Loop through irregular list of numbers to append rows to summary table - sql

Question

I'm trying to write code that will loop through a list of integers, which relate to a number of sensors, to provide summary statistics (at this stage just cor()).
# GOOD TO HERE
corr_table <-data.frame(ID = integer()
, HxT = double())
for(j in gt_thrsh_key){ #this is currently set to 2:5 for testing - its a list of sensors I want to summarise
# extract humidity and time vectors
x <- sqldf(sprintf("SELECT humidity FROM data_agg_2 WHERE ID = %s",j))
y <- sqldf(sprintf("SELECT time_elapsed FROM data_agg_2 WHERE ID = %s",j))
# format into row
new_row <- data.frame(ID = c(j), HxT = c(cor(x,y))) #insert new variables into row
# append to dataframe
corr_table <- rbind(corr_table, new_row)
print(sprintf("Sensor %s has been summarised.",j)) # check 1
print(cor(x,y)) # check 2
}
print(corr_table)
assign("data_agg_2", data_agg_2, envir = .GlobalEnv)
I get output:
[1] "Sensor 2 has been summarised." "Sensor 3 has been summarised." "Sensor 4 has been summarised." "Sensor 5 has been summarised."
humidity -0.08950285
ID HxT
1 2 -0.08950285 #INCORRECT
2 3 -0.08950285 #INCORRECT
3 4 -0.08950285 #INCORRECT
4 5 -0.08950285 #correct
This is only the correct measurement for the final iteration of loop (id = 5), so somehow I must be overwriting previous entries. Does anyone know why this is happening? Or can you recommend a better way to perform this loop?
Thanks!!
EDIT: check 2 which prints the cor() of x and y through the loop confirms that only the final run of loop is calculating a value. Has anyone seen this before?

Answer 1

Here is a base R solution that uses lapply() to generate the correlations and write them to a list(). The list is converted to a data frame with do.call(rbind,...).
# simulate some data
set.seed(19041798) # ensure consistency across multiple runs
ID <- rep(1:10,20)
humidity <- rnorm(200,mean = 30,sd = 15)
elapsed_time <- rpois(200,2.5)
data <- data.frame(ID,humidity, elapsed_time)
uniqueIDs <- unique(data$ID)
correlationList <- lapply(uniqueIDs,function(x){
y <- subset(data,ID == x)
HxT <- cor(y$humidity,y$elapsed_time)
# return as data frame
data.frame(ID = x,HxT = HxT)
})
correlations <- do.call(rbind,correlationList)
...and the output:
> correlations
ID HxT
1 1 -0.1805885
2 2 -0.3166290
3 3 0.1749233
4 4 -0.2517737
5 5 0.1428092
6 6 0.3112812
7 7 -0.3180825
8 8 0.3774637
9 9 -0.3790178
10 10 -0.3070866
>
sqldf() version
We can restructure the code from the original post so it extracts all the data it needs through a single SQL query, and performs all subsequent processing in R.
First, we simulate 60,000 rows of data.
set.seed(19041798) # ensure consistency across multiple runs
ID <- rep(1:30,2000)
humidity <- rnorm(60000,mean = 30,sd = 15)
elapsed_time <- rpois(60000,2.5)
data <- data.frame(ID,humidity, elapsed_time)
Next, we extract data for the first 5 sensors from the data with sqldf(), as well as the vector of uniqueIDs.
library(sqldf)
# select ID <= 5
sqlStmt <- "select ID, humidity,elapsed_time from data where ID <= 5"
dataSubset <- sqldf(sqlStmt)
sqlStmt <- "select distinct ID from data where ID <= 5"
uniqueIDs <- sqldf(sqlStmt)[[1]]
At this point, the dataSubset data frame has 10,000 observations. We use lapply() with the vector of uniqueIDs to generate correlations by ID, count the complete.cases() included in each correlation, and write the results to a list of data frames.
correlationList <- lapply(uniqueIDs,function(x){
y <- subset(dataSubset,ID == x)
count <- sum(complete.cases(y)) # number of obs included in cor()
HxT <- cor(y$humidity,y$elapsed_time)
# return as data frame
data.frame(ID = x,count = count,HxT = HxT)
})
Finally, a do.call(rbind,...) and a print, and we have our list of correlations including counts of rows used to calculate the correlation.
correlations <- do.call(rbind,correlationList)
correlations
...and the output:
> correlations
ID count HxT
1 1 2000 0.015640244
2 2 2000 0.017143573
3 3 2000 -0.011283180
4 4 2000 0.052482666
5 5 2000 0.002083603
>