Different test data than train data - r

I have a large dataframe (54160 observations) that needs to be split into a training and a test set. This should not be a problem, but in the dataframe there are several historical weather variables (per day, 2013-2018). These can be used for training, but not for prediction, because one cannot know the weather in advance. Therefore, I replaced these variables with the historical average per month (e.g. the average temperature in January is around 5 degrees Celsius).
Now I would like to do a regression in R and train my model on 75% of the data (with the original weather variables). Then I want to predict on the remaining 25% of the data (but with the replaced weather variables). How do I do this in R? Because essentially I'm dealing with two different datasets, an original one and a modified one. Thus: from the original one I need 75% for training, and from the modified one I need 25% for testing (but of course the data points should not overlap).
How do I make sure the data does not overlap? Or should I also train on the modified dataframe?


You are right in wanting to separate your training and testing data. To do this you need to randomly select 75% and then take the other 25%. This solution first randomizes the order of the data and then takes the first .75 and last .25 of the data.
weather_data <- data.frame(day = 1:50000,temp = sample(1:100,50000,replace = TRUE))
random.order <- sample(1:50000,50000)
weather_data <- weather_data[order(random.order),]
training_data <- weather_data[1:37500,]
test_data <- weather_data[37501:50000,]

Related

When setting your obsCovs for the function pcount (package unmarked) how does R "know" which obsCov observation corresponds to each y value?

I'm relatively new at R particularly with this package. I am running n-mixture models assessing detection probabilities and abundance. I have abundance data, site covariates and observation covariates. There are three repeated observations(rounds)/site. The observation covariates are set up as columns (three column/covariate, one for each round). The rows are individual sites. The abundance data is formatted similarly, with each column heading representing a different round. I've copied my code below.
y.abun2<-COYE[2:4]
obsCovs.ss <- list(temp=Covariate2021[3:5], Date=Covariate2021[13:15], Cloud=Covariate2021[17:19], Wind=Covariate2021[21:23],Observ=Covariate2021[25:27])
siteCovs.ss <- Covariate2021[c(29,30,31,32)]
coyeabund<-unmarkedFramePCount(y=y.abun2, siteCovs = siteCovs.ss,
obsCovs = obsCovs.ss)
After this I scale using this code:
coyeabund#siteCovs$TreeCover <-
scale(coyeabund#siteCovs$TreeCover)
Moving on to my model I use this code:
abun.coye.full<-pcount(~TreeCover+temp+Date+Cloud+Wind+Observ ~ HHSDI+ProportionNH+Quality, coyeabund,mixture="NB", K=132,se=TRUE)
Is the model matching the observation covariates to the abundance measurements to each round? (i.e., is it able to tell that temp column 5 corresponds to the third round of abundance measurements?)
The models seem fine so far but I am so new at this I want to confirm that I haven't gone astray.

Model predicted values around mean using training data

I tried to ask these questions through imputations, but I want to see if this can be done with predictive modelling instead. I am trying to use information from 2003-2004 NHANES to predict future NHANES cycles. For some context, in 2003-2004 NHANES measured blood contaminants in individual people's blood. In this cycle, they also measured things such as triglycerides, cholesterol etc. that influence the concentration of these blood contaminants.
The first step in my workflow is the impute missing blood contaminant concentrations in 2003-2004 using the measured values of triglycerides, cholesterol etc. This is an easy step and very straightforward. This will be my training dataset.
For future NHANES years (for example 2005-2006), they took individual blood samples combined them (or pooled in other words) and then measured blood contaminants. I need to figure out what the individual concentrations were in these cycles. I have individual measurements for triglycerides, cholesterol etc. and the pooled value is considered the mean. Could I use the mean, 2003-2004 data to unpool or predict the values? For example, if a pool contains 8 individuals, we know the mean, the distribution (2003-2004) and the other parameters (triglycerides) which we can use in the regression to estimate the blood contaminants in those 8 individuals. This would be my test dataset where I have the same contaminants as in the training dataset, with a column for the number of individuals in each pool and the mean value. Alternatively, I can create rows of empty values for contaminants, add mean values separately.
I can easily run MICE, but I need to make sure that the distribution of the imputed data matches 2003-2004 and that the average of the imputed 8 individuals from the pools is equal to the measured pool. So the 8 values for each pool, need to average to the measured pool value while the distribution has to be the same as 2003-2004.
Does that make sense? Happy to provide context if need be. There is an outline code below.
library(mice)
library(tidyverse)
library(VIM)
#Papers detailing these functions can be found in MICE Cran package
df <- read.csv('2003_2004_template.csv', stringsAsFactors = TRUE, na.strings = c("", NA))
#Checking out the NA's that we are working with
non_detect_summary <- as.data.frame(df %>% summarize_all(funs(sum(is.na(.)))))
#helpful representation of ND
aggr_plot <- aggr(df[, 7:42], col=c('navyblue', 'red'),
numbers=TRUE,
sortVars=TRUE,
labels=names(df[, 7:42]),
cex.axis=.7,
gap=3,
ylab=c("Histogram of Missing Data", "Pattern"))
#Mice time, m is the number of imputed datasets (you can think of this as # of cycles)
#You can check out what regression methods below in console
methods(mice)
#Pick Method based on what you think is the best method. Read up.
#Now apply the right method
imputed_data <- mice(df, m = 30)
summary(imputed_data)
#if you want to see imputed values
imputed_data$imp
#finish the dataset
finished_imputed_data <- complete(imputed_data)
#Check for any missing values
sapply(finished_imputed_data, function(x) sum(is.na(x))) #All features should have a value of zero
#Helpful plot is the density plot. The density of the imputed data for each imputed dataset is showed
#in magenta while the density of the observed data is showed in blue.
#Again, under our previous assumptions we expect the distributions to be similar.
densityplot(x = imputed_data, data = ~ LBX028LA+LBX153LA+LBX189LA)
#Print off finished dataset
write_csv(finished_imputed_data, "finished_imputed_data.csv")
#This is where I need to use the finished_imputed_data to impute the values in the future years.

How can I get the spatial correlation between two datsets in r?

I have two arrays:
data1=array(-10:30, c(2160,1080,12))
data2=array(-20:30, c(2160,1080,12))
#Add in some NAs
ind <- which(data1 %in% sample(data1, 1500))
data1[ind] <- NA
One is modelled global gridded data (lon,lat,month) and the other, global gridded observations (lon,lat,month).
I want to assess how 'skillful' the modelled data is at recreating the obs. I think the best way to do this is with a spatial correlation between the datasets. How can I do that?
I tried a straightforward x<-cor(data1,data2) but that just returned x<-NA_real_.
Then I was thinking that I probably have to break it up by month or season. So, just looking at one month x<-cor(data1[,,1],data2[,,1]) it returned a matrix of size 1080*1080 (most of which are NAs).
How can I get a spatial correlation between these two datasets? i.e. I want to see where the modelled data performs 'well' i.e. has high correlation with observations, or where it does badly (low correlation with observations).

How to specify subset/ sample number for permutations using specaccum() in R's vegan package

I have a community matrix (species as columns, samples as rows) from which I would like to generate a species accumulation curve (SAC) using the specaccum() and fitspecaccum() functions in R's vegan package. In order for the resulting SAC and cumulative species richness at sample X to be comparable among regions (I have 1 community matrix per region), I need to have specaccum() choose the same number of sets within each region. My problem is that some regions have a larger number of sets than others. I would like to limit the sample size to the minimum number of sets among regions (in my case, the minimum number of sets is 45, so I would like specaccum() to randomly sample 45 sets, 100 times (set permutations=100) for each region. I would like to sample from the entire data set available for each region. The code below has not worked... it doesn't recognize "subset=45". The vegan package info says "subset" needs to be logical... I don't understand how subset number can be logical, but maybe I am misinterpreting what subset is... Is there another way to do this? Would it be sufficient to run specaccum() for the entire number of sets available for each region and then just truncate the output to 45?
require(vegan)
pool1<-specaccum(comm.matrix, gamma="jack1", method="random", subet=45, permutations=100)
Any help is much appreciated.

Why do you want to limit the function to work in a random sample of 45 cases? Just use the species accumulation up to 45 cases. Taking a random subset of 45 cases gives you the same accumulation, except for the random error of subsampling and throwing away information. If you want to compare your different cases, just compare them at the sample size that suits all cases, that is, at 45 or less. That is the idea of species accumulation models.
The subset is intended for situations where you have (possibly) heterogeneous collection of sampling units, and you want to stratify data. For instance, if you want to see only the species accumulation in the "OldLow" habitat type of the Barro Colorado data, you could do:
data(BCI, BCI.env)
plot(specaccum(BCI, subset = BCI.env$Habitat == "OldLow"))
If you want to have, say, a subset of 30 sample plots of the same data, you could do:
take <- c(rep(TRUE, 30), rep(FALSE, 20))
plot(specaccum(BCI)) # to see it all
# repeat the following to see how taking subset influences
lines(specaccum(BCI, subset = sample(take)), col = "blue")
If you repeat the last line, you see how taking random subset influences the results: the lines are normally within the error bars of all data, but differ from each other due to random error.

Time series forecasting, dealing with known big orders

I have many data sets with known outliers (big orders)
data <- matrix(c("08Q1","08Q2","08Q3","08Q4","09Q1","09Q2","09Q3","09Q4","10Q1","10Q2","10Q3","10Q4","11Q1","11Q2","11Q3","11Q4","12Q1","12Q2","12Q3","12Q4","13Q1","13Q2","13Q3","13Q4","14Q1","14Q2","14Q3","14Q4","15Q1", 155782698, 159463653.4, 172741125.6, 204547180, 126049319.8, 138648461.5, 135678842.1, 242568446.1, 177019289.3, 200397120.6, 182516217.1, 306143365.6, 222890269.2, 239062450.2, 229124263.2, 370575384.7, 257757410.5, 256125841.6, 231879306.6, 419580274, 268211059, 276378232.1, 261739468.7, 429127062.8, 254776725.6, 329429882.8, 264012891.6, 496745973.9, 284484362.55),ncol=2,byrow=FALSE)
The top 11 outliers of this specific series are:
outliers <- matrix(c("14Q4","14Q2","12Q1","13Q1","14Q2","11Q1","11Q4","14Q2","13Q4","14Q4","13Q1",20193525.68, 18319234.7, 12896323.62, 12718744.01, 12353002.09, 11936190.13, 11356476.28, 11351192.31, 10101527.85, 9723641.25, 9643214.018),ncol=2,byrow=FALSE)
What methods are there that i can forecast the time series taking these outliers into consideration?
I have already tried replacing the next biggest outlier (so running the data set 10 times replacing the outliers with the next biggest until the 10th data set has all the outliers replaced).
I have also tried simply removing the outliers (so again running the data set 10 times removing an outlier each time until all 10 are removed in the 10th data set)
I just want to point out that removing these big orders does not delete the data point completely as there are other deals that happen in that quarter
My code tests the data through multiple forecasting models (ARIMA weighted on the out sample, ARIMA weighted on the in sample, ARIMA weighted, ARIMA, Additive Holt-winters weighted and Multiplcative Holt-winters weighted) so it needs to be something that can be adapted to these multiple models.
Here are a couple more data sets that i used, i do not have the outliers for these series yet though
data <- matrix(c("08Q1","08Q2","08Q3","08Q4","09Q1","09Q2","09Q3","09Q4","10Q1","10Q2","10Q3","10Q4","11Q1","11Q2","11Q3","11Q4","12Q1","12Q2","12Q3","12Q4","13Q1","13Q2","13Q3","13Q4","14Q1","14Q2","14Q3", 26393.99306, 13820.5037, 23115.82432, 25894.41036, 14926.12574, 15855.8857, 21565.19002, 49373.89675, 27629.10141, 43248.9778, 34231.73851, 83379.26027, 54883.33752, 62863.47728, 47215.92508, 107819.9903, 53239.10602, 71853.5, 59912.7624, 168416.2995, 64565.6211, 94698.38748, 80229.9716, 169205.0023, 70485.55409, 133196.032, 78106.02227), ncol=2,byrow=FALSE)
data <- matrix(c("08Q1","08Q2","08Q3","08Q4","09Q1","09Q2","09Q3","09Q4","10Q1","10Q2","10Q3","10Q4","11Q1","11Q2","11Q3","11Q4","12Q1","12Q2","12Q3","12Q4","13Q1","13Q2","13Q3","13Q4","14Q1","14Q2","14Q3",3311.5124, 3459.15634, 2721.486863, 3286.51708, 3087.234059, 2873.810071, 2803.969394, 4336.4792, 4722.894582, 4382.349583, 3668.105825, 4410.45429, 4249.507839, 3861.148928, 3842.57616, 5223.671347, 5969.066896, 4814.551389, 3907.677816, 4944.283864, 4750.734617, 4440.221993, 3580.866991, 3942.253996, 3409.597269, 3615.729974, 3174.395507),ncol=2,byrow=FALSE)
If this is too complicated then an explanation of how, in R, once outliers are detected using certain commands, the data is dealt with to forecast. e.g smoothing etc and how i can approach that writing a code myself (not using the commands that detect outliers)

Your outliers appear to be seasonal variations with the largest orders appearing in the 4-th quarter. Many of the forecasting models you mentioned include the capability for seasonal adjustments. As an example, the simplest model could have a linear dependence on year with corrections for all seasons. Code would look like:
df <- data.frame(period= c("08Q1","08Q2","08Q3","08Q4","09Q1","09Q2","09Q3","09Q4","10Q1","10Q2","10Q3",
"10Q4","11Q1","11Q2","11Q3","11Q4","12Q1","12Q2","12Q3","12Q4","13Q1","13Q2",
"13Q3","13Q4","14Q1","14Q2","14Q3","14Q4","15Q1"),
order= c(155782698, 159463653.4, 172741125.6, 204547180, 126049319.8, 138648461.5,
135678842.1, 242568446.1, 177019289.3, 200397120.6, 182516217.1, 306143365.6,
222890269.2, 239062450.2, 229124263.2, 370575384.7, 257757410.5, 256125841.6,
231879306.6, 419580274, 268211059, 276378232.1, 261739468.7, 429127062.8, 254776725.6,
329429882.8, 264012891.6, 496745973.9, 42748656.73))
seasonal <- data.frame(year=as.numeric(substr(df$period, 1,2)), qtr=substr(df$period, 3,4), data=df$order)
ord_model <- lm(data ~ year + qtr, data=seasonal)
seasonal <- cbind(seasonal, fitted=ord_model$fitted)
library(reshape2)
library(ggplot2)
plot_fit <- melt(seasonal,id.vars=c("year", "qtr"), variable.name = "Source", value.name="Order" )
ggplot(plot_fit, aes(x=year, y = Order, colour = qtr, shape=Source)) + geom_point(size=3)
which gives the results shown in the chart below:
Models with a seasonal adjustment but nonlinear dependence upon year may give better fits.

You already said you tried different Arima-models, but as mentioned by WaltS, your series don't seem to contain big outliers, but a seasonal-component, which is nicely captured by auto.arima() in the forecast package:
myTs <- ts(as.numeric(data[,2]), start=c(2008, 1), frequency=4)
myArima <- auto.arima(myTs, lambda=0)
myForecast <- forecast(myArima)
plot(myForecast)
where the lambda=0 argument to auto.arima() forces a transformation (or you could take log) of the data by boxcox to take the increasing amplitude of the seasonal-component into account.

The approach you are trying to use to cleanse your data of outliers is not going to be robust enough to identify them. I should add that there is a free outlier package in R called tsoutliers, but it won't do the things I am about to show you....
You have an interesting time series here. The trend changes over time with the upward trend weakening a bit. If you bring in two time trend variables with the first beginning at 1 and another beginning at period 14 and forward you will capture this change. As for seasonality, you can capture the high 4th quarter with a dummy variable. The model is parsimonios as the other 3 quarters are not different from the average plus no need for an AR12, seasonal differencing or 3 seasonal dummies. You can also capture the impact of the last two observations being outliers with two dummy variables. Ignore the 49 above the word trend as that is just the name of the series being modeled.

Resources