A lot of the data was modified from

Leach, TH, LA Winslow, FW Acker, JA Bloomfield, CW Boylen, PA Bukaveckas,

DF Charles, RA Daniels, CT Driscoll, LW Eichler, JL Farrell, CS Funk,

CA Goodrich, TM Michelena, SA Nierzwicki-Bauer, KM Roy, WH Shaw,

JW Sutherland, MW Swinton, DA Winkler, KC Rose.

Long-term dataset on aquatic responses to concurrent climate change

and recovery from acidification. 2018. Scientific Data. online.

https://doi.org/10.1038/sdata.2018.59. 10.1038/sdata.2018.59

Load Libraries

Again, we use these libraries almost all the time in every script

# Load Libraries ----
# this is done each time you run a script
library(readxl) # read in excel files
library(tidyverse) # dplyr and piping and ggplot etc
library(lubridate) # dates and times
library(scales) # scales on ggplot ases
library(skimr) # quick summary stats
library(janitor) # clean up excel imports
library(patchwork) # multipanel graphs

So now we have seen how to look at the data

What if we wanted to modify the data in terms of columns or rows

# lets read in a new file to add some complexity for fun
lakes.df <- read_csv("data/reduced_lake_long_genus_species.csv")
## 
## ── Column specification ────────────────────────────────────────────────────────
## cols(
##   permanent_id = col_double(),
##   lake_name = col_character(),
##   date = col_date(format = ""),
##   group = col_character(),
##   genus_species = col_character(),
##   org_l = col_double(),
##   year = col_double()
## )

Mutate —–

If you want to modify variables you can change them with MUTATE

# Mutate - log
lakes_modified.df <- lakes.df %>%
  mutate(log_org_l = log10(org_l + 1))
# Mutate and mean ----
lakes_modified.df <- lakes.df %>%
  mutate(mean_org_l = mean(org_l, na.rm=TRUE))
# Mean by group ------
lakes_modified.df <- lakes.df %>%
  group_by(group) %>%
  mutate(mean_org_l = mean(org_l, na.rm=TRUE))
# how would you modify this to do the mean by group and lake?
lakes_modified.df <- lakes.df %>%
  group_by(group) %>%
  mutate(mean_org_l = mean(org_l, na.rm=TRUE))
# Mean and Standard Error -----
# there is no na.rm=TRUE for sum so we have to do some 
# special things
lakes_modified.df <- lakes.df %>%
  group_by(group) %>%
  mutate(mean_org_l = mean(org_l, na.rm=TRUE),
         se_org_l = sd(org_l, na.rm = T) / sqrt(sum(!is.na(org_l))))

So mutate is a key thing we will use a lot in the future

but this just adds a new column

Summarize data —-

What if we wanted a summary dataset rather than adding a new column

# there are two ways...
# the first is do all of the math manually
lakes_summary.df <- lakes.df %>%
  group_by(lake_name, group) %>%
  summarize(mean_org_l = mean(org_l, na.rm=TRUE),
         se_org_l = sd(org_l, na.rm = T) / sqrt(sum(!is.na(org_l))))
## `summarise()` has grouped output by 'lake_name'. You can override using the `.groups` argument.

the other way to do this is using skimr to look at summary data

lakes.df %>% group_by(lake_name, group) %>% skim(org_l)
Data summary
Name Piped data
Number of rows 1368
Number of columns 7
_______________________
Column type frequency:
numeric 1
________________________
Group variables lake_name, group

Variable type: numeric

skim_variable lake_name group n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
org_l Grass Cladoceran 0 1 1.50 3.12 0 0 0.08 1.63 19.48 ▇▁▁▁▁
org_l Grass Copepod 0 1 4.88 9.47 0 0 0.00 4.51 46.06 ▇▁▁▁▁
org_l Indian Cladoceran 0 1 2.58 7.19 0 0 0.00 0.80 56.20 ▇▁▁▁▁
org_l Indian Copepod 0 1 3.21 6.72 0 0 0.07 1.96 34.22 ▇▁▁▁▁
org_l South Cladoceran 0 1 1.44 5.00 0 0 0.00 0.62 55.60 ▇▁▁▁▁
org_l South Copepod 0 1 3.27 7.76 0 0 0.00 2.04 56.03 ▇▁▁▁▁
org_l Willis Cladoceran 0 1 1.87 5.91 0 0 0.00 1.06 48.35 ▇▁▁▁▁
org_l Willis Copepod 0 1 2.35 7.00 0 0 0.00 0.73 57.34 ▇▁▁▁▁ 
# this can be saved to a dataframe as well
skim.df <- lakes.df %>% dplyr::group_by(group) %>% skim(org_l)

there are a lot of things we can do with mutate and the possibilities are

endless. What would you like to see done?