# -02-data preparation Link to the module: [Module02-data-preparation](https://github.com/itsmecevi/r-bootcamp-module02/blob/master/02-data-prep.pdf) {% file src="/files/-LMJPgYd1HNXxM9JRJkg" %} CustomerData.csv {% endfile %} {% file src="/files/-LMJRVJKcwMdmPqIDFLh" %} CustomerData.xlsx {% endfile %} {% file src="/files/-LMJRbPx-Y4at0MPMRb6" %} mydata.csv {% endfile %} {% file src="/files/-LMJRjEqZpHrXDHNfBSC" %} mydata.xlsx {% endfile %} ![](/files/-LLxZJCraRRIHqXFcuB1) ![](/files/-LLxZLaf8vAp9lc9-Gsd) ![](/files/-LLzeqslLeq0j7QWPn47) ```r install.packages("readxl") install.packages("tidyverse") library(readxl) library(tidyverse) ####################### #READING IN A .CSV FILE ####################### #Text files are a popular way to hold and exchange tabular data #Text file formats use delimiters to separate the different elements #(.csv, .tsv, .txt, etc.) #.csv most common - use read_csv() to read in read_csv("mydata.csv") #To use this data in R you need to save it to an R object #In this case I save it as an object called mydata mydata<-read_csv("mydata.csv") print(mydata) ######################### #READING IN AN EXCEL FILE ######################## #Excel is still the spreadsheet software of choice #You need to understand both the workbook and the sheet #that you want to read in # identify the sheet you want excel_sheets("mydata.xlsx") # now read in the data read_excel("mydata.xlsx", sheet = "PICK_ME_FIRST!") ########################### #ADDITIONAL SPECIFICATIONS ########################### #Similar specifications exist with readr::read_csv read_excel("mydata.xlsx",sheet = "extra_header",skip = 2) read_excel("mydata.xlsx",sheet = "unique_NA",na ="999") #Or you can direct import data with GUI from Rstudio IDE #Import dataset ########### #YOUR TURN! ########### #1. Read in the CustomerData.csv file and save as raw_data #2. What spreadsheets are contained in the “CustomerData.xlsx” file? #3. Read in the spreadsheet that contains the data. # read in .csv raw_data <-read_csv("CustomerData.csv") View(raw_data) # read in spreadsheet names excel_sheets("CustomerData.xlsx") # read in spreadsheet that contains the data raw_data <- read_excel("CustomerData.xlsx", sheet = "Data") View(raw_data) ####################### #UNDERSTANDING OUR DATA ####################### #WHAT ARE THE DIMENSIONS? # load built-in data set data(mtcars) nrow(mtcars) ncol(mtcars) dim(mtcars) names(mtcars) glimpse(mtcars) #Alternatively, you can just type: View(mtcars) ############ #YOUR TURN! ############ #1. What are the dimensions of our customer data (raw_data)? #2.What are the variable names? #3.Take a peak at the entire data set. # dimension dim(raw_data) # names of variables names(raw_data) # take a peak at the entire data View(raw_data) ########################## #ARE THERE MISSING VALUES? ########################## #We identify missing values with: is.na() # load built-in data set data(airquality) is.na(airquality) #How many missing values are there? sum(is.na(airquality)) #Where are these missing values? colSums(is.na(airquality)) #Remove missing values? clean_data <- na.omit(airquality) clean_data ############# #YOUR TURN! ############ #1. How many missing values are in our customer data (raw_data)? #2.Which variables have the most missing data? #3.How would you omit missing values so we have a complete data set? # how many missing values are in our customer data? sum(is.na(raw_data)) # which variables have the most missing values? missing <-colSums(is.na(raw_data)) missing sort(missing, decreasing = TRUE) # how would you delete missing observations? clean_data <- na.omit(raw_data) clean_data dim(clean_data) ############### #DATA STRUCTURE ############### #VECTORS #1 (one) dimension #Can only contain homogenous data #For an example type "state.abb" in your console state.abb #CREATING #Most common way to create a vector is with c() or : #For numeric vectors there are numerous ways to #generate sequences of numbers # vectors with no set sequence c("Learning", "to", "create", "character", "vectors") c(3, 2, 10, 55) c(TRUE, FALSE, FALSE, FALSE, TRUE) # numeric vectors with regular sequence 6:15 #INDEXING # create this vector v1 <- 1:10 v1[4] v1[4:7] v1[c(4, 3, 4)] v1[v1 > 6] v1[v1 > 8 | v1 <=3] #Quick Summaries length(v1) summary(v1) mean(v1) median(v1) v1>5 sum(v1>5) ########### #YOUR TURN! ########### #1. check out the built-in character vector state.name #2. how many elements are in this vector #3. Subset state.name for elements 35, 38, 14, 17. #Which states are these? # check out state.name state.name # how many elements are in state.name length(state.name) # subset state.name for V35, V17, V14, V38 state.name[c(35, 38, 14, 17)] #MATRICES # 2 dimensions # • rows # • columns # • Can only contain homogenous data # • All columns must be of equal length #CREATING set.seed(123) v1 <-sample(1:10, 25, replace = TRUE) v1 m1 <- matrix(v1, nrow = 5) m1 #INDEXING/SUBSETTING # extract individual elements m1[1, 3] # extract all rows and columns 1 through 3 m1[, 1:3] # index for all rows and just the second column m1[1:3, ] #QUICK SUMMARIES summary(m1) mean(m1) mean(m[1,]) rowMeans(m1) colMeans(m1) rowSums(m1) colSums(m1) m1 > .5 sum(m > .5) which(m > .5) m[m > .5] ############ #YOUR TURN! ############ #1. Compute the column means of the built-in matrix named VADeaths. #2. Compute the row means of the built-in matrix named VADeaths. #4. Index VADeaths for females aged 55-64. # compute column means colMeans(VADeaths) # compute row means rowMeans(VADeaths) # Index for females aged 55-64 VADeaths[2:3, c(2, 4)] #DATA FRAMES # • Spreadsheet style data # • 2 dimensions # • rows # • columns # • Can contain heterogenous data # • All columns must be of equal length #INDEXING # extract the second column and all rows using column indexing #or the name raw_data[, 4] raw_data[, "Gender"] # extract all rows and columns 1 through 3 raw_data[, 1:3] raw_data[, c("CustomerID", "Region", "TownSize")] # index for first row and all columns raw_data[1, ] #LISTS # • 1 dimension # • Can only contain heterogeneous data - # to include multiple and different objects # (i.e. vectors, data frames, matrices, and even lists) #Lists are very important objects in R! #They may be confusing but they are worth learning #WHAT YOU NEED TO KNOW #•Many statistical modeling results come in the form of lists #•You need to know how to extract parts of a list to access model results # here's a linear regression model model <- lm(mpg ~ wt, data = mtcars) model summary(model) #•Model is simply a list of statistical results for our regression model # here's a linear regression model model <- lm(mpg ~ wt, data = mtcars) names(model) str(model) #INDEXING # • Its important that you know how to index/subset a list # • Elements of lists can be extracted using 3 approaches: # preserve: list[component] # simplify: list[[component]] # simplify: list$component # try these on our l1 list model["residuals"] model[["residuals"]] model$residuals model[["residuals"]][1:20] # •Model is simply a list of statistical results for our regression model # •So if you want to extract the residuals or fitted values you can just use # normal list subsetting procedures # extract the regression model residuals model$residuals ``` ![](/files/-LMJU6XGDs3djTlw3-S4) --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://r-pedia.gitbook.io/cevi/intro-to-r-bootcamp/02-data-preparation.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.