Name – Sanskruti Nimje

Reg. no. – 2023PGDM1233

Section – B

DTE-2

SECTION-A

Q-1) Simple Liner Regression

syntax

#simple liner regression

salary_data=read.csv("D:\\salary_data.csv")

View(salary_data)

attach(salary_data)

#model

model=lm(Salary~Years.of.Experience,data=salary_data)

names(salary_data)

summary(model)

prediction=predict(model,data.frame(Years.of.Experience=5))

prediction

output

#simple liner regression

> salary_data=read.csv("D:\\salary_data.csv")

> View(salary_data)

> attach(salary_data)

The following objects are masked from salary_data (pos = 3):

The following objects are masked from salary_data (pos = 4):

Age, Education.Level, Gender, Salary, Years.of.Experience

The following objects are masked from salary_data (pos = 5):

Age, Education.Level, Gender, Salary, Years.of.Experience

The following objects are masked from salary_data (pos = 6):

Age, Education.Level, Gender, Salary, Years.of.Experience

> #model

> model=lm(Salary~Years.of.Experience,data=salary_data)

> names(salary_data)

[1] "Age" "Gender" "Education.Level" "Years.of.Experience"

[5] "Salary"

> summary(model)

Call:

lm(formula = Salary ~ Years.of.Experience, data = salary_data)

Residuals:

Min 1Q Median 3Q Max

-69589 -7188 1189 9634 78567

Coefficients:

Estimate Std. Error t value Pr(>|t|)

Years.of.Experience 6844.5 140.1 48.87 <2e-16 ***

---

Signif. codes: 0 ‘’ 0.001 ‘’ 0.01 ‘’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 17710 on 371 degrees of freedom

(2 observations deleted due to missingness)

Multiple R-squared: 0.8655, Adjusted R-squared: 0.8652

F-statistic: 2388 on 1 and 371 DF, p-value: < 2.2e-16

> prediction=predict(model,data.frame(Years.of.Experience=5))

> prediction

66143.77

>

>

………………………………………………………………………………………………………………….

SECTION-B

Q-4)

# SVM MODEL

data=read.csv("C://Users/HP/Desktop/DATA DAR/heart.csv")

View(data)

index=sample(2,nrow(data),replace = TRUE,prob = c(0.9,0.1))

test_data=data[index==2,]

install.packages('e1071')

library(e1071)

model=svm(target~.,train_data,kernel = "linear",type = "C-classification")

prediction_class=predict(model,test_data)

prediction_class

matrix=table(test_data$target,prediction_class)

matrix

accuracy=(sum(diag(matrix))/sum(matrix))

accuracy

OUTPUT

data=read.csv("D:\\heart.csv")
> View(data)
> index=sample(2,nrow(data),replace = TRUE,prob = c(0.8,0.2))
> train_data=data[index==1,]
> test_data=data[index==2,]
> library(e1071)
model=svm(target~.,train_data,kernel = "linear",type = "C-classification")
> prediction_class=predict(model,test_data)
> prediction_class
1 8 11 17 21 28 31 36 40 46 50 51 54 59 68 72 77 89 99
0 0 1 1 1 1 0 0 1 1 0 1 0 1 0 0 1 0 1
111 112 113 115 118 119 123 129 136 156 161 162 163 164 178 180 188 201 204
1 0 0 1 0 1 0 1 0 1 0 1 0 0 0 0 0 1 1
210 211 237 241 256 257 266 271 272 277 280 281 290 292 299 305 310 318 322
0 1 1 1 1 1 0 1 1 0 1 1 1 0 1 1 1 1 1
323 329 330 334 335 336 341 343 344 353 360 368 381 384 389 391 399 405 418
0 0 1 1 0 0 1 1 1 0 1 1 0 0 0 1 0 0 1
421 427 447 454 467 469 472 485 486 488 490 491 494 496 499 504 508 513 519
1 1 1 1 1 1 1 1 0 0 1 1 0 0 1 1 1 1 0
520 533 536 537 539 541 549 551 558 559 565 566 573 579 581 587 588 589 594
0 1 1 1 0 0 1 0 1 1 0 1 1 1 1 0 0 0 0
 597 602 603 605 606 610 614 620 622 623 632 647 666 671 675 685 688 694 700
1 0 1 1 1 0 0 1 0 0 1 1 1 1 0 1 0 1 0
706 710 711 716 722 728 739 750 762 764 781 795 802 814 823 826 833 834 842
0 1 1 1 1 1 0 0 1 1 0 1 1 0 0 1 1 0 1
846 847 851 853 854 876 880 886 890 892 916 919 932 936 945 948 951 958 960
0 1 1 0 0 0 1 0 0 1 0 1 1 1 0 1 0 1 1
961 963 964 965 966 969 981 983 988 990 996 1000 1001 1004 1010 1014
1 0 0 1 1 0 1 1 1 1 1 0 0 0 1 0
Levels: 0 1
> matrix=table(test_data$target,prediction_class)
> matrix
prediction_class
0 1
0 71 26
1 8 82
> accuracy=(sum(diag(matrix))/sum(matrix))
> accuracy
[1] 0.8181818
>

…………………………………………………………………………………………………………………………..

SECTION -C

Q-5) CASE STUDY

syntax

#ANN MODEL

install.packages('neuralnet')

library(neuralnet)

binary_data<-read.csv("D:\\dividendinfo.csv")

View(binary_data)

index<-sample(2,nrow(binary_data), replace = TRUE, prob = c(0.9,0.1))

train_data<-binary_data[index==1,]

test_data<-binary_data[index==2,]
ann_model<-neuralnet(dividend~.,train_data,hidden = 1,err.fct = 'ce',linear.output = FALSE)

plot(ann_model)

prediction<-compute(ann_model,test_data[,-9])

result<-prediction$net.result

pred_class<-ifelse(result>0.5,1,0)

pred_class

matrix<-table(test_data$dividend,pred_class)

matrix

accuracy<-(sum(diag(matrix))/sum(matrix))

accuracy

output

library(neuralnet)

> binary_data<-read.csv("D:\\dividendinfo.csv")

> View(binary_data)

> index<-sample(2,nrow(binary_data), replace = TRUE, prob = c(0.9,0.1))

> train_data<-binary_data[index==1,]

> test_data<-binary_data[index==2,]

> ann_model<-neuralnet(dividend~.,train_data,hidden = 1,err.fct = 'ce',linear.output = FALSE)

> plot(ann_model)

prediction<-compute(ann_model,test_data[,-9])

> result<-prediction$net.result

> pred_class<-ifelse(result>0.5,1,0)

> pred_class

[,1]

8 1

10 1

18 1
41 1

69 1

81 1

87 1

112 1

121 1

127 1

132 1

137 1

153 1

161 1

183 1

186 1

194 1

> matrix<-table(test_data$Outcome,pred_class)

Error in table(test_data$Outcome, pred_class) :

all arguments must have the same length

> matrix<-table(test_data$dividend,pred_class)

> matrix

pred_class

09

18

> accuracy<-(sum(diag(matrix))/sum(matrix))

> accuracy

[1] 0.5294118

>
……………………………………………………………………………………………………………………………………………………………