Module 10: Code Along 9

R for Data Science: Chapter 14

knitr::opts_chunk$set(echo = TRUE)

# Load package]
library(tidyverse)

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.3     ✔ readr     2.1.4
## ✔ forcats   1.0.0     ✔ stringr   1.5.0
## ✔ ggplot2   3.4.3     ✔ tibble    3.2.1
## ✔ lubridate 1.9.2     ✔ 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(readxl) # for importing excel files
library(janitor) # cleaning data

## 
## Attaching package: 'janitor'
## 
## The following objects are masked from 'package:stats':
## 
##     chisq.test, fisher.test

library(nycflights13)

Introduction

String basics

chac_data <- "I'm 'very' hungry."

stringr::str_length("I am hungry.")

## [1] 12

stringr::str_c(c("I", " am"), collapse = " ")

## [1] "I  am"

stringr::str_c("I", " am", sep = ";")

## [1] "I; am"

str_sort(c("John", "Mary", "Aaron"))

## [1] "Aaron" "John"  "Mary"

Matching patterns with regular expressions

flights %>% glimpse()

## Rows: 336,776
## Columns: 19
## $ year           <int> 2013, 2013, 2013, 2013, 2013, 2013, 2013, 2013, 2013, 2…
## $ month          <int> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1…
## $ day            <int> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1…
## $ dep_time       <int> 517, 533, 542, 544, 554, 554, 555, 557, 557, 558, 558, …
## $ sched_dep_time <int> 515, 529, 540, 545, 600, 558, 600, 600, 600, 600, 600, …
## $ dep_delay      <dbl> 2, 4, 2, -1, -6, -4, -5, -3, -3, -2, -2, -2, -2, -2, -1…
## $ arr_time       <int> 830, 850, 923, 1004, 812, 740, 913, 709, 838, 753, 849,…
## $ sched_arr_time <int> 819, 830, 850, 1022, 837, 728, 854, 723, 846, 745, 851,…
## $ arr_delay      <dbl> 11, 20, 33, -18, -25, 12, 19, -14, -8, 8, -2, -3, 7, -1…
## $ carrier        <chr> "UA", "UA", "AA", "B6", "DL", "UA", "B6", "EV", "B6", "…
## $ flight         <int> 1545, 1714, 1141, 725, 461, 1696, 507, 5708, 79, 301, 4…
## $ tailnum        <chr> "N14228", "N24211", "N619AA", "N804JB", "N668DN", "N394…
## $ origin         <chr> "EWR", "LGA", "JFK", "JFK", "LGA", "EWR", "EWR", "LGA",…
## $ dest           <chr> "IAH", "IAH", "MIA", "BQN", "ATL", "ORD", "FLL", "IAD",…
## $ air_time       <dbl> 227, 227, 160, 183, 116, 150, 158, 53, 140, 138, 149, 1…
## $ distance       <dbl> 1400, 1416, 1089, 1576, 762, 719, 1065, 229, 944, 733, …
## $ hour           <dbl> 5, 5, 5, 5, 6, 5, 6, 6, 6, 6, 6, 6, 6, 6, 6, 5, 6, 6, 6…
## $ minute         <dbl> 15, 29, 40, 45, 0, 58, 0, 0, 0, 0, 0, 0, 0, 0, 0, 59, 0…
## $ time_hour      <dttm> 2013-01-01 05:00:00, 2013-01-01 05:00:00, 2013-01-01 0…

flights_small <- flights %>% select(where(is.character)) %>% head(n = 10)

Basic matches

flights_small %>% filter(str_detect(dest, "M"))

## # A tibble: 2 × 4
##   carrier tailnum origin dest 
##   <chr>   <chr>   <chr>  <chr>
## 1 AA      N619AA  JFK    MIA  
## 2 B6      N593JB  JFK    MCO

flights_small %>% filter(str_detect(dest, ".M"))

## # A tibble: 0 × 4
## # ℹ 4 variables: carrier <chr>, tailnum <chr>, origin <chr>, dest <chr>

flights_small %>% filter(str_detect(dest, "M."))

## # A tibble: 2 × 4
##   carrier tailnum origin dest 
##   <chr>   <chr>   <chr>  <chr>
## 1 AA      N619AA  JFK    MIA  
## 2 B6      N593JB  JFK    MCO

flights_small %>% filter(str_detect(dest, "M\\."))

## # A tibble: 0 × 4
## # ℹ 4 variables: carrier <chr>, tailnum <chr>, origin <chr>, dest <chr>

Anchors

flights_small %>% filter(str_detect(origin, "E$"))

## # A tibble: 0 × 4
## # ℹ 4 variables: carrier <chr>, tailnum <chr>, origin <chr>, dest <chr>

Character classes and alternatives

flights_small %>% filter(str_detect(carrier, "\\d"))

## # A tibble: 3 × 4
##   carrier tailnum origin dest 
##   <chr>   <chr>   <chr>  <chr>
## 1 B6      N804JB  JFK    BQN  
## 2 B6      N516JB  EWR    FLL  
## 3 B6      N593JB  JFK    MCO

flights_small %>% filter(str_detect(carrier, "\\s"))

## # A tibble: 0 × 4
## # ℹ 4 variables: carrier <chr>, tailnum <chr>, origin <chr>, dest <chr>

flights_small %>% filter(str_detect(carrier, "[ABD]"))

## # A tibble: 9 × 4
##   carrier tailnum origin dest 
##   <chr>   <chr>   <chr>  <chr>
## 1 UA      N14228  EWR    IAH  
## 2 UA      N24211  LGA    IAH  
## 3 AA      N619AA  JFK    MIA  
## 4 B6      N804JB  JFK    BQN  
## 5 DL      N668DN  LGA    ATL  
## 6 UA      N39463  EWR    ORD  
## 7 B6      N516JB  EWR    FLL  
## 8 B6      N593JB  JFK    MCO  
## 9 AA      N3ALAA  LGA    ORD

flights_small %>% filter(str_detect(carrier, "[^ABD]"))

## # A tibble: 8 × 4
##   carrier tailnum origin dest 
##   <chr>   <chr>   <chr>  <chr>
## 1 UA      N14228  EWR    IAH  
## 2 UA      N24211  LGA    IAH  
## 3 B6      N804JB  JFK    BQN  
## 4 DL      N668DN  LGA    ATL  
## 5 UA      N39463  EWR    ORD  
## 6 B6      N516JB  EWR    FLL  
## 7 EV      N829AS  LGA    IAD  
## 8 B6      N593JB  JFK    MCO

Repitition

# ? 0 or 1
flights %>% filter(str_detect(carrier, "A?"))

## # A tibble: 336,776 × 19
##     year month   day dep_time sched_dep_time dep_delay arr_time sched_arr_time
##    <int> <int> <int>    <int>          <int>     <dbl>    <int>          <int>
##  1  2013     1     1      517            515         2      830            819
##  2  2013     1     1      533            529         4      850            830
##  3  2013     1     1      542            540         2      923            850
##  4  2013     1     1      544            545        -1     1004           1022
##  5  2013     1     1      554            600        -6      812            837
##  6  2013     1     1      554            558        -4      740            728
##  7  2013     1     1      555            600        -5      913            854
##  8  2013     1     1      557            600        -3      709            723
##  9  2013     1     1      557            600        -3      838            846
## 10  2013     1     1      558            600        -2      753            745
## # ℹ 336,766 more rows
## # ℹ 11 more variables: arr_delay <dbl>, carrier <chr>, flight <int>,
## #   tailnum <chr>, origin <chr>, dest <chr>, air_time <dbl>, distance <dbl>,
## #   hour <dbl>, minute <dbl>, time_hour <dttm>

# + 1 or more
flights %>% filter(str_detect(carrier, "A+"))

## # A tibble: 92,450 × 19
##     year month   day dep_time sched_dep_time dep_delay arr_time sched_arr_time
##    <int> <int> <int>    <int>          <int>     <dbl>    <int>          <int>
##  1  2013     1     1      517            515         2      830            819
##  2  2013     1     1      533            529         4      850            830
##  3  2013     1     1      542            540         2      923            850
##  4  2013     1     1      554            558        -4      740            728
##  5  2013     1     1      558            600        -2      753            745
##  6  2013     1     1      558            600        -2      924            917
##  7  2013     1     1      558            600        -2      923            937
##  8  2013     1     1      559            600        -1      941            910
##  9  2013     1     1      559            600        -1      854            902
## 10  2013     1     1      606            610        -4      858            910
## # ℹ 92,440 more rows
## # ℹ 11 more variables: arr_delay <dbl>, carrier <chr>, flight <int>,
## #   tailnum <chr>, origin <chr>, dest <chr>, air_time <dbl>, distance <dbl>,
## #   hour <dbl>, minute <dbl>, time_hour <dttm>

# * 0 or more
flights %>% filter(str_detect(carrier, "A*"))

## # A tibble: 336,776 × 19
##     year month   day dep_time sched_dep_time dep_delay arr_time sched_arr_time
##    <int> <int> <int>    <int>          <int>     <dbl>    <int>          <int>
##  1  2013     1     1      517            515         2      830            819
##  2  2013     1     1      533            529         4      850            830
##  3  2013     1     1      542            540         2      923            850
##  4  2013     1     1      544            545        -1     1004           1022
##  5  2013     1     1      554            600        -6      812            837
##  6  2013     1     1      554            558        -4      740            728
##  7  2013     1     1      555            600        -5      913            854
##  8  2013     1     1      557            600        -3      709            723
##  9  2013     1     1      557            600        -3      838            846
## 10  2013     1     1      558            600        -2      753            745
## # ℹ 336,766 more rows
## # ℹ 11 more variables: arr_delay <dbl>, carrier <chr>, flight <int>,
## #   tailnum <chr>, origin <chr>, dest <chr>, air_time <dbl>, distance <dbl>,
## #   hour <dbl>, minute <dbl>, time_hour <dttm>

Grouping and backreferences

# (..)\\1

flights %>% select(where(is.character)) %>% filter(str_detect(tailnum, "(\\d{2})\\1"))

## # A tibble: 1,990 × 4
##    carrier tailnum origin dest 
##    <chr>   <chr>   <chr>  <chr>
##  1 EV      N15555  EWR    MKE  
##  2 EV      N11119  LGA    CLE  
##  3 UA      N14242  EWR    TPA  
##  4 EV      N14143  EWR    PIT  
##  5 EV      N15555  EWR    SAV  
##  6 UA      N12125  EWR    LAX  
##  7 EV      N15555  EWR    PWM  
##  8 EV      N15555  EWR    BUF  
##  9 EV      N15555  EWR    RIC  
## 10 EV      N13133  EWR    DTW  
## # ℹ 1,980 more rows

Tools

Detect matches

flights_small %>%
    summarise(sum(str_detect(tailnum, "8$")))

## # A tibble: 1 × 1
##   `sum(str_detect(tailnum, "8$"))`
##                              <int>
## 1                                1

str_detect(flights_small$tailnum, "8$")

##  [1]  TRUE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE

sum(str_detect(flights_small$tailnum, "8$"))

## [1] 1

mean(str_detect(flights_small$tailnum, "8$"))

## [1] 0.1

Extract matches

colours <- c("red", "orange", "yellow", "green", "blue", "pueple")
colour_match <- str_c(colours, collapse = "|")
colour_match

## [1] "red|orange|yellow|green|blue|pueple"

# Extract strings with a color
has_colour <- str_subset(sentences, colour_match)
str_extract(has_colour, colour_match)

##  [1] "blue"   "blue"   "red"    "red"    "red"    "blue"   "yellow" "red"   
##  [9] "red"    "green"  "red"    "red"    "blue"   "red"    "red"    "red"   
## [17] "red"    "blue"   "red"    "blue"   "red"    "green"  "red"    "red"   
## [25] "red"    "red"    "red"    "red"    "green"  "red"    "green"  "red"   
## [33] "green"  "red"    "red"    "red"    "red"    "red"    "blue"   "red"   
## [41] "blue"   "red"    "red"    "red"    "red"    "green"  "green"  "green" 
## [49] "red"    "red"    "yellow" "red"    "orange" "red"    "red"    "red"

Grouped matches

# Extract strings with a noun
noun <- "(a|the) ([^ ]+)"
had_nouns <- str_subset(sentences, noun) %>% head(10)
had_nouns %>% str_extract(noun)

##  [1] "the smooth" "the sheet"  "the depth"  "a chicken"  "the parked"
##  [6] "the sun"    "the huge"   "the ball"   "the woman"  "a helps"

Replacing matches

flights_small %>% mutate(tailnum_rev = tailnum %>% str_replace("^[A-Z]", "-"))

## # A tibble: 10 × 5
##    carrier tailnum origin dest  tailnum_rev
##    <chr>   <chr>   <chr>  <chr> <chr>      
##  1 UA      N14228  EWR    IAH   -14228     
##  2 UA      N24211  LGA    IAH   -24211     
##  3 AA      N619AA  JFK    MIA   -619AA     
##  4 B6      N804JB  JFK    BQN   -804JB     
##  5 DL      N668DN  LGA    ATL   -668DN     
##  6 UA      N39463  EWR    ORD   -39463     
##  7 B6      N516JB  EWR    FLL   -516JB     
##  8 EV      N829AS  LGA    IAD   -829AS     
##  9 B6      N593JB  JFK    MCO   -593JB     
## 10 AA      N3ALAA  LGA    ORD   -3ALAA

flights_small %>% mutate(tailnum_rev = tailnum %>% str_replace_all("^[A-Z]", "-"))

## # A tibble: 10 × 5
##    carrier tailnum origin dest  tailnum_rev
##    <chr>   <chr>   <chr>  <chr> <chr>      
##  1 UA      N14228  EWR    IAH   -14228     
##  2 UA      N24211  LGA    IAH   -24211     
##  3 AA      N619AA  JFK    MIA   -619AA     
##  4 B6      N804JB  JFK    BQN   -804JB     
##  5 DL      N668DN  LGA    ATL   -668DN     
##  6 UA      N39463  EWR    ORD   -39463     
##  7 B6      N516JB  EWR    FLL   -516JB     
##  8 EV      N829AS  LGA    IAD   -829AS     
##  9 B6      N593JB  JFK    MCO   -593JB     
## 10 AA      N3ALAA  LGA    ORD   -3ALAA

Splitting

sentences[1] %>% str_split(" ", n = 3, simplify = TRUE)

##      [,1]  [,2]    [,3]                              
## [1,] "The" "birch" "canoe slid on the smooth planks."

Other types of patterns

flights_small %>% filter(str_detect(origin, regex("^e", ignore_case = TRUE)))

## # A tibble: 3 × 4
##   carrier tailnum origin dest 
##   <chr>   <chr>   <chr>  <chr>
## 1 UA      N14228  EWR    IAH  
## 2 UA      N39463  EWR    ORD  
## 3 B6      N516JB  EWR    FLL