Data visualization with ggplot2
Marvanessa Dinorog
3/29/2022
library(tidyverse)## Warning: package 'tidyverse' was built under R version 4.1.3## -- Attaching packages --------------------------------------- tidyverse 1.3.1 --## v ggplot2 3.3.5 v purrr 0.3.4
## v tibble 3.1.6 v dplyr 1.0.8
## v tidyr 1.2.0 v stringr 1.4.0
## v readr 2.1.2 v forcats 0.5.1## Warning: package 'ggplot2' was built under R version 4.1.3## Warning: package 'tidyr' was built under R version 4.1.3## Warning: package 'readr' was built under R version 4.1.3## Warning: package 'forcats' was built under R version 4.1.3## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()library(readxl)
Surveys <- read_csv("D:/stat 50/Surveys.csv")## Rows: 34786 Columns: 13
## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (6): species_id, sex, genus, species, taxa, plot_type
## dbl (7): record_id, month, day, year, plot_id, hindfoot_length, weight
##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.Surveys## # A tibble: 34,786 x 13
## record_id month day year plot_id species_id sex hindfoot_length weight
## <dbl> <dbl> <dbl> <dbl> <dbl> <chr> <chr> <dbl> <dbl>
## 1 1 7 16 1977 2 NL M 32 NA
## 2 72 8 19 1977 2 NL M 31 NA
## 3 224 9 13 1977 2 NL <NA> NA NA
## 4 266 10 16 1977 2 NL <NA> NA NA
## 5 349 11 12 1977 2 NL <NA> NA NA
## 6 363 11 12 1977 2 NL <NA> NA NA
## 7 435 12 10 1977 2 NL <NA> NA NA
## 8 506 1 8 1978 2 NL <NA> NA NA
## 9 588 2 18 1978 2 NL M NA 218
## 10 661 3 11 1978 2 NL <NA> NA NA
## # ... with 34,776 more rows, and 4 more variables: genus <chr>, species <chr>,
## # taxa <chr>, plot_type <chr>surveys_complete<-SurveysPlotting with ggplot2
library(ggplot2)
ggplot(data = surveys_complete, aes(x = weight, y = hindfoot_length)) +
geom_point()## Warning: Removed 4048 rows containing missing values (geom_point).
ggplot(data = surveys_complete)
ggplot(data = surveys_complete, mapping = aes(x = weight, y = hindfoot_length))
# Assign plot to a variable
surveys_plot <- ggplot(data = surveys_complete,
mapping = aes(x = weight, y = hindfoot_length))
# Draw the plot
surveys_plot +
geom_point()## Warning: Removed 4048 rows containing missing values (geom_point).
Building your plots iteratively
ggplot(data = surveys_complete, aes(x = weight, y = hindfoot_length)) +
geom_point()## Warning: Removed 4048 rows containing missing values (geom_point).
ggplot(data = surveys_complete, aes(x = weight, y = hindfoot_length)) +
geom_point(alpha = 0.1)## Warning: Removed 4048 rows containing missing values (geom_point).
ggplot(data = surveys_complete, mapping = aes(x = weight, y = hindfoot_length)) +
geom_point(alpha = 0.1, color = "blue")## Warning: Removed 4048 rows containing missing values (geom_point).
ggplot(data = surveys_complete, mapping = aes(x = weight, y = hindfoot_length)) +
geom_point(alpha = 0.1, aes(color = species_id))## Warning: Removed 4048 rows containing missing values (geom_point).
Challenge
ggplot(data = surveys_complete,
mapping = aes(x = species_id, y = weight)) +
geom_point(aes(color = plot_type))## Warning: Removed 2503 rows containing missing values (geom_point).
Boxplot
ggplot(data = surveys_complete, mapping = aes(x = species_id, y = weight)) +
geom_boxplot()## Warning: Removed 2503 rows containing non-finite values (stat_boxplot).
ggplot(data = surveys_complete, mapping = aes(x = species_id, y = weight)) +
geom_boxplot(alpha = 0) +
geom_jitter(alpha = 0.3, color = "tomato")## Warning: Removed 2503 rows containing non-finite values (stat_boxplot).## Warning: Removed 2503 rows containing missing values (geom_point).
Plotting time series data
yearly_counts <- surveys_complete %>%
count(year, genus)ggplot(data = yearly_counts, aes(x = year, y = n)) +
geom_line()
ggplot(data = yearly_counts, aes(x = year, y = n, group = genus)) +
geom_line()
ggplot(data = yearly_counts, aes(x = year, y = n, color = genus)) +
geom_line()
Integrating the pipe operator with ggplot2
yearly_counts %>%
ggplot(mapping = aes(x = year, y = n, color = genus)) +
geom_line()
yearly_counts_graph <- surveys_complete %>%
count(year, genus) %>%
ggplot(mapping = aes(x = year, y = n, color = genus)) +
geom_line()
yearly_counts_graph
Faceting
ggplot(data = yearly_counts, aes(x = year, y = n)) +
geom_line() +
facet_wrap(facets = vars(genus))## geom_path: Each group consists of only one observation. Do you need to adjust
## the group aesthetic?
## geom_path: Each group consists of only one observation. Do you need to adjust
## the group aesthetic?
yearly_sex_counts <- surveys_complete %>%
count(year, genus, sex)ggplot(data = yearly_sex_counts, mapping = aes(x = year, y = n, color = sex)) +
geom_line() +
facet_wrap(facets = vars(genus))## geom_path: Each group consists of only one observation. Do you need to adjust
## the group aesthetic?
## geom_path: Each group consists of only one observation. Do you need to adjust
## the group aesthetic?
ggplot(data = yearly_sex_counts,
mapping = aes(x = year, y = n, color = sex)) +
geom_line() +
facet_grid(rows = vars(sex), cols = vars(genus))## geom_path: Each group consists of only one observation. Do you need to adjust
## the group aesthetic?
## geom_path: Each group consists of only one observation. Do you need to adjust
## the group aesthetic?
## geom_path: Each group consists of only one observation. Do you need to adjust
## the group aesthetic?
## geom_path: Each group consists of only one observation. Do you need to adjust
## the group aesthetic?
## geom_path: Each group consists of only one observation. Do you need to adjust
## the group aesthetic?
# One column, facet by rows
ggplot(data = yearly_sex_counts,
mapping = aes(x = year, y = n, color = sex)) +
geom_line() +
facet_grid(rows = vars(genus))## geom_path: Each group consists of only one observation. Do you need to adjust
## the group aesthetic?
## geom_path: Each group consists of only one observation. Do you need to adjust
## the group aesthetic?
iggplot2 themes
ggplot(data = yearly_sex_counts,
mapping = aes(x = year, y = n, color = sex)) +
geom_line() +
facet_wrap(vars(genus)) +
theme_bw()## geom_path: Each group consists of only one observation. Do you need to adjust
## the group aesthetic?
## geom_path: Each group consists of only one observation. Do you need to adjust
## the group aesthetic?
Challenge
yearly_weight <- surveys_complete %>%
group_by(year, species_id) %>%
summarize(avg_weight = mean(weight))## `summarise()` has grouped output by 'year'. You can override using the
## `.groups` argument.ggplot(data = yearly_weight, mapping = aes(x=year, y=avg_weight)) +
geom_line() +
facet_wrap(vars(species_id)) +
theme_bw()## Warning: Removed 89 row(s) containing missing values (geom_path).## geom_path: Each group consists of only one observation. Do you need to adjust
## the group aesthetic?
## geom_path: Each group consists of only one observation. Do you need to adjust
## the group aesthetic?
## geom_path: Each group consists of only one observation. Do you need to adjust
## the group aesthetic?
## geom_path: Each group consists of only one observation. Do you need to adjust
## the group aesthetic?
## geom_path: Each group consists of only one observation. Do you need to adjust
## the group aesthetic?
Customization
ggplot(data = yearly_sex_counts, aes(x = year, y = n, color = sex)) +
geom_line() +
facet_wrap(vars(genus)) +
labs(title = "Observed genera through time",
x = "Year of observation",
y = "Number of individuals") +
theme_bw()## geom_path: Each group consists of only one observation. Do you need to adjust
## the group aesthetic?
## geom_path: Each group consists of only one observation. Do you need to adjust
## the group aesthetic?
ggplot(data = yearly_sex_counts, mapping = aes(x = year, y = n, color = sex)) +
geom_line() +
facet_wrap(vars(genus)) +
labs(title = "Observed genera through time",
x = "Year of observation",
y = "Number of individuals") +
theme_bw() +
theme(text=element_text(size = 16))## geom_path: Each group consists of only one observation. Do you need to adjust
## the group aesthetic?
## geom_path: Each group consists of only one observation. Do you need to adjust
## the group aesthetic?
ggplot(data = yearly_sex_counts, mapping = aes(x = year, y = n, color = sex)) +
geom_line() +
facet_wrap(vars(genus)) +
labs(title = "Observed genera through time",
x = "Year of observation",
y = "Number of individuals") +
theme_bw() +
theme(axis.text.x = element_text(colour = "grey20", size = 12, angle = 90, hjust = 0.5, vjust = 0.5),
axis.text.y = element_text(colour = "grey20", size = 12),
strip.text = element_text(face = "italic"),
text = element_text(size = 16))## geom_path: Each group consists of only one observation. Do you need to adjust
## the group aesthetic?
## geom_path: Each group consists of only one observation. Do you need to adjust
## the group aesthetic?
grey_theme <- theme(axis.text.x = element_text(colour="grey20", size = 12,
angle = 90, hjust = 0.5,
vjust = 0.5),
axis.text.y = element_text(colour = "grey20", size = 12),
text=element_text(size = 16))
ggplot(surveys_complete, aes(x = species_id, y = hindfoot_length)) +
geom_boxplot() +
grey_theme## Warning: Removed 3348 rows containing non-finite values (stat_boxplot).
Arranging plots
library(patchwork)## Warning: package 'patchwork' was built under R version 4.1.3plot_weight <- ggplot(data = surveys_complete, aes(x = species_id, y = weight)) +
geom_boxplot() +
labs(x = "Species", y = expression(log[10](Weight))) +
scale_y_log10()
plot_count <- ggplot(data = yearly_counts, aes(x = year, y = n, color = genus)) +
geom_line() +
labs(x = "Year", y = "Abundance")
plot_weight / plot_count + plot_layout(heights = c(3, 2))## Warning: Removed 2503 rows containing non-finite values (stat_boxplot).
Exporting plots
my_plot <- ggplot(data = yearly_sex_counts,
aes(x = year, y = n, color = sex)) +
geom_line() +
facet_wrap(vars(genus)) +
labs(title = "Observed genera through time",
x = "Year of observation",
y = "Number of individuals") +
theme_bw() +
theme(axis.text.x = element_text(colour = "grey20", size = 12, angle = 90,
hjust = 0.5, vjust = 0.5),
axis.text.y = element_text(colour = "grey20", size = 12),
text = element_text(size = 16))
ggsave("name_of_file.png", my_plot, width = 15, height = 10)## geom_path: Each group consists of only one observation. Do you need to adjust
## the group aesthetic?
## geom_path: Each group consists of only one observation. Do you need to adjust
## the group aesthetic?## This also works for plots combined with patchwork
plot_combined <- plot_weight / plot_count + plot_layout(heights = c(3, 2))
ggsave("plot_combined.png", plot_combined, width = 10, dpi = 300)## Saving 10 x 5 in image## Warning: Removed 2503 rows containing non-finite values (stat_boxplot).