#1 Which traffic sign appears most frequently in the dataset?
traffic_signs <- read.csv("C:/Users/Vivek singh/Downloads/labels.csv")
head(traffic_signs)
## ClassId Name
## 1 0 Speed limit (5km/h)
## 2 1 Speed limit (15km/h)
## 3 2 Speed limit (30km/h)
## 4 3 Speed limit (40km/h)
## 5 4 Speed limit (50km/h)
## 6 5 Speed limit (60km/h)
summary(traffic_signs)
## ClassId Name
## Min. : 0.00 Length:52
## 1st Qu.:12.75 Class :character
## Median :25.50 Mode :character
## Mean :25.50
## 3rd Qu.:38.25
## Max. :51.00
sign_counts <- table(traffic_signs$traffic_sign_type)
most_frequent_sign <- names(sign_counts)[which.max(sign_counts)]
print(most_frequent_sign)
## NULL
# 2 Distribution of different types of traffic signs in the dataset?
library(dplyr)
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
library(ggplot2)
traffic_signs <- read.csv("C:/Users/Vivek singh/Downloads/labels.csv")
traffic_sign_distribution <- table(traffic_signs$Name)
distribution_df <- data.frame(
sign_category = names(traffic_sign_distribution),
count = as.numeric(traffic_sign_distribution)
)
distribution_df <- distribution_df %>%
arrange(desc(count))
ggplot(distribution_df, aes(x = reorder(sign_category, count), y = count)) +
geom_bar(stat = "identity", fill = "skyblue", color = "black") +
theme_minimal() +
labs(x = "Traffic Sign Category", y = "Frequency", title = "Distribution of Traffic Sign Categories") +
theme(axis.text.x = element_text(angle = 45, hjust = 1))
# 3 Which traffic sign categories are the most common and least common?
library(dplyr)
traffic_signs <- read.csv("C:/Users/Vivek singh/Downloads/labels.csv")
traffic_sign_frequency <- traffic_signs %>%
count(Name) %>%
arrange(desc(n))
cat("Most common traffic sign categories:\n")
## Most common traffic sign categories:
print(traffic_sign_frequency[1:5, ])
## Name n
## 1 Bicycles crossing 2
## 2 Children crossing 1
## 3 Danger Ahead 1
## 4 Dangerous curve to the left 1
## 5 Dangerous curve to the right 1
cat("\nLeast common traffic sign categories:\n")
##
## Least common traffic sign categories:
print(traffic_sign_frequency[nrow(traffic_sign_frequency): (nrow(traffic_sign_frequency) - 4), ])
## Name n
## 51 watch out for cars 1
## 50 speed limit (80km/h) 1
## 49 keep Right 1
## 48 keep Left 1
## 47 ZigZag Curve 1
# 4 Are there any underrepresented traffic sign categories in the dataset?
library(dplyr)
traffic_signs <- read.csv("C:/Users/Vivek singh/Downloads/labels.csv")
traffic_sign_frequency <- traffic_signs %>%
count(Name) %>%
arrange(n)
cat("Underrepresented traffic sign categories:\n")
## Underrepresented traffic sign categories:
print(traffic_sign_frequency[1:5, ])
## Name n
## 1 Children crossing 1
## 2 Danger Ahead 1
## 3 Dangerous curve to the left 1
## 4 Dangerous curve to the right 1
## 5 Dont Go Left 1
# 5 How many traffic sign categories contain the word "Unknown"?
library(dplyr)
traffic_signs_data <- read.csv("C:/Users/Vivek singh/Downloads/labels.csv")
unknown_signs_count <- traffic_signs_data %>%
filter(grepl("Unknown", Name, ignore.case = TRUE)) %>%
nrow()
print(unknown_signs_count)
## [1] 7
# 6 How many traffic sign categories include the word "speed limit"?
library(dplyr)
traffic_signs_data <- read.csv("C:/Users/Vivek singh/Downloads/labels.csv")
speed_limit_signs_count <- traffic_signs_data %>%
filter(grepl("speed limit", Name, ignore.case = TRUE)) %>%
nrow()
print(speed_limit_signs_count)
## [1] 8
# 7 What is the distribution of traffic signs based on their positional instructions (e.g., left, right, straight)?
library(dplyr)
traffic_signs_data <- read.csv("C:/Users/Vivek singh/Downloads/labels.csv")
positional_instructions <- c("Left", "Right", "Straight")
positional_instruction_counts <- data.frame(Positional_Instruction = positional_instructions,
Count = rep(0, length(positional_instructions)))
for (instruction in positional_instructions) {
positional_instruction_counts$Count[instruction == "Left" | instruction == "Right" | instruction == "Straight"] <-
sum(grepl(instruction, traffic_signs_data$Name, ignore.case = TRUE))
}
print(positional_instruction_counts)
## Positional_Instruction Count
## 1 Left 6
## 2 Right 6
## 3 Straight 6
# 8 Are there any traffic sign categories indicating specific hazards or dangers?
library(dplyr)
traffic_signs_data <- read.csv("C:/Users/Vivek singh/Downloads/labels.csv")
hazard_keywords <- c("Danger", "Hazard", "Warning")
hazard_signs <- traffic_signs_data %>%
filter(grepl(paste(hazard_keywords, collapse = "|"), Name, ignore.case = TRUE))
print(unique(hazard_signs$Name))
## [1] "Danger Ahead" "Dangerous curve to the left"
## [3] "Dangerous curve to the right"
# 9 How many traffic sign categories are related to railway crossings?
library(dplyr)
traffic_signs_data <- read.csv("C:/Users/Vivek singh/Downloads/labels.csv")
railway_crossing_keywords <- c("Train Crossing", "Railway Crossing")
railway_crossing_signs <- traffic_signs_data %>%
filter(grepl(paste(railway_crossing_keywords, collapse = "|"), Name, ignore.case = TRUE))
num_railway_crossing_signs <- nrow(railway_crossing_signs)
print(num_railway_crossing_signs)
## [1] 1
# 10 Are there any traffic sign categories indicating temporary conditions or construction?
library(dplyr)
traffic_signs_data <- read.csv("C:/Users/Vivek singh/Downloads/labels.csv")
construction_keywords <- c("Under Construction", "Construction", "Temporary")
construction_signs <- traffic_signs_data %>%
filter(grepl(paste(construction_keywords, collapse = "|"), Name, ignore.case = TRUE))
print(unique(construction_signs$Name))
## [1] "Under Construction"
# 11 Are there any duplicate traffic sign categories in the dataset?
library(dplyr)
traffic_signs_data <- read.csv("C:/Users/Vivek singh/Downloads/labels.csv")
duplicate_signs <- traffic_signs_data %>%
group_by(Name) %>%
summarise(count = n()) %>%
filter(count > 1)
print(duplicate_signs)
## # A tibble: 1 × 2
## Name count
## <chr> <int>
## 1 Bicycles crossing 2
# 12 What is the proportion of traffic signs indicating mandatory actions?
library(dplyr)
traffic_signs_data <- read.csv("C:/Users/Vivek singh/Downloads/labels.csv")
mandatory_keywords <- c("mandatory", "must")
mandatory_signs_count <- traffic_signs_data %>%
filter(grepl(paste(mandatory_keywords, collapse = "|"), Name, ignore.case = TRUE)) %>%
nrow()
total_signs_count <- nrow(traffic_signs_data)
proportion_mandatory <- mandatory_signs_count / total_signs_count
print(proportion_mandatory)
## [1] 0.01923077
# 13 How many traffic sign categories contain the word "curve"?
library(dplyr)
traffic_signs_data <- read.csv("C:/Users/Vivek singh/Downloads/labels.csv")
curve_signs_count <- traffic_signs_data %>%
filter(grepl("curve", Name, ignore.case = TRUE)) %>%
nrow()
print(curve_signs_count)
## [1] 3
# 14 How many traffic sign categories are related to pedestrian crossings?
library(dplyr)
traffic_signs_data <- read.csv("C:/Users/Vivek singh/Downloads/labels.csv")
pedestrian_crossing_keywords <- c("pedestrian crossing", "crosswalk", "zebra crossing")
pedestrian_crossing_signs <- traffic_signs_data %>%
filter(grepl(paste(pedestrian_crossing_keywords, collapse = "|"), Name, ignore.case = TRUE))
num_pedestrian_crossing_signs <- nrow(unique(pedestrian_crossing_signs))
print(num_pedestrian_crossing_signs)
## [1] 1
# 15 How many traffic sign categories are related to parking regulations ?
library(dplyr)
traffic_signs_data <- read.csv("C:/Users/Vivek singh/Downloads/labels.csv")
parking_keywords <- c("parking", "no parking", "park", "no park")
parking_signs <- traffic_signs_data %>%
filter(grepl(paste(parking_keywords, collapse = "|"), Name, ignore.case = TRUE))
num_parking_signs <- nrow(unique(parking_signs))
print(num_parking_signs)
## [1] 0