high_sales <- trees %>%
#mutate(Sales_Price = coalesce(as.numeric(Sales_Price), 0)) %>%
mutate(Sales_Price = as.numeric(Sales_Price)) %>%
select(Sales_Price) %>%
count(Sales_Price) %>%
mutate(Label = ifelse(Sales_Price >= 4500, "High Sale", "Low Sales")) %>%
arrange(desc(Sales_Price))
## Warning: Problem with `mutate()` input `Sales_Price`.
## i NAs introduced by coercion
## i Input `Sales_Price` is `as.numeric(Sales_Price)`.
## Warning in mask$eval_all_mutate(dots[[i]]): NAs introduced by coercion
#view(high_sales)
high_sales
## # A tibble: 2,788 x 3
## Sales_Price n Label
## <dbl> <int> <chr>
## 1 45000 1 High Sale
## 2 17760 1 High Sale
## 3 16334. 1 High Sale
## 4 14438. 1 High Sale
## 5 14392. 1 High Sale
## 6 10978. 1 High Sale
## 7 10745 1 High Sale
## 8 10581 1 High Sale
## 9 8835 1 High Sale
## 10 8607. 1 High Sale
## # … with 2,778 more rows
lostMoney <- cleanedtreesdf2 %>%
filter(Amount < 0) %>%
arrange((Amount))
lostMoneyItems <- lostMoney %>%
count(Item) %>%
arrange(desc(n))
lostMoneyItems
## # A tibble: 112 x 2
## Item n
## <chr> <int>
## 1 Replacement Discount 1048
## 2 Customer Discount 227
## 3 Invoice Balancer 137
## 4 Misc. Labor 44
## 5 Installation 39
## 6 Donation 30
## 7 Extended Warranty 20
## 8 Tree Staking 11
## 9 Restaking Discount 9
## 10 Fertilization 7
## # … with 102 more rows
lostMoneyReplacements <- lostMoney %>%
filter(Item == "Replacement Discount")
money_lost <- sum(lostMoney$Amount)
money_lost_replacement <- sum(lostMoneyReplacements$Amount)
cat("Total money lost: $", money_lost, "\n")
## Total money lost: $ -852663.1
cat("Total money lost from replacemnt: $", money_lost_replacement, "\n")
## Total money lost from replacemnt: $ -614929.9
gainedMoney <- cleanedtreesdf2 %>%
filter(Amount > 0) %>%
arrange((Amount))
gainedMoney
## # A tibble: 19,887 x 10
## X1 Type Date Num Ship_To_Address2 Ship_Zip Item Qty Sales_Price
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl> <chr>
## 1 50 Invo… 8/5/… 9858 E Cobblestone C… 46725 Invo… 1 0.01
## 2 764 Invo… 4/12… 1025 <NA> <NA> Invo… 1 0.01
## 3 842 Invo… 4/15… 1039 <NA> <NA> Invo… 1 0.01
## 4 858 Invo… 4/12… 1024 <NA> <NA> Invo… 1 0.01
## 5 1194 Invo… 5/5/… 1117 <NA> <NA> Invo… 1 0.01
## 6 1904 Invo… 9/20… 1362 <NA> <NA> Invo… 1 0.01
## 7 1924 Invo… 5/26… 2474 <NA> <NA> Invo… 1 0.01
## 8 2028 Invo… 7/12… 1283 <NA> <NA> Invo… 1 0.01
## 9 2052 Invo… 8/2/… 1297 <NA> <NA> Invo… 1 0.01
## 10 2262 Invo… 6/24… 1856 <NA> <NA> Invo… 1 0.01
## # … with 19,877 more rows, and 1 more variable: Amount <dbl>
gainedMoneyItems <- gainedMoney %>%
count(Item) %>%
arrange(desc(n))
gainedMoneyItems
## # A tibble: 1,298 x 2
## Item n
## <chr> <int>
## 1 Installation 2761
## 2 Extended Warranty 1330
## 3 Tree Staking 1239
## 4 Trip Charge 654
## 5 Fertilization 473
## 6 Trees:Arborvitae:6' Emerald Green Arborvitae 411
## 7 Delivery Fee 383
## 8 Trees:Spruce:6' Norway Spruce 378
## 9 Trees:Spruce:6' White Spruce 264
## 10 Misc. Labor 226
## # … with 1,288 more rows
#trees_sold <- gainedMoneyItems %>%
# filter(str_detect(trees_sold$Item, "Trees:"))
#trees_sold
gained_money <- sum(gainedMoney$Amount)
cat("Total Gross Income: $", gained_money, "\n")
## Total Gross Income: $ 10778956
count_dates <- cleanedtreesdf2 %>%
mutate(Date = as.Date(Date, format="%m/%d/%Y")) %>%
mutate(year = lubridate::year(Date)) %>%
count(year) %>%
mutate(Label = paste("Sales")) %>%
arrange(desc(year))
count_dates
## # A tibble: 10 x 3
## year n Label
## <dbl> <int> <chr>
## 1 2023 1820 Sales
## 2 2022 360 Sales
## 3 2021 3919 Sales
## 4 2020 4239 Sales
## 5 2019 2978 Sales
## 6 2018 2116 Sales
## 7 2017 1960 Sales
## 8 2016 1929 Sales
## 9 2015 1721 Sales
## 10 2014 1060 Sales
#View(count_dates)
graph_dates <- cleanedtreesdf2 %>%
ggplot(aes(x= Date, y = Qty, froup = 1, colour = Amount)) +
geom_line() +
labs(title = "Sale amount each day",
colour = "Date")
graph_dates
## Warning: Removed 111 row(s) containing missing values (geom_path).
count_years <- count_dates %>%
filter(year >= 2014 & year <= 2023) %>%
ggplot(aes(x = year, y = n)) +
geom_line(stat = "identity") +
labs(title = "Number of tree sales each year",
x = "Year",
y = "Sales")
print(count_years)
total_sales_no_address <- 0
total_sales_with_address <- 0
for (i in seq_along(cleanedtreesdf2$Ship_To_Address2)) {
if (is.na(cleanedtreesdf2$Ship_To_Address2[i])) {
#cat("Adress for sale ", cleanedtreesdf2$Num[i], " is blank", "\n") <- prints each individual sale WITHOUT address
total_sales_no_address <- total_sales_no_address + 1
} else {
total_sales_with_address <- total_sales_with_address + 1
}
}
cat("Total orders WITH address: ", total_sales_with_address, "\n")
## Total orders WITH address: 751
cat("Total orders WITHOUT address: ", total_sales_no_address, "\n")
## Total orders WITHOUT address: 21351