, 0.3, 0.466666666667, 0.566666666667, 0.0333333333333,
0.4, 0.0666666666667, 0.633333333333, 0.4, 0.466666666667,
0.466666666667, 0.3, 0.5, 0.0333333333333, 0.333333333333,
0.333333333333, 0.266666666667, 0.366666666667, 0.666666666667,
0.333333333333, 0.533333333333, 0.466666666667, 0.6, 0.333333333333,
0.4, 0.266666666667, 0.366666666667, 0.2, 0.0333333333333,
0.266666666667, 0.3, 0.166666666667, 0.4, 0.566666666667,
0.4, 0.1, 0.1, 0.0666666666667, 0.366666666667, 0, 0.4, 0.0333333333333,
0.1, 0.0666666666667, 0.5, 0.3, 0.466666666667, 0.0333333333333,
0.4, 0.1, 0.0666666666667, 0.766666666667, 0.5, 0.466666666667,
0.333333333333, 0.4, 0.333333333333, 0.4, 0.266666666667,
0.2, 0.3, 0.7, 0.166666666667, 0.2, 0, 0.5, 0.166666666667,
0.533333333333, 0.233333333333, 0.166666666667, 0.133333333333,
0.0666666666667, 0.4, 0.333333333333, 0.133333333333, 0.4,
0.233333333333, 0.466666666667, 0.366666666667, 0.266666666667,
0.266666666667, 0.266666666667, 0.4, 0.2, 0.166666666667,
0.4, 0.333333333333, 0.166666666667, 0.266666666667, 0.1,
0.333333333333, 0.733333333333, 0.466666666667, 0.466666666667,
0.2, 0.1, 1.13333333333, 0.2, 0.3)), class = "data.frame", row.names = c(NA,
-200L))
Objective I would like to do the same with various FABI have FAB label from M0 to M7 I would like to ignore nc
So for each FAB label I would like to see the correlation for example if I have to take the M0 class then I would like to see their Age vs Wbc correlation and similarly for other FAB class as well. Is it possible to do these in ggstataplot as I don't see for correlation any such functionality there .
Simple way is I can subset them and do the same like M0 ,M1, M2 etc etc but that is a long process can I split the FAB column and pass it to the library?
I would like to know other ways to do the above and plot the same
Any help or suggestion would be appreciated

Update: We could also use the built in function see comments:
Many thanks to #Indrajeet Patil: https://indrajeetpatil.github.io/ggstatsplot/articles/web_only/ggscatterstats.html#grouped-analysis-with-grouped_ggscatterstats
To subset FAB we use filter:
## for reproducibility
set.seed(123)
## plot
grouped_ggscatterstats(
## arguments relevant for ggscatterstats
data = df2 %>% filter(as.integer(FAB)<5),
x = AGE,
y = Wbc,
grouping.var = FAB,
type = "r",
# ggtheme = ggthemes::theme_tufte(),
## arguments relevant for combine_plots
annotation.args = list(
title = "Relationship between Wbc and Age",
caption = "Source: stackoverflow"
),
plotgrid.args = list(nrow = 2, ncol = 2)
)
First answer:
We could do something like this:
write a function and pass the data frame + the column FAB value:
library(ggstatsplot)
my_function <- function(df, x){
ggscatterstats(
df %>% filter(FAB == x),
x = AGE,
y = Wbc,
type = "np" # try the "robust" correlation too! It might be even better here
#, marginal.type = "boxplot"
)
}
M0 <- my_function(df2, "M0")
M1 <- my_function(df2, "M1")
M2 <- my_function(df2, "M2")
M3 <- my_function(df2, "M3")
.
.
.
library(patchwork)
(M0 / M1 | M2 / M3)

Subtract Values based on Multiple Grouping Factors

I have a dataset with phosphorus concentrations for 17 separate days (concentrations are cumulative, so increase from Day1 to Day102 in all cases). There are 22 different treatments (column = Trmt). Each Trmt has 3 Levels (Level = X, Y, Z). 2 measurements per Level for a total of 6 per Trmt.
My goal is to plot a 3-line graph of Days (x-axis; numeric) by Concentration (y-axis) using ggplot2. Data should be grouped by Trmt, Level and day for a total of 51 measurements (3 lines x 17 days).
My data looks as follows:
structure(list(Trmt = structure(c(2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 4L, 4L, 4L, 4L, 4L, 4L, 3L, 3L, 3L, 3L, 3L, 3L, 6L, 6L, 6L, 6L, 6L, 6L, 5L, 5L, 5L, 5L, 5L, 5L, 8L, 8L, 8L, 8L, 8L, 8L, 7L, 7L, 7L, 7L, 7L, 7L, 10L, 10L, 10L, 10L, 10L, 10L, 9L, 9L, 9L, 9L, 9L, 9L, 12L, 12L, 12L, 12L, 12L, 12L, 11L, 11L, 11L, 11L, 11L, 11L, 14L, 14L, 14L, 14L, 14L, 14L, 13L, 13L, 13L, 13L, 13L, 13L, 16L, 16L, 16L, 16L, 16L, 16L, 15L, 15L, 15L, 15L, 15L, 15L, 18L, 18L, 18L, 18L, 18L, 18L, 17L, 17L, 17L, 17L, 17L, 17L, 20L, 20L, 20L, 20L, 20L, 20L, 19L, 19L, 19L, 19L, 19L, 19L, 22L, 22L, 22L, 22L, 22L, 22L, 21L, 21L, 21L, 21L, 21L, 21L), .Label = c("A01nF", "A01yT", "A02nF", "A02yT", "A03nF", "A03yT", "A04nF", "A04yT", "A05nF", "A05yT", "A06nF", "A06yT", "A07nF", "A07yT", "A08nF", "A08yT", "A10nF", "A10yT", "A11nF", "A11yT", "A13nF", "A13yT"), class = "factor"), Level = structure(c(1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L), .Label = c("X", "Y", "Z"), class = "factor"), Day1 = c(3L, 1L, 4L, 2L, 4L, 2L, 5L, 4L, 1L, 2L, 5L, 1L, 5L, 2L, 5L, 5L, 3L, 5L, 3L, 3L, 1L, 4L, 1L, 1L, 5L, 4L, 1L, 5L, 4L, 5L, 3L, 5L, 3L, 5L, 3L, 4L, 2L, 4L, 2L, 4L, 3L, 1L, 1L, 3L, 1L, 3L, 1L, 5L, 2L, 4L, 4L, 3L, 1L, 4L, 4L, 1L, 4L, 1L, 2L, 5L, 1L, 5L, 1L, 2L, 4L, 4L, 4L, 4L, 2L, 4L, 5L, 5L, 4L, 1L, 3L, 2L, 3L, 5L, 4L, 3L, 2L, 3L, 5L, 4L, 1L, 3L, 4L, 3L, 3L, 5L, 3L, 1L, 1L, 4L, 4L, 5L, 1L, 4L, 4L, 4L, 1L, 4L, 5L, 5L, 1L, 5L, 3L, 1L, 4L, 1L, 4L, 5L, 5L, 3L, 3L, 2L, 4L, 5L, 3L, 2L, 1L, 5L, 5L, 2L, 2L, 3L, 4L, 3L, 4L, 2L, 2L, 4L), Day2 = c(10L, 9L, 7L, 7L, 6L, 7L, 10L, 9L, 10L, 6L, 10L, 7L, 8L, 9L, 8L, 9L, 7L, 10L, 7L, 10L, 6L, 8L, 6L, 8L, 8L, 8L, 10L, 6L, 8L, 8L, 6L, 10L, 7L, 10L, 7L, 10L, 6L, 6L, 7L, 9L, 8L, 10L, 8L, 7L, 9L, 8L, 6L, 9L, 7L, 9L, 8L, 6L, 6L, 8L, 10L, 7L, 8L, 6L, 8L, 8L, 6L, 9L, 10L, 6L, 8L, 7L, 9L, 7L, 8L, 10L, 10L, 6L, 7L, 10L, 9L, 9L, 8L, 9L, 6L, 8L, 6L, 8L, 6L, 9L, 10L, 7L, 7L, 7L, 8L, 7L, 8L, 10L, 7L, 8L, 9L, 6L, 8L, 9L, 8L, 9L, 6L, 7L, 10L, 9L, 10L, 7L, 6L, 9L, 9L, 9L, 6L, 10L, 9L, 8L, 9L, 7L, 10L, 7L, 10L, 9L, 6L, 8L, 9L, 8L, 9L, 6L, 6L, 10L, 9L, 8L, 8L, 7L), Day4 = c(11L, 12L, 14L, 11L, 15L, 15L, 12L, 11L, 15L, 12L, 15L, 12L, 12L, 11L, 15L, 15L, 13L, 11L, 13L, 14L, 12L, 11L, 13L, 12L, 15L, 15L, 14L, 11L, 15L, 11L, 12L, 11L, 13L, 11L, 12L, 13L, 13L, 14L, 13L, 15L, 14L, 15L, 12L, 14L, 11L, 13L, 15L, 11L, 12L, 13L, 11L, 15L, 11L, 13L, 11L, 11L, 14L, 12L, 14L, 15L, 11L, 12L, 15L, 12L, 13L, 12L, 14L, 12L, 11L, 13L, 12L, 12L, 11L, 15L, 13L, 12L, 11L, 12L, 13L, 14L, 14L, 14L, 13L, 12L, 15L, 12L, 15L, 15L, 12L, 13L, 12L, 12L, 12L, 14L, 13L, 13L, 14L, 11L, 12L, 11L, 15L, 11L, 11L, 11L, 14L, 11L, 12L, 15L, 15L, 11L, 12L, 14L, 15L, 14L, 14L, 12L, 14L, 13L, 15L, 15L, 14L, 13L, 12L, 15L, 15L, 11L, 13L, 12L, 11L, 13L, 12L, 14L), Day7 = c(19L, 17L, 17L, 20L, 17L, 19L, 18L, 19L, 17L, 20L, 16L, 20L, 19L, 18L, 20L, 19L, 17L, 16L, 18L, 18L, 17L, 18L, 19L, 18L, 17L, 19L, 17L, 20L, 19L, 20L, 19L, 20L, 17L, 18L, 20L, 19L, 20L, 18L, 18L, 20L, 18L, 20L, 17L, 19L, 17L, 19L, 17L, 17L, 20L, 18L, 18L, 17L, 16L, 18L, 20L, 16L, 17L, 19L, 16L, 19L, 16L, 17L, 16L, 20L, 16L, 19L, 19L, 17L, 17L, 17L, 20L, 19L, 18L, 16L, 20L, 17L, 19L, 16L, 18L, 19L, 16L, 19L, 20L, 20L, 16L, 16L, 18L, 17L, 16L, 18L, 16L, 17L, 16L, 18L, 20L, 16L, 16L, 20L, 20L, 16L, 20L, 18L, 17L, 19L, 18L, 18L, 19L, 19L, 16L, 18L, 19L, 19L, 17L, 17L, 18L, 18L, 20L, 18L, 20L, 20L, 18L, 19L, 19L, 16L, 16L, 17L, 20L, 16L, 17L, 18L, 16L, 20L), Day10 = c(24L, 23L, 23L, 21L, 21L, 23L, 21L, 21L, 22L, 25L, 21L, 23L, 21L, 25L, 25L, 25L, 24L, 22L, 25L, 24L, 21L, 23L, 24L, 23L, 23L, 22L, 23L, 22L, 22L, 25L, 25L, 22L, 21L, 24L, 25L, 23L, 23L, 23L, 24L, 23L, 25L, 23L, 21L, 23L, 22L, 24L, 22L, 23L, 24L, 22L, 25L, 23L, 23L, 21L, 25L, 24L, 24L, 25L, 25L, 25L, 22L, 23L, 21L, 22L, 24L, 22L, 23L, 22L, 24L, 22L, 21L, 22L, 23L, 21L, 25L, 25L, 22L, 21L, 25L, 24L, 22L, 21L, 25L, 24L, 21L, 24L, 25L, 22L, 23L, 22L, 24L, 23L, 25L, 25L, 23L, 25L, 22L, 23L, 23L, 23L, 22L, 25L, 22L, 23L, 24L, 25L, 22L, 21L, 21L, 22L, 23L, 24L, 21L, 24L, 23L, 23L, 25L, 24L, 25L, 23L, 22L, 25L, 25L, 25L, 21L, 22L, 23L, 21L, 24L, 24L, 25L, 21L), Day13 = c(29L, 29L, 26L, 27L, 30L, 30L, 30L, 26L, 30L, 29L, 30L, 27L, 26L, 29L, 28L, 26L, 30L, 28L, 29L, 27L, 28L, 26L, 29L, 28L, 30L, 26L, 27L, 30L, 26L, 29L, 26L, 28L, 29L, 28L, 29L, 28L, 27L, 27L, 28L, 26L, 26L, 27L, 27L, 29L, 27L, 29L, 27L, 30L, 26L, 27L, 30L, 26L, 29L, 29L, 27L, 29L, 26L, 29L, 28L, 28L, 29L, 30L, 28L, 30L, 30L, 30L, 28L, 29L, 28L, 27L, 28L, 27L, 27L, 28L, 27L, 30L, 27L, 30L, 27L, 28L, 29L, 27L, 30L, 29L, 30L, 30L, 26L, 30L, 29L, 30L, 27L, 26L, 27L, 27L, 28L, 26L, 30L, 28L, 30L, 30L, 30L, 30L, 26L, 28L, 27L, 26L, 29L, 26L, 29L, 26L, 30L, 29L, 30L, 26L, 27L, 30L, 29L, 30L, 27L, 30L, 28L, 26L, 30L, 27L, 30L, 26L, 28L, 29L, 26L, 28L, 28L, 26L), Day18 = c(32L, 31L, 32L, 31L, 31L, 34L, 32L, 34L, 32L, 33L, 31L, 34L, 35L, 34L, 34L, 32L, 33L, 35L, 32L, 35L, 31L, 31L, 33L, 33L, 32L, 31L, 32L, 31L, 32L, 34L, 33L, 33L, 34L, 31L, 35L, 35L, 31L, 34L, 32L, 32L, 34L, 33L, 34L, 33L, 33L, 35L, 35L, 31L, 35L, 31L, 33L, 34L, 31L, 33L, 34L, 32L, 32L, 33L, 31L, 32L, 35L, 34L, 31L, 32L, 34L, 35L, 34L, 31L, 34L, 33L, 35L, 35L, 31L, 32L, 35L, 34L, 31L, 32L, 32L, 33L, 32L, 35L, 32L, 32L, 35L, 33L, 34L, 32L, 34L, 35L, 34L, 33L, 33L, 31L, 31L, 31L, 35L, 34L, 33L, 32L, 33L, 33L, 33L, 35L, 34L, 33L, 31L, 34L, 34L, 34L, 34L, 33L, 33L, 31L, 31L, 31L, 33L, 33L, 35L, 32L, 32L, 31L, 31L, 32L, 33L, 32L, 34L, 34L, 31L, 35L, 31L, 35L), Day23 = c(39L, 40L, 38L, 37L, 37L, 38L, 37L, 36L, 37L, 36L, 36L, 38L, 40L, 38L, 37L, 36L, 36L, 40L, 40L, 40L, 40L, 39L, 40L, 36L, 38L, 36L, 36L, 37L, 38L, 37L, 36L, 37L, 39L, 39L, 38L, 38L, 37L, 40L, 36L, 38L, 37L, 40L, 36L, 37L, 39L, 38L, 38L, 38L, 40L, 38L, 37L, 36L, 38L, 36L, 36L, 36L, 39L, 40L, 39L, 37L, 39L, 39L, 37L, 36L, 37L, 39L, 39L, 37L, 36L, 37L, 40L, 36L, 39L, 40L, 39L, 40L, 39L, 38L, 39L, 40L, 37L, 40L, 38L, 38L, 38L, 40L, 40L, 36L, 39L, 39L, 39L, 39L, 38L, 37L, 37L, 36L, 37L, 39L, 37L, 40L, 40L, 40L, 38L, 38L, 39L, 38L, 36L, 37L, 36L, 36L, 40L, 39L, 39L, 39L, 36L, 39L, 38L, 40L, 36L, 37L, 38L, 38L, 36L, 37L, 39L, 36L, 40L, 40L, 39L, 38L, 37L, 38L), Day28 = c(42L, 43L, 43L, 44L, 44L, 44L, 42L, 42L, 43L, 42L, 45L, 43L, 43L, 43L, 42L, 44L, 42L, 44L, 45L, 44L, 44L, 45L, 44L, 41L, 41L, 42L, 44L, 44L, 44L, 45L, 43L, 42L, 43L, 42L, 41L, 44L, 43L, 43L, 42L, 42L, 44L, 42L, 42L, 42L, 45L, 44L, 45L, 42L, 43L, 45L, 45L, 44L, 41L, 42L, 42L, 41L, 44L, 44L, 44L, 44L, 42L, 45L, 41L, 42L, 45L, 43L, 44L, 45L, 44L, 42L, 41L, 43L, 41L, 44L, 43L, 41L, 45L, 42L, 45L, 41L, 45L, 41L, 45L, 42L, 45L, 42L, 45L, 45L, 41L, 41L, 43L, 41L, 41L, 42L, 43L, 41L, 42L, 44L, 43L, 45L, 41L, 41L, 44L, 41L, 44L, 43L, 43L, 45L, 44L, 41L, 44L, 43L, 42L, 45L, 45L, 41L, 45L, 42L, 41L, 44L, 41L, 41L, 41L, 43L, 41L, 41L, 45L, 41L, 42L, 45L, 41L, 44L), Day35 = c(50L, 50L, 50L, 50L, 48L, 46L, 50L, 46L, 48L, 50L, 50L, 50L, 46L, 49L, 46L, 47L, 49L, 49L, 48L, 49L, 46L, 47L, 49L, 46L, 49L, 50L, 49L, 46L, 49L, 50L, 46L, 48L, 50L, 46L, 50L, 48L, 46L, 48L, 50L, 50L, 47L, 47L, 47L, 47L, 47L, 49L, 48L, 46L, 46L, 48L, 50L, 46L, 49L, 48L, 46L, 49L, 50L, 49L, 48L, 48L, 48L, 50L, 49L, 47L, 48L, 50L, 50L, 46L, 47L, 46L, 48L, 48L, 48L, 47L, 49L, 48L, 49L, 46L, 47L, 50L, 47L, 50L, 47L, 47L, 46L, 46L, 47L, 50L, 49L, 49L, 48L, 47L, 46L, 50L, 46L, 50L, 50L, 46L, 47L, 47L, 49L, 50L, 50L, 46L, 47L, 50L, 47L, 48L, 46L, 50L, 49L, 46L, 46L, 50L, 50L, 49L, 46L, 49L, 46L, 46L, 46L, 48L, 47L, 47L, 50L, 47L, 46L, 48L, 50L, 48L, 46L, 46L), Day42 = c(52L, 51L, 53L, 53L, 54L, 55L, 55L, 54L, 52L, 51L, 55L, 51L, 54L, 53L, 53L, 55L, 54L, 55L, 51L, 51L, 55L, 54L, 54L, 53L, 55L, 53L, 52L, 53L, 53L, 51L, 54L, 54L, 55L, 53L, 54L, 55L, 51L, 51L, 54L, 52L, 51L, 51L, 55L, 54L, 54L, 52L, 52L, 55L, 55L, 51L, 55L, 52L, 55L, 51L, 53L, 52L, 53L, 54L, 51L, 54L, 54L, 55L, 52L, 54L, 52L, 52L, 51L, 52L, 55L, 52L, 54L, 51L, 52L, 55L, 51L, 52L, 55L, 54L, 52L, 53L, 53L, 52L, 55L, 51L, 51L, 55L, 52L, 55L, 55L, 55L, 53L, 52L, 53L, 54L, 52L, 52L, 52L, 52L, 53L, 51L, 54L, 54L, 51L, 53L, 55L, 51L, 54L, 54L, 54L, 53L, 53L, 54L, 54L, 55L, 52L, 52L, 54L, 51L, 52L, 51L, 51L, 55L, 52L, 51L, 51L, 53L, 54L, 51L, 51L, 54L, 55L, 52L), Day52 = c(59L, 57L, 56L, 58L, 59L, 59L, 57L, 59L, 57L, 56L, 58L, 58L, 60L, 59L, 56L, 56L, 60L, 57L, 60L, 57L, 59L, 56L, 60L, 59L, 59L, 56L, 60L, 58L, 60L, 57L, 57L, 60L, 56L, 57L, 59L, 60L, 56L, 58L, 57L, 57L, 58L, 58L, 59L, 56L, 58L, 56L, 57L, 60L, 58L, 59L, 58L, 56L, 56L, 57L, 60L, 59L, 60L, 58L, 59L, 60L, 57L, 60L, 59L, 57L, 60L, 56L, 57L, 56L, 58L, 60L, 56L, 58L, 56L, 60L, 57L, 57L, 57L, 60L, 58L, 59L, 58L, 60L, 59L, 58L, 56L, 56L, 58L, 57L, 60L, 56L, 58L, 56L, 57L, 58L, 58L, 60L, 59L, 60L, 59L, 59L, 59L, 57L, 57L, 60L, 59L, 57L, 57L, 58L, 59L, 57L, 59L, 58L, 60L, 59L, 56L, 57L, 57L, 56L, 57L, 60L, 58L, 57L, 56L, 59L, 59L, 59L, 57L, 57L, 58L, 56L, 58L, 60L), Day62 = c(67L, 65L, 68L, 65L, 69L, 70L, 69L, 66L, 65L, 70L, 70L, 65L, 67L, 68L, 65L, 67L, 65L, 66L, 66L, 68L, 68L, 66L, 65L, 67L, 66L, 69L, 69L, 69L, 68L, 67L, 66L, 69L, 65L, 65L, 69L, 66L, 69L, 68L, 69L, 67L, 65L, 69L, 69L, 69L, 70L, 67L, 65L, 65L, 65L, 66L, 66L, 69L, 68L, 66L, 67L, 66L, 70L, 70L, 70L, 69L, 70L, 70L, 67L, 66L, 65L, 69L, 67L, 66L, 70L, 70L, 70L, 65L, 66L, 67L, 66L, 66L, 67L, 68L, 70L, 67L, 69L, 66L, 67L, 65L, 70L, 65L, 70L, 66L, 66L, 69L, 68L, 65L, 65L, 67L, 68L, 67L, 69L, 68L, 69L, 66L, 68L, 70L, 69L, 68L, 70L, 66L, 69L, 66L, 66L, 67L, 65L, 69L, 69L, 67L, 70L, 65L, 70L, 69L, 66L, 68L, 67L, 68L, 66L, 65L, 67L, 70L, 66L, 67L, 66L, 67L, 67L, 70L), Day72 = c(74L, 74L, 71L, 75L, 74L, 71L, 75L, 71L, 75L, 71L, 72L, 72L, 75L, 73L, 75L, 74L, 74L, 74L, 71L, 74L, 72L, 71L, 71L, 74L, 74L, 73L, 72L, 73L, 71L, 71L, 75L, 72L, 73L, 74L, 75L, 73L, 71L, 71L, 74L, 71L, 73L, 75L, 75L, 74L, 71L, 75L, 74L, 72L, 72L, 71L, 72L, 75L, 73L, 74L, 71L, 75L, 75L, 73L, 72L, 73L, 73L, 72L, 75L, 72L, 71L, 72L, 73L, 72L, 72L, 74L, 72L, 72L, 73L, 75L, 74L, 75L, 73L, 74L, 75L, 72L, 75L, 73L, 71L, 71L, 72L, 74L, 72L, 75L, 71L, 71L, 71L, 73L, 72L, 71L, 75L, 75L, 74L, 73L, 71L, 71L, 72L, 71L, 71L, 74L, 72L, 73L, 71L, 75L, 74L, 75L, 74L, 73L, 73L, 73L, 72L, 75L, 73L, 71L, 71L, 72L, 72L, 71L, 71L, 71L, 72L, 73L, 75L, 75L, 72L, 73L, 75L, 75L), Day82 = c(76L, 78L, 78L, 78L, 79L, 77L, 78L, 77L, 80L, 79L, 80L, 76L, 76L, 80L, 80L, 80L, 78L, 78L, 78L, 78L, 80L, 78L, 76L, 79L, 76L, 77L, 76L, 79L, 78L, 76L, 76L, 79L, 79L, 77L, 77L, 77L, 78L, 78L, 80L, 77L, 77L, 76L, 77L, 79L, 78L, 78L, 78L, 80L, 79L, 76L, 79L, 77L, 76L, 80L, 78L, 77L, 79L, 80L, 77L, 80L, 78L, 79L, 78L, 76L, 76L, 79L, 77L, 77L, 78L, 78L, 79L, 78L, 78L, 78L, 80L, 79L, 78L, 77L, 78L, 78L, 78L, 79L, 80L, 77L, 77L, 80L, 77L, 80L, 77L, 76L, 77L, 76L, 77L, 77L, 80L, 79L, 77L, 78L, 80L, 80L, 79L, 80L, 79L, 79L, 78L, 76L, 76L, 79L, 79L, 80L, 79L, 78L, 76L, 79L, 77L, 77L, 76L, 76L, 78L, 78L, 79L, 78L, 76L, 78L, 79L, 76L, 77L, 78L, 76L, 79L, 78L, 77L), Day92 = c(85L, 84L, 85L, 85L, 83L, 82L, 83L, 82L, 85L, 85L, 82L, 85L, 85L, 85L, 81L, 81L, 84L, 81L, 85L, 82L, 85L, 84L, 81L, 82L, 83L, 82L, 84L, 84L, 81L, 85L, 83L, 85L, 82L, 81L, 83L, 83L, 85L, 83L, 81L, 83L, 82L, 84L, 83L, 83L, 82L, 85L, 85L, 82L, 82L, 82L, 85L, 81L, 81L, 82L, 82L, 84L, 81L, 85L, 81L, 82L, 81L, 81L, 85L, 83L, 81L, 83L, 83L, 84L, 83L, 85L, 85L, 83L, 81L, 85L, 81L, 84L, 83L, 83L, 85L, 83L, 82L, 82L, 82L, 83L, 82L, 83L, 81L, 84L, 83L, 84L, 82L, 83L, 81L, 83L, 81L, 82L, 82L, 82L, 85L, 85L, 84L, 81L, 81L, 81L, 84L, 81L, 84L, 81L, 81L, 84L, 84L, 83L, 83L, 82L, 82L, 81L, 85L, 85L, 82L, 83L, 81L, 83L, 82L, 84L, 83L, 82L, 84L, 81L, 83L, 82L, 84L, 85L), Day102 = c(89L, 88L, 88L, 90L, 88L, 90L, 87L, 88L, 89L, 87L, 90L, 86L, 86L, 89L, 86L, 89L, 90L, 88L, 87L, 88L, 88L, 87L, 90L, 86L, 90L, 87L, 88L, 89L, 88L, 90L, 88L, 87L, 89L, 90L, 88L, 87L, 89L, 88L, 87L, 86L, 90L, 86L, 89L, 89L, 90L, 88L, 90L, 86L, 88L, 88L, 90L, 89L, 88L, 88L, 90L, 87L, 88L, 88L, 87L, 90L, 89L, 87L, 90L, 90L, 86L, 87L, 86L, 90L, 88L, 87L, 86L, 88L, 90L, 86L, 89L, 90L, 87L, 87L, 88L, 86L, 86L, 89L, 89L, 86L, 87L, 86L, 86L, 88L, 88L, 88L, 89L, 90L, 88L, 86L, 88L, 88L, 87L, 88L, 90L, 89L, 89L, 86L, 90L, 89L, 89L, 88L, 90L, 88L, 86L, 90L, 90L, 87L, 89L, 90L, 90L, 88L, 88L, 89L, 90L, 88L, 90L, 90L, 87L, 89L, 90L, 90L, 90L, 89L, 86L, 88L, 89L, 88L)), class = "data.frame", row.names = c(NA, -132L))
Required libraries:
tidyr, plyr, ggplot2
The steps that I have taken so far are to:
Convert the data to long format (df = name of dataset):
Fig1 <- gather(df, day, phosphorus, Day1:Day102, factor_key=TRUE)
Change the factor day to numeric
df$day2 <-revalue(df$day, c("Day1"="1", "Day2"="2", "Day4"="4", "Day7"="7", "Day10"="10", "Day13"="13", "Day18"="18", "Day23" = "23","Day28" = "28", "Day35" = "35", "Day42" = "42", "Day52" = "52", "Day62" = "62", "Day72" = "72", "Day82" = "82", Day92" = "92", "Day102" = "102"))
and
df$day3 <- as.numeric(as.character(df$day2))
Group by Trmt, Level and day3
GroupedDF <- df %>% group_by(Trmt, Level, day3)
GroupedCO2M <- GroupedDF %>% summarise(disp = mean(phosphorus))
I would now like to subtract values by accounting for Trmt and Level, thus reducing the number of rows from 102 to 51. I would like to subtract 'yT' Trmt cases from respective 'nF' cases, uniquely for each Level (X, Y and Z). For example, subtract A01yT_X from A01nf_X, A01yT_Y from A01nf_Y, A01yT_Z from A01nf_Z etc. This should give a total of 51 points, 17 for each Level.
Here is a figure of what I have in mind:
Many thanks for any advice.

thanks for sharing the data. The data you have posted is a bit long, hence might not be able to totally copy and paste
Your data is in the wide format, and you need to find the average for each measurement between similar groups (defined by Day, Level, Treatment). So we can work on this in the wide format:
tmp <- Data %>% group_by(Trmt,Level) %>% summarise_all(mean)
> head(tmp)
# A tibble: 6 x 19
# Groups: Trmt [2]
Trmt Level Day1 Day2 Day4 Day7 Day10 Day13 Day18 Day23 Day28 Day35 Day42
<fct> <fct> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 A01nF X 3.5 8 12 19 23 29.5 32.5 36.5 42 50 53
2 A01nF Y 4.5 9.5 13 17.5 21 28 32.5 36 43.5 48 54.5
3 A01nF Z 1 8.5 13.5 18.5 22.5 28.5 33 37.5 43 49 51.5
4 A01yT X 2.5 8.5 11 19.5 22.5 28 31.5 38 43 50 52.5
5 A01yT Y 2.5 7.5 13.5 17 22 29.5 31 38.5 43.5 49 52.5
6 A01yT Z 3 7 14.5 18 23 28 33 38 43.5 48 54
This gives you the average for each Trmt,Level, and each column (Day) is average separately. Next step is to define the 2 subgroups under Trmt (nF and yT for A01,A02..), and for this we can introduce a subgroup called "site", which is Trmt without the nF,yT. Once you group your data.frame with this "site" and level, the first row will always be nF, and 2nd row yT, so taking the diff for all your Day columns within this grouping, will give you the difference. So we do it like this:
# need to ungroup Trmt to remove it later
tmp <- tmp%>% ungroup(Trmt) %>%
mutate(site = sub("[yn][TF]","",Trmt)) %>%
select(-Trmt) %>%
group_by(site,Level) %>%
summarize_all(diff)
Now you have the nF - yT values for each treatment, each level and each day
> head(tmp)
# A tibble: 6 x 19
# Groups: site [2]
site Level Day1 Day2 Day4 Day7 Day10 Day13 Day18 Day23 Day28 Day35 Day42
<chr> <fct> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 A01 X -1 0.5 -1 0.5 -0.5 -1.5 -1 1.5 1 0 -0.5
2 A01 Y -2 -2 0.5 -0.5 1 1.5 -1.5 2.5 0 1 -2
3 A01 Z 2 -1.5 1 -0.5 0.5 -0.5 0 0.5 0.5 -1 2.5
4 A02 X 1.5 1 1.5 1 -1 -1.5 2 -1.5 -1.5 -1 2
5 A02 Y 0.5 0 -1.5 -1 0.5 1.5 -0.5 -3 -1.5 0 1
6 A02 Z 4 2 1 0.5 1.5 0 2.5 0.5 0.5 1.5 0
Come the last part, which is to plot. We convert it to long and also make "Day", a numeric form of day.
plotdf <- gather(tmp, day, Diff, Day1:Day102, factor_key=TRUE) %>%
mutate(Day=as.numeric(sub("Day","",day)))
# and plot
ggplot(plotdf,aes(x=Day,y=Diff,col=Level,shape=Level)) + geom_line() + geom_point() + facet_wrap(~site) + scale_color_manual(values=c("grey10","grey40","grey80"))
Plot above shows the difference for each site. For diff that is the average across all sites:
meandf <- plotdf %>% group_by(Level,Day) %>% summarize(Diff=mean(Diff))
ggplot(meandf,aes(x=Day,y=Diff,col=Level,shape=Level)) + geom_line() + geom_point() + scale_color_manual(values=c("grey10","grey40","grey80"))
example dataset, subsetted for Day1, Day2 and Day4
Data <- structure(list(Trmt = structure(c(2L, 2L, 2L, 2L, 2L, 2L, 1L,
1L, 1L, 1L, 1L, 1L, 4L, 4L, 4L, 4L, 4L, 4L, 3L, 3L, 3L, 3L, 3L,
3L, 6L, 6L, 6L, 6L, 6L, 6L, 5L, 5L, 5L, 5L, 5L, 5L, 8L, 8L, 8L,
8L, 8L, 8L, 7L, 7L, 7L, 7L, 7L, 7L, 10L, 10L, 10L, 10L, 10L,
10L, 9L, 9L, 9L, 9L, 9L, 9L, 12L, 12L, 12L, 12L, 12L, 12L, 11L,
11L, 11L, 11L, 11L, 11L, 14L, 14L, 14L, 14L, 14L, 14L, 13L, 13L,
13L, 13L, 13L, 13L, 16L, 16L, 16L, 16L, 16L, 16L, 15L, 15L, 15L,
15L, 15L, 15L, 18L, 18L, 18L, 18L, 18L, 18L, 17L, 17L, 17L, 17L,
17L, 17L, 20L, 20L, 20L, 20L, 20L, 20L, 19L, 19L, 19L, 19L, 19L,
19L, 22L, 22L, 22L, 22L, 22L, 22L, 21L, 21L, 21L, 21L, 21L, 21L
), .Label = c("A01nF", "A01yT", "A02nF", "A02yT", "A03nF", "A03yT",
"A04nF", "A04yT", "A05nF", "A05yT", "A06nF", "A06yT", "A07nF",
"A07yT", "A08nF", "A08yT", "A10nF", "A10yT", "A11nF", "A11yT",
"A13nF", "A13yT"), class = "factor"), Level = structure(c(1L,
2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L,
3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L,
1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L,
2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L,
3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L,
1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L,
2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L,
3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L,
1L, 2L, 3L), .Label = c("X", "Y", "Z"), class = "factor"), Day1 = c(3L,
1L, 4L, 2L, 4L, 2L, 5L, 4L, 1L, 2L, 5L, 1L, 5L, 2L, 5L, 5L, 3L,
5L, 3L, 3L, 1L, 4L, 1L, 1L, 5L, 4L, 1L, 5L, 4L, 5L, 3L, 5L, 3L,
5L, 3L, 4L, 2L, 4L, 2L, 4L, 3L, 1L, 1L, 3L, 1L, 3L, 1L, 5L, 2L,
4L, 4L, 3L, 1L, 4L, 4L, 1L, 4L, 1L, 2L, 5L, 1L, 5L, 1L, 2L, 4L,
4L, 4L, 4L, 2L, 4L, 5L, 5L, 4L, 1L, 3L, 2L, 3L, 5L, 4L, 3L, 2L,
3L, 5L, 4L, 1L, 3L, 4L, 3L, 3L, 5L, 3L, 1L, 1L, 4L, 4L, 5L, 1L,
4L, 4L, 4L, 1L, 4L, 5L, 5L, 1L, 5L, 3L, 1L, 4L, 1L, 4L, 5L, 5L,
3L, 3L, 2L, 4L, 5L, 3L, 2L, 1L, 5L, 5L, 2L, 2L, 3L, 4L, 3L, 4L,
2L, 2L, 4L), Day2 = c(10L, 9L, 7L, 7L, 6L, 7L, 10L, 9L, 10L,
6L, 10L, 7L, 8L, 9L, 8L, 9L, 7L, 10L, 7L, 10L, 6L, 8L, 6L, 8L,
8L, 8L, 10L, 6L, 8L, 8L, 6L, 10L, 7L, 10L, 7L, 10L, 6L, 6L, 7L,
9L, 8L, 10L, 8L, 7L, 9L, 8L, 6L, 9L, 7L, 9L, 8L, 6L, 6L, 8L,
10L, 7L, 8L, 6L, 8L, 8L, 6L, 9L, 10L, 6L, 8L, 7L, 9L, 7L, 8L,
10L, 10L, 6L, 7L, 10L, 9L, 9L, 8L, 9L, 6L, 8L, 6L, 8L, 6L, 9L,
10L, 7L, 7L, 7L, 8L, 7L, 8L, 10L, 7L, 8L, 9L, 6L, 8L, 9L, 8L,
9L, 6L, 7L, 10L, 9L, 10L, 7L, 6L, 9L, 9L, 9L, 6L, 10L, 9L, 8L,
9L, 7L, 10L, 7L, 10L, 9L, 6L, 8L, 9L, 8L, 9L, 6L, 6L, 10L, 9L,
8L, 8L, 7L), Day4 = c(11L, 12L, 14L, 11L, 15L, 15L, 12L, 11L,
15L, 12L, 15L, 12L, 12L, 11L, 15L, 15L, 13L, 11L, 13L, 14L, 12L,
11L, 13L, 12L, 15L, 15L, 14L, 11L, 15L, 11L, 12L, 11L, 13L, 11L,
12L, 13L, 13L, 14L, 13L, 15L, 14L, 15L, 12L, 14L, 11L, 13L, 15L,
11L, 12L, 13L, 11L, 15L, 11L, 13L, 11L, 11L, 14L, 12L, 14L, 15L,
11L, 12L, 15L, 12L, 13L, 12L, 14L, 12L, 11L, 13L, 12L, 12L, 11L,
15L, 13L, 12L, 11L, 12L, 13L, 14L, 14L, 14L, 13L, 12L, 15L, 12L,
15L, 15L, 12L, 13L, 12L, 12L, 12L, 14L, 13L, 13L, 14L, 11L, 12L,
11L, 15L, 11L, 11L, 11L, 14L, 11L, 12L, 15L, 15L, 11L, 12L, 14L,
15L, 14L, 14L, 12L, 14L, 13L, 15L, 15L, 14L, 13L, 12L, 15L, 15L,
11L, 13L, 12L, 11L, 13L, 12L, 14L)), class = "data.frame", row.names = c(NA,
-132L))

Tabu search in R

Good evening,
As part of a data analysis course we have been thrown into the Metaheuristics realm.....and I am really struggling to understand how to implement a Tabu search in R since my background in programming is rather limited.
I haven't found any R or Python example on Google or youtube either so I'm really praying I'll find something here.
The problem I have is similar to the "location problem" in optimisation. I need to find the best combination of Hubs that minimizes the total distance between Hubs and nodes.
I need to find 5 hubs, and the total capacity for each one is 120
nodes <- structure(list(node_number = 1:50,
x = c(2L, 80L, 36L, 57L, 33L, 76L, 77L, 94L,
89L, 59L, 39L, 87L, 44L, 2L, 19L, 5L,
58L, 14L, 43L, 87L, 11L, 31L, 51L, 55L,
84L, 12L, 53L, 53L, 33L, 69L, 43L, 10L,
8L, 3L, 96L, 6L, 59L, 66L, 22L, 75L, 4L,
41L, 92L, 12L, 60L, 35L, 38L, 9L, 54L, 1L),
y = c(62L, 25L, 88L, 23L, 17L, 43L, 85L, 6L, 11L,
72L, 82L, 24L, 76L, 83L, 43L, 27L, 72L, 50L,
18L, 7L, 56L, 16L, 94L, 13L, 57L, 2L, 33L, 10L,
32L, 67L, 5L, 75L, 26L, 1L, 22L, 48L, 22L, 69L,
50L, 21L, 81L, 97L, 34L, 64L, 84L, 100L, 2L, 9L, 59L, 58L),
node_demand = c(3L, 14L, 1L, 14L, 19L, 2L, 14L, 6L,
7L, 6L, 10L, 18L, 3L, 6L, 20L, 4L,
14L, 11L, 19L, 15L, 15L, 4L, 13L,
13L, 5L, 16L, 3L, 7L, 14L, 17L,
3L, 3L, 12L, 14L, 20L, 13L, 10L,
9L, 6L, 18L, 7L, 20L, 9L, 1L, 8L,
5L, 1L, 7L, 9L, 2L)),
.Names = c("node_number", "x", "y", "node_demand"),
class = "data.frame", row.names = c(NA, -50L))
hubs_required = 5
total_capacity = 120
My strategy was to create a distance matrix, then I will create another 50 x 50 matrix to represent wether a node becomes a hub or not, and finally I will multiply both and add all the distances to get the total distance.
I created the dataframe:
nodes_df <- as.data.frame(nodes)
colnames(nodes_df) <- c("x", "y", "node_demand")
rownames(nodes_df) <- paste('Node',1:50)
I created the distance matrix
distance_df <-as.data.frame(as.matrix(round(dist(nodes_df,method = "euclidean",diag = TRUE,upper = TRUE))))
colnames(distance_df) <- paste("Node",1:50)
I created the node demand matrix:
demand <- as.vector(rep(c(nodes_df[,'node_demand']),50))
demand_matrix <- matrix(demand,nrow=50,ncol=50,byrow = TRUE)
diag(demand_matrix) <- 0
demand_matrix <- as.data.frame(demand_matrix)
I created an empty matrix to show whether a node becomes a hub "1" or not "0"
hubs_matrix <- matrix(0,nrow = 50,ncol = 50,byrow = TRUE)
colnames(hubs_matrix) <- paste("Hub",1:50)
rownames(hubs_matrix) <- paste("Node",1:50)
Then to create the initial solution I randomly assign Hubs and calculate the distance and demand.
set.seed(37)
hubs_matrix <- do.call("cbind", lapply(1:50, function(x) sample(c(1, rep(0, 49)), 50)))
sum_distances <- (hubs_matrix * distance_df)
sum(rowSums(sum_distances))
The idea is to try different combinations of '1'' and '0' as to minimise the total distance but I am having the following issues:
I got no idea how to do the local search and do the permutations from the initial solution.
I got no idea how to prevent R to use the best solution for a certain period of time, i.e the Tabu list
I got no idea how to deal with the supply restriction for each node ( total demand from each node < 120), I could do it with a loop but since in this case I'm multiplying matrices I'm pretty lost.
Anybody could give me a hand???
Many thanks!

Subsetting from a dataframe in R

I have sampled 'n' rows from a dataframe called nodes:
nodes <- structure(list(node_number = 1:50,
x = c(2L, 80L, 36L, 57L, 33L, 76L, 77L, 94L,
89L, 59L, 39L, 87L, 44L, 2L, 19L, 5L,
58L, 14L, 43L, 87L, 11L, 31L, 51L, 55L,
84L, 12L, 53L, 53L, 33L, 69L, 43L, 10L,
8L, 3L, 96L, 6L, 59L, 66L, 22L, 75L, 4L,
41L, 92L, 12L, 60L, 35L, 38L, 9L, 54L, 1L),
y = c(62L, 25L, 88L, 23L, 17L, 43L, 85L, 6L, 11L,
72L, 82L, 24L, 76L, 83L, 43L, 27L, 72L, 50L,
18L, 7L, 56L, 16L, 94L, 13L, 57L, 2L, 33L, 10L,
32L, 67L, 5L, 75L, 26L, 1L, 22L, 48L, 22L, 69L,
50L, 21L, 81L, 97L, 34L, 64L, 84L, 100L, 2L, 9L, 59L, 58L),
node_demand = c(3L, 14L, 1L, 14L, 19L, 2L, 14L, 6L,
7L, 6L, 10L, 18L, 3L, 6L, 20L, 4L,
14L, 11L, 19L, 15L, 15L, 4L, 13L,
13L, 5L, 16L, 3L, 7L, 14L, 17L,
3L, 3L, 12L, 14L, 20L, 13L, 10L,
9L, 6L, 18L, 7L, 20L, 9L, 1L, 8L,
5L, 1L, 7L, 9L, 2L)),
.Names = c("node_number", "x", "y", "node_demand"),
class = "data.frame", row.names = c(NA, -50L))
To sample I use this code:
hubs <- nodes[sample(1:total_nodes, hubs_required, replace = FALSE),]
Which returns :
node_number x y node_demand
33 33 8 26 12
14 14 2 83 6
42 42 41 97 20
13 13 44 76 3
10 10 59 72 6
I would like to return all the rows that haven't been selected so that I can perform a series of calculations on them.
I thought that using something like data[-sample,] would work but I get the following error
Error in xj[i] : invalid subscript type 'list'.
Anybody know who could I get these values?

It would be easier to keep the list of indexes that selected. Somthing like
hubs <- nodes[keep <- sample(1:total_nodes, hubs_required, replace = FALSE),]
other_hubs <- nodes[-keep, ]
Otherwise, if your data has some sort of key/ID, you can do something like
other_hubs <- nodes[nodes%node_number %in% hubs$node_number, ]
or with dplyr, this can be an anti-join
nodes %>% anti_join(hubs, by="node_number")

polynomial fitting and plotting regression line in R

I am trying to find orthogonal polynomials of degree 3 for my data. The purpose of this is that i would like to visualise different polynomials fittings on my data: degree 3 and degree 7. I am using the same code as our profesor in class, however I cannot obtain nice results.
orthpoly <- poly(Air_reduced$Temp, order=3)
Air_reduced$xo1 <- orthpoly[,1]
Air_reduced$xo2 <- orthpoly[,2]
Air_reduced$xo3 <- orthpoly[,3]
polymodel1 <- lm(Ozone ~ xo1 + xo2 + xo3, data=Air_reduced)
Air_reduced$fitted1 <- fitted(polymodel1)
?plot
plot(Air_reduced$Temp,Air_reduced$Ozone,xlab="x",ylab="f(x)",
cex.lab=1.5,cex.axis=1.3,col="red",cex=1.3,
main="Polynomial of degree 3", xlim = c(50,97), ylim = c(0,100))
lines(Air_reduced$Temp, Air_reduced$fitted1,col="blue",lwd=3)
however this produces an ugly graph. There seem to be numerous regression lines.
What am i doing wrong?
Data:
structure(list(Ozone = c(41L, 36L, 12L, 18L, 23L, 19L, 8L, 16L,
11L, 14L, 18L, 14L, 34L, 6L, 30L, 11L, 1L, 11L, 4L, 32L, 23L,
45L, 37L, 29L, 71L, 39L, 23L, 21L, 37L, 20L, 12L, 13L, 49L, 32L,
64L, 40L, 77L, 97L, 97L, 85L, 10L, 27L, 7L, 48L, 35L, 61L, 79L,
63L, 16L, 80L, 108L, 20L, 52L, 82L, 50L, 64L, 59L, 39L, 9L, 16L,
122L, 89L, 110L, 44L, 28L, 65L, 22L, 59L, 23L, 31L, 44L, 21L,
9L, 45L, 73L, 76L, 118L, 84L, 85L, 96L, 78L, 73L, 91L, 47L, 32L,
20L, 23L, 21L, 24L, 44L, 21L, 28L, 9L, 13L, 46L, 18L, 13L, 24L,
16L, 13L, 23L, 36L, 7L, 14L, 30L, 14L, 18L, 20L), Solar.R = c(190L,
118L, 149L, 313L, 299L, 99L, 19L, 256L, 290L, 274L, 65L, 334L,
307L, 78L, 322L, 44L, 8L, 320L, 25L, 92L, 13L, 252L, 279L, 127L,
291L, 323L, 148L, 191L, 284L, 37L, 120L, 137L, 248L, 236L, 175L,
314L, 276L, 267L, 272L, 175L, 264L, 175L, 48L, 260L, 274L, 285L,
187L, 220L, 7L, 294L, 223L, 81L, 82L, 213L, 275L, 253L, 254L,
83L, 24L, 77L, 255L, 229L, 207L, 192L, 273L, 157L, 71L, 51L,
115L, 244L, 190L, 259L, 36L, 212L, 215L, 203L, 225L, 237L, 188L,
167L, 197L, 183L, 189L, 95L, 92L, 252L, 220L, 230L, 259L, 236L,
259L, 238L, 24L, 112L, 237L, 224L, 27L, 238L, 201L, 238L, 14L,
139L, 49L, 20L, 193L, 191L, 131L, 223L), Wind = c(7.4, 8, 12.6,
11.5, 8.6, 13.8, 20.1, 9.7, 9.2, 10.9, 13.2, 11.5, 12, 18.4,
11.5, 9.7, 9.7, 16.6, 9.7, 12, 12, 14.9, 7.4, 9.7, 13.8, 11.5,
8, 14.9, 20.7, 9.2, 11.5, 10.3, 9.2, 9.2, 4.6, 10.9, 5.1, 6.3,
5.7, 7.4, 14.3, 14.9, 14.3, 6.9, 10.3, 6.3, 5.1, 11.5, 6.9, 8.6,
8, 8.6, 12, 7.4, 7.4, 7.4, 9.2, 6.9, 13.8, 7.4, 4, 10.3, 8, 11.5,
11.5, 9.7, 10.3, 6.3, 7.4, 10.9, 10.3, 15.5, 14.3, 9.7, 8, 9.7,
2.3, 6.3, 6.3, 6.9, 5.1, 2.8, 4.6, 7.4, 15.5, 10.9, 10.3, 10.9,
9.7, 14.9, 15.5, 6.3, 10.9, 11.5, 6.9, 13.8, 10.3, 10.3, 8, 12.6,
9.2, 10.3, 10.3, 16.6, 6.9, 14.3, 8, 11.5), Temp = c(67L, 72L,
74L, 62L, 65L, 59L, 61L, 69L, 66L, 68L, 58L, 64L, 66L, 57L, 68L,
62L, 59L, 73L, 61L, 61L, 67L, 81L, 76L, 82L, 90L, 87L, 82L, 77L,
72L, 65L, 73L, 76L, 85L, 81L, 83L, 83L, 88L, 92L, 92L, 89L, 73L,
81L, 80L, 81L, 82L, 84L, 87L, 85L, 74L, 86L, 85L, 82L, 86L, 88L,
86L, 83L, 81L, 81L, 81L, 82L, 89L, 90L, 90L, 86L, 82L, 80L, 77L,
79L, 76L, 78L, 78L, 77L, 72L, 79L, 86L, 97L, 94L, 96L, 94L, 91L,
92L, 93L, 93L, 87L, 84L, 80L, 78L, 75L, 73L, 81L, 76L, 77L, 71L,
71L, 78L, 67L, 76L, 68L, 82L, 64L, 71L, 81L, 69L, 63L, 70L, 75L,
76L, 68L), Month = c(5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L,
5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 6L, 6L, 6L,
6L, 6L, 6L, 6L, 6L, 6L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L,
7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 8L,
8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L,
8L, 8L, 8L, 8L, 8L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L,
9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L,
9L, 9L), Day = c(1L, 2L, 3L, 4L, 7L, 8L, 9L, 12L, 13L, 14L, 15L,
16L, 17L, 18L, 19L, 20L, 21L, 22L, 23L, 24L, 28L, 29L, 31L, 7L,
9L, 10L, 13L, 16L, 17L, 18L, 19L, 20L, 2L, 3L, 5L, 6L, 7L, 8L,
9L, 10L, 12L, 13L, 15L, 16L, 17L, 18L, 19L, 20L, 21L, 24L, 25L,
26L, 27L, 28L, 29L, 30L, 31L, 1L, 2L, 3L, 7L, 8L, 9L, 12L, 13L,
14L, 16L, 17L, 18L, 19L, 20L, 21L, 22L, 24L, 26L, 28L, 29L, 30L,
31L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 11L, 12L, 13L,
14L, 15L, 16L, 17L, 18L, 19L, 20L, 21L, 22L, 23L, 24L, 25L, 26L,
28L, 29L, 30L), ID = c(1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L,
11L, 12L, 13L, 14L, 15L, 16L, 17L, 18L, 19L, 20L, 21L, 22L, 24L,
25L, 26L, 27L, 28L, 29L, 30L, 31L, 32L, 33L, 35L, 36L, 37L, 38L,
39L, 40L, 41L, 42L, 43L, 44L, 45L, 46L, 47L, 48L, 49L, 50L, 51L,
52L, 53L, 54L, 55L, 56L, 57L, 58L, 59L, 60L, 61L, 62L, 63L, 64L,
65L, 66L, 67L, 68L, 69L, 70L, 71L, 72L, 73L, 74L, 75L, 76L, 78L,
79L, 80L, 81L, 82L, 83L, 84L, 85L, 86L, 87L, 88L, 89L, 90L, 91L,
92L, 93L, 94L, 95L, 96L, 97L, 98L, 99L, 100L, 101L, 102L, 103L,
104L, 105L, 106L, 107L, 108L, 109L, 110L, 111L)), .Names = c("Ozone",
"Solar.R", "Wind", "Temp", "Month", "Day", "ID"), row.names = c(NA,
-108L), class = c("tbl_df", "tbl", "data.frame"))

Order your data by your x-axis before plotting, and your plot will be pretty:
Air_reduced = Air_reduced[order(Air_reduced$Temp), ]
As a side note, I'd encourage you to try out ggplot2 for plotting. It can fit simple models and plot all at once, and it's smart about defaults (default labels, default ordering the points when plotting a line...). In this case, if you just want a plot with both polynomials, it takes just a few lines of code:
library(ggplot2)
ggplot(Air_reduced, aes(x = Temp, y = Ozone)) +
geom_point(color = "red") +
stat_smooth(method = "lm",
formula = y ~ poly(x, 3),
aes(color = "3rd")) +
stat_smooth(method = "lm",
formula = y ~ poly(x, 7),
aes(color = "7th")) +
scale_color_manual(
name = "Polynomial Degree",
breaks = c("3rd", "7th"),
values = c("blue", "green4")
)

Resources