luisDVA

## %######################################################%##
#                                                          #
####         Empty rows and columns - your turn         ####
#                                                          #
## %######################################################%##


# Import the Marine Protected Areas dataset (MPAS-your.csv)
# Identify the empty rows and columns, and create a new object with only the empty rows and columns
#  Remove the empty rows and columns

luisDVA

## %######################################################%##
#                                                          #
####            Parsing numbers - your turn             ####
#                                                          #
## %######################################################%##

# Import the Marine Protected Areas dataset (MPAS-mine.csv)
# Subset to keep only the MPA names and columns with extent data
# Make the columns that hold the MPA extent into usable numeric variables
# Watch out for decimals

luisDVA

## %######################################################%##
#                                                          #
####            Putting everything together             ####
####        Chained data cleaning demonstration         ####
#                                                          #
## %######################################################%##


# Load the raw Age of Empires units dataset from csv (aoe_raw.csv)
# Identify and fix common issues that make these data unusable

luisDVA

## %######################################################%##
#                                                          #
####         Useful dplyr functions - your turn         ####
#                                                          #
## %######################################################%##


# Load the mammal sleep data bundled with ggplot2
# Select "name" and "conservation" columns and those that include the string 'sleep' in their name
# Create a new column that contains the values of 'sleep_total' multiplied by 3

luisDVA

## %######################################################%##
#                                                          #
####   Working with columns with 'across' - Your Turn   ####
#                                                          #
## %######################################################%##

# Load the midwest data bundled with ggplot2
# Keep only rows for Ohio (OH)
# Subset the 'county' column and all columns that match the string 'pop' (hint: use a selection helper)
# Square-root transform all numeric variables

luisDVA

## %######################################################%##
#                                                          #
####             Pivoting Data - Your Turn              ####
#                                                          #
## %######################################################%##

# Load the dog ranks data ("dogranks_your.csv")
# Pivot the data (wide to long and back to wide)

# load packages -----------------------------------------------------------

luisDVA

## %######################################################%##
#                                                          #
####           Coalesce and Fill - Your Turn            ####
#                                                          #
## %######################################################%##

# Load the fish landings data 'fish-landings.csv'
# Fill the 'Fish' and 'Lake' columns
# Reorder the numeric variables ('Comission reported total' first)
# create a new column, coalescing the three numeric variables

luisDVA

##%######################################################%##
#                                                          #
####               Regex in R - Your Turn               ####
#                                                          #
##%######################################################%##


# Match the following regular expressions against the test vector below using `str_detect`.  
## Can you explain the matches?

luisDVA

## %######################################################%##
#                                                          #
####        Regex for data cleaning 1 - your turn        ####
#                                                          #
## %######################################################%##

# After running the code below: 

library(ggplot2)
library(dplyr)

luisDVA

# lista 1
dat1a <- tibble(id=c("A","B","C","D","E"),val=rnorm(5))
dat1b <- tibble(id=c("A","B","C","D","E"),val=rnorm(5))

dat1 <- list(dat1a,dat1b)
dat1

# lista dos
dat2a <- tibble(id=c("A","D","E"),label=rnorm(3))
dat2b_1 <- tibble(id=c("A","B","C","E"),label=rnorm(4))