For Loop Efficiency - r

Question

The following loop is effective in that it gets me to the finish line but i'm looking for a way to make it more efficient as I'm looping through a large dataset. Possibly using a Purrr function?
library(tidyverse)
library(timetk)
#### CREATE DATA
df_1 <- data.frame(Date = seq.Date(as.Date("2016-01-01"), length.out = 36, by = "month"),
Inventory = round(runif(36,5,100),0),
Purchases = round(runif(36,5,100),0),
Sales = round(runif(36,5,100),0),
Ending_Inventory = round(runif(36,5,100),0)) %>%
mutate(Starting_Inventory = lag(Ending_Inventory,1)) %>%
mutate(product = "Product_1")
df_2 <- data.frame(Date = seq.Date(as.Date("2016-01-01"), length.out = 36, by = "month"),
Inventory = round(runif(36,5,100),0),
Purchases = round(runif(36,5,100),0),
Sales = round(runif(36,5,100),0),
Ending_Inventory = round(runif(36,5,100),0)) %>%
mutate(Starting_Inventory = lag(Ending_Inventory,1)) %>%
mutate(product = "Product_2")
df <- rbind(df_1, df_2) %>%
group_by(product) %>%
timetk::future_frame(
.date_var = Date,
.length_out = "12 months",
.bind_data = TRUE
)
Here I'm creating a date sequence to iterate through the for loop
#### CREATE DATE SEQUENCE
Dates <- seq(min(df$Date) %m+% months(36), min(df$Date) %m+% months(48), by = "month")
The dates from the sequence above will iterate through the loop to fill in the future data and then I join, rename some columns, and drop all that contain ("y")... Seems like I'm performing some steps that aren't necessary.
for (i in 1:length(Dates)){
df <- df %>%
mutate(Purchases = case_when(Date < Dates[i] ~ Purchases,
Date == Dates[i] ~ lag(Purchases, 12)*1.05,
TRUE ~ 0
)) %>%
mutate(Starting_Inventory = case_when(Date < Dates[i] ~ Starting_Inventory,
Date == Dates[i] ~ lag(Ending_Inventory,1),
TRUE ~ 0
)) %>%
mutate(Sales = case_when(Date < Dates[i] ~ Sales,
Date == Dates[i] ~ lag(Sales,12) * 1.15,
TRUE ~ 0
)) %>%
mutate(Ending_Inventory = case_when(Date < Dates[i] ~ Ending_Inventory,
Date == Dates[i] ~ Starting_Inventory + Sales + Purchases,
TRUE ~ 0
)) %>%
mutate(Inventory = case_when(Date < Dates[i] ~ Inventory,
Date == Dates[i] ~ Ending_Inventory,
TRUE ~ 0
))
new_data <- df[df$Date == (Dates[i]),]
df <- df %>%
left_join(., new_data, by = c("product", "Date")) %>%
mutate(Inventory.x = ifelse(Date == Dates[i],Inventory.y,Inventory.x),
Purchases.x = ifelse(Date == Dates[i],Purchases.y,Purchases.x),
Sales.x = ifelse(Date == Dates[i],Sales.y,Sales.x),
Starting_Inventory.x = ifelse(Date == Dates[i],Starting_Inventory.y,Starting_Inventory.x),
Ending_Inventory.x = ifelse(Date == Dates[i],Ending_Inventory.y,Ending_Inventory.x),
) %>%
rename(Inventory = Inventory.x,
Purchases = Purchases.x,
Starting_Inventory = Starting_Inventory.x,
Sales = Sales.x,
Ending_Inventory = Ending_Inventory.x) %>%
dplyr::select(-contains(".y"))
return
print(i)
gc()
}

Answer 1

There are a lot of unnecessary steps in there.
Mutate can take more than one expression at once.
The case_when is unnecessary since in the next step you only keep the rows that got modified.
Then, for the same reason, the join and renaming is more steps than needed, you can just replace the old rows with the new row by selecting a subset.
for (i in seq_along(Dates)){
new_data <- df2 %>%
mutate(Purchases = lag(Purchases, 12)*1.05,
Starting_Inventory = lag(Ending_Inventory,1),
Sales = lag(Sales,12) * 1.15,
Ending_Inventory = Starting_Inventory + Sales + Purchases,
Inventory = Ending_Inventory)
df2[df2$Date == Dates[i],] <- new_data[new_data$Date == Dates[i],]
}
But then you're stil recalculating your whole data.frame for each loop. No need for that either since mutate() is iterative. You can do it all with just that function.
Also, since there are only 2 conditions really needed, you can replace the case_when with ifelse and it's faster.
df <- df %>%
mutate(
Purchases = ifelse(
Date %in% Dates, lag(Purchases, 12)*1.05, Purchases
),
Starting_Inventory = ifelse(
Date %in% Dates, lag(Ending_Inventory,1), Starting_Inventory
),
Sales = ifelse(
Date %in% Dates, lag(Sales,12) * 1.15, Sales
),
Ending_Inventory = ifelse(
Date %in% Dates, Starting_Inventory + Sales + Purchases,
Ending_Inventory
),
Inventory = ifelse(
Date %in% Dates, Ending_Inventory, Inventory
)
)
Edit:
I think it's important to break down what you're trying to do when you end up with long for loop like this. Since you're trying to do in place modifications, even in base R, you could do this with this short a for loop :
df3 <- df.o
df3 <- df3 |> within({
for (i in which(Date %in% Dates)){
Purchases[i] = Purchases[i-12]*1.05
Sales[i] = Sales[i-12] * 1.15
Ending_Inventory[i] = Starting_Inventory[i] + Sales[i] + Purchases[i]
Inventory[i] = Ending_Inventory[i]
Starting_Inventory[i] = Ending_Inventory[i-1]
}
i = NULL
})
A bit slower than mutate, but it's the same logic.