#Fetching The Dataset
library(readxl)
## Warning: package 'readxl' was built under R version 4.3.3
cybercrime <- read_excel("C:/Users/Nitin/Desktop/4th sem/ca/vasvi/data exploration/cybercrime.xlsx")
View(cybercrime)
#1. Which Indian state reports the highest number of cyber crimes overall?
max_crimes<- cybercrime[which.max(cybercrime$Total),]
print(max_crimes)
## # A tibble: 1 × 24
## State `Personal Revenge` Anger Fraud Extortion `Causing Disrepute` Prank
## <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 Karnataka 12 4 11381 43 109 1
## # ℹ 17 more variables: `Sexual Exploitation` <dbl>, `Political Motives` <dbl>,
## # `Terrorist Activities (Total)` <dbl>,
## # `Terrorist Activities - Terrorist Recruitment` <dbl>,
## # `Terrorist Activities - Terrorist Funding` <dbl>,
## # `Terrorist Activities - Others` <dbl>,
## # `Inciting Hate against Country` <dbl>, `Disrupt Public Service` <dbl>,
## # `Sale Purchase Illegal Drugs` <dbl>, `Developing own Business` <dbl>, …
#2.What is the overall trend in cyber crime rates across different Indian states over the years?
cyber_data <- cybercrime[-1,]
# Convert 'Year' column to numeric
cyber_data$Year <- as.numeric(cyber_data$Year)
# Calculate total cyber crime rates for each year
crime_year <- aggregate(Total ~ Year, data = cyber_data, sum)
print(crime_year)
## Year Total
## 1 2017 20662
## 2 2018 27004
## 3 2019 44395
## 4 2020 49708
#3.Which state has the highest incidence of cyber crimes involving personal revenge and anger?
cybercrime$Total_Revenge_Anger <- cybercrime$'Personal Revenge' + cybercrime$'Anger'
state_highest_incidence <- cybercrime$'State'[which.max(cybercrime$Total_Revenge_Anger)]
cat("State with the highest incidence of cyber crimes involving personal revenge and anger:", state_highest_incidence, "\n")
## State with the highest incidence of cyber crimes involving personal revenge and anger: Assam
#4.What is the distribution of cyber crimes involving fraud across different states?
fraud_distribution <- aggregate(cybercrime$Fraud,
by = list(State = cybercrime$State, Year = cybercrime$Year),
sum)
print(fraud_distribution)
## State Year x
## 1 Andhra Pradesh 2017 537
## 2 Arunachal Pradesh 2017 0
## 3 Assam 2017 48
## 4 Bihar 2017 397
## 5 Chhattisgarh 2017 47
## 6 Goa 2017 8
## 7 Gujarat 2017 305
## 8 Haryana 2017 43
## 9 Himachal Pradesh 2017 8
## 10 Jammu & Kashmir 2017 15
## 11 Jharkhand 2017 460
## 12 Karnataka 2017 2764
## 13 Kerala 2017 77
## 14 Madhya Pradesh 2017 155
## 15 Maharashtra 2017 2171
## 16 Manipur 2017 35
## 17 Meghalaya 2017 15
## 18 Mizoram 2017 7
## 19 Nagaland 2017 0
## 20 Odisha 2017 531
## 21 Punjab 2017 53
## 22 Rajasthan 2017 331
## 23 Sikkim 2017 0
## 24 Tamil Nadu 2017 51
## 25 Telangana 2017 529
## 26 Tripura 2017 3
## 27 Uttar Pradesh 2017 3450
## 28 Uttarakhand 2017 54
## 29 West Bengal 2017 45
## 30 Andhra Pradesh 2018 733
## 31 Arunachal Pradesh 2018 2
## 32 Assam 2018 389
## 33 Bihar 2018 351
## 34 Chhattisgarh 2018 23
## 35 Goa 2018 11
## 36 Gujarat 2018 401
## 37 Haryana 2018 137
## 38 Himachal Pradesh 2018 18
## 39 Jammu & Kashmir 2018 20
## 40 Jharkhand 2018 783
## 41 Karnataka 2018 5441
## 42 Kerala 2018 93
## 43 Madhya Pradesh 2018 230
## 44 Maharashtra 2018 1998
## 45 Manipur 2018 14
## 46 Meghalaya 2018 35
## 47 Mizoram 2018 0
## 48 Nagaland 2018 0
## 49 Odisha 2018 506
## 50 Punjab 2018 48
## 51 Rajasthan 2018 499
## 52 Sikkim 2018 0
## 53 Tamil Nadu 2018 55
## 54 Telangana 2018 732
## 55 Tripura 2018 8
## 56 Uttar Pradesh 2018 2351
## 57 Uttarakhand 2018 46
## 58 West Bengal 2018 68
## 59 Andhra Pradesh 2019 1211
## 60 Arunachal Pradesh 2019 0
## 61 Assam 2019 243
## 62 Bihar 2019 844
## 63 Chhattisgarh 2019 47
## 64 Goa 2019 9
## 65 Gujarat 2019 363
## 66 Haryana 2019 151
## 67 Himachal Pradesh 2019 15
## 68 Jammu & Kashmir 2019 27
## 69 Jharkhand 2019 964
## 70 Karnataka 2019 11381
## 71 Kerala 2019 67
## 72 Madhya Pradesh 2019 178
## 73 Maharashtra 2019 3551
## 74 Manipur 2019 0
## 75 Meghalaya 2019 50
## 76 Mizoram 2019 0
## 77 Nagaland 2019 0
## 78 Odisha 2019 1000
## 79 Punjab 2019 81
## 80 Rajasthan 2019 938
## 81 Sikkim 2019 0
## 82 Tamil Nadu 2019 73
## 83 Telangana 2019 2013
## 84 Tripura 2019 2
## 85 Uttar Pradesh 2019 3549
## 86 Uttarakhand 2019 28
## 87 West Bengal 2019 68
## 88 Andhra Pradesh 2020 1149
## 89 Arunachal Pradesh 2020 26
## 90 Assam 2020 242
## 91 Bihar 2020 1218
## 92 Chhattisgarh 2020 75
## 93 Goa 2020 25
## 94 Gujarat 2020 875
## 95 Haryana 2020 157
## 96 Himachal Pradesh 2020 19
## 97 Jharkhand 2020 1069
## 98 Karnataka 2020 9680
## 99 Kerala 2020 96
## 100 Madhya Pradesh 2020 292
## 101 Maharashtra 2020 3413
## 102 Manipur 2020 40
## 103 Meghalaya 2020 81
## 104 Mizoram 2020 3
## 105 Nagaland 2020 5
## 106 Odisha 2020 1380
## 107 Punjab 2020 164
## 108 Rajasthan 2020 641
## 109 Sikkim 2020 0
## 110 Tamil Nadu 2020 134
## 111 Telangana 2020 4436
## 112 Tripura 2020 11
## 113 Uttar Pradesh 2020 4674
## 114 Uttarakhand 2020 98
## 115 West Bengal 2020 72
#5.Which states report the most cases of cyber crimes involving extortion?
extortion_cases <- aggregate(Extortion ~ State, data = cybercrime,sum)
max_extortion_cases <- extortion_cases[which.max(extortion_cases$Extortion), ]
print(max_extortion_cases)
## State Extortion
## 27 Uttar Pradesh 2217
#6.Which states report the most cases of cyber crimes involving causing disrepute?
disrepute_cases <- aggregate(`Causing Disrepute` ~ State, data = cybercrime,sum)
max_disrepute_cases <- disrepute_cases[which.max(disrepute_cases$`Causing Disrepute`), ]
print(max_disrepute_cases)
## State Causing Disrepute
## 27 Uttar Pradesh 2209
#7.Which state has the highest incidence of cyber crimes involving sexual exploitation?
sexual_exploitation <- aggregate(`Sexual Exploitation` ~ State, data = cybercrime,sum)
max_sexual_exploitation <- sexual_exploitation[which.max(sexual_exploitation$`Sexual Exploitation`), ]
print(max_sexual_exploitation)
## State Sexual Exploitation
## 15 Maharashtra 2355
#8. What is the distribution of cyber crimes involving the sale and purchase of illegal drugs across different states?
illegal_drugs <- aggregate(`Sale Purchase Illegal Drugs` ~ State, data = cybercrime,sum)
print(illegal_drugs)
## State Sale Purchase Illegal Drugs
## 1 Andhra Pradesh 0
## 2 Arunachal Pradesh 0
## 3 Assam 0
## 4 Bihar 2
## 5 Chhattisgarh 0
## 6 Goa 0
## 7 Gujarat 2
## 8 Haryana 2
## 9 Himachal Pradesh 0
## 10 Jammu & Kashmir 0
## 11 Jharkhand 26
## 12 Karnataka 2
## 13 Kerala 0
## 14 Madhya Pradesh 0
## 15 Maharashtra 2
## 16 Manipur 0
## 17 Meghalaya 2
## 18 Mizoram 0
## 19 Nagaland 0
## 20 Odisha 0
## 21 Punjab 3
## 22 Rajasthan 0
## 23 Sikkim 0
## 24 Tamil Nadu 0
## 25 Telangana 0
## 26 Tripura 0
## 27 Uttar Pradesh 0
## 28 Uttarakhand 4
## 29 West Bengal 0
#9.How prevalent is cyber crime involving disrupting public services in each state?
public_service_disruption_cases <- aggregate(`Disrupt Public Service` ~ State, data = cybercrime,sum)
print(public_service_disruption_cases)
## State Disrupt Public Service
## 1 Andhra Pradesh 4
## 2 Arunachal Pradesh 0
## 3 Assam 15
## 4 Bihar 1
## 5 Chhattisgarh 1
## 6 Goa 0
## 7 Gujarat 14
## 8 Haryana 3
## 9 Himachal Pradesh 1
## 10 Jammu & Kashmir 13
## 11 Jharkhand 30
## 12 Karnataka 6
## 13 Kerala 1
## 14 Madhya Pradesh 2
## 15 Maharashtra 6
## 16 Manipur 0
## 17 Meghalaya 1
## 18 Mizoram 1
## 19 Nagaland 0
## 20 Odisha 0
## 21 Punjab 4
## 22 Rajasthan 0
## 23 Sikkim 0
## 24 Tamil Nadu 28
## 25 Telangana 2
## 26 Tripura 0
## 27 Uttar Pradesh 58
## 28 Uttarakhand 0
## 29 West Bengal 0
#10. In which states are cyber crimes involving the development of one's own business most common?
business_development <- aggregate(`Developing own Business` ~ State, data = cybercrime,sum)
max_business_development <- business_development[which.max(business_development$`Developing own Business`), ]
print(max_business_development)
## State Developing own Business
## 27 Uttar Pradesh 247
#11.Which states report the highest cases of cyber crimes involving spreading piracy?
max_piracy_state <- cybercrime[which.max(cybercrime$`Spreading Piracy`), "State"]
print(max_piracy_state)
## # A tibble: 1 × 1
## State
## <chr>
## 1 Uttar Pradesh
#12.How does the distribution of a specific type of cybercrime (e.g., fraud, extortion, political motives, etc.)
#vary across different states? Visualize this using a box plot
#to compare the median, quartiles, and potential outliers of the reported cybercrime counts in each state.
# Specify the specific type of cybercrime you want to analyze (e.g., fraud, extortion, political motives)
specific_cybercrime <- "Fraud"
filtered_data <- subset(cybercrime, select = c("State", specific_cybercrime))
boxplot(filtered_data[[specific_cybercrime]] ~ filtered_data$State,
xlab = "State", ylab = paste("Reported Instances of", specific_cybercrime),
main = paste("Distribution of", specific_cybercrime, "across Different States"),
col = "skyblue", border = "black")
#13.Is there a relationship between the year and the total number of cybercrimes reported?
#Can we use regression to predict the expected number of cybercrimes in future years?
str(cybercrime)
## tibble [115 × 25] (S3: tbl_df/tbl/data.frame)
## $ State : chr [1:115] "Andhra Pradesh" "Arunachal Pradesh" "Assam" "Bihar" ...
## $ Personal Revenge : num [1:115] 24 0 246 12 8 0 6 7 5 0 ...
## $ Anger : num [1:115] 5 0 83 5 3 0 5 6 4 1 ...
## $ Fraud : num [1:115] 537 0 48 397 47 8 305 43 8 15 ...
## $ Extortion : num [1:115] 65 0 65 3 4 0 12 4 6 10 ...
## $ Causing Disrepute : num [1:115] 0 0 40 0 29 5 79 9 3 0 ...
## $ Prank : num [1:115] 0 0 40 0 18 0 3 2 3 3 ...
## $ Sexual Exploitation : num [1:115] 61 0 217 16 16 0 24 36 10 7 ...
## $ Political Motives : num [1:115] 12 0 10 0 3 0 4 0 3 0 ...
## $ Terrorist Activities (Total) : num [1:115] 8 0 44 0 0 0 0 0 0 3 ...
## $ Terrorist Activities - Terrorist Recruitment: num [1:115] 0 0 0 0 0 0 0 0 0 0 ...
## $ Terrorist Activities - Terrorist Funding : num [1:115] 0 0 0 0 0 0 0 0 0 0 ...
## $ Terrorist Activities - Others : num [1:115] 8 0 44 0 0 0 0 0 0 3 ...
## $ Inciting Hate against Country : num [1:115] 0 0 2 0 1 0 6 0 0 0 ...
## $ Disrupt Public Service : num [1:115] 1 0 0 0 0 0 2 1 0 10 ...
## $ Sale Purchase Illegal Drugs : num [1:115] 0 0 0 0 0 0 0 2 0 0 ...
## $ Developing own Business : num [1:115] 0 0 0 0 0 0 1 7 4 0 ...
## $ Spreading Piracy : num [1:115] 1 0 0 0 0 0 0 4 1 0 ...
## $ Psycho or Pervert : num [1:115] 0 0 0 0 0 0 0 0 0 0 ...
## $ Steal Information : num [1:115] 0 0 3 0 0 0 0 1 0 0 ...
## $ Abetment to Suicide : num [1:115] 0 0 0 0 0 0 0 0 0 0 ...
## $ Others : num [1:115] 217 1 322 0 42 0 11 382 9 14 ...
## $ Total : num [1:115] 931 1 1120 433 171 13 458 504 56 63 ...
## $ Year : num [1:115] 2017 2017 2017 2017 2017 ...
## $ Total_Revenge_Anger : num [1:115] 29 0 329 17 11 0 11 13 9 1 ...
total_crimes_per_year <- aggregate(Total ~ Year, data = cybercrime,sum)
model <- lm(Total ~ Year, data = total_crimes_per_year)
summary(model)
##
## Call:
## lm(formula = Total ~ Year, data = total_crimes_per_year)
##
## Residuals:
## 1 2 3 4
## 1178 -3584 3633 -1227
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -20499737 3433929 -5.97 0.0269 *
## Year 10174 1701 5.98 0.0268 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 3804 on 2 degrees of freedom
## Multiple R-squared: 0.947, Adjusted R-squared: 0.9206
## F-statistic: 35.76 on 1 and 2 DF, p-value: 0.02684
future_years <- data.frame(Year = c(2025, 2026, 2027))
predicted_crimes <- predict(model, newdata = future_years)
print(predicted_crimes)
## 1 2 3
## 101803.4 111977.0 122150.6
#14.Can we identify any correlations between different types of cybercrimes
#(e.g., fraud and theft of information)?
str(cybercrime)
## tibble [115 × 25] (S3: tbl_df/tbl/data.frame)
## $ State : chr [1:115] "Andhra Pradesh" "Arunachal Pradesh" "Assam" "Bihar" ...
## $ Personal Revenge : num [1:115] 24 0 246 12 8 0 6 7 5 0 ...
## $ Anger : num [1:115] 5 0 83 5 3 0 5 6 4 1 ...
## $ Fraud : num [1:115] 537 0 48 397 47 8 305 43 8 15 ...
## $ Extortion : num [1:115] 65 0 65 3 4 0 12 4 6 10 ...
## $ Causing Disrepute : num [1:115] 0 0 40 0 29 5 79 9 3 0 ...
## $ Prank : num [1:115] 0 0 40 0 18 0 3 2 3 3 ...
## $ Sexual Exploitation : num [1:115] 61 0 217 16 16 0 24 36 10 7 ...
## $ Political Motives : num [1:115] 12 0 10 0 3 0 4 0 3 0 ...
## $ Terrorist Activities (Total) : num [1:115] 8 0 44 0 0 0 0 0 0 3 ...
## $ Terrorist Activities - Terrorist Recruitment: num [1:115] 0 0 0 0 0 0 0 0 0 0 ...
## $ Terrorist Activities - Terrorist Funding : num [1:115] 0 0 0 0 0 0 0 0 0 0 ...
## $ Terrorist Activities - Others : num [1:115] 8 0 44 0 0 0 0 0 0 3 ...
## $ Inciting Hate against Country : num [1:115] 0 0 2 0 1 0 6 0 0 0 ...
## $ Disrupt Public Service : num [1:115] 1 0 0 0 0 0 2 1 0 10 ...
## $ Sale Purchase Illegal Drugs : num [1:115] 0 0 0 0 0 0 0 2 0 0 ...
## $ Developing own Business : num [1:115] 0 0 0 0 0 0 1 7 4 0 ...
## $ Spreading Piracy : num [1:115] 1 0 0 0 0 0 0 4 1 0 ...
## $ Psycho or Pervert : num [1:115] 0 0 0 0 0 0 0 0 0 0 ...
## $ Steal Information : num [1:115] 0 0 3 0 0 0 0 1 0 0 ...
## $ Abetment to Suicide : num [1:115] 0 0 0 0 0 0 0 0 0 0 ...
## $ Others : num [1:115] 217 1 322 0 42 0 11 382 9 14 ...
## $ Total : num [1:115] 931 1 1120 433 171 13 458 504 56 63 ...
## $ Year : num [1:115] 2017 2017 2017 2017 2017 ...
## $ Total_Revenge_Anger : num [1:115] 29 0 329 17 11 0 11 13 9 1 ...
correlation_matrix <- cor(cybercrime[, c("Fraud", "Steal Information")])
print(correlation_matrix)
## Fraud Steal Information
## Fraud 1.00000000 0.04347427
## Steal Information 0.04347427 1.00000000
#15.Are there noticeable trends in cyber crime types in specific states over time?
target_states <- c("Tamil Nadu", "Uttar Pradesh")
filtered_data <- cybercrime[cybercrime$State %in% target_states, ]
library(dplyr)
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
crime_trends <- filtered_data %>%
group_by(Year) %>%
summarise(
`Personal Revenge` = sum(`Personal Revenge`),
Anger = sum(Anger),
Fraud = sum(Fraud),
Extortion = sum(Extortion)
)
library(ggplot2)
## Warning: package 'ggplot2' was built under R version 4.3.3
ggplot(crime_trends, aes(x = Year)) +
geom_line(aes(y = `Personal Revenge`, color = "Personal Revenge")) +
geom_line(aes(y = Anger, color = "Anger")) +
geom_line(aes(y = Fraud, color = "Fraud")) +
geom_line(aes(y = Extortion, color = "Extortion")) +
labs(title = "Trends in Cyber Crime Types Over Time",
x = "Year", y = "Total Cases") +
scale_color_manual(values = c("red", "blue", "green", "orange"),
breaks = c("Personal Revenge", "Anger", "Fraud", "Extortion"),
labels = c("Personal Revenge", "Anger", "Fraud", "Extortion"))
# Comparative Analysis:
#16.How do different states compare in terms of the number and types of cyber crimes?
library(dplyr)
state_crime_summary <- cybercrime %>%
group_by(State) %>%
summarise_all(sum)
library(ggplot2)
crime_distribution_long <- state_crime_summary[order(state_crime_summary$Total), ]
ggplot(state_crime_summary, aes(x = reorder(State, Total), y = Total, fill = State)) +
geom_col() +
labs(title = "Total Number of Cyber Crime Cases by State",
x = "State", y = "Total Cases") +
theme(axis.text.x = element_text(angle = 90))
#17.How is the distribution of different types of cyber crimes across Indian states (e.g., extortion, fraud, sexual harassment)
library(dplyr)
crime_distribution <- cybercrime %>%
group_by(State) %>%
summarise(
Extortion = sum(Extortion),
Fraud = sum(Fraud),
Sexual_Harassment = sum(`Sexual Exploitation`)
)
library(ggplot2)
ggplot(crime_distribution_long, aes(x = State, y = Total)) +
geom_col(fill = "blue") +
labs(title = "Cyber Crime Distribution Across Indian States",
x = "State", y = "Total Cases") +
theme(axis.text.x = element_text(angle = 90))
#18.What is the total number of cyber crime incidents reported in each Indian state?
library(dplyr)
total_incidents_by_state <- cybercrime %>%
group_by(State) %>%
summarise(Total_Incidents = sum(Total))
print(total_incidents_by_state)
## # A tibble: 29 × 2
## State Total_Incidents
## <chr> <dbl>
## 1 Andhra Pradesh 5923
## 2 Arunachal Pradesh 46
## 3 Assam 8903
## 4 Bihar 3369
## 5 Chhattisgarh 782
## 6 Goa 97
## 7 Gujarat 3227
## 8 Haryana 2142
## 9 Himachal Pradesh 299
## 10 Jammu & Kashmir 209
## # ℹ 19 more rows