Lab-6
Emily Turcotte
2024-02-12
Loading packages
library(tidyverse)
library(here)
library(repurrrsive)Exercise 1
Import the Month.XX.csv files into one data frame
df <- list.files(here("Lab 6/data"), full.names = TRUE) %>%
map_df(read_csv)
glimpse(df)## Rows: 698,159
## Columns: 10
## $ Account_ID <dbl> 5, 16, 28, 40, 62, 64, 69, 69, 70, 79, 88, 90, 9…
## $ Transaction_Timestamp <dttm> 2009-01-08 00:16:41, 2009-01-20 22:40:08, 2009-…
## $ Factor_A <dbl> 2, 2, 2, 2, 2, 7, 2, 2, 2, 7, 8, 10, 10, 2, 2, 2…
## $ Factor_B <dbl> 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 18, 6, 6, 6, 6, 6,…
## $ Factor_C <chr> "VI", "VI", "VI", "VI", "VI", "MC", "VI", "VI", …
## $ Factor_D <dbl> 20, 20, 21, 20, 20, 20, 20, 20, 20, 20, 20, 20, …
## $ Factor_E <chr> "A", "H", "NULL", "H", "B", "NULL", "H", "H", "B…
## $ Response <dbl> 1020, 1020, 1020, 1020, 1020, 1020, 1020, 1020, …
## $ Transaction_Status <chr> "Approved", "Approved", "Approved", "Approved", …
## $ Month <chr> "Jan", "Jan", "Jan", "Jan", "Jan", "Jan", "Jan",…Exercise 2
Check the current class of each column
df %>%
map(class)## $Account_ID
## [1] "numeric"
##
## $Transaction_Timestamp
## [1] "POSIXct" "POSIXt"
##
## $Factor_A
## [1] "numeric"
##
## $Factor_B
## [1] "numeric"
##
## $Factor_C
## [1] "character"
##
## $Factor_D
## [1] "numeric"
##
## $Factor_E
## [1] "character"
##
## $Response
## [1] "numeric"
##
## $Transaction_Status
## [1] "character"
##
## $Month
## [1] "character"Exercise 3
How many unique values exist in each column?
df %>%
map_int(n_distinct)## Account_ID Transaction_Timestamp Factor_A
## 475413 686538 7
## Factor_B Factor_C Factor_D
## 6 4 15
## Factor_E Response Transaction_Status
## 63 42 2
## Month
## 11Exercise 4
Recode any values where Factor_D == 26 to be 25. How many unique values exist in the column? How many observations are there for each level of Factor_D?
df %>%
mutate(Factor_D = ifelse(Factor_D == 26, 25, Factor_D)) %>%
count(Factor_D)## # A tibble: 14 × 2
## Factor_D n
## <dbl> <int>
## 1 10 4595
## 2 15 1089
## 3 20 527882
## 4 21 68072
## 5 25 41021
## 6 30 7030
## 7 31 512
## 8 35 25298
## 9 40 2720
## 10 50 3709
## 11 55 15200
## 12 70 54
## 13 85 4
## 14 90 973Exercise 5
Filter out “Factor_” observations that contain “NULL”
df <- df %>%
filter_at(c(3:7), all_vars(. != "NULL"))Exercise 6
Convert all variables to factors and make sure the “Month” variable is an ordered factor
df <- df %>%
mutate_at(-2, as.factor) %>%
mutate(Month = factor((Month), levels = month.abb))
glimpse(df)## Rows: 489,537
## Columns: 10
## $ Account_ID <fct> 5, 16, 40, 62, 69, 69, 70, 95, 101, 101, 102, 10…
## $ Transaction_Timestamp <dttm> 2009-01-08 00:16:41, 2009-01-20 22:40:08, 2009-…
## $ Factor_A <fct> 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, …
## $ Factor_B <fct> 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, …
## $ Factor_C <fct> VI, VI, VI, VI, VI, VI, VI, VI, VI, VI, VI, VI, …
## $ Factor_D <fct> 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, …
## $ Factor_E <fct> A, H, H, B, H, H, B, G, G2, G2, A, A, C, A, A, A…
## $ Response <fct> 1020, 1020, 1020, 1020, 1020, 1020, 1020, 1020, …
## $ Transaction_Status <fct> Approved, Approved, Approved, Approved, Approved…
## $ Month <fct> Jan, Jan, Jan, Jan, Jan, Jan, Jan, Jan, Jan, Jan…levels(df$Month)## [1] "Jan" "Feb" "Mar" "Apr" "May" "Jun" "Jul" "Aug" "Sep" "Oct" "Nov" "Dec"Exercise 7
Assess how many unique values there are for all the other variables in our data set
df %>% summarize_if(is.factor, n_distinct)## # A tibble: 1 × 9
## Account_ID Factor_A Factor_B Factor_C Factor_D Factor_E Response
## <int> <int> <int> <int> <int> <int> <int>
## 1 324174 2 3 2 13 62 30
## # ℹ 2 more variables: Transaction_Status <int>, Month <int>For transactions that are approved versus declined, do we have near equal representation of observations across each variable?
df %>%
group_by(Transaction_Status) %>%
summarize_if(is.factor, n_distinct)## # A tibble: 2 × 9
## Transaction_Status Account_ID Factor_A Factor_B Factor_C Factor_D Factor_E
## <fct> <int> <int> <int> <int> <int> <int>
## 1 Approved 316172 2 3 2 12 59
## 2 Declined 14066 2 3 2 11 57
## # ℹ 2 more variables: Response <int>, Month <int>Exercise 8
Create a convert_to_qtr function that takes in a abbreviated month and turns it into its corresponding quarter
convert_to_qtr <- function(month) {
case_when(
month %in% c("Jan", "Feb", "Mar") ~ "Q1",
month %in% c("Apr", "May", "Jun") ~ "Q2",
month %in% c("Jul", "Aug", "Sep") ~ "Q3",
month %in% c("Oct", "Nov", "Dec") ~ "Q4"
)
}Test the convert_to_qtr function
example_months <- c("Jan", "Mar", "May", "May", "Aug", "Nov", "Nov", "Dec")
convert_to_qtr(example_months)## [1] "Q1" "Q1" "Q2" "Q2" "Q3" "Q4" "Q4" "Q4"Make a new variable Qtr with the convert_to_qtr function and find how many observations are in each quarter?
df %>%
mutate(Qtr = convert_to_qtr(Month)) %>%
group_by(Qtr) %>%
count(Qtr)## # A tibble: 4 × 2
## # Groups: Qtr [4]
## Qtr n
## <chr> <int>
## 1 Q1 85588
## 2 Q2 100227
## 3 Q3 161071
## 4 Q4 142651Exercise 9
Extract the name of each Star Wars character
sw_people %>% map_chr(~.x$name)## [1] "Luke Skywalker" "C-3PO" "R2-D2"
## [4] "Darth Vader" "Leia Organa" "Owen Lars"
## [7] "Beru Whitesun lars" "R5-D4" "Biggs Darklighter"
## [10] "Obi-Wan Kenobi" "Anakin Skywalker" "Wilhuff Tarkin"
## [13] "Chewbacca" "Han Solo" "Greedo"
## [16] "Jabba Desilijic Tiure" "Wedge Antilles" "Jek Tono Porkins"
## [19] "Yoda" "Palpatine" "Boba Fett"
## [22] "IG-88" "Bossk" "Lando Calrissian"
## [25] "Lobot" "Ackbar" "Mon Mothma"
## [28] "Arvel Crynyd" "Wicket Systri Warrick" "Nien Nunb"
## [31] "Qui-Gon Jinn" "Nute Gunray" "Finis Valorum"
## [34] "Jar Jar Binks" "Roos Tarpals" "Rugor Nass"
## [37] "Ric Olié" "Watto" "Sebulba"
## [40] "Quarsh Panaka" "Shmi Skywalker" "Darth Maul"
## [43] "Bib Fortuna" "Ayla Secura" "Dud Bolt"
## [46] "Gasgano" "Ben Quadinaros" "Mace Windu"
## [49] "Ki-Adi-Mundi" "Kit Fisto" "Eeth Koth"
## [52] "Adi Gallia" "Saesee Tiin" "Yarael Poof"
## [55] "Plo Koon" "Mas Amedda" "Gregar Typho"
## [58] "Cordé" "Cliegg Lars" "Poggle the Lesser"
## [61] "Luminara Unduli" "Barriss Offee" "Dormé"
## [64] "Dooku" "Bail Prestor Organa" "Jango Fett"
## [67] "Zam Wesell" "Dexter Jettster" "Lama Su"
## [70] "Taun We" "Jocasta Nu" "Ratts Tyerell"
## [73] "R4-P17" "Wat Tambor" "San Hill"
## [76] "Shaak Ti" "Grievous" "Tarfful"
## [79] "Raymus Antilles" "Sly Moore" "Tion Medon"
## [82] "Finn" "Rey" "Poe Dameron"
## [85] "BB8" "Captain Phasma" "Padmé Amidala"Exercise 10
Find the number of films each Star Wars character has been in
sw_people %>% map_int(~ length(.$films))## [1] 5 6 7 4 5 3 3 1 1 6 3 2 5 4 1 3 3 1 5 5 3 1 1 2 1 2 1 1 1 1 1 3 1 2 1 1 1 2
## [39] 1 1 2 1 1 3 1 1 1 3 3 3 2 2 2 1 3 2 1 1 1 2 2 1 1 2 2 1 1 1 1 1 1 1 2 1 1 2
## [77] 1 1 2 2 1 1 1 1 1 1 3Exercise 11
Create a plot that shows the number of films each Star Wars Character has been in.
sw_people %>%
map_chr(~ .$name) %>%
set_names(sw_people, nm = .) %>%
map_df(~ length(.$films)) %>%
pivot_longer(
cols = everything(),
names_to = "Character",
values_to = "Films"
) %>%
ggplot(aes(Films, reorder(Character, Films))) +
geom_point() +
scale_y_discrete("Characters") +
scale_x_continuous("Number of Films")