# Load necessary libraries
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)
## Warning: package 'ggplot2' was built under R version 4.3.3
library(tidyr)
library(readxl)
# Read the Netflix dataset from Excel file
netflix2 <- read_excel("C:/Users/91904/Desktop/netflix2.xlsx")
# View the first few rows of the dataset
View(netflix2)
# Check for missing values in each column
missing_values_count <- colSums(is.na(netflix2))
missing_values_count
## show_id type title director country date_added
## 0 0 0 0 0 0
## release_year rating duration listed_in
## 0 0 0 0
#2What is the distribution of movies vs TV shows in dataset by bar graph?
netflix2 <- read_excel("C:/Users/91904/Desktop/netflix2.xlsx")
library(ggplot2)
ggplot(netflix2,aes(x = type))+
geom_bar(fill = c("blue","red")) +
labs(title="Distribution of Movies vs TV Shows" ,
xlab="Content Type",
ylab="Count")
#3In which year most movies and tv shows are releases?
netflix2 <- read_excel("C:/Users/91904/Desktop/netflix2.xlsx")
library(dplyr)
library(ggplot2)
movies_data = netflix2 %>% filter(type == "Movie")
tv_shows_data =netflix2 %>% filter(type == "TV Show")
movies_in_year = movies_data %>%
group_by(release_year) %>%
summarise(count = n()) %>%
arrange(desc(count)) %>%
head(1)
tv_shows_in_year= tv_shows_data %>%
group_by(release_year) %>%
summarise(count = n()) %>%
arrange(desc(count)) %>%
head(1)
cat("Most Tv shows releases in year : ",tv_shows_in_year $release_year,"\n",
"Most movies releases in year : ", movies_in_year$release_year)
## Most Tv shows releases in year : 2020
## Most movies releases in year : 2018
#4What are top 10 movies with highest rating?
netflix2 <- read_excel("C:/Users/91904/Desktop/netflix2.xlsx")
library(dplyr)
top_movies =netflix2 %>%
filter(type == "Movie") %>%
arrange(desc(movies_data)) %>%
select(title, rating) %>%
head(10)
top_movies
## # A tibble: 10 × 2
## title rating
## <chr> <chr>
## 1 "Searching For Sheela" TV-14
## 2 "HOMUNCULUS" TV-MA
## 3 "Vizontele" TV-MA
## 4 "This Lady Called Life" TV-14
## 5 "Perfume Imaginary Museum “Time Warpâ€\u009d" TV-G
## 6 "One Like It" TV-G
## 7 "Niyazi Gül Dörtnala" TV-MA
## 8 "My Travel Buddy" TV-MA
## 9 "Legal Hash" TV-MA
## 10 "Kocan Kadar Konus 2: Dirilis" TV-14
#5Top 10 countries have the most content on Netflix and show on bar graph?
netflix2 <- read_excel("C:/Users/91904/Desktop/netflix2.xlsx")
library(ggplot2)
country_count=netflix2 %>% group_by(country) %>%
summarise(Count = n())
Top10=head(country_count, 10)
ggplot(Top10, aes(x = country, y = Count)) +
geom_bar(stat = "identity", fill = "skyblue") +
labs(title = "Top 10 Countries with Most Content on Netflix",
x = "Country",
y = "Number of Titles")
#6Create a bar chart to visualize the distribution of content ratings?
netflix2 <- read_excel("C:/Users/91904/Desktop/netflix2.xlsx")
library(ggplot2)
rating_counts= netflix2 %>%
group_by(rating) %>%
summarise(count = n()) %>%
arrange(desc(count))
ggplot(rating_counts, aes(x= rating, y = count)) +
geom_bar(stat = "identity", fill = "skyblue") +
labs(title = "Distribution of content ratings on Netflix",
x = "Content rating",
y = "Number of titles")
#7visualize releases TV Shows over the years.
netflix2 <- read_excel("C:/Users/91904/Desktop/netflix2.xlsx")
tv_shows_data =netflix2 %>% filter(type == "TV Shows")
ggplot(tv_shows_data, aes(x= release_year)) +
geom_histogram(binwidth = 3, fill = "blue", color = "black") +
labs(title = "Release year of TV Shows on netflix" ,
x = "Release year",
y = "Count")
#8visualize releases movies over the years.
netflix2 <- read_excel("C:/Users/91904/Desktop/netflix2.xlsx")
movies_data =netflix2 %>% filter(type == "Movie")
ggplot(movies_data, aes(x = release_year)) +
geom_histogram(binwidth = 2, fill = "blue", color = "black") +
labs(title = "Histogram of movie release year on netflix",
x = "Release year",
y = "Number of movies")
#9 visualize top 10 director with most released movies and TV shows?
netflix2 <- read_excel("C:/Users/91904/Desktop/netflix2.xlsx")
top_director= netflix2 %>%
group_by(director) %>%
summarise(count = n()) %>%
arrange(desc(count)) %>% slice(-1) %>%
head(10)
ggplot(top_director, aes(x =director, y = count)) +
geom_bar(stat = "identity", fill = c("red","blue","pink","skyblue","yellow",
"purple","green","grey","orange","black")) +
labs(title = "Top 10 directors with most content on Netflix",
x = "Director",
y = "Number of titles")
#10What number of movies and tv shows watch by Children & Family Movies, Comedies?
netflix2 <- read_excel("C:/Users/91904/Desktop/netflix2.xlsx")
Seen_by= netflix2 %>% filter(listed_in=="Children & Family Movies, Comedies")
total_no. = Seen_by %>%
group_by(listed_in) %>%
summarise(count=n())
total_no.
## # A tibble: 1 × 2
## listed_in count
## <chr> <int>
## 1 Children & Family Movies, Comedies 201
#11On which date most movies and Tv shows are released?
netflix2 <- read_excel("C:/Users/91904/Desktop/netflix2.xlsx")
release_date_year =netflix2 %>%
group_by(date_added) %>%
summarise(Count = n()) %>%
arrange(desc(Count)) %>%
head(1)
release_date_year
## # A tibble: 1 × 2
## date_added Count
## <chr> <int>
## 1 43831 110
#12is there correlation between type and rating??
netflix2 <- read_excel("C:/Users/91904/Desktop/netflix2.xlsx")
str(netflix2)
## tibble [8,790 × 10] (S3: tbl_df/tbl/data.frame)
## $ show_id : chr [1:8790] "s1" "s3" "s6" "s14" ...
## $ type : chr [1:8790] "Movie" "TV Show" "TV Show" "Movie" ...
## $ title : chr [1:8790] "Dick Johnson Is Dead" "Ganglands" "Midnight Mass" "Confessions of an Invisible Girl" ...
## $ director : chr [1:8790] "Kirsten Johnson" "Julien Leclercq" "Mike Flanagan" "Bruno Garotti" ...
## $ country : chr [1:8790] "United States" "France" "United States" "Brazil" ...
## $ date_added : chr [1:8790] "9/25/2021" "9/24/2021" "9/24/2021" "9/22/2021" ...
## $ release_year: num [1:8790] 2020 2021 2021 2021 1993 ...
## $ rating : chr [1:8790] "PG-13" "TV-MA" "TV-MA" "TV-PG" ...
## $ duration : chr [1:8790] "90 min" "1 Season" "1 Season" "91 min" ...
## $ listed_in : chr [1:8790] "Documentaries" "Crime TV Shows, International TV Shows, TV Action & Adventure" "TV Dramas, TV Horror, TV Mysteries" "Children & Family Movies, Comedies" ...
#13 What number of movies are of Comedies?
netflix2 <- read_excel("C:/Users/91904/Desktop/netflix2.xlsx")
movies_data_1=netflix2 %>% filter(type == "Movie")
A= movies_data_1%>% filter(listed_in=="Comedies")
movie_number = A %>%
group_by(listed_in) %>%
summarise(count=n())
movie_number
## # A tibble: 1 × 2
## listed_in count
## <chr> <int>
## 1 Comedies 110
#14 Visualize the borplot between type and release_year?
netflix2 <- read_excel("C:/Users/91904/Desktop/netflix2.xlsx")
ggplot(netflix2, aes(x = type, y = release_year, color = type)) +
geom_boxplot()+
labs(x = "Type", y = "Release Year")
