R Bridge Week 2 Assignment

url<- "https://raw.githubusercontent.com/akarimhammoud/R_Bridge_CUNY_Week2/master/datasets.csv"
data1 <- read.csv(file= url, header=TRUE, sep=",")
head(data1)

#1. Use the summary function to gain an overview of the data set. Then display the mean and median for at least two attributes.

#summary
summary(data1)

# Mean and Median of attribute n_binary
binary_mean <- mean(data1$n_binary)
binary_median <- median(data1$n_binary)
print(paste0("binary mean is ", round(binary_mean, 2),", binary median is ", round(binary_median, 2)))

# Mean and Median of attribute  n_factor 
factor_mean <- mean(data1$n_factor)
factor_median <- median(data1$ n_factor)
print(paste0("factor mean is ", round(factor_mean, 2),", factor median is ", round(factor_median)))

2. Create a new data frame with a subset of the columns and rows. Make sure to rename it.

frame1 <- data.frame(subset(data1, n_character >= 1 & n_logical == 1))

frame1 <- data1[2:10, c("Item","Title","Rows","Cols")]
colnames(frame1) <- c("Unit","Kind","Records","Quantity")
frame1

#3. Create new column names for the new data frame.

colnames(frame1) <- c("Unit1","Kind2","Records3","Quantity4")
frame1

#4. Use the summary function to create an overview of your new data frame. The print the mean and median for the same two attributes. Please compare.

summary(frame1)

# Mean and Median of attribute Records3 compated with n_binary
Records3_mean <- mean(frame1$Records3)
Records3_median <- median(frame1$Records3)
print(paste0("n_binary mean is ", round(binary_mean, 2),", Records3 mean is ", round(Records3_mean, 2)))
print(paste0("n_binary median is ", round(binary_median, 2),", Records3 median is ", round(Records3_median, 2)))

# Mean and Median of attribute H Compared with n_character
Quantity4_mean <- mean(frame1$Quantity4)
Quantity4_median <- median(frame1$Quantity4)
print(paste0("n_character mean is ", round(factor_mean, 2),", Quantity mean is ", round(Quantity4_mean, 2)))
print(paste0("n_character median is ", round(factor_median, 2),", Quantity median is ", round(Quantity4_median, 2)))

#5. For at least 3 values in a column please rename so that every value in that column is renamed. For example, suppose I have 20 values of the letter “e” in one column. Rename those values so that all 20 would show as “excellent”.

frame1

#Replacing 'aids' to 'diabities', 'amis' to 'HeartAttack' and 'beaver' to 'fever' in column Unit1
frame1$Unit1 <- sub("*aids", "diabities", frame1$Unit1)
frame1$Unit1 <- sub("*(amis)", "heartattack", frame1$Unit1)
frame1$Unit1 <- sub("*(beaver)", "fever", frame1$Unit1)
frame1

#6. Display enough rows to see examples of all of steps 1-5 above.

frame1

#BONUS – place the original .csv in a github file and have R read from the link. This will be a very useful skill as you progress in your data science education and career.

url<- "https://raw.githubusercontent.com/akarimhammoud/R_Bridge_CUNY_Week2/master/datasets.csv"
data1 <- read.csv(file= url, header=TRUE, sep=",")
head(data1)

head(data1$Item)