![head(mtcars) #To view top records of mtcars
# print first 10 rows of mydata
head(mtcars, n=10)
tail(mtcars) #to view bottom records of mtcars
##Variable Identification - Inferences
nrow(mtcars)
ncol(mtcars)
mean(mtcars[,2])
median(mtcars[,9])
range(mtcars$mpg)
mean(mtcars$mpg)](https://image.slidesharecdn.com/aimachinelearning-241106073303-622948b5/85/Artificial-inteliggence-and-machine-learning-ppt-4-320.jpg)
![3. MULTIVARIATE ANALYSIS
## To check the correlation among the variables
pairs(~ mpg + disp + hp + wt + drat + qsec , data = mtcars) #graphical
representation
cor(mtcars[,c(1,2,3,4,5,6,7,8,9,10,11)])](https://image.slidesharecdn.com/aimachinelearning-241106073303-622948b5/85/Artificial-inteliggence-and-machine-learning-ppt-14-320.jpg)
Artificial inteliggence and machine learning ppt
- 1. AI & MACHINE LEARNING
- 2. MODULE 2 : EXPLORATORY DATA ANALYSIS Basic R oblects •Variables •Vector •Array •Matrics •Data Frame
- 3. BASIC FUNCTIONS # To pull mtcars data in this session data() data("mtcars") #To view the variables / data dictionary mtcars # print mydata #To view the variables / data dictionary str(mtcars) #To view the variables / data dictionary dim(mtcars) # dimensions of an object names(mtcars) class(mtcars) # class of an object (numeric, matrix, data frame, etc)
- 4. head(mtcars) #To view top records of mtcars # print first 10 rows of mydata head(mtcars, n=10) tail(mtcars) #to view bottom records of mtcars ##Variable Identification - Inferences nrow(mtcars) ncol(mtcars) mean(mtcars[,2]) median(mtcars[,9]) range(mtcars$mpg) mean(mtcars$mpg)
- 5. 1. UNIVARIATE ANALYSIS #Interquartile range (75 percentile - 25 percentile) IQR(mtcars$mpg) ## Univariate Analysis (Pattern Recognition) summary(mtcars) # Complete summary of the dataset fivenum(mtcars) fivenum(mtcars$mpg) # edit the the data for Outliers mtcars=edit(mtcars) mtcars
- 6. HISTOGRAM #Histogram hist(mtcars$mpg) hist(mtcars$mpg,col = "Red") # Colored Histogram with Different Number of Bins hist(mtcars$mpg, breaks=12, col="red") # Add labels to the graph x <- mtcars$mpg h<-hist(x, breaks=10, col="red", xlab="Miles Per Gallon", main="Histogram")
- 7. ##(Histograms can be a poor method for determining the shape of a distribution because it is so strongly affected by the number of bins used.) ##Kernal density plots are usually a much more effective way to view the distribution of a variable. # Kernel Density Plot d <- density(mtcars$mpg) # returns the density data plot(d) # plots the results # Filled Density Plot d <- density(mtcars$mpg) plot(d, main="Kernel Density of Miles Per Gallon") polygon(d, col="red", border="blue")
- 8. BAR PLOT # Simple Bar Plot counts <- table(mtcars$gear) counts barplot(counts, main="Car Distribution", xlab="Number of Gears") barplot(counts,col="Yellow", main="Car Distribution", xlab="Number of Gears") # Simple Horizontal Bar Plot with Added Labels counts <- table(mtcars$gear) barplot(counts, main="Car Distribution", horiz=TRUE) barplot(counts, main="Car Distribution", horiz=TRUE, names.arg=c("3 Gears", "4 Gears", "5 Gears"))
- 9. BOX PLOT #Boxplot boxplot(mtcars$mpg) boxplot(mtcars$mpg,horizontal = TRUE) boxplot(mtcars$mpg,horizontal = TRUE,col = "Pink") boxplot(mtcars$mpg,horizontal = TRUE,col = "Green",main="Mileage")
- 10. 2. BIVARIATE ANALYSIS o Continous Numerical Variables vs Continous Numerical Variables o Continous Numerical Variables vs Discrete Numerical Variables o Discrete Numerical Variables vs Categorical Variables
- 11. STACKED BAR PLOT # Stacked Bar Plot with Colors and Legend counts <- table(mtcars$vs, mtcars$gear) barplot(counts, main="Car Distribution by Gears and VS", xlab="Number of Gears", col=c("darkblue","red"), legend = rownames(counts)) counts <- table(mtcars$cyl, mtcars$gear) barplot(counts, main="Car Distribution by Gears and Cylinders", xlab="Number of Gears", col=c("darkblue","red","Yellow"), legend = rownames(counts))
- 12. GROUPED BAR PLOT # Grouped Bar Plot counts <- table(mtcars$vs, mtcars$gear) barplot(counts, main="Car Distribution by Gears and VS", xlab="Number of Gears", col=c("darkblue","red"), legend = rownames(counts), beside=TRUE) counts <- table(mtcars$cyl, mtcars$gear) barplot(counts, main="Car Distribution by Gears and Cylinders", xlab="Number of Gears", col=c("darkblue","red","Yellow"), legend = rownames(counts),beside = TRUE)
- 14. 3. MULTIVARIATE ANALYSIS ## To check the correlation among the variables pairs(~ mpg + disp + hp + wt + drat + qsec , data = mtcars) #graphical representation cor(mtcars[,c(1,2,3,4,5,6,7,8,9,10,11)])