Lesson1_pcw_answers

#############
# Answer key to pre-class work for Lesson 1


#***Step 1:

#Load dataset 
#Note: This step may take several seconds to complete
# click the link for the data set and see that it's a .csv file
# so use "read.csv" -- also, don't name this data object "data"
# because "data()" is a built-in R function. Choose another name.
# mm <- read.csv("https://tinyurl.com/UNpckpdata")
# head(mm)
un_data <- read.csv("https://tinyurl.com/UNpckpdata")
head(un_data)
nrow(un_data)
ncol(un_data)
# the original data contains 147631 rows and 9 columns 

#***Step 2
#Check each column for missing values and/or NAs and drop the observations that have them.
#HINT: Use the function na.omit after dealing with all the blanks by setting them to NAs. 
#for example: https://www.youtube.com/watch?v=O_gPPrezk5o
clean_data <- na.omit(un_data)
nrow(clean_data)
# 147626

ncol(clean_data)
#9

#### How many observations (rows) are there in the original data set (before removing NAs)?
#147631 

#### How many observations (rows) are there in the cleaned data set (after removing NAs)?
# 147626

#### How many columns are there, and what are the names of the first column and the last column?
# 9 columns

# names(clean_data)
#[1] "Contribution_ID"      "ISOCode3"             "M49_Code"             "Contributing_Country"
#[5] "Mission_Acronym"      "Personnel_Type"       "Female_Personnel"     "Male_Personnel"      
#[9] "Last_Reporting_Date" 

# First column name is "Contribution_ID"
# Last column name is "Last Reporting Date"