adding tests

NAMESPACE

@@ -21,6 +21,7 @@ export(integrity.check)
 export(itrends)
 export(live.map)
 export(mtrends)
+export(nullify.data)
 export(plt.SIR.model)
 export(preProcessingData)
 export(report.summary)
@@ -70,6 +71,7 @@ importFrom(rentrez,entrez_search)
 importFrom(rentrez,entrez_summary)
 importFrom(rentrez,extract_from_esummary)
 importFrom(stats,Gamma)
+importFrom(stats,complete.cases)
 importFrom(stats,glm)
 importFrom(stats,lm)
 importFrom(stats,na.omit)

R/covid19_checks.R

@@ -64,7 +64,7 @@ integrity.check <- function(data, datasetName="", disclose=FALSE, recommend=TRUE
 
 			if  ( sum(condn, na.rm=TRUE) !=0 ) {
 				warning("number of 'active+recovered+deaths' cases does NOT match the number of 'confirmed' cases!",'\n',
-					'\t',"on ", length(which(condn))," entries -- ", which(condn), '\n',
+					'\t',"on ", length(which(condn))," entries -- ", paste(which(condn),collapse=' '), '\n',
 					'\t ||  ',paste(colnames(data),collapse='  '),'\n',
 					"  ", paste(which(condn),collapse=' '), ' || ', paste(data[which(condn),],collapse='  '))
 				disclose.entries <- c(disclose.entries, which(condn))
@@ -197,7 +197,7 @@ nullify.data <- function(data,stringent=FALSE) {
 
 	orig.recs <- nrow(data)
 	# aggregated data-type
-	susp.entries <- integrity.check(data, datasetName, disclose=TRUE, recommend=FALSE)
+	susp.entries <- integrity.check(data, disclose=TRUE, recommend=FALSE)
 
 	susp.recs <- length(susp.entries)
 	if (susp.recs > 0) {

tests/testthat.R

@@ -0,0 +1,4 @@
+library(testthat)
+library(covid19.analytics)
+
+test_check("covid19.analytics")

tests/testthat/covid19_checks_tests.R

@@ -0,0 +1,12 @@
+test.data.checks <- function() {
+datasets <- c("TS-all","TS-confirmed","TS-confirmed-US","TS-Toronto","aggregated")
+
+for (i in datasets) {
+	print(i)
+	data <- covid19.data(i)
+	nullify.data(data)
+	nullify.data(data, stringent=TRUE)
+	print(paste(rep("#",80),collapse=''))
+}
+
+}

tests/testthat/test_examples.R

@@ -0,0 +1,200 @@
+# TESTS SET for the covid19.analytics package
+# M.Ponce
+
+
+#############################################
+############  DATA  RETRIEVAL  ##############
+#############################################
+test_that("Data Retrieval", {
+
+	loc.data <- c(F,T)
+
+	for (repo in loc.data) {
+		# WORLD DATA
+		# aggregated
+		agg.data <- covid19.data("aggregated", local.data=repo)
+		expect_s3_class(agg.data,"data.frame")
+
+		# TS
+		ts.data <- covid19.data("ts-ALL", local.data=repo)
+		expect_s3_class(ts.data,"data.frame")
+
+		# ALL
+		all.data <- covid19.data("ALL", local.data=repo)
+		expect_type(all.data,"list")
+	}
+
+	# Toronto Data
+        # original data type
+        expect_type(covid19.Toronto.data("original"), "list")
+
+        # TS Toronto data
+        tor.data <- covid19.Toronto.data()
+        expect_s3_class(tor.data,"data.frame")
+
+	# US data
+	us.data <- covid19.US.data()
+	expect_s3_class(us.data,"data.frame")
+})
+
+
+#####################################################################
+
+### Toronto Data
+
+test_that("Toronto Data", {
+	# TS Toronto data
+	tor.data <- covid19.Toronto.data()
+	expect_s3_class(tor.data,"data.frame")
+
+	# TRENDS
+	# single trend
+	st.Tor <- unique(tor.data$status)
+	for (i in st.Tor) {
+		expect_warning(single.trend(tor.data[tor.data$status == i,], info=i))
+	}
+
+	# Multiple trends
+	expect_output(mtrends(tor.data))
+})
+
+
+#####################################################################
+
+### Integrity/Consistencies tests
+
+test_that("integrity/consistency", {
+	source("covid19_checks_tests.R")
+	expect_warning(test.data.checks())
+})
+
+#####################################################################
+
+
+### TOTS.PER.LOCATION()
+
+test_that("TOTS.PER.LOCATION fn", {
+	cases <- c("confirmed","deaths","recovered")
+
+	for (i in seq_along(cases)) {
+		i.case <- cases[i]
+		header("",paste('processing ',i.case))
+
+		# read the time series data for confirmed cases
+		all.data <- covid19.data(paste0('ts-',i.case))
+		expect_s3_class(all.data,"data.frame")
+
+		# run on all the cases
+		#pdf(paste0("Japan_",i.case,".pdf"))
+		expect_invisible(tots.per.location(all.data,"Japan"))
+		#dev.off()
+
+	}
+})
+
+
+### GROWTH.RATE()
+test_that("GROWTH.RATE fn", {
+	# read time series data for confirmed cases
+	TS.data <- covid19.data("ts-confirmed")
+	expect_s3_class(TS.data,"data.frame")
+
+	locs <- c("Hubei","Italy","Germany","Canada")
+	for (i in seq_along(locs)) {
+		i.loc <- locs[i]
+
+		print(i.loc)
+
+		# compute changes and growth rates per location for 'Italy'
+		#pdf(paste0("gr-changes_",i.loc,".pdf"))
+		expect_output( growth.rate(TS.data,geo.loc=i.loc) )
+		#dev.off()
+
+	}
+})
+
+
+test_that("GROWTH.RATE fn with more cases...", {
+	# obtain Time Series data
+	TSconfirmed <- covid19.data("ts-confirmed")
+
+	# explore different combinations of regions/cities/countries
+	# when combining different locations heatmaps will also be generated comparing the trends among these locations
+	expect_output( growth.rate(TSconfirmed,geo.loc=c("Italy","Canada","Ontario","Quebec","Uruguay")) )
+
+	expect_output( growth.rate(TSconfirmed,geo.loc=c("Hubei","Italy","Spain","United States","Canada","Ontario","Quebec","Uruguay")) )
+
+	expect_output( growth.rate(TSconfirmed,geo.loc=c("Hubei","Italy","Spain","US","Canada","Ontario","Quebec","Uruguay")) )
+})
+
+
+##########################################################################
+
+
+########### REPORTS ##############
+
+test_that("REPORTS ...", {
+	expect_output(report.summary(graphical.output=FALSE))
+
+	expect_output(report.summary(graphical.output=FALSE, saveReport=TRUE) )
+})
+
+###########################################################################
+
+#### INTERACTIVE PLOTS
+# retrieve time series data
+TS.data <- covid19.data("ts-ALL")
+
+# static and interactive plot 
+totals.plt(TS.data, interactive.display=FALSE)
+
+
+# retrieve aggregated data
+data <- covid19.data("aggregated")
+
+# interactive map of aggregated cases -- with more spatial resolution
+live.map(data, interactive.display=FALSE)
+
+# or
+live.map(interactive.display=FALSE)
+
+# interactive map of the time series data of the confirmed cases with less spatial resolution, ie. aggregated by country
+live.map(covid19.data("ts-confirmed"), interactive.display=FALSE)
+
+
+
+#### SIR MODEL
+# read time series data for confirmed cases
+data <- covid19.data("ts-confirmed")
+
+# run a SIR model for a given geographical location
+generate.SIR.model(data,"Hubei", t0=1,t1=15)
+generate.SIR.model(data,"Germany",tot.population=83149300)
+generate.SIR.model(data,"Uruguay", tot.population=3500000)
+generate.SIR.model(data,"Ontario",tot.population=14570000)
+
+# the function will agregate data for a geographical location, like a country with multiple entries
+generate.SIR.model(data,"Canada",tot.population=37590000)
+
+# modelling the spread for the whole world, storing the model and generating an interactive visualization
+world.SIR.model <- generate.SIR.model(data,"ALL", t0=1,t1=15, tot.population=7.8e9, staticPlt=FALSE)
+# plotting and visualizing the model
+plt.SIR.model(world.SIR.model,"World",interactiveFig=FALSE,fileName="world.SIR.model")
+
+
+
+####
+# clean up
+# use a variable "covid19analytics.test.DONT.cleanup" to don't delete files
+
+#if(!("covid19analytics.test.DONT.cleanup" %in% ls())) {
+if (FALSE) {
+	rm.file.tps <- c("txt","pdf") 
+	for (tp in rm.file.tps)
+		for (fl in dir(pattern=tp)) {
+			message("clean-up: removing",fl)
+			file.remove(fl)
+		}
+}
+
+####