R Notebook
This is an R Markdown Notebook. When you execute code within the notebook, the results appear beneath the code.
Try executing this chunk by clicking the Run button within the chunk or by placing your cursor inside it and pressing Ctrl+Shift+Enter.
This is the 2nd in series of R Code Files.
Refer the GitHub Repository , for all Code files —> https://github.com/RohitDhankar/R-Beginners-Online-Virtual-Learning-Session
Its a good practise from time to time to keep a track of our current Working Directory and list out all the Objects in our R ENVIRONMENT - specially so when we are committing changes to a Git Remote.
getwd()[1] "/home/dhankar/Desktop/R_Own/Proj_1"#
ls() [1] "a1" "array_1" "array_2" "b1" "c1" "char_vector" "ch_v"
[8] "col_boxes" "col_names" "d1" "df_1" "df_2" "df_3" "df_4"
[15] "logical_vector" "m_1" "nm_1" "nm_2" "nm_3" "nm_4" "nm_5"
[22] "nm_range" "nm_v" "nmv_q" "num_vector" "num_vector1" "num_vector3" "nv"
[29] "nv1" "percent_1" "percent_2" "percent_3" "R_1_Sheet1" "row_names"
We could remove any object with command - rm(“Object Name”)
We can also use print() , to view any objects stored value.
# Code Section -1
a1 <- "FINANCE"
b1 <- "MARKETING"
c1 <- "SALES"
d1 <- 3.1416
char_vector <- c("x","d","c","f")
print(a1)[1] "FINANCE"#
print(char_vector)[1] "x" "d" "c" "f"#
Going further with VECTORS .
We combine two or more vectors to get another vector .
# Code Section -2
num_vector <- c(22,22,33,33,44)
print(num_vector)[1] 22 22 33 33 44num_vector1 <- c(11,12,13,14,15)
#
num_vector3 <- c(num_vector,num_vector1)
print(num_vector3) [1] 22 22 33 33 44 11 12 13 14 15
Some basic Maths and Stats with VECTORS.
# Code Section -3
num_vector3 + 5 [1] 27 27 38 38 49 16 17 18 19 20# Adds NUMERIC VALUE = 5 to all ELEMENTS of the Num Vector. # Code Section -4
num_vector1 * num_vector3 [1] 242 264 429 462 660 121 144 169 196 225# First 5 elements of - num_vector3 multiplied by the Five Elements
# of num_vector1 and again the Next 5 elements of num_vector3
# multiplied by the Five Elements of num_vector1
Check out the LENGTH of a VECTOR with length()
# Code Section -5
length(num_vector1 * num_vector3)[1] 10# Code Section -6
#num_vector1 %*% num_vector3 # Error in num_vector1 %*% num_vector3 : non-conformable arguments
# Vectors are not of same Length above - below they are of same length
nv <- c(1,2,3,4,5)
nv1 <- c(6,7,8,9,10)
nv %*% nv1 # Inner Product of same Length Vectors [,1]
[1,] 130# Algeberic Dot Product as defined by WikiPedia - "https://en.wikipedia.org/wiki/Dot_product"
Operate upon a ELEMENT of the Vector.
# Code Section -7
log(num_vector3[2]) # Log Base 2 of 22 [1] 3.091042#
log(22)[1] 3.091042#
Converting a CHAR Vector into a NUMERIC Vector .
# Code Section -8
ch_v <- c("11","12","13","14","15")
#
class(ch_v)[1] "character"#ch_v + 2 # Error in ch_v + 2 : non-numeric argument to binary operator
# Cant do a Math operation on CHAR Vector - lets Convert into NUM Vector
#
nm_v <- as.numeric(ch_v)
#
class(nm_v)[1] "numeric"nm_v + 2 [1] 13 14 15 16 17#
#Summary of the Num Vector as below :-
#
summary(nm_v+2) Min. 1st Qu. Median Mean 3rd Qu. Max.
13 14 15 15 16 17 #
summary(nm_v+5) Min. 1st Qu. Median Mean 3rd Qu. Max.
16 17 18 18 19 20 #
sum(nm_v+5)[1] 90#
sd(nm_v+5)[1] 1.581139#
max(nm_v+5)[1] 20#
min(nm_v+5)[1] 16#
mean(nm_v+5)[1] 18#
median(nm_v+5)[1] 18#
#The Quantile -
#
quantile(nm_v+5) 0% 25% 50% 75% 100%
16 17 18 19 20 #
quantile(nm_v+100) 0% 25% 50% 75% 100%
111 112 113 114 115 #
#We can also specify the Quantile buckets or Percentiles as an argument to the Quantile function :-
#
nmv_q <- c(10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,100)
percent_1 <- quantile(nmv_q, c(.50,.75,.84, .97, .99))
percent_1 50% 75% 84% 97% 99%
52.50 73.75 81.40 94.90 98.30 boxplot(percent_1,col = "red",horizontal = TRUE,
main = "Box and Whisker Plot of Quantiles",
xlab = "Quantile Values")
# Kindly note how the ARGUMENTs to boxplot()
# have been bumped to the next row - keeping in mind
# the Horizontal space of our PDF knit of the .Rmd file
# Seen above we have the MEDIAN quartile - 50% and the UPPER Quartile - 75% along with THREE more percentiles.
Wiki reference – Percentile Rank - “https://en.wikipedia.org/wiki/Percentile_rank” #
We also carry out ONE Way ANOVA or ANALYSIS of VARIANCE test with the BOX and WHISKERS plots as seen below :-
# Code Section -9
nmv_q <- c(10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,100)
percent_1 <- quantile(nmv_q, c(.50,.75,.84, .97, .99))
percent_1 50% 75% 84% 97% 99%
52.50 73.75 81.40 94.90 98.30 percent_2 <- quantile(nmv_q, c(.1, .3, .16, .40, .50))
percent_2 10% 30% 16% 40% 50%
18.5 35.5 23.6 44.0 52.5 percent_3 <- quantile(nmv_q, c(.16, .40, .50,.75,.84))
percent_3 16% 40% 50% 75% 84%
23.60 44.00 52.50 73.75 81.40 col_boxes = (c("red","blue","green"))
boxplot(percent_1,percent_2,percent_3,col = col_boxes,
names = c("perc_1","perc_2","perc_3"),horizontal = TRUE,
main = "Box and Whisker Plot of Quantiles",
xlab = "Quantile Values")
# Kindly note the Quantiles are randomly chosen here
# this is not the best way to choose quantiles
# we shall come back for details later in this text# Code Section -10
# Code Section -11