library(completejourney)
## Warning: package 'completejourney' was built under R version 4.2.3
## Welcome to the completejourney package! Learn more about these data
## sets at http://bit.ly/completejourney.
library(dplyr)
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
library(ggplot2)
library(stringr)
Create campaign_data dataset
campaign_data <- full_join(campaigns, campaign_descriptions, by = "campaign_id")
campaign_data <- campaign_data %>%
mutate(campaign_duration = difftime(end_date, start_date, units = "days")) %>%
group_by(campaign_type) %>%
summarise(avg_duration = mean(campaign_duration, na.rm = TRUE))
campaign_data
## # A tibble: 3 × 2
## campaign_type avg_duration
## <ord> <drtn>
## 1 Type A 49.68138 days
## 2 Type B 35.31841 days
## 3 Type C 66.00174 days
Create bar chart
ggplot(data = campaign_data, aes(x = campaign_type, y = avg_duration, fill = campaign_type)) +
geom_bar(stat = "identity", position = "dodge", color = "black") +
labs(title = "Average Campaign Duration by Type", x = "Campaign Type", y = "Average Duration")
## Don't know how to automatically pick scale for object of type <difftime>.
## Defaulting to continuous.
products
## # A tibble: 92,331 × 7
## product_id manufacturer_id department brand product_c…¹ produ…² packa…³
## <chr> <chr> <chr> <fct> <chr> <chr> <chr>
## 1 25671 2 GROCERY National FRZN ICE ICE - … 22 LB
## 2 26081 2 MISCELLANEOUS National <NA> <NA> <NA>
## 3 26093 69 PASTRY Private BREAD BREAD:… <NA>
## 4 26190 69 GROCERY Private FRUIT - SH… APPLE … 50 OZ
## 5 26355 69 GROCERY Private COOKIES/CO… SPECIA… 14 OZ
## 6 26426 69 GROCERY Private SPICES & E… SPICES… 2.5 OZ
## 7 26540 69 GROCERY Private COOKIES/CO… TRAY P… 16 OZ
## 8 26601 69 DRUG GM Private VITAMINS VITAMI… 300 CT…
## 9 26636 69 PASTRY Private BREAKFAST … SW GDS… <NA>
## 10 26691 16 GROCERY Private PNT BTR/JE… HONEY 12 OZ
## # … with 92,321 more rows, and abbreviated variable names ¹product_category,
## # ²product_type, ³package_size
transactions_sample
## # A tibble: 75,000 × 11
## house…¹ store…² baske…³ produ…⁴ quant…⁵ sales…⁶ retai…⁷ coupo…⁸ coupo…⁹ week
## <chr> <chr> <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <int>
## 1 2261 309 316252… 940996 1 3.86 0.43 0 0 5
## 2 2131 368 320531… 873902 1 1.59 0.9 0 0 10
## 3 511 316 324458… 847901 1 1 0.69 0 0 13
## 4 400 388 319322… 130949… 2 11.9 2.9 0 0 8
## 5 918 340 320746… 1085604 1 1.29 0 0 0 10
## 6 718 324 326146… 883203 1 2.5 0.49 0 0 15
## 7 868 323 320747… 9884484 1 3.49 0 0 0 10
## 8 1688 450 348504… 1028715 1 2 1.79 0 0 33
## 9 467 31782 312807… 896613 2 6.55 4.44 0 0 2
## 10 1947 32004 327441… 978497 1 3.99 0 0 0 16
## # … with 74,990 more rows, 1 more variable: transaction_timestamp <dttm>, and
## # abbreviated variable names ¹household_id, ²store_id, ³basket_id,
## # ⁴product_id, ⁵quantity, ⁶sales_value, ⁷retail_disc, ⁸coupon_disc,
## # ⁹coupon_match_disc
Create product_transactions dataset
product_transactions <- inner_join(
transactions_sample, products, by = "product_id"
)
custom_order <- c("January", "February", "March", "April", "May", "June",
"July", "August", "September", "October", "November", "December")
#product_transactions
product_transactions <- product_transactions %>%
group_by(transaction_month = months(transaction_timestamp)) %>%
filter(str_detect(product_category, "BREAD")) %>%
summarise(total_retail_disc = sum(retail_disc)) %>%
arrange(desc(transaction_month))
product_transactions <- product_transactions %>%
mutate(transaction_month = factor(transaction_month, levels = custom_order, ordered = TRUE)) %>%
arrange(transaction_month)
Create histogram
ggplot(product_transactions, aes(x = transaction_month, y = total_retail_disc)) +
geom_line(color = "blue") +
geom_point(color = "red") +
labs(title = "Total Retail Discount for BREAD Products by Month",
x = "Month",
y = "Total Retail Discount") +
theme_minimal()
## `geom_line()`: Each group consists of only one observation.
## ℹ Do you need to adjust the group aesthetic?
Create coupon_data dataset
coupon_data <- inner_join(coupons, coupon_redemptions, by = "coupon_upc")
coupon_data <- coupon_data %>%
group_by(campaign_id.x) %>%
summarise(total_coupons = n()) %>%
filter(total_coupons > 250000)
coupon_data
## # A tibble: 3 × 2
## campaign_id.x total_coupons
## <chr> <int>
## 1 13 803086
## 2 18 989217
## 3 8 391651
Create coupon_data bar chart
ggplot(coupon_data, aes(x = campaign_id.x, y = total_coupons)) +
geom_bar(stat = "identity", fill = "skyblue", color = "black") +
labs(title = "Total Coupons per Popular Campaign",
x = "Campaign ID",
y = "Total Coupons") +
theme_minimal()