Netflix Data Analysis
Tarek Atassi
2022-04-26
- Netflix Movies Data
- Loading the libraries
- Loading the dataset
- looking at the data in brief
- types of datatype in each column
- Does the data contain any N/A values?
- Converting the “Premiere” from character to datetime
- Getting each year, month, and date separated, also adding the
- corresponding day of the week for each release.
- Whem the movies were
released?
- Number of Movies released each year
- Number of Movies released each month
- Number of movies released by date of the month
- Number of movies releaes each day of the week
- 5 Most popular Genres
- 5 Most Popular Languages
- IMDB Scores - How were most movies rated?
- Highest Rated Movies
- Lowest Rated Movies
- Runtime - How long are the movies?
- Longest Movies
- Shortest Movies
- Runtime vs IMDB-Score
- Basic Statistical Analysis
- Thank You
Netflix Movies Data
Loading the libraries
install.packages("pacman")## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-library/4.1'
## (as 'lib' is unspecified)library(pacman)
p_load(tidyverse,lubridate,showtext)
showtext_auto()
font_add_google("Bebas Neue", "Bebas Neue")Loading the dataset
netflix <- read_csv('NetflixOriginals.csv')## Rows: 584 Columns: 6
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (4): Title, Genre, Premiere, Language
## dbl (2): Runtime, IMDB Score
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.looking at the data in brief
head(netflix)## # A tibble: 6 × 6
## Title Genre Premiere Runtime `IMDB Score` Language
## <chr> <chr> <chr> <dbl> <dbl> <chr>
## 1 Enter the Anime Documentary August 5,… 58 2.5 English…
## 2 Dark Forces Thriller August 21… 81 2.6 Spanish
## 3 The App Science fiction/Drama December … 79 2.6 Italian
## 4 The Open House Horror thriller January 1… 94 3.2 English
## 5 Kaali Khuhi Mystery October 3… 90 3.4 Hindi
## 6 Drive Action November … 147 3.5 Hinditypes of datatype in each column
as_tibble(sapply(netflix, class))## # A tibble: 6 × 1
## value
## <chr>
## 1 character
## 2 character
## 3 character
## 4 numeric
## 5 numeric
## 6 characterDoes the data contain any N/A values?
any(is.na(netflix))## [1] FALSEConverting the “Premiere” from character to datetime
netflix <- netflix %>% mutate(Released = mdy(Premiere))Getting each year, month, and date separated, also adding the
corresponding day of the week for each release.
netflix <- netflix %>%
mutate(Year = year(Released)) %>%
mutate(Month = month(Released, label=TRUE)) %>%
mutate(Date = day(Released)) %>%
mutate(Day = wday(Released, label=TRUE, abbr=FALSE))Whem the movies were released?
Number of Movies released each year
n <- netflix %>% group_by(Year) %>% summarise(total=n())
n_graph <- ggplot(data=n)+
geom_col(mapping=aes(
x=Year,
y=total,
fill=ifelse(total==max(total),"red","grey"))
)+
labs(title="Netflix Movies released each year")+
theme_minimal()+
scale_fill_manual(values=c("#2d2d2d","#E50914"))+
theme(
legend.position="none",
plot.title=element_text(
family="Bebas Neue",
size=25,
color="#E50914"),
axis.title.x = element_blank(),
axis.title.y = element_blank(),
panel.grid.major.x = element_blank(),
panel.grid.minor = element_blank()
)
n_graph
Number of Movies released each month
n1 <- netflix %>% group_by(Month) %>% summarise(total=n())
n1_graph <- ggplot(data=n1)+
geom_col(mapping = aes(
x=Month,
y=total,
fill=ifelse(total==max(total),"red","grey")))+
labs(title='Netflix Movies Released Each Month')+
theme_minimal()+
scale_fill_manual(values=c("#2d2d2d","#E50914"))+
theme(
legend.position='none',
plot.title = element_text(
family="Bebas Neue",
size=25,
color="#E50914"),
axis.title.x=element_blank(),
axis.title.y=element_blank(),
panel.grid.major.x = element_blank(),
panel.grid.minor = element_blank(),
text = element_text(size=20))
n1_graph
Number of movies released by date of the month
n2 <- netflix %>% group_by(Date) %>% summarise(total=n())
n2_graph <- ggplot(data=n2)+
geom_col(mapping=aes(x=Date, y=total,
fill=ifelse(total==max(total),"red","grey")))+
labs(
title="Netflix Movies released by date of each month")+
theme_minimal()+
scale_fill_manual(values = c("#2d2d2d","#E50914"))+
theme(
legend.position="none",
plot.title=element_text(
family="Bebas Neue",
size=25,
color="#E50914"
),
axis.title.x=element_blank(),
axis.title.y=element_blank(),
panel.grid.major.x=element_blank(),
panel.grid.minor = element_blank(),
text=element_text(size=20)
)
n2_graph
Number of movies releaes each day of the week
n3 <- netflix %>% group_by(Day) %>% summarise(total=n())
n3_graph <-
ggplot(data=n3)+
geom_col(mapping=aes(
x=Day,
y=total,
fill=ifelse(total==max(total),"red","black")))+
labs(title="Netflix Movies released by day of the week")+
theme_minimal()+
scale_fill_manual(values=c("#2d2d2d","#E50914"))+
theme(
legend.position="none",
plot.title = element_text(
family="Bebas Neue",
size=25,
color="#E50914"),
axis.title.x=element_blank(),
axis.title.y=element_blank(),
panel.grid.major.x=element_blank(),
panel.grid.minor=element_blank(),
text=element_text(size=20)
)
n3_graph
5 Most popular Genres
n4 <- netflix %>% group_by(Genre) %>%
summarise(Movies=n()) %>%
arrange(desc(Movies)) %>%
head(5)
n4_graph <-
ggplot(data=n4)+
geom_col(mapping = aes(
x=reorder(Genre, -Movies),
y=Movies,
fill=ifelse(Movies == max(Movies),"red","black")))+
labs(title="Most Popular Genres")+
theme_minimal()+
scale_fill_manual(values = c("#2d2d2d","#E50914"))+
theme(
legend.position="none",
plot.title = element_text(
family="Bebas Neue",
size=25,
color="#E50914"),
axis.title.x=element_blank(),
axis.title.y=element_blank(),
panel.grid.major.x=element_blank(),
panel.grid.minor = element_blank(),
text = element_text(size=20)
)
n4_graph
5 Most Popular Languages
n5 <- netflix %>%
group_by(Language) %>%
summarise(Movies=n()) %>%
arrange(desc(Movies)) %>%
head(5)
n5_graph <-
ggplot(data=n5)+
geom_col(mapping=aes(
x=reorder(Language, -Movies),
y=Movies,
fill=ifelse(Movies == max(Movies),"red","black")))+
labs(title="Most Popular Languages")+
theme_minimal()+
scale_fill_manual(values=c("#2d2d2d","#E50914"))+
theme(
legend.position="none",
plot.title = element_text(
family="Bebas Neue",
size=25,
color="#E50914"),
axis.title.x=element_blank(),
axis.title.y=element_blank(),
panel.grid.major.x=element_blank(),
panel.grid.minor = element_blank(),
title=element_text(size=20)
)
n5_graph
IMDB Scores - How were most movies rated?
n6_graph <- ggplot(netflix)+
geom_dotplot(mapping=aes(x=`IMDB Score`),
binwidth=0.3,fill="#2d2d2d",color="#e9ecef")+
labs(title="IMDB Score Distribution")+
theme_minimal()+
theme(
legend.position="none",
plot.title=element_text(
family="Bebas Neue",
size=25,
color="#E50914"),
axis.title.x=element_blank(),
axis.title.y=element_blank(),
panel.grid.major.x=element_blank()
)
n6_graph
Highest Rated Movies
n7 <- netflix %>% arrange(desc(`IMDB Score`)) %>% head(5)
n7_graph <- ggplot(data=n7)+
geom_col(mapping=aes(
x=reorder(`Title`,`IMDB Score`),
y=`IMDB Score`,
fill=ifelse(
`IMDB Score`==max(`IMDB Score`),
"red","black")))+
labs(title="Highest Rated Movies")+
theme_minimal()+
scale_fill_manual(values = c("#2d2d2d","#E50914"))+
coord_flip()+
theme(
legend.position="none",
plot.title = element_text(
family="Bebas Neue",
size=25,
color="#E50914"),
axis.title.x=element_blank(),
axis.title.y=element_blank(),
panel.grid.major.x=element_blank()
)
n7_graph
Lowest Rated Movies
n8 <- netflix %>% arrange(desc(-`IMDB Score`)) %>% head(5)
n8_graph <- ggplot(data=n8)+
geom_col(mapping=aes(
x=reorder(`Title`, -`IMDB Score`),
y=`IMDB Score`,
fill=ifelse(
`IMDB Score`==min(`IMDB Score`),
"red","black")))+
labs(title="Lowest Rated Movies")+
theme_minimal()+
scale_fill_manual(values = c("#2d2d2d","#E50914"))+
coord_flip()+
theme(
legend.position="none",
plot.title = element_text(
family="Bebas Neue",
size=25,
color="#E50914"),
axis.title.x=element_blank(),
axis.title.y=element_blank(),
panel.grid.major.x=element_blank()
)
n8_graph
Runtime - How long are the movies?
n9_graph <- ggplot(data=netflix)+
geom_dotplot(
mapping=aes(x=Runtime),
binwidth=2.25,
fill="#2d2d2d",
color="#e9ecef")+
labs(title="Movie Runtime")+
theme_minimal()+
theme(
legend.position="none",
plot.title=element_text(
family="Bebas Neue",
size=25,
color="#E50914"),
axis.title.x = element_blank(),
axis.title.y=element_blank(),
panel.grid.major.x=element_blank()
)
n9_graph
Longest Movies
n10 <- netflix %>% arrange(desc(Runtime)) %>% head(5)
n10_graph <- ggplot(data=n10)+
geom_col(mapping=aes(
x=reorder(`Title`,`Runtime`),
y=`Runtime`,
fill=ifelse(Runtime==max(`Runtime`),"red","black")))+
labs(title="Longest Movies")+
theme_minimal()+
scale_fill_manual(values=c("#2d2d2d","#E50914"))+
coord_flip()+
theme(
legend.position="none",
plot.title = element_text(
family="Bebas Neue",
size=25,
color="#E50914"),
axis.title.x=element_blank(),
axis.title.y=element_blank(),
panel.grid.major.x=element_blank()
)
n10_graph
Shortest Movies
n11 <- netflix %>% arrange(desc(-Runtime)) %>% head(5)
n11_graph <- ggplot(data=n11)+
geom_col(mapping=aes(
x = reorder(`Title`,`Runtime`),
y = `Runtime`,
fill = ifelse(Runtime==min(`Runtime`),"red","black")))+
labs(title="Shortest Movies")+
theme_minimal()+
scale_fill_manual(values = c("#2d2d2d","#E50914"))+
coord_flip()+
theme(
legend.position="none",
plot.title = element_text(
family="Bebas Neue",
size=25,
color="#E50914"),
axis.title.x=element_blank(),
axis.title.y=element_blank(),
panel.grid.major.x=element_blank(),
text=element_text(size=20)
)
n11_graph
Runtime vs IMDB-Score
n12_graph <- ggplot(data=netflix,aes(x = `IMDB Score`, y = Runtime))+
geom_point()+
geom_smooth(method = "lm", color="#E50914")+
labs(title="Runtime vs IMDB Rating")+
theme_minimal()+
scale_fill_manual(values=c("#2d2d2d","#E50914"))+
theme(
legend.position = "none",
plot.title=element_text(
family="Bebas Neue",
size=25,
color="#E50914"),
axis.title.x=element_blank(),
axis.title.y=element_blank(),
panel.grid.major.x=element_blank()
)
n12_graph## `geom_smooth()` using formula 'y ~ x'
Basic Statistical Analysis
Linear Models
model <- lm(data=netflix, formula = Runtime ~ `IMDB Score`)
summary(model)##
## Call:
## lm(formula = Runtime ~ `IMDB Score`, data = netflix)
##
## Residuals:
## Min 1Q Median 3Q Max
## -91.399 -7.439 3.398 14.467 117.195
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 100.849 7.453 13.531 <2e-16 ***
## `IMDB Score` -1.159 1.174 -0.987 0.324
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 27.76 on 582 degrees of freedom
## Multiple R-squared: 0.001673, Adjusted R-squared: -4.283e-05
## F-statistic: 0.975 on 1 and 582 DF, p-value: 0.3238Correlation Test
res <- cor.test(netflix$Runtime, netflix$`IMDB Score`,method="pearson")
res##
## Pearson's product-moment correlation
##
## data: netflix$Runtime and netflix$`IMDB Score`
## t = -0.98744, df = 582, p-value = 0.3238
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.12162699 0.04037194
## sample estimates:
## cor
## -0.04089629P-Value
res$p.value## [1] 0.3238393Correlation Coefficient
res$estimate## cor
## -0.04089629