added ggridges_lineage_country.R for dist by country
This commit is contained in:
parent
ee69445f11
commit
645827570f
1 changed files with 279 additions and 0 deletions
279
scripts/plotting/ggridges_lineage_country.R
Normal file
279
scripts/plotting/ggridges_lineage_country.R
Normal file
|
|
@ -0,0 +1,279 @@
|
||||||
|
|
||||||
|
|
||||||
|
#########################################################
|
||||||
|
# 1: Installing and loading required packages
|
||||||
|
#########################################################
|
||||||
|
|
||||||
|
#source("../Header_TT.R")
|
||||||
|
install.packages("qqman")
|
||||||
|
library(qqman)
|
||||||
|
|
||||||
|
source("combining_dfs_plotting.R")
|
||||||
|
#mcsm_data: raw file, 225, 15
|
||||||
|
#merged_df2 = 2201, 35
|
||||||
|
#merged_df3 = 205, 35 ("Can't trust non-numerical params')
|
||||||
|
|
||||||
|
#===============================================
|
||||||
|
# PLOTS: DUET vs GWAS: non-numerical
|
||||||
|
# lineage, country_code, etc
|
||||||
|
# merged_df2: 1592, 35
|
||||||
|
#===============================================
|
||||||
|
|
||||||
|
#########################
|
||||||
|
# Data for plot
|
||||||
|
#########################
|
||||||
|
df = merged_df2
|
||||||
|
df = merged_df2_comp
|
||||||
|
|
||||||
|
|
||||||
|
#========================
|
||||||
|
# Plot 1a: Lineage barplot
|
||||||
|
# x = lineage y = No of samples
|
||||||
|
# col = Lineage
|
||||||
|
# fill = lineage
|
||||||
|
#========================
|
||||||
|
is.factor(df$lineage)
|
||||||
|
df$lineage = as.factor(df$lineage)
|
||||||
|
is.factor(df$lineage)
|
||||||
|
|
||||||
|
table(df$lineage)
|
||||||
|
|
||||||
|
# subset only lineages1-4
|
||||||
|
sel_lineages = c("lineage1"
|
||||||
|
, "lineage2"
|
||||||
|
, "lineage3"
|
||||||
|
, "lineage4"
|
||||||
|
#, "lineage5"
|
||||||
|
#, "lineage6"
|
||||||
|
#, "lineage7"
|
||||||
|
)
|
||||||
|
|
||||||
|
# uncomment as necessary
|
||||||
|
df_lin = subset(df, subset = lineage %in% sel_lineages )
|
||||||
|
table(df_lin$lineage)
|
||||||
|
|
||||||
|
#%%%%%%%%%%%%%%%%%%%%%%%%%
|
||||||
|
# REASSIGNMENT
|
||||||
|
df <- df_lin
|
||||||
|
#%%%%%%%%%%%%%%%%%%%%%%%%%
|
||||||
|
|
||||||
|
############## begin plot
|
||||||
|
g = ggplot(df, aes(x = lineage))
|
||||||
|
g + geom_bar(aes(fill = lineage)) +
|
||||||
|
theme( axis.text.x = element_text(size = 13
|
||||||
|
, angle = 90
|
||||||
|
, hjust = 1
|
||||||
|
, vjust = 0.4)
|
||||||
|
, axis.text.y = element_text(size = 15
|
||||||
|
, angle = 0
|
||||||
|
, hjust = 1
|
||||||
|
, vjust = 0)
|
||||||
|
, axis.title.x = element_text(size = 15)
|
||||||
|
, axis.title.y = element_text(size = 15) ) +
|
||||||
|
labs(title = "Lineage"
|
||||||
|
, x = "Lineage"
|
||||||
|
, y = "No of samples")
|
||||||
|
|
||||||
|
|
||||||
|
#========================
|
||||||
|
# Plot 2: DUET, lineage, country_code and or_mychisq
|
||||||
|
# x = lineage y = DUET
|
||||||
|
# col = Lineage
|
||||||
|
# fill = country_code
|
||||||
|
#========================
|
||||||
|
### begin plot
|
||||||
|
g = ggplot(df, aes(x = country_code
|
||||||
|
, y = duet_scaled))
|
||||||
|
g + geom_point(aes(col = lineage
|
||||||
|
, size = or_mychisq)) +
|
||||||
|
theme(axis.text.x = element_text(size = 13
|
||||||
|
, angle = 90
|
||||||
|
, hjust = 1
|
||||||
|
, vjust = 0.4)
|
||||||
|
, axis.text.y = element_text(size = 15
|
||||||
|
, angle = 0
|
||||||
|
, hjust = 1
|
||||||
|
, vjust = 0)
|
||||||
|
, axis.title.x = element_text(size = 15)
|
||||||
|
, axis.title.y = element_text(size = 15) ) +
|
||||||
|
labs(title = "DUET, country_code, lineage, or_mychisq"
|
||||||
|
, x = "Lineage"
|
||||||
|
, y = "DUET (PS)")
|
||||||
|
|
||||||
|
|
||||||
|
#############
|
||||||
|
#========================
|
||||||
|
# Plot 3: DUET, lineage, or_mychisq
|
||||||
|
# x = lineage y = DUET
|
||||||
|
# col = Lineage
|
||||||
|
# fill = country_code
|
||||||
|
#========================
|
||||||
|
|
||||||
|
### begin plot
|
||||||
|
table(df$lineage)
|
||||||
|
|
||||||
|
g = ggplot(df, aes(x = lineage
|
||||||
|
, y = duet_scaled))
|
||||||
|
g + geom_point(aes(col = lineage
|
||||||
|
, size = or_mychisq)) +
|
||||||
|
theme(axis.text.x = element_text(size = 13
|
||||||
|
, angle = 90
|
||||||
|
, hjust = 1
|
||||||
|
, vjust = 0.4)
|
||||||
|
, axis.text.y = element_text(size = 15
|
||||||
|
, angle = 0
|
||||||
|
, hjust = 1
|
||||||
|
, vjust = 0)
|
||||||
|
, axis.title.x = element_text(size = 15)
|
||||||
|
, axis.title.y = element_text(size = 15) ) +
|
||||||
|
labs(title = "DUET, lineage, or_mychisq"
|
||||||
|
, x = "Lineage"
|
||||||
|
, y = "DUET (PS)")
|
||||||
|
|
||||||
|
#========================
|
||||||
|
# Plot 4-6: Distributions
|
||||||
|
# ggrdiges
|
||||||
|
#========================
|
||||||
|
|
||||||
|
df$country_code_symbols = as.character(df$country_code)
|
||||||
|
foo = df
|
||||||
|
|
||||||
|
foo = foo%>%
|
||||||
|
add_count(country_code)
|
||||||
|
|
||||||
|
n = which(colnames(foo) == "n")
|
||||||
|
colnames(foo)[n] = "count_country"
|
||||||
|
|
||||||
|
|
||||||
|
table(foo$count_country)
|
||||||
|
|
||||||
|
|
||||||
|
check = as.data.frame(cbind(foo$country_code_symbols, foo$count_country))
|
||||||
|
str(check)
|
||||||
|
check$V2 = as.numeric(check$V2)
|
||||||
|
min(check$V2); max(check$V2)
|
||||||
|
table(check$V2)
|
||||||
|
|
||||||
|
check2 = subset(check, check$V2>100)
|
||||||
|
check2 = subset(check2, is.na(check2$V1))
|
||||||
|
min(check2$V2); max(check2$V2)
|
||||||
|
|
||||||
|
check3 = subset(check2, check2$V1 != "")
|
||||||
|
table(check3$V1 != "")
|
||||||
|
|
||||||
|
|
||||||
|
# subset df with country containing >100 samples
|
||||||
|
# and no missing
|
||||||
|
|
||||||
|
#%%%%%%%%%%%%%%%%%%%%%%%%
|
||||||
|
# REASSIGNMENT
|
||||||
|
df2 = df
|
||||||
|
#%%%%%%%%%%%%%%%%%%%%%%%%
|
||||||
|
df2 = df2%>%
|
||||||
|
add_count(country_code)
|
||||||
|
|
||||||
|
str(df2$country_code); str(df2$n)
|
||||||
|
|
||||||
|
n = which(colnames(df2) == "n")
|
||||||
|
colnames(df2)[n] = "count_country"
|
||||||
|
|
||||||
|
table(df2$count_country>100 & df$country_code!= "")
|
||||||
|
df3 = subset(df2, df2$count_country>100 & df2$country_code != "")
|
||||||
|
|
||||||
|
|
||||||
|
#%%%%%%%%%%%%%%%%%%%%%%%%
|
||||||
|
# REASSIGNMENT
|
||||||
|
df = df3
|
||||||
|
#%%%%%%%%%%%%%%%%%%%%%%%%
|
||||||
|
|
||||||
|
#==================================================
|
||||||
|
my_ats = 15 # axis text size
|
||||||
|
my_als = 20 # axis label size
|
||||||
|
|
||||||
|
my_labels = c('Lineage 1', 'Lineage 2', 'Lineage 3', 'Lineage 4'
|
||||||
|
#, 'Lineage 5', 'Lineage 6', 'Lineage 7'
|
||||||
|
)
|
||||||
|
names(my_labels) = c('lineage1', 'lineage2', 'lineage3', 'lineage4'
|
||||||
|
# , 'lineage5', 'lineage6', 'lineage7'
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
|
#========================
|
||||||
|
# Plot 4: Distribution
|
||||||
|
# x = duet_scaled
|
||||||
|
# y = country
|
||||||
|
# fill = country_code
|
||||||
|
# facet = lineage
|
||||||
|
#========================
|
||||||
|
# works neatly!
|
||||||
|
|
||||||
|
p1 = ggplot(df, aes(x = duet_scaled
|
||||||
|
, y = country_code))+
|
||||||
|
|
||||||
|
#printFile=geom_density_ridges_gradient(
|
||||||
|
geom_density_ridges_gradient(aes(fill = country_code)
|
||||||
|
, scale = 3
|
||||||
|
, size = 0.3 ) +
|
||||||
|
facet_wrap( ~lineage
|
||||||
|
, scales = "free"
|
||||||
|
, switch = 'x'
|
||||||
|
, labeller = labeller(lineage = my_labels)
|
||||||
|
) +
|
||||||
|
coord_cartesian( xlim = c(-1, 1)) +
|
||||||
|
#scale_fill_gradientn(colours = c("#f8766d", "white", "#00bfc4")
|
||||||
|
# , name = "DUET" ) +
|
||||||
|
theme(axis.text.x = element_text(size = my_ats
|
||||||
|
, angle = 90
|
||||||
|
, hjust = 1
|
||||||
|
, vjust = 0.4)
|
||||||
|
|
||||||
|
#, axis.text.y = element_blank()
|
||||||
|
, axis.title.x = element_blank()
|
||||||
|
, axis.title.y = element_blank()
|
||||||
|
, axis.ticks.y = element_blank()
|
||||||
|
, plot.title = element_blank()
|
||||||
|
, strip.text = element_text(size = my_als)
|
||||||
|
, legend.text = element_text(size = my_als-5)
|
||||||
|
, legend.title = element_text(size = my_als)
|
||||||
|
)
|
||||||
|
|
||||||
|
p1
|
||||||
|
|
||||||
|
|
||||||
|
#========================
|
||||||
|
# Plot 5: Distribution
|
||||||
|
# x = duet_scaled
|
||||||
|
# y = country_code
|
||||||
|
# fill = lineage
|
||||||
|
# facet = NONE
|
||||||
|
#========================
|
||||||
|
# no facet wrap
|
||||||
|
|
||||||
|
p2 = ggplot(df, aes(x = duet_scaled
|
||||||
|
, y = country_code))+
|
||||||
|
|
||||||
|
geom_density_ridges_gradient(aes(fill = factor(lineage))
|
||||||
|
, scale = 3
|
||||||
|
, size = 0.3 ) +
|
||||||
|
coord_cartesian( xlim = c(-1, 1)) +
|
||||||
|
#scale_fill_gradientn(colours = c("#f8766d", "white", "#00bfc4")
|
||||||
|
# , name = "DUET" ) +
|
||||||
|
#scale_fill_continuous(colours = c("darkgreen", "pink", "orange", "brown")
|
||||||
|
# , name = "lineage" ) +
|
||||||
|
theme(axis.text.x = element_text(size = my_ats
|
||||||
|
, angle = 90
|
||||||
|
, hjust = 1
|
||||||
|
, vjust = 0.4)
|
||||||
|
|
||||||
|
#, axis.text.y = element_blank()
|
||||||
|
, axis.title.x = element_blank()
|
||||||
|
, axis.title.y = element_blank()
|
||||||
|
, axis.ticks.y = element_blank()
|
||||||
|
, plot.title = element_blank()
|
||||||
|
, strip.text = element_text(size = my_als)
|
||||||
|
, legend.text = element_text(size = my_als-5)
|
||||||
|
, legend.title = element_text(size = my_als)
|
||||||
|
)
|
||||||
|
|
||||||
|
p2
|
||||||
|
|
||||||
Loading…
Add table
Add a link
Reference in a new issue