##Data Set https://vincentarelbundock.github.io/Rdatasets/csv/AER/CPSSWEducation.csv https://vincentarelbundock.github.io/Rdatasets/doc/AER/CPSSWEducation.html
Use the summary function to gain an overview of the data set. Then display the mean and median for at least two attributes of your data.
#read dataset by import
#Data_education <- CPSSWEducation
#read dataset from online site
Data_education <- read.csv(file="https://raw.githubusercontent.com/Benson90/BrigeR/main/CPSSWEducation.csv", header = TRUE, sep = ",")
summary(Data_education)## X age gender earnings
## Min. : 1.0 Min. :29.0 Length:2950 Min. : 2.137
## 1st Qu.: 738.2 1st Qu.:29.0 Class :character 1st Qu.:10.577
## Median :1475.5 Median :29.0 Mode :character Median :14.615
## Mean :1475.5 Mean :29.5 Mean :16.743
## 3rd Qu.:2212.8 3rd Qu.:30.0 3rd Qu.:20.192
## Max. :2950.0 Max. :30.0 Max. :97.500
## education
## Min. : 6.00
## 1st Qu.:12.00
## Median :13.00
## Mean :13.55
## 3rd Qu.:16.00
## Max. :18.00#display mean and median with data frame method
mean <- sapply(Data_education[c("age","earnings")], mean)
median <- sapply(Data_education[c("age","earnings")], median)
mmFrame <- data.frame(mean,median)
print(mmFrame)## mean median
## age 29.49763 29.00000
## earnings 16.74272 14.61539Create a new data frame with a subset of the columns AND rows. There are several ways to do this so feel free to try a couple if you want. Make sure to rename the new data set so it simply just doesn’t write it over.
#create new data frame
newFrame <- Data_education[1:20, c("age", "gender", "earnings", "education")]
#subset education = 12
print(subset(newFrame,education == 12))## age gender earnings education
## 3 30 female 13.736263 12
## 6 30 female 8.000000 12
## 7 30 male 19.230770 12
## 10 30 female 6.221719 12
## 15 29 male 5.769231 12
## 16 29 male 13.500000 12Create new column names for each column in the new data frame created in step 2.
#new column name
colnames(newFrame) <- c("new_age", "new_gender", "new_earnings", "new_education")
print(newFrame)## new_age new_gender new_earnings new_education
## 1 30 male 34.615383 16
## 2 30 female 19.230770 16
## 3 30 female 13.736263 12
## 4 30 female 13.942307 13
## 5 30 female 19.230770 16
## 6 30 female 8.000000 12
## 7 30 male 19.230770 12
## 8 29 male 26.153847 16
## 9 29 male 26.442308 16
## 10 30 female 6.221719 12
## 11 29 male 24.038462 14
## 12 29 male 38.461540 18
## 13 29 male 19.230770 18
## 14 29 female 10.817307 11
## 15 29 male 5.769231 12
## 16 29 male 13.500000 12
## 17 30 male 12.980769 16
## 18 30 male 35.470085 13
## 19 30 male 18.750000 16
## 20 30 female 24.038462 16Use the summary function to create an overview of your new data frame created in step 2. The print the mean and median for the same two attributes. Please compare (i.e. tell me how the values changed and why).
summary(newFrame)## new_age new_gender new_earnings new_education
## Min. :29.0 Length:20 Min. : 5.769 Min. :11.00
## 1st Qu.:29.0 Class :character 1st Qu.:13.370 1st Qu.:12.00
## Median :30.0 Mode :character Median :19.231 Median :15.00
## Mean :29.6 Mean :19.493 Mean :14.35
## 3rd Qu.:30.0 3rd Qu.:24.567 3rd Qu.:16.00
## Max. :30.0 Max. :38.462 Max. :18.00#display mean and median with data frame method
newmean <- sapply(newFrame[c("new_age","new_earnings")], mean)
newmedian <- sapply(newFrame[c("new_age","new_earnings")], median)
newmmFrame <- data.frame(newmean,newmedian)
print(newmmFrame)## newmean newmedian
## new_age 29.60000 30.00000
## new_earnings 19.49304 19.23077mmCompare <- mmFrame - newmmFrame
colnames(mmCompare) <- c("compare_mean", "compare_median")
mmCompare## compare_mean compare_median
## age -0.1023729 -1.000000
## earnings -2.7503209 -4.615385print("Since the new data frame have less data, the mean and median result will be somewhat different")## [1] "Since the new data frame have less data, the mean and median result will be somewhat different"For at least 3 different/distinct values in a column please rename so that every value in that column is renamed. For example, change the letter “e” to “excellent”, the letter “a” to “average’ and the word “bad” to “terrible”.
#insert lib
library("stringr")
#show value in variable
newValue <- newFrame[, "new_education"]
newValue <- sapply(newValue, as.character)
unique(newValue)## [1] "16" "12" "13" "14" "18" "11"#convert value * Knit shows an error if the pattern doesn't exit in the column.
#newValue <- str_replace(string = newValue, pattern = "9", "Freshman HighSchool")
#newValue <- str_replace(string = newValue, pattern = "10", "Junior HighSchool")
newValue <- str_replace(string = newValue, pattern = "11", "Senior HighSchool")
newValue <- str_replace(string = newValue, pattern = "12", "Freshman Undergrad")
newValue <- str_replace(string = newValue, pattern = "13", "Sophomore Undergrad")
newValue <- str_replace(string = newValue, pattern = "14", "Junior Undergrad")
#newValue <- str_replace(string = newValue, pattern = "15", "Senior Undergrad")
newValue <- str_replace(string = newValue, pattern = "16", "Gradurate student")
#newValue <- str_replace(string = newValue, pattern = "17", "PHD")
newValue <- str_replace(string = newValue, pattern = "18", "MD")
unique(newValue)## [1] "Gradurate student" "Freshman Undergrad" "Sophomore Undergrad"
## [4] "Junior Undergrad" "MD" "Senior HighSchool"#apply into the data
newFrame[,"new_education"] <-newValue
newFrame## new_age new_gender new_earnings new_education
## 1 30 male 34.615383 Gradurate student
## 2 30 female 19.230770 Gradurate student
## 3 30 female 13.736263 Freshman Undergrad
## 4 30 female 13.942307 Sophomore Undergrad
## 5 30 female 19.230770 Gradurate student
## 6 30 female 8.000000 Freshman Undergrad
## 7 30 male 19.230770 Freshman Undergrad
## 8 29 male 26.153847 Gradurate student
## 9 29 male 26.442308 Gradurate student
## 10 30 female 6.221719 Freshman Undergrad
## 11 29 male 24.038462 Junior Undergrad
## 12 29 male 38.461540 MD
## 13 29 male 19.230770 MD
## 14 29 female 10.817307 Senior HighSchool
## 15 29 male 5.769231 Freshman Undergrad
## 16 29 male 13.500000 Freshman Undergrad
## 17 30 male 12.980769 Gradurate student
## 18 30 male 35.470085 Sophomore Undergrad
## 19 30 male 18.750000 Gradurate student
## 20 30 female 24.038462 Gradurate studentDisplay enough rows to see examples of all of steps 1-5 above. This means use a function to show me enough row values that I can see the changes.
BONUS – place the original .csv in a github file and have R read from the link. This should be your own github – not the file source. This will be a very useful skill as you progress in your data science education and career.