//Name: - Hemant Sharma

//Roll No: - 61

Practical No: 1

Study R Studio and basis of R programming.

# A simple R program

# Assign values to variables

a <- 10

b <- 5

# Perform arithmetic operations

sum_result <- a + b
diff_result <- a - b

prod_result <- a * b

quot_result <- a / b

# Print the results

print(paste("Sum:", sum_result))

print(paste("Difference:", diff_result))

print(paste("Product:", prod_result))
print(paste("Quotient:", quot_result))

# Use a built-in function

numbers <- c(10, 20, 30, 40, 50)

mean_value <- mean(numbers)

print(paste("Mean of the numbers:", mean_value))

OUTPUT:

> # A simple R program

>

> # Assign values to variables

> a <- 10

> b <- 5
>

> # Perform arithmetic operations

> sum_result <- a + b

> diff_result <- a - b

> prod_result <- a * b

> quot_result <- a / b

>

> # Print the results

> print(paste("Sum:", sum_result))

[1] "Sum: 15"

> print(paste("Difference:", diff_result))

[1] "Difference: 5"

> print(paste("Product:", prod_result))

[1] "Product: 50"

> print(paste("Quotient:", quot_result))

[1] "Quotient: 2"

>

> # Use a built-in function

> numbers <- c(10, 20, 30, 40, 50)

> mean_value <- mean(numbers)

> print(paste("Mean of the numbers:", mean_value))

[1] "Mean of the numbers: 30"

 //Name: - Hemant Sharma

//Roll No: - 61

Practical No: 2
Linear Regression Analysis Regression Analysis and Plot Interpretations using R.

# Input vectors

x <- c(151, 174, 138, 186, 128, 136, 179, 163, 152, 131) # Heights in cm

y <- c(63, 81, 56, 91, 47, 57, 76, 72, 62, 48) # Weights in kg

# Create a data frame

data <- [Link](x, y)

# Fit a linear regression model

relation <- lm(x ~ y)

# Print the model and summary

print(relation)

print(summary(relation))

# Predict height for a person weighing 70 kg

a <- [Link](y = 70)

result <- predict(relation, a)

print(result)

# Save regression plot to PNG

png("[Link]")
plot(y, x,

col = "red",

main = "Height and Weight Regression",

cex = 1.3,
pch = 16,

xlab = "Weight in Kg",

ylab = "Height in cm")

abline(relation, col = "black", lwd = 2)

[Link]()

OUTPUT:

> # Input vectors

> x <- c(151, 174, 138, 186, 128, 136, 179, 163, 152, 131) # Heights in cm

> y <- c(63, 81, 56, 91, 47, 57, 76, 72, 62, 48) # Weights in kg

>

> # Create a data frame

> data <- [Link](x, y)

>

> # Fit a linear regression model

> relation <- lm(x ~ y)

>

> # Print the model and summary

> print(relation)

Call:
lm(formula = x ~ y)

Coefficients:

(Intercept) y

61.380 1.415
> print(summary(relation))

Call:

lm(formula = x ~ y)

Residuals:

Min 1Q Median 3Q Max

-6.0529 -2.4833 -0.0912 1.3774 10.0562

Coefficients:

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

(Intercept) 61.3803 7.2653 8.448 2.94e-05 ***

y 1.4153 0.1089 12.997 1.16e-06 ***

---

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

Residual standard error: 4.712 on 8 degrees of freedom

Multiple R-squared: 0.9548, Adjusted R-squared: 0.9491

F-statistic: 168.9 on 1 and 8 DF, p-value: 1.164e-06

>

> # Predict height for a person weighing 70 kg

> a <- [Link](y = 70)

> result <- predict(relation, a)

> print(result)

160.452
>

> # Save regression plot to PNG

> png("[Link]")

>
> plot(y, x,

+ col = "blue",

+ main = "Height and Weight Regression",

+ cex = 1.3,

+ pch = 16,

+ xlab = "Height in cm",

+ ylab = "Weight in kg")

>
> abline(relation, col = "black", lwd = 2)

>

> [Link]()

null device

GRAPH:
 //Name: - Hemant Sharma

//Roll No: - 61

Practical No: 3

Logistic Regression Analysis in R.

# Load the mtcars dataset

input <- mtcars[, c("am", "cyl", "hp", "wt")]

# Print the first few rows of the selected data

print(head(input))

# Fit a logistic regression model (glm) predicting 'am' using 'cyl', 'hp', and 'wt'

[Link] <- glm(formula = am ~ cyl + hp + wt, data = input, family = binomial)

# Print the summary of the model

print(summary([Link]))

OUTPUT:

> # Load the mtcars dataset

> input <- mtcars[, c("am", "cyl", "hp", "wt")]

>

> # Print the first few rows of the selected data

> print(head(input))

am cyl hp wt

Mazda RX4 1 6 110 2.620

Mazda RX4 Wag 1 6 110 2.875

Datsun 710 1 4 93 2.320

Hornet 4 Drive 0 6 110 3.215

Hornet Sportabout 0 8 175 3.440

Valiant 0 6 105 3.460

>
> # Fit a logistic regression model (glm) predicting 'am' using 'cyl', 'hp', and 'wt'

> [Link] <- glm(formula = am ~ cyl + hp + wt, data = input, family = binomial)

>

> # Print the summary of the model

> print(summary([Link]))

Call:

glm(formula = am ~ cyl + hp + wt, family = binomial, data = input)

Coefficients:

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

(Intercept) 19.70288 8.11637 2.428 0.0152 *

cyl 0.48760 1.07162 0.455 0.6491

hp 0.03259 0.01886 1.728 0.0840 .

wt -9.14947 4.15332 -2.203 0.0276 *

---

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

(Dispersion parameter for binomial family taken to be 1)

Null deviance: 43.2297 on 31 degrees of freedom

Residual deviance: 9.8415 on 28 degrees of freedom

AIC: 17.841

Number of Fisher Scoring iterations: 8

 //Name: - Hemant Sharma

//Roll No: - 61

Practical No: 4
Random Forest and Parameter Tuning in R

# Load iris dataset

data(iris)

# Structure of the dataset

str(iris)

# Install packages (only run once)

# [Link]("caTools")

# [Link]("randomForest")

# Load necessary libraries

library(caTools)

library(randomForest)

# Splitting data into training and testing sets

[Link](123) # For reproducibility

split <- [Link](iris$Species, SplitRatio = 0.7)

train <- subset(iris, split == TRUE)

test <- subset(iris, split == FALSE)

# Fitting Random Forest to the training set

[Link](120)

classifier_RF <- randomForest(x = train[-5],

y = train$Species,

ntree = 500)

# Print model summary

print(classifier_RF)

# Predicting the Test set results

Y_pred <- predict(classifier_RF, newdata = test[-5])

# Confusion Matrix
confusion_matrix <- table(Predicted = Y_pred,

Actual = test$Species)

print(confusion_matrix)

# Plotting the Random Forest model

plot(classifier_RF)

# Variable Importance Plot

importance(classifier_RF)

varImpPlot(classifier_RF)

png("RF_ErrorPlot.png")

plot(classifier_RF)

[Link]()
png("RF_VariableImportance.png")

varImpPlot(classifier_RF)

[Link]()

OUTPUT:
> # Load iris dataset

> data(iris)

>

> # Structure of the dataset

> str(iris)

'[Link]': 150 obs. of 5 variables:

$ [Link]: num 5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...

$ [Link] : num 3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
$ [Link]: num 1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...

$ [Link] : num 0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...

$ Species : Factor w/ 3 levels "setosa","versicolor",..: 1 1 1 1 1 1 1 1 1 1 ...

>

> # Install packages (only run once)

> # [Link]("caTools")

> # [Link]("randomForest")
>

> # Load necessary libraries

> library(caTools)

> library(randomForest)

>

> # Splitting data into training and testing sets

> [Link](123) # For reproducibility

> split <- [Link](iris$Species, SplitRatio = 0.7)

>

> train <- subset(iris, split == TRUE)

> test <- subset(iris, split == FALSE)

>

> # Fitting Random Forest to the training set

> [Link](120)

> classifier_RF <- randomForest(x = train[-5],

+ y = train$Species,

+ ntree = 500)

>

> # Print model summary

> print(classifier_RF)

Call:

randomForest(x = train[-5], y = train$Species, ntree = 500)

Type of random forest: classification

Number of trees: 500

No. of variables tried at each split: 2

OOB estimate of error rate: 2.86%

Confusion matrix:

setosa versicolor virginica [Link]

setosa 35 0 0 0.00000000

versicolor 0 34 1 0.02857143

virginica 0 2 33 0.05714286

>

> # Predicting the Test set results

> Y_pred <- predict(classifier_RF, newdata = test[-5])

>

> # Confusion Matrix

> confusion_matrix <- table(Predicted = Y_pred,

+ Actual = test$Species)

>

> print(confusion_matrix)

Actual

Predicted setosa versicolor virginica

setosa 15 0 0

versicolor 0 12 1

virginica 0 3 14
>

> # Plotting the Random Forest model

> plot(classifier_RF)

>

> # Variable Importance Plot

> importance(classifier_RF)

MeanDecreaseGini
[Link] 7.055030

[Link] 1.170081

[Link] 33.522055

[Link] 27.537816

> varImpPlot(classifier_RF)

>

> png("RF_ErrorPlot.png")
> plot(classifier_RF)

> [Link]()

RStudioGD

2
>

> png("RF_VariableImportance.png")

> varImpPlot(classifier_RF)

> [Link]()

RStudioGD

GRAPH:
 //Name: - Hemant Sharma

//Roll No: - 61

Practical No: 5

Clustering Algorithms and Evaluation in R

data("iris")

c <- head(iris)

print(c)

x <- iris[3:4]

print(x)

print(head(x))

model <- kmeans(x, 3)

library(cluster)

# Save clustering plot

png("KMeans_Clustering.png")

clusplot(x, model$cluster, color = TRUE, shade = TRUE)

[Link]()
OUTPUT:

> data("iris")
>

> c <- head(iris)

> print(c)

[Link] [Link] [Link] [Link] Species

1 5.1 3.5 1.4 0.2 setosa

2 4.9 3.0 1.4 0.2 setosa

3 4.7 3.2 1.3 0.2 setosa

4 4.6 3.1 1.5 0.2 setosa

5 5.0 3.6 1.4 0.2 setosa

6 5.4 3.9 1.7 0.4 setosa

>

> x <- iris[3:4]

> print(x)

[Link] [Link]

1 1.4 0.2
2 1.4 0.2

3 1.3 0.2

4 1.5 0.2

5 1.4 0.2

6 1.7 0.4

7 1.4 0.3

8 1.5 0.2
9 1.4 0.2

10 1.5 0.1

11 1.5 0.2

12 1.6 0.2
13 1.4 0.1

14 1.1 0.1

15 1.2 0.2

16 1.5 0.4

17 1.3 0.4

18 1.4 0.3

19 1.7 0.3

20 1.5 0.3
21 1.7 0.2

22 1.5 0.4

23 1.0 0.2

24 1.7 0.5

25 1.9 0.2

26 1.6 0.2

27 1.6 0.4
28 1.5 0.2

29 1.4 0.2

30 1.6 0.2

31 1.6 0.2

32 1.5 0.4

33 1.5 0.1

34 1.4 0.2
35 1.5 0.2

36 1.2 0.2

37 1.3 0.2

38 1.4 0.1
39 1.3 0.2

40 1.5 0.2

41 1.3 0.3

42 1.3 0.3

43 1.3 0.2

44 1.6 0.6

45 1.9 0.4

46 1.4 0.3
47 1.6 0.2

48 1.4 0.2

49 1.5 0.2

50 1.4 0.2

51 4.7 1.4

52 4.5 1.5

53 4.9 1.5
54 4.0 1.3

55 4.6 1.5

56 4.5 1.3

57 4.7 1.6

58 3.3 1.0

59 4.6 1.3

60 3.9 1.4
61 3.5 1.0

62 4.2 1.5

63 4.0 1.0

64 4.7 1.4
65 3.6 1.3

66 4.4 1.4

67 4.5 1.5

68 4.1 1.0

69 4.5 1.5

70 3.9 1.1

71 4.8 1.8

72 4.0 1.3
73 4.9 1.5

74 4.7 1.2

75 4.3 1.3

76 4.4 1.4

77 4.8 1.4

78 5.0 1.7

79 4.5 1.5
80 3.5 1.0

81 3.8 1.1

82 3.7 1.0

83 3.9 1.2

84 5.1 1.6

85 4.5 1.5

86 4.5 1.6
87 4.7 1.5

88 4.4 1.3

89 4.1 1.3

90 4.0 1.3
91 4.4 1.2

92 4.6 1.4

93 4.0 1.2

94 3.3 1.0

95 4.2 1.3

96 4.2 1.2

97 4.2 1.3

98 4.3 1.3
99 3.0 1.1

100 4.1 1.3

101 6.0 2.5

102 5.1 1.9

103 5.9 2.1

104 5.6 1.8

105 5.8 2.2

106 6.6 2.1

107 4.5 1.7

108 6.3 1.8

109 5.8 1.8

110 6.1 2.5

111 5.1 2.0

112 5.3 1.9

113 5.5 2.1

114 5.0 2.0

115 5.1 2.4

116 5.3 2.3

117 5.5 1.8

118 6.7 2.2

119 6.9 2.3

120 5.0 1.5

121 5.7 2.3

122 4.9 2.0

123 6.7 2.0

124 4.9 1.8

125 5.7 2.1

126 6.0 1.8

127 4.8 1.8

128 4.9 1.8

129 5.6 2.1

130 5.8 1.6

131 6.1 1.9

132 6.4 2.0

133 5.6 2.2

134 5.1 1.5

135 5.6 1.4

136 6.1 2.3

137 5.6 2.4

138 5.5 1.8

139 4.8 1.8

140 5.4 2.1

141 5.6 2.4

142 5.1 2.3

143 5.1 1.9

144 5.9 2.3

145 5.7 2.5

146 5.2 2.3

147 5.0 1.9

148 5.2 2.0

149 5.4 2.3

150 5.1 1.8

> print(head(x))

[Link] [Link]

1 1.4 0.2

2 1.4 0.2

3 1.3 0.2

4 1.5 0.2

5 1.4 0.2
6 1.7 0.4

>

> model <- kmeans(x, 3)

>

> library(cluster)

>

> # Save clustering plot

> png("KMeans_Clustering.png")

>

> clusplot(x, model$cluster, color = TRUE, shade = TRUE)

>
> [Link]()

RStudioGD

>

GRAPH: