Chapter 4 Data Exploration

t1 <- dat.s %>%
  group_by(patientID) %>%
  summarise(types = n(), m=max(as.numeric(dist_cat)), 
            f = median(freq), k = sum(n_clust)) %>%
  filter(types == 3)

epiDisplay::tab1(t1$types)

4.1 Profiles

dat.s %>%
  ggplot(aes(x=dist_cat, fill = dist_cat)) +
  geom_bar(alpha = .6) +
  guides(fill = F) +
  scale_fill_viridis_d() +
  theme_classic()

4.2 Example base-stayer (ID=419)

dat.t4 %>%
  filter(patientID==419) %>%
  dplyr::select(data) %>%
  unnest() %>%
  n.clust.sp(full=T)

## $K
## [1] 1
## 
## $`Cluster Plot`

dat.t4 %>%
  filter(patientID==419) %>%
  dplyr::select(c3_gd) %>%
  unnest() %>%
  plot.pattern()

dat.t4 %>%
  filter(patientID==419) %>%
  dplyr::select(c3_s) %>%
  unnest()

## # A tibble: 1 x 11
##   dist_cat avg_gd min_gd max_gd sd_gd avg_GC min_GC max_GC sd_GC  freq n_clust
##   <fct>     <dbl>  <dbl>  <dbl> <dbl>  <dbl>  <dbl>  <dbl> <dbl> <int>   <int>
## 1 base          0      0      0    NA      0      0      0    NA   145       1

4.3 Example local mover (ID=584)

dat.t4 %>%
  filter(patientID==584) %>%
  dplyr::select(data) %>%
  unnest() %>%
  n.clust.sp(full=T)

## $K
## [1] 41
## 
## $`Cluster Plot`

dat.t4 %>%
  filter(patientID==584) %>%
  dplyr::select(c3_gd) %>%
  unnest() %>%
  plot.pattern()

dat.t4 %>%
  filter(patientID==584) %>%
  dplyr::select(c3_s) %>%
  unnest()

## # A tibble: 2 x 11
##   dist_cat avg_gd min_gd max_gd sd_gd avg_GC min_GC max_GC sd_GC  freq n_clust
##   <fct>     <dbl>  <dbl>  <dbl> <dbl>  <dbl>  <dbl>  <dbl> <dbl> <int>   <int>
## 1 base         0      0      0    NA      0      0      0    NA     95       1
## 2 local     2752.   392.  8958. 2015.  2752.   392.  8958. 2015.   210      40

4.4 Example mid mover (ID=178)

dat.t4 %>%
  filter(patientID==283) %>%
  dplyr::select(data) %>%
  unnest() %>%
  n.clust.sp(full=T)

## $K
## [1] 33
## 
## $`Cluster Plot`

dat.t4 %>%
  filter(patientID==283) %>%
  dplyr::select(c3_gd) %>%
  unnest() %>%
  plot.pattern()

dat.t4 %>%
  filter(patientID==283) %>%
  dplyr::select(c3_s) %>%
  unnest()

## # A tibble: 3 x 11
##   dist_cat avg_gd min_gd max_gd  sd_gd avg_GC min_GC max_GC  sd_GC  freq n_clust
##   <fct>     <dbl>  <dbl>  <dbl>  <dbl>  <dbl>  <dbl>  <dbl>  <dbl> <int>   <int>
## 1 base     0.         0  0.        NA  0.         0  0.        NA     64       1
## 2 local    1.14e4  1153. 3.44e4  8328. 1.14e4  1153. 3.44e4  8328.    75      27
## 3 mid      2.23e5 93743. 3.06e5 98417. 2.23e5 93743. 3.06e5 98417.     9       5

4.5 Example distant mover (ID=44)

dat.t4 %>%
  filter(patientID==44) %>%
  dplyr::select(data) %>%
  unnest() %>%
  n.clust.sp(full=T)

## $K
## [1] 29
## 
## $`Cluster Plot`

dat.t4 %>%
  filter(patientID==44) %>%
  dplyr::select(c3_gd) %>%
  unnest() %>%
  plot.pattern()

dat.t4 %>%
  filter(patientID==44) %>%
  dplyr::select(c3_s) %>%
  unnest()

## # A tibble: 4 x 11
##   dist_cat avg_gd min_gd max_gd   sd_gd avg_GC min_GC max_GC   sd_GC  freq
##   <fct>     <dbl>  <dbl>  <dbl>   <dbl>  <dbl>  <dbl>  <dbl>   <dbl> <int>
## 1 base     0.     0.     0.         NA  0.     0.     0.         NA     89
## 2 local    6.87e3 1.24e2 1.41e4   3489. 6.87e3 1.24e2 1.41e4   3489.   111
## 3 mid      2.67e5 1.48e5 3.43e5  76464. 2.67e5 1.48e5 3.43e5  76464.    16
## 4 distant  7.61e5 6.67e5 9.54e5 141553. 7.61e5 6.67e5 9.54e5 141553.    12
## # … with 1 more variable: n_clust <int>