library(tidyverse)
library(repurrrsive)
Exercise 1
monthly_data_files <- list.files("data/", pattern = "Month", full.names = TRUE)
monthly_data <- data.frame()
for (monthly_file in monthly_data_files) {
df <- read_csv(monthly_file)
monthly_data <- rbind(monthly_data, df)
}
## Rows: 54535 Columns: 10
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (4): Factor_C, Factor_E, Transaction_Status, Month
## dbl (5): Account_ID, Factor_A, Factor_B, Factor_D, Response
## dttm (1): Transaction_Timestamp
##
## 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.
## Rows: 44380 Columns: 10
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (4): Factor_C, Factor_E, Transaction_Status, Month
## dbl (5): Account_ID, Factor_A, Factor_B, Factor_D, Response
## dttm (1): Transaction_Timestamp
##
## 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.
## Rows: 53259 Columns: 10
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (4): Factor_C, Factor_E, Transaction_Status, Month
## dbl (5): Account_ID, Factor_A, Factor_B, Factor_D, Response
## dttm (1): Transaction_Timestamp
##
## 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.
## Rows: 51033 Columns: 10
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (4): Factor_C, Factor_E, Transaction_Status, Month
## dbl (5): Account_ID, Factor_A, Factor_B, Factor_D, Response
## dttm (1): Transaction_Timestamp
##
## 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.
## Rows: 55079 Columns: 10
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (4): Factor_C, Factor_E, Transaction_Status, Month
## dbl (5): Account_ID, Factor_A, Factor_B, Factor_D, Response
## dttm (1): Transaction_Timestamp
##
## 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.
## Rows: 59666 Columns: 10
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (4): Factor_C, Factor_E, Transaction_Status, Month
## dbl (5): Account_ID, Factor_A, Factor_B, Factor_D, Response
## dttm (1): Transaction_Timestamp
##
## 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.
## Rows: 64268 Columns: 10
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (4): Factor_C, Factor_E, Transaction_Status, Month
## dbl (5): Account_ID, Factor_A, Factor_B, Factor_D, Response
## dttm (1): Transaction_Timestamp
##
## 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.
## Rows: 69492 Columns: 10
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (4): Factor_C, Factor_E, Transaction_Status, Month
## dbl (5): Account_ID, Factor_A, Factor_B, Factor_D, Response
## dttm (1): Transaction_Timestamp
##
## 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.
## Rows: 71855 Columns: 10
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (4): Factor_C, Factor_E, Transaction_Status, Month
## dbl (5): Account_ID, Factor_A, Factor_B, Factor_D, Response
## dttm (1): Transaction_Timestamp
##
## 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.
## Rows: 80277 Columns: 10
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (4): Factor_C, Factor_E, Transaction_Status, Month
## dbl (5): Account_ID, Factor_A, Factor_B, Factor_D, Response
## dttm (1): Transaction_Timestamp
##
## 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.
## Rows: 94315 Columns: 10
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (4): Factor_C, Factor_E, Transaction_Status, Month
## dbl (5): Account_ID, Factor_A, Factor_B, Factor_D, Response
## dttm (1): Transaction_Timestamp
##
## 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.
glimpse(monthly_data)
## 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",…
options(readr.show_col_types = FALSE)
Exercise 2
column_classes <- map(monthly_data, class)
print(column_classes)
## $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
unique_counts <- map_int(monthly_data, ~length(unique(.)))
print(unique_counts)
## 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
## 11
Exercise 4
monthly_data <- monthly_data %>%
mutate(Factor_D = ifelse(Factor_D == 26, 25, Factor_D))
unique_values_after_recode <- monthly_data %>%
pull(Factor_D) %>%
unique()
print("Unique values in Factor_D after recoding:")
## [1] "Unique values in Factor_D after recoding:"
print(unique_values_after_recode)
## [1] 20 21 30 25 35 55 50 90 10 15 85 70 40 31
factor_d_counts <- monthly_data %>%
group_by(Factor_D) %>%
summarise(count = n())
print("Observations for each level of Factor_D:")
## [1] "Observations for each level of Factor_D:"
print(factor_d_counts)
## # A tibble: 14 × 2
## Factor_D count
## <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 90 973
Exercise 5
df_filtered <- df %>%
filter_at(vars(starts_with("Factor_")), all_vars(. != "NULL"))
num_rows_filtered <- nrow(df_filtered)
print("Number of rows after filtering:")
## [1] "Number of rows after filtering:"
print(num_rows_filtered)
## [1] 77197
Exercise 6
df2 <- df %>%
mutate_at(-2, as.factor) %>%
mutate(Month = factor((Month), levels = month.name))
glimpse(df2)
## Rows: 94,315
## Columns: 10
## $ Account_ID <fct> 2, 2, 2, 2, 19, 23, 27, 29, 44, 52, 52, 81, 81, …
## $ Transaction_Timestamp <dttm> 2009-11-18 22:58:29, 2009-11-25 11:24:29, 2009-…
## $ Factor_A <fct> 7, 7, 7, 7, 2, 15, 7, 15, 15, 2, 2, 2, 2, 2, 2, …
## $ Factor_B <fct> 15, 15, 15, 15, 6, 23, 15, 23, 23, 6, 6, 6, 6, 6…
## $ Factor_C <fct> MC, MC, MC, MC, VI, AX, MC, AX, AX, VI, VI, VI, …
## $ Factor_D <fct> 20, 50, 50, 20, 20, 21, 20, 21, 21, 25, 25, 20, …
## $ Factor_E <fct> MCG, MCG, MCG, MCG, B, NULL, MCS, NULL, NULL, G2…
## $ Response <fct> 1020, 1100, 1100, 1020, 1020, 1020, 1020, 1020, …
## $ Transaction_Status <fct> Approved, Declined, Declined, Approved, Approved…
## $ Month <fct> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, …
levels <- levels(df2$Month)
levels
## [1] "January" "February" "March" "April" "May" "June"
## [7] "July" "August" "September" "October" "November" "December"
Exercise 7
df2 %>%
group_by(Transaction_Status) %>%
summarise_if(is.factor, n_distinct)
## # A tibble: 2 × 9
## Transaction_Status Account_ID Factor_A Factor_B Factor_C Factor_D Factor_E
## <fct> <int> <int> <int> <int> <int> <int>
## 1 Approved 71916 4 4 4 13 50
## 2 Declined 3019 5 5 4 13 48
## # ℹ 2 more variables: Response <int>, Month <int>
Exercise 8
## # A tibble: 1 × 2
## Qtr total
## <chr> <int>
## 1 Q4 94315
Excersie 9
sw_people %>%
map_chr(~.x$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"
Excersie 10
sw_people%>%
map_int(~ length(.x$films))
## [1] 5 6 7 4 5 3 3 1 1 6 3 2 5 4 1 3 3 1 5 5 3 1 1 2 1 2 1 1 1 1 1 3 1 2 1 1 1 2
## [39] 1 1 2 1 1 3 1 1 1 3 3 3 2 2 2 1 3 2 1 1 1 2 2 1 1 2 2 1 1 1 1 1 1 1 2 1 1 2
## [77] 1 1 2 2 1 1 1 1 1 1 3
Exercise 11
sw_people %>%
map_chr(~.x$name) %>%
set_names(sw_people, nm = .) %>%
map_df(~ length(.x$films)) %>%
pivot_longer(
cols=everything(),
names_to = "Character",
values_to = "Films",
) %>%
ggplot(aes(Films, reorder(Character, Films))) +
geom_point()
