Import your data

Summer_Movies <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/refs/heads/master/data/2024/2024-07-30/summer_movies.csv')
## Rows: 905 Columns: 10
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (6): tconst, title_type, primary_title, original_title, genres, simple_t...
## dbl (4): year, runtime_minutes, average_rating, num_votes
## 
## 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.

Chapter 14

Tools

Detect matches

Summer_Movies$year
##   [1] 1920 1935 1941 1944 1946 1946 1947 1948 1949 1951 1950 1951 1951 1951 1953
##  [16] 1954 1955 1955 1955 1955 1956 1957 1956 1957 1957 1958 1958 1958 1958 1959
##  [31] 1959 1959 1959 1959 1959 1960 1961 1961 1961 1961 1962 1964 1963 1963 1964
##  [46] 1965 1965 1966 1966 1967 1967 1967 1963 1967 1968 1968 1968 1968 1968 1968
##  [61] 1969 1971 1969 1970 1971 1970 1971 1971 1971 1971 1972 1972 1972 1972 1972
##  [76] 1972 1973 1973 1973 1973 1972 1974 1974 1981 1976 1975 1976 1976 1976 1976
##  [91] 1977 1978 1971 1977 1977 1978 1978 1978 1978 1978 1978 1979 1979 1979 1978
## [106] 1981 1980 1982 1981 1980 1981 1982 1982 1982 1982 1982 1982 1982 1984 1983
## [121] 1983 1983 1983 1984 1984 1984 1984 1983 1979 1984 1985 1985 1985 1986 1987
## [136] 1986 1986 1987 1986 1986 1986 1987 1987 1987 1988 1988 1988 1988 1988 1988
## [151] 1988 1988 1988 1988 1988 1989 1990 1989 1989 1989 1989 1990 1990 1990 1990
## [166] 1991 1991 1991 1991 1992 1992 1993 1992 1992 1993 1993 1993 1993 1994 1994
## [181] 1994 1994 1994 1994 1995 1995 1996 1996 1996 1997 1996 1996 1996 1996 1996
## [196] 1996 1997 1997 1973 1996 1976 1985 1998 1998 1997 1970 1997 1928 1955 1963
## [211] 1989 1999 1997 1998 1998 1998 1975 1996 1999 1988 1999 1985 2003 1970 1969
## [226] 1970 1981 1980 1969 1968 1978 1961 1997 1999 1999 1998 1999 2001 1982 2000
## [241] 1993 2000 1977 1999 2001 2000 2000 1997 2000 1944 1981 1968 2001 1990 1965
## [256] 1999 2001 1967 1971 2001 1981 2000 2000 1985 1971 1992 1970 1970 2001 1998
## [271] 1990 1999 1969 1974 1977 2001 2000 1993 2002 1979 2001 2002 2002 2001 2001
## [286] 2001 1997 2001 2001 2002 2004 1988 1994 1987 2000 2002 2002 2002 1997 2002
## [301] 1980 2001 1954 2004 2003 2004 2003 2003 2003 2003 1984 1960 1995 2001 1999
## [316] 2002 2000 2000 1961 2003 2004 1979 2002 2004 2003 2003 2005 1998 2003 2004
## [331] 1997 1988 2003 2003 2004 2004 2004 2004 2004 1999 1994 2003 2005 2000 1968
## [346] 2004 1972 2002 2004 2005 1999 2006 2002 2005 2007 2006 1989 1981 2006 2007
## [361] 2007 2006 2005 2005 2006 2006 2004 2007 2005 2006 2006 2006 2005 2008 2006
## [376] 2006 2006 2005 2006 2008 2006 2007 2006 2001 2007 2008 2001 2008 2007 2007
## [391] 2010 2007 2006 1999 2008 2006 2007 1989 2008 2006 2008 2003 2002 2006 1994
## [406] 2008 2006 2019 2019 2019 2009 2006 2020 2019 2019 2008 2017 2020 2019 2019
## [421] 2020 2019 1983 2017 2021 2020 2019 2019 2019 2020 1977 2019 2007 2021 2020
## [436] 1992 2020 2019 2019 2007 2008 2007 2020 2020 2021 2007 2007 2008 2006 2008
## [451] 2017 2008 2021 2009 2007 2008 2008 2008 2020 2008 1989 2023 2008 2009 2009
## [466] 2009 2008 2014 2016 2020 2021 2008 1992 2007 2023 2010 2008 2021 2009 2018
## [481] 2020 2020 2009 2007 2007 2009 2021 2009 2020 2008 2020 2009 2009 2020 2010
## [496] 2008 1996 2007 2020 2008 2016 2008 2009 2019 2020 2022 2005 2010 2010 2018
## [511] 2020 2021 2009 2007 2021 2023 2009 2022 2010 2008 2009 2021 2022 2006 2023
## [526] 2022 2020 2021 2009 2021 2010 2021 2020 2021 2023 2010 2021 2022 2021 2023
## [541] 2006 2010 2008 2010 2011 2008 2023 2022 2010 2009 2022 2011 2011 2010 2013
## [556] 2008 2011 2010 2010 1981 2022 2023 1974 2022 2011 2013 2022 2023 2010 2024
## [571] 2010 2010 2010 2010 2022 2022 2011 2011 2011 2022 2009 2011 2011 2012 2022
## [586] 2010 2011 2009 2022 2009 2009 2023 2009 2011 2011 2008 2012 2013 2011 2015
## [601] 2012 2023 2022 2022 2013 2011 2012 2008 1985 2022 2022 2012 2015 2011 2022
## [616] 2021 2013 1959 2011 2011 2022 2022 2022 2024 2023 2022 2022 2022 2023 2022
## [631] 2011 2012 2011 2013 2023 2015 2013 2022 2012 2022 2017 2024 2023 2012 1968
## [646] 2013 2020 1987 2011 2012 1992 2012 2013 2012 2012 2012 2011 2012 2013 2012
## [661] 2022 1993 2013 2017 2023 2012 2023 2023 2015 2012 2014 1967 2012 2014 2013
## [676] 2013 2024 2024 2013 1956 2013 2013 2023 2015 2023 2023 2014 2024 2013 2023
## [691] 2013 2023 2023 2023 2023 2013 2023 2023 2023 2023 2024 2010 2010 2013 2024
## [706] 2013 2015 2014 2015 2013 2013 2014 2013 2013 2015 2014 2014 2013 2016 2024
## [721] 2014 2024 2013 2013 2015 2014 2009 2024 2024 2024 2013 2024 2014 2013 2018
## [736] 2017 2014 2014 2014 1969 2015 2015 2014 2014 2014 2014 2014 2014 2014 2014
## [751] 2011 2015 2017 2014 1992 2014 2015 2014 2015 2008 2016 2016 2014 2006 2023
## [766] 2015 2015 2006 2015 2015 2014 2015 2016 2012 2015 2016 2015 2020 2015 2016
## [781] 2018 2015 2015 2015 2016 2015 2016 2015 2016 1999 2015 2016 2018 2015 2015
## [796] 2014 2011 2016 2016 2017 2012 2017 2017 2017 2019 2016 2019 2016 2017 2016
## [811] 2018 2009 2016 2016 2016 2018 2017 2017 2016 2016 2017 2016 2017 2017 2016
## [826] 2016 2017 2016 2016 2015 2017 2017 2016 2015 1985 2017 2018 2021 2017 1973
## [841] 2017 2018 2020 2019 2017 2022 2017 2017 2018 2017 2017 2017 2017 2000 2017
## [856] 2018 1998 2018 1992 2019 2017 2018 2019 2019 1996 2017 2020 2020 2018 2018
## [871] 2018 2019 2018 2019 2021 2018 2018 2018 2017 2018 2018 2020 2018 2018 2018
## [886] 2018 2018 2008 2018 2018 2019   NA 2020 2018 2018 2019 2019 2019 2022 2023
## [901] 2019 2017 2019 2020 2018
str_detect(Summer_Movies$year, "1958")
##   [1] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
##  [13] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
##  [25] FALSE  TRUE  TRUE  TRUE  TRUE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
##  [37] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
##  [49] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
##  [61] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
##  [73] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
##  [85] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
##  [97] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [109] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [121] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [133] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [145] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [157] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [169] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [181] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [193] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [205] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [217] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [229] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [241] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [253] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [265] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [277] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [289] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [301] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [313] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [325] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [337] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [349] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [361] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [373] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [385] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [397] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [409] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [421] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [433] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [445] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [457] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [469] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [481] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [493] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [505] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [517] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [529] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [541] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [553] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [565] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [577] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [589] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [601] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [613] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [625] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [637] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [649] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [661] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [673] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [685] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [697] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [709] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [721] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [733] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [745] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [757] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [769] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [781] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [793] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [805] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [817] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [829] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [841] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [853] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [865] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [877] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [889] FALSE FALSE FALSE    NA FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [901] FALSE FALSE FALSE FALSE FALSE
sum(str_detect(Summer_Movies$year, "1958"))
## [1] NA
Summer_Movies %>%
    summarise(num_1958 = sum(str_detect(year, "1958"), na.rm = TRUE))
## # A tibble: 1 × 1
##   num_1958
##      <int>
## 1        4

Extract matches

Summer_Movies %>%
    mutate(col_Drama = str_extract(genres, "Drama")) %>%
    select(genres, col_Drama) %>%
    filter(!is.na(col_Drama))
## # A tibble: 489 × 2
##    genres                col_Drama
##    <chr>                 <chr>    
##  1 Drama                 Drama    
##  2 Crime,Drama,Film-Noir Drama    
##  3 Drama,Fantasy         Drama    
##  4 Comedy,Drama,Musical  Drama    
##  5 Comedy,Drama,Romance  Drama    
##  6 Drama,Romance         Drama    
##  7 Drama,Romance         Drama    
##  8 Drama,Romance         Drama    
##  9 Action,Drama,Romance  Drama    
## 10 Comedy,Drama          Drama    
## # ℹ 479 more rows

Replacing matches

Summer_Movies %>%
    mutate(col_Drama = str_replace(genres, "Drama", "Romance")) %>%
    select(genres, col_Drama)
## # A tibble: 905 × 2
##    genres                 col_Drama              
##    <chr>                  <chr>                  
##  1 Drama                  Romance                
##  2 Comedy,Fantasy,Romance Comedy,Fantasy,Romance 
##  3 Comedy                 Comedy                 
##  4 Crime,Drama,Film-Noir  Crime,Romance,Film-Noir
##  5 History,Music,Romance  History,Music,Romance  
##  6 Drama,Fantasy          Romance,Fantasy        
##  7 Comedy                 Comedy                 
##  8 Musical                Musical                
##  9 Comedy,Musical,Romance Comedy,Musical,Romance 
## 10 Comedy,Drama,Musical   Comedy,Romance,Musical 
## # ℹ 895 more rows