Assignment 2

Assignment 2

1) Filtering Movies

library(tidyverse)
Warning: package 'tidyverse' was built under R version 4.3.2
Warning: package 'ggplot2' was built under R version 4.3.2
Warning: package 'tidyr' was built under R version 4.3.2
Warning: package 'readr' was built under R version 4.3.2
Warning: package 'purrr' was built under R version 4.3.2
Warning: package 'dplyr' was built under R version 4.3.2
Warning: package 'forcats' was built under R version 4.3.2
Warning: package 'lubridate' was built under R version 4.3.2
── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
✔ dplyr     1.1.4     ✔ readr     2.1.4
✔ forcats   1.0.0     ✔ stringr   1.5.0
✔ ggplot2   3.4.4     ✔ tibble    3.2.1
✔ lubridate 1.9.3     ✔ tidyr     1.3.0
✔ purrr     1.0.2     
── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
✖ dplyr::filter() masks stats::filter()
✖ dplyr::lag()    masks stats::lag()
ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
library(stringr)
library(rvest)
Warning: package 'rvest' was built under R version 4.3.2

Attaching package: 'rvest'

The following object is masked from 'package:readr':

    guess_encoding
library(ggplot2)
library(knitr)

url_vector_1 <- "https://m.imdb.com/search/title/?title_type=feature&release_date=2010-01-01,2023-12-31&num_votes=2500,&country_of_origin=TR&count=250"
url_vector_2 <- "https://m.imdb.com/search/title/?title_type=feature&release_date=,2009-12-31&num_votes=2500,&country_of_origin=TR&count=250"

2) Creating Data Frame

html_1 <- read_html(url_vector_1)
html_2 <- read_html(url_vector_2)
#title
title_names_1 <- html_1 |> html_nodes(".ipc-title__text")
title_names_1 <- html_text(title_names_1)
title_names_1 <- tail(head(title_names_1,-1),-1)
title_names_1 <- str_split(title_names_1, " ", n=2)
title_names_1 <- unlist(lapply(title_names_1, function(x) {x[2]}))

title_names_2 <- html_2 |> html_nodes(".ipc-title__text")
title_names_2 <- html_text(title_names_2)
title_names_2 <- tail(head(title_names_2,-1),-1)
title_names_2 <- str_split(title_names_2, " ", n=2)
title_names_2 <- unlist(lapply(title_names_2, function(x) {x[2]}))

title <- c(title_names_1, title_names_2)

#year
year_1 <- html_1 |> html_nodes(".sc-43986a27-8.jHYIIK.dli-title-metadata-item:nth-child(1)")
year_1 <- html_text(year_1)
year_1 <- as.numeric(year_1)

year_2 <- html_2 |> html_nodes(".sc-43986a27-8.jHYIIK.dli-title-metadata-item:nth-child(1)")
year_2 <- html_text(year_2)
year_2 <- as.numeric(year_2)

year <- c(year_1, year_2)

# vote
vote_1 <- html_1 |> html_nodes(".sc-53c98e73-0.kRnqtn")
vote_1 <- html_text(vote_1)
vote_1  <- as.numeric(gsub("\\D", "", vote_1 ))

vote_2 <- html_2 |> html_nodes(".kRnqtn")
vote_2 <- html_text(vote_2)
vote_2  <- as.numeric(gsub("\\D", "", vote_2 ))

vote <- c(vote_1, vote_2)

#ratings
rating_1 <- html_1 |> html_nodes(".ipc-rating-star.ipc-rating-star--base.ipc-rating-star--imdb.sc-9ab53865-1.iXEijC.ratingGroup--imdb-rating")
rating_1 <- html_text(rating_1)
rating_1  <- as.numeric(str_sub(rating_1, 1, 3))

rating_2 <- html_2 |> html_nodes(".ipc-rating-star.ipc-rating-star--base.ipc-rating-star--imdb.sc-9ab53865-1.iXEijC.ratingGroup--imdb-rating")
rating_2 <- html_text(rating_2)
rating_2  <- as.numeric(str_sub(rating_2, 1, 3))

rating <- c(rating_1, rating_2)

#duration (I got help from Chatgpt)
duration_1 <- html_1 |> html_nodes (".sc-43986a27-8.jHYIIK.dli-title-metadata-item:nth-child(2)")
duration_1 <- html_text(duration_1)

duration_2 <- html_2 |> html_nodes (".sc-43986a27-8.jHYIIK.dli-title-metadata-item:nth-child(2)")
duration_2 <- html_text(duration_2)

convert_time_to_minutes <- function(time_strings) {
  total_minutes <- numeric(length(time_strings))
  
  for (i in seq_along(time_strings)) {
    parts <- strsplit(time_strings[i], "h|m")[[1]]
    hours <- as.numeric(parts[1])
    minutes <- as.numeric(parts[2])
    
    total_minutes[i] <- hours * 60 + minutes
  }
  
  return(total_minutes)
}
total_minutes_result_1 <- convert_time_to_minutes(duration_1)
total_minutes_result_2 <- convert_time_to_minutes(duration_2)

duration <- c(total_minutes_result_1, total_minutes_result_2)

movies <- data.frame(title, year, duration, rating, vote)

3) Exploratory Data Analysis

a) Top and Bottom 5 Movies by Ranking

movies <- data.frame(title, year, duration, rating, vote)

movies <- arrange(movies, desc(rating))

top_5_movies <- head(movies, 5)

last_5_movies <- tail(movies, 5)

kable(rbind(top_5_movies, last_5_movies), caption = "Best and Worst 5 Movies")
Best and Worst 5 Movies
title year duration rating vote
1 Hababam Sinifi 1975 87 9.2 42515
2 CM101MMXI Fundamentals 2013 139 9.1 46998
3 Tosun Pasa 1976 90 8.9 24330
4 Hababam Sinifi Sinifta Kaldi 1975 95 8.9 24370
5 Süt Kardesler 1976 80 8.8 20890
466 Cumali Ceber 2 2018 100 1.2 10230
467 Müjde 2022 NA 1.2 9920
468 15/07 Safak Vakti 2021 95 1.2 20608
469 Cumali Ceber: Allah Seni Alsin 2017 100 1.0 39269
470 Reis 2017 108 1.0 73975

I watched the first 5 movies on the list. 4 of these are Yeşilçam films that have not lost their importance for years and are known to everyone, therefore they deserve the points they received, but at the same time, films that have a place in world cinema and can compete with these films should also be among these Yeşilçam films. In my opinion, there are other films that should be at least as high as the Yeşilçam films on this list.

I can’t comment because I haven’t watched the last 5 movies.

b) My Favorite Movies

fav_movies <- c("Ise Yarar Bir Sey", "Ölümlü Dünya 2", "Kurak Günler")

fav_movies_data <- movies[movies$title %in% fav_movies, ]

kable(rbind(fav_movies_data), caption = "My Favorite Movies")
My Favorite Movies
title year duration rating vote
80 Kurak Günler 2022 129 7.6 11179
85 Ise Yarar Bir Sey 2017 104 7.6 5512
94 Ölümlü Dünya 2 2023 117 7.5 3532

c) Visualization

by_year <- movies %>%
         group_by(year) %>%
         summarise(avg_rating = mean(rating))

ggplot(by_year, aes(x= year, y= avg_rating)) + geom_point()

As can be seen from the plot, average ratings decrease as the years increase.

ggplot(movies, aes(x = year, y = rating, group = year)) + geom_boxplot()

d) Do you believe there is a relationship between the number of votes a movie received and its rating? Investigate the correlation between Votes and Ratings.

cor(movies$vote, movies$rating)
[1] 0.1309764

e)Do you believe there is a relationship between a movie's duration and its rating? Investigate the correlation between Duration and Ratings.

cor(movies$duration, movies$rating)
[1] NA

4) Turkish Movies in the Top 1000 on IMDb

url_vector_3 <- "https://m.imdb.com/search/title/?title_type=feature&groups=top_1000&country_of_origin=TR&count=250"


html_3 <- read_html(url_vector_3)

#title
title_names_3 <- html_3 |> html_nodes(".ipc-title__text")
title_names_3 <- html_text(title_names_3)
title_names_3 <- tail(head(title_names_3,-1),-1)
title_names_3 <- str_split(title_names_3, " ", n=2)
title_names_3 <- unlist(lapply(title_names_3, function(x) {x[2]}))

title <- title_names_3

#year

year_3 <- html_3 |> html_nodes(".sc-43986a27-8.jHYIIK.dli-title-metadata-item:nth-child(1)")
year_3 <- html_text(year_3)
year_3 <- as.numeric(year_3)

year <- year_3

top1000_df <- data.frame(title, year)

kable(rbind(top1000_df), caption= "Turkish Movies in IMDB Top 1000")
Turkish Movies in IMDB Top 1000
title year
Yedinci Kogustaki Mucize 2019
Kis Uykusu 2014
Nefes: Vatan Sagolsun 2009
Ayla: The Daughter of War 2017
Babam ve Oglum 2005
Ahlat Agaci 2018
Bir Zamanlar Anadolu’da 2011
Eskiya 1996
G.O.R.A. 2004
Vizontele 2001
Her Sey Çok Güzel Olacak 1998 
final_df <- movies %>%
  inner_join(top1000_df, by = c("title", "year"))

kable(rbind(final_df), caption= "Turkish Movies in IMDB Top 1000")
Turkish Movies in IMDB Top 1000
title year duration rating vote
Ayla: The Daughter of War 2017 125 8.3 42997
Yedinci Kogustaki Mucize 2019 132 8.2 54182
Babam ve Oglum 2005 108 8.2 91046
Eskiya 1996 128 8.1 71704
Her Sey Çok Güzel Olacak 1998 107 8.1 27124
Kis Uykusu 2014 196 8.0 54654
Ahlat Agaci 2018 188 8.0 27022
Nefes: Vatan Sagolsun 2009 128 8.0 35026
G.O.R.A. 2004 127 8.0 66037
Vizontele 2001 110 8.0 38407
Bir Zamanlar Anadolu’da 2011 157 7.8 49374 
final_df <- arrange(final_df, desc(rating))
kable(rbind(final_df), caption= "Turkish Movies in IMDB Top 1000 by Ranked")
Turkish Movies in IMDB Top 1000 by Ranked
title year duration rating vote
Ayla: The Daughter of War 2017 125 8.3 42997
Yedinci Kogustaki Mucize 2019 132 8.2 54182
Babam ve Oglum 2005 108 8.2 91046
Eskiya 1996 128 8.1 71704
Her Sey Çok Güzel Olacak 1998 107 8.1 27124
Kis Uykusu 2014 196 8.0 54654
Ahlat Agaci 2018 188 8.0 27022
Nefes: Vatan Sagolsun 2009 128 8.0 35026
G.O.R.A. 2004 127 8.0 66037
Vizontele 2001 110 8.0 38407
Bir Zamanlar Anadolu’da 2011 157 7.8 49374

We see that this is not the same as the first dataframe. When I examined the first dataframe, only one of the first 11 movies was released after 2000. In this dataframe, only 2 dataframes were released before 2000. In other words, IMDb may consider the year parameter more than ratings in its rankings.

Back to top