Ds
Ds
BANKAI summary(cor)
BANKAI cor.test(cor$aptitude,cor$job_prof,alternative = "two.sided",method =
BANKIA "pearson")
AIDEJDXSKN #paired t-test application
FDNVFJSKNDCK stud<-read.csv("student.csv",sep = ",",header = T)
FVISJICKN;KSJFNVXC View(stud)
str(stud)
JM’LFVKNLKNXFV summary(stud)
boxplot(stud)
t.test(stud$Test1,stud$Test2,alternative="less",paired = T)
#correlation - Ice cream
OXMFMVL NKLJVF ice<-read.csv("icecream.csv",sep = ",",header = T)
;X KNDKLFVXN LXKNVF View(ice)
mean(biopsy1$predict==biopsy1$class) str(ice)
summary(ice)
Practical of Decision Tree boxplot(ice)
Regression tree cor.test(ice$Total.sales,ice$Temp,alternative = "two.sided",method =
data<-read.csv("Hitters.csv",sep = ",",header = T) "pearson")
View(data)...str(data) …summary(data)... names(data) …library(rpart)
regtree<-rpart(Salary~Hits+Runs+Years,data=data) Aim : Practical of Analysis of Variance
regtree …plot(regtree) …plot(regtree)... text(regtree) #one-way-anova test
install.packages("rpart.plot") library(rpart.plot) …rpart.plot(regtree) … data1<-read.csv("one-way-anova.csv",sep = ",", header = T)
View(regtree) … names(data1) …str(data1)
//Cp-complexity parameter data1$dept<-as.factor(data1$dept)
regtree$cptable …cp=min(regtree$cptable[5,]) … str(data1) …summary(data1) …View(data1) …head(data1)
pr=prune(regtree,cp=cp) …rpart.plot(pr) … anv1<-aov(formula=satindex~dept,data=data1)...summary(anv1)
//Classification Tree
library("MASS") …data("biopsy") …View(biopsy) …str(biopsy) … #two-way-anova test
names(biopsy) …summary(biopsy) …biopsy$ID=NULL data2<-read.csv("crop-data.csv",sep = ",",header = T)
classtree<-rpart(class~.,data=biopsy) names(data2)
rpart.plot(classtree) str(data2)
biopsy$pred=predict(classtree,biopsy,type = "class") data2$density<-as.factor(data2$density)
table(biopsy$pred,biopsy$class) str(data2)
install.packages("titanic") summary(data2)
library("titanic") head(data2)
data("titanic_train") View(data2)
str(titanic_train) anv2<-aov(formula=yield~density+block+fertilizer,data=data2)
View(titanic_train) summary(anv2)
titanic_train$Name=NULL
titanictree<-rpart(Survived~Pclass+Age+Parch,data = titanic_train) library(readxl)
rpart.plot(titanictree) mydata<-read.csv("newsadv.csv") …View(mydata) …names(mydata)
anv<-aov(formula=Count~Day+Section,data=mydata)
'Classification tree' summary(anv)
golf<-read.csv("Golf.csv",sep = ',',header = T) Practical of Clustering
View(golf)...str(golf) …names(golf) …library("rpart") … # K-means clustering on IRIS dataset
install.packages("rpart.plot") …library("rpart.plot") … data("iris")...names(iris)...newdata<-iris[,-5]...head(newdata)
tree<-rpart(Play~.,data=golf,control = rpart.control(minsplit = fit<-kmeans(newdata,3)
1,minbucket = 1,cp=0)) …rpart.plot(tree) library(cluster)
clusplot(newdata,fit$cluster,color=T,shade=T,labels=2,lines=0)
fit… fit$size
Practical of Hypothesis Testing #one sample t-test dim(newdata)
data<-read.csv("onesample.csv",sep = ",",header = T) # Hierarchical clustering on IRIS dataset
View(data) …str(data) …summary(data) …boxplot(data) # dist function is used to compute the distance matrix
t.test(data$Time,mu=80,alternative="greater") # i.e. Euclidean distance between every pair of observations
#two sample t-test clust<-hclust(dist(iris[,3:4]))
my_data<-read.csv("twosample.csv",sep = ",",header = T) plot(clust)
View(my_data) …str(my_data) … clusterCut<-cutree(clust,3)
summary(my_data) …boxplot(my_data) … table(clusterCut,iris$Species)
var.test(my_data$time_g1,my_data$time_g2,alternative="two.sided") clust<-hclust(dist(iris[,3:4]),method = "average")
t.test(my_data$time_g1,my_data$time_g2,alternative="two.sided") plot(clust)
#paired t-test clusterCut<-cutree(clust,3)
time<-read.csv("paired_t_test.csv",sep = ",",header = T) table(clusterCut,iris$Species)
View(time) …str(time) …
summary(time) …boxplot(time) Aim : Practical of Time-Series Forecasting
t.test(time$time_before,time$time_after,alternative="greater",paired = # Time Series Analysis and Forecasting on AirPassengers
T) install.packages("forecast")
#correlation library(forecast)
cor<-read.csv("correlation.csv",sep = ",",header = T) data("AirPassengers")
View(cor) class(AirPassengers)
head(AirPassengers)
sum(is.na(AirPassengers))
summary(AirPassengers)
plot(AirPassengers)
tsdata<-ts(AirPassengers,frequency = 12)
ddata<-decompose(tsdata)
plot(ddata)
holt<-HoltWinters(tsdata,beta = FALSE,gamma = FALSE)
plot(holt)
# Time Series Analysis on Rainfall dataset
rainfall<-read.csv("rainfall.csv",sep = ",",header = T)
head(rainfall)
summary(rainfall)
class(rainfall)
tsdata<-ts(rainfall,frequency = 12,start = c(2012,1))
class(tsdata)
plot(tsdata)
db.student.insert({_id=101,RollNo:4,Name=”Laxmi”,Marks:450,H
obbies:[“Reading”,”Danci ng”]});
db.student.find({Class:”TYCS”},{Name:1,Class:1,_id=0})
db.student.find({Class:{$ne:”TYCS”}},{Name:1,Class:1,_id:0})
db.student.find().sort({Marks:1}) //ascending
db.student.find({Class:”TYCS”},Marks:{$gt:400}})
//or, and, not
db.student.find({$or:[{Class:”TYCS”},Marks:{$gt:500}}]})
db.student.find({Class:{$ne:”TYCS”}},{Name:1,Class:1,_id:0}) ->
will name and class of those students whose class not TYCS
db.student.update({RollNo:2},{$set:{Marks:531}})
db.student.remove({Class:”FYCS”})
db.student.updateMany({Class:”TYCS”},{$inc:{Marks:5}})
db.Employee.aggregate({$group:{“_id”:”$Dept”,”Count”:{$sum:
1}}}) -> This will retrieve the number of employees in each
department
…………..:”$Dept”,”Count”:{$avg:”$Salary”}}})
db.student.find({},{Name:1,Marks:1,_is:0}).sort({Marks:1}) ->
sort the name and marks using projection argument