Lab Experiment File

of
DATA ANALYTICS USING R (150701)

Submitted By:

Anirban Das
(0901CS211140)

Prof. Khushboo Agarwal

Assistant Professor
Computer Science and Engineering

DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING

MADHAV INSTITUTE OF TECHNOLOGY & SCIENCE
GWALIOR - 474005 (MP) est. 1957

JULY-DEC 2024
3
 Experiment = 1

Write a program in R to understand the basics of R programming,

including data types, variables, and basic operations.

# 1. Data Types
# Numeric
num_var <- 10.5
print(paste("Numeric:", num_var))

# Integer
int_var <- 5L
print(paste("Integer:", int_var))

# Character
char_var <- "Hello, R!"
print(paste("Character:", char_var))

# Logical
log_var <- TRUE
print(paste("Logical:", log_var))

# 2. Variables
# Assigning values to variables
a <- 5
b <- 10

# 3. Basic Operations
# Addition
sum_result <- a + b
print(paste("Sum:", sum_result))

# Subtraction
sub_result <- a - b
print(paste("Subtraction:", sub_result))

# Multiplication
mul_result <- a * b
print(paste("Multiplication:", mul_result))

# Division
div_result <- a / b
print(paste("Division:", div_result))

4
OUTPUT :

5
 Experiment = 2

Write a program in R to import and export data in different formats such

as CSV and Excel.

library(readr) # For CSV handling

library(openxlsx) # For Excel handling

# Import data from CSV

csv_data <- read_csv("data.csv")
print("Imported CSV Data:")
print(csv_data)

# Export data to CSV

write_csv(csv_data, "data/exported_sample.csv")

# Import data from Excel

excel_data <- read.xlsx("data.xlsx", sheet = 1)
print("Imported Excel Data:")
print(excel_data)

# Export data to Excel

write.xlsx(excel_data, "data/exported_sample.xlsx", sheetName =
"Sheet1") # Change the path as needed

OUTPUT :

File created

6
 Experiment = 3

Write a program in R using the dplyr package to perform data manipulation

tasks like filtering, selecting, and summarizing data
library(dplyr)

# Sample data frame

data <- data.frame(
Name = c("Alice", "Bob", "Charlie", "David", "Eve"),
Age = c(25, 30, 35, 40, 22),
Score = c(85.5, 90.0, 78.5, 88.0, 92.5)
)

print("Original Data:")
print(data)

# 1. Filtering Data
# Filter for rows where Age is greater than 30
filtered_data <- data %>%
filter(Age > 30)

print("Filtered Data (Age > 30):")

print(filtered_data)

# 2. Selecting Columns
# Select only the Name and Score columns
selected_data <- data %>%
select(Name, Score)

print("Selected Columns (Name and Score):")

print(selected_data)

# 3. Summarizing Data
# Calculate the average score
average_score <- data %>%
summarize(Average_Score = mean(Score))

print("Average Score:")
print(average_score)

7
OUTPUT :

8
 Experiment = 4

Write a program in R using the ggplot2 package to create various data

visualizations including scatter plots, bar charts, and histograms

library(ggplot2)

# Sample data frame

data <- data.frame(
Name = c("Alice", "Bob", "Charlie", "David", "Eve"),
Age = c(25, 30, 35, 40, 22),
Score = c(85.5, 90.0, 78.5, 88.0, 92.5)
)

# 1. Scatter Plot
scatter_plot <- ggplot(data, aes(x = Age, y = Score)) +
geom_point(color = "blue", size = 3) +
labs(title = "Scatter Plot of Age vs Score",
x = "Age",
y = "Score") +
theme_minimal()

print(scatter_plot)

# 2. Bar Chart
# Create a bar chart for Scores by Name
bar_chart <- ggplot(data, aes(x = Name, y = Score, fill = Name)) +
geom_bar(stat = "identity") +
labs(title = "Bar Chart of Scores by Name",
x = "Name",
y = "Score") +
theme_minimal()

# Print the bar chart

print(bar_chart)

# 3. Histogram
# Create a histogram of Scores
histogram <- ggplot(data, aes(x = Score)) +
geom_histogram(binwidth = 5, fill = "lightblue", color = "black") +
labs(title = "Histogram of Scores",
x = "Score",
y = "Frequency") +
theme_minimal()

print(histogram)

9
OUTPUT :

10
 Experiment = 5

Write a program in R to perform Exploratory Data Analysis (EDA) by

generating summary statistics, visualizing distributions, and identifying
correlations.

library(ggplot2)
library(dplyr)
library(corrplot)

# Sample data frame

set.seed(123)
data <- data.frame(
Age = sample(20:50, 100, replace = TRUE),
Score = rnorm(100, mean = 75, sd = 10),
Height = rnorm(100, mean = 160, sd = 15),
Weight = rnorm(100, mean = 65, sd = 10)
)

# 1. Summary Statistics
summary_statistics <- summary(data)
print("Summary Statistics:")
print(summary_statistics)

# 2. Visualizing Distributions
# Histogram for Age
hist_age <- ggplot(data, aes(x = Age)) +
geom_histogram(binwidth = 2, fill = "lightblue", color = "black") +
labs(title = "Histogram of Age", x = "Age", y = "Frequency") +
theme_minimal()

print(hist_age)

# 3. Correlation Matrix
correlation_matrix <- cor(data)
print("Correlation Matrix:")
print(correlation_matrix)

# Visualizing the correlation matrix

corrplot(correlation_matrix, method = "circle", type = "upper",
tl.col = "black", tl.srt = 45,
title = "Correlation Matrix", mar = c(0, 0, 1, 0))

10
OUTPUT :

11
 Experiment = 6

Write a program in R to clean and preprocess data, including handling

missing values, detecting outliers, and normalizing data.

library(dplyr)
library(ggplot2)

# Sample data frame creation with missing values and outliers

set.seed(123)
n <- 100

data <- data.frame(

Age = c(sample(20:50, n - 2, replace = TRUE), NA, 100), # 1 missing value
and 1 outlier
Score = c(rnorm(n - 1, mean = 75, sd = 10), NA), # 1 missing value
Height = c(rnorm(n - 2, mean = 160, sd = 15), 180, 250) # 1 outlier and 1
missing
)

print("Original Data:")
print(head(data))

# 1. Handling Missing Values

# Check for missing values
missing_summary <- sapply(data, function(x) sum(is.na(x)))
print("Missing Values Summary:")
print(missing_summary)

# Impute missing values with the mean of each column

data <- data %>%
mutate(
Age = ifelse(is.na(Age), mean(Age, na.rm = TRUE), Age),
Score = ifelse(is.na(Score), mean(Score, na.rm = TRUE), Score)
)

# Print data after handling missing values

print("Data after Handling Missing Values:")
print(head(data))

# 2. Detecting Outliers
# Function to detect outliers using IQR method
detect_outliers <- function(x) {
Q1 <- quantile(x, 0.25)
Q3 <- quantile(x, 0.75)
IQR <- Q3 - Q1
lower_bound <- Q1 - 1.5 * IQR

12
 upper_bound <- Q3 + 1.5 * IQR
return(x < lower_bound | x > upper_bound)
}

# Detect outliers in Age and Height

data$Age_Outlier <- detect_outliers(data$Age)
data$Height_Outlier <- detect_outliers(data$Height)

# Print detected outliers

print("Detected Outliers:")
print(data %>% filter(Age_Outlier | Height_Outlier))

# 3. Normalizing Data
# Normalizing using min-max scaling
normalize <- function(x) {
return((x - min(x)) / (max(x) - min(x)))
}

data_normalized <- data %>%

mutate(
Age = normalize(Age),
Score = normalize(Score),
Height = normalize(Height)
)

print("Normalized Data:")
print(head(data_normalized))

OUTPUT :

13
14
 Experiment = 7

Write a program in R to perform linear regression analysis, fit a model,

interpret coefficients, and make predictions .

library(ggplot2)

# Sample Data: Create a simple data frame

set.seed(42)
data <- data.frame(
x = rnorm(100, mean = 5, sd = 2), # Independent variable
y = rnorm(100, mean = 10, sd = 3) # Dependent variable
)

# Introduce a linear relationship

data$y <- 3 * data$x + rnorm(100) # y = 3x + noise

# Explore the data

head(data)
summary(data)

# Fit a linear regression model

model <- lm(y ~ x, data = data)

# Summarize the model

summary(model)

# Make predictions
new_data <- data.frame(x = c(3, 5, 7)) # New x values for prediction
predictions <- predict(model, new_data)

# Show predictions
predictions

# Visualize the data and the fitted model

ggplot(data, aes(x = x, y = y)) +
geom_point(color = 'blue') + # Scatter plot of the data
geom_smooth(method = 'lm', color = 'red') + # Regression line
labs(title = "Linear Regression Analysis",
x = "Independent Variable (x)",
y = "Dependent Variable (y)")

15
OUTPUT :

A data.frame: 6 × 2

x y

<dbl> <dbl>

1 7.741917 21.22482

2 3.870604 11.94559

3 5.726257 18.35010

4 6.265725 20.85671

5 5.808537 16.04875

6 4.787751 13.21240
x y
Min. :-0.9862 Min. :-3.976
1st Qu.: 3.7666 1st Qu.:11.827
Median : 5.1796 Median :15.581
Mean : 5.0650 Mean :15.185
3rd Qu.: 6.3231 3rd Qu.:19.132
Max. : 9.5733 Max. :30.757

Call:
lm(formula = y ~ x, data = data)

Residuals:
Min 1Q Median 3Q Max
-2.5640 -0.6301 -0.1046 0.6518 2.4347

Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 0.34771 0.26710 1.302 0.196
x 2.92930 0.04881 60.018 <2e-16 ***
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 1.011 on 98 degrees of freedom

Multiple R-squared: 0.9735, Adjusted R-squared: 0.9732
F-statistic: 3602 on 1 and 98 DF, p-value: < 2.2e-16
1
9.13562194092176
2
14.9942291875231
3
20.8528364341244
`geom_smooth()` using formula = 'y ~ x'

16
17
 Experiment = 8

Write a program in R to apply logistic regression for classification, interpret

model coefficients, and evaluate performance with a confusion matrix and
ROC curve.

library(ggplot2)
library(caret)
library(pROC)

# Sample Data: Using the built-in iris dataset for binary

classification
data <- iris
data$Species <- ifelse(data$Species == "setosa", 1, 0)

# Split the data into training and testing sets

set.seed(42)
train_index <- createDataPartition(data$Species, p = 0.7, list = FALSE)
train_data <- data[train_index, ]
test_data <- data[-train_index, ]

# Fit a logistic regression model

model <- glm(Species ~ Sepal.Length + Sepal.Width, data = train_data,
family = binomial)

# Summarize the model

summary(model)

# Make predictions on the test set

test_data$predicted_prob <- predict(model, newdata = test_data, type =
"response")
test_data$predicted_class <- ifelse(test_data$predicted_prob > 0.5, 1,
0)

# Create a confusion matrix

conf_matrix <- confusionMatrix(as.factor(test_data$predicted_class),
as.factor(test_data$Species))
print(conf_matrix)

# ROC Curve
roc_obj <- roc(test_data$Species, test_data$predicted_prob)
auc_value <- auc(roc_obj)

18
OUTPUT :

Number of Fisher Scoring iterations: 25

Confusion Matrix and Statistics

Reference
Prediction 0 1
0 33 0
1 0 12

Accuracy : 1
95% CI : (0.9213, 1)
No Information Rate : 0.7333
P-Value [Acc > NIR] : 8.681e-07

Kappa : 1

Mcnemar's Test P-Value : NA

Sensitivity : 1.0000
Specificity : 1.0000
Pos Pred Value : 1.0000
Neg Pred Value : 1.0000
Prevalence : 0.7333
Detection Rate : 0.7333
Detection Prevalence : 0.7333
Balanced Accuracy : 1.0000

'Positive' Class : 0

Setting levels: control = 0, case = 1

Setting direction: controls < cases

19
 Experiment = 9

Write a program in R to perform clustering analysis using the k-means

algorithm, determine optimal clusters, and visualize results.

library(ggplot2)

data <- iris[, -5]

# Standardize the data

data_scaled <- scale(data)

# Determine optimal number of clusters using the Elbow method

wss <- numeric(10)
for (k in 1:10) {
kmeans_model <- kmeans(data_scaled, centers = k, nstart = 20)
wss[k] <- kmeans_model$tot.withinss
}

# Plot the Elbow curve

elbow_plot <- data.frame(Clusters = 1:10, WSS = wss)
ggplot(elbow_plot, aes(x = Clusters, y = WSS)) +
geom_line() +
geom_point() +
labs(title = "Elbow Method for Optimal k",
x = "Number of Clusters (k)",
y = "Total Within-Cluster Sum of Squares (WSS)") +
theme_minimal()

# Fit the k-means model with the optimal number of clusters

optimal_k <- which.min(diff(wss)) + 1 # Change this based on elbow
observation
kmeans_model <- kmeans(data_scaled, centers = optimal_k, nstart = 20)

# Add cluster assignments to the original data

iris$Cluster <- as.factor(kmeans_model$cluster)

# Visualize the clusters using a scatter plot

ggplot(iris, aes(x = Sepal.Length, y = Sepal.Width, color = Cluster)) +
geom_point(size = 3) +
labs(title = paste("K-Means Clustering (k =", optimal_k, ")"),
x = "Sepal Length",
y = "Sepal Width") +
theme_minimal()

20
OUTPUT :

21
 Experiment = 10

Write a program in R to analyze and forecast time series data using

techniques like moving averages, exponential smoothing, and ARIMA
models.

library(forecast)
library(ggplot2)

# Load the AirPassengers dataset

data("AirPassengers")

# Plot the original time series data

autoplot(AirPassengers) +
labs(title = "Air Passengers Over Time",
x = "Year",
y = "Number of Passengers") +
theme_minimal()

# Moving Average
# Calculate moving averages
ma_12 <- ma(AirPassengers, order = 12)
autoplot(AirPassengers) +
autolayer(ma_12, series = "12-Month Moving Average", PI = FALSE) +
labs(title = "Air Passengers with 12-Month Moving Average",
x = "Year",
y = "Number of Passengers") +
theme_minimal()

# Exponential Smoothing
# Fit exponential smoothing model
ets_model <- ets(AirPassengers)
summary(ets_model)

# Forecast using exponential smoothing

ets_forecast <- forecast(ets_model, h = 12)
autoplot(ets_forecast) +
labs(title = "Exponential Smoothing Forecast",
x = "Year",
y = "Number of Passengers") +
theme_minimal()

# ARIMA Model
# Fit an ARIMA model
arima_model <- auto.arima(AirPassengers)

22
summary(arima_model)

# Forecast using ARIMA

arima_forecast <- forecast(arima_model, h = 12)
autoplot(arima_forecast) +
labs(title = "ARIMA Forecast",
x = "Year",
y = "Number of Passengers") +
theme_minimal()

# Compare forecasts
autoplot(AirPassengers) +
autolayer(ets_forecast, series = "ETS Forecast", PI = FALSE) +
autolayer(arima_forecast, series = "ARIMA Forecast", PI = FALSE) +
labs(title = "Forecast Comparison: ETS vs ARIMA",
x = "Year",
y = "Number of Passengers") +
theme_minimal()

OUTPUT :

ETS(M,Ad,M)

23
Call:
ets(y = AirPassengers)

Smoothing parameters:
alpha = 0.7096
beta = 0.0204
gamma = 1e-04
phi = 0.98

Initial states:
l = 120.9939
b = 1.7705
s = 0.8944 0.7993 0.9217 1.0592 1.2203 1.2318
1.1105 0.9786 0.9804 1.011 0.8869 0.9059

sigma: 0.0392

AIC AICc BIC

1395.166 1400.638 1448.623

Training set error measures:

ME RMSE MAE MPE MAPE MASE
ACF1
Training set 1.567359 10.74726 7.791605 0.4357799 2.857917 0.2432573
0.03945056

Series: AirPassengers
ARIMA(2,1,1)(0,1,0)[12]

Coefficients:
ar1 ar2 ma1
0.5960 0.2143 -0.9819
s.e. 0.0888 0.0880 0.0292

24
sigma^2 = 132.3: log likelihood = -504.92
AIC=1017.85 AICc=1018.17 BIC=1029.35

Training set error measures:

ME RMSE MAE MPE MAPE MASE
ACF1
Training set 1.342299 10.84619 7.86754 0.4206976 2.800458 0.245628 -
0.001248475

25