library( irs990efile ) # functions for parsing efile XMLs
library( dplyr ) # data wrangling
library( purrr ) # data wrangling
library( pander ) # formatting
library( knitr ) # formatting
library( DT ) # table printing
library( httr ) # web requests
library( xmltools ) # xml utilities
library( xml2 ) # xml utilities
library( XML ) # xml utilities
library( data.tree ) # network visualization
library( networkD3 ) # network visualization
library( igraph ) # network visualization
source( "R/rdb-functions-v2.R")
source( "R/utils.R")head( index )The concordance is an RDB to XML Crosswalk that maps all xpaths onto a specified set of variables. It is located in the irs990efile package.
The full data dictionary is available on GitHub.
concordance %>%
filter( rdb_table == table.name )
| xpath | id |
|---|---|
| /Return/ReturnData/IRS990ScheduleJ/Form990ScheduleJPartII/BaseCompensationFilingOrg | 1 |
| /Return/ReturnData/IRS990ScheduleJ/Form990ScheduleJPartII/BonusFilingOrg | 2 |
| /Return/ReturnData/IRS990ScheduleJ/Form990ScheduleJPartII/BonusRelatedOrgs | 3 |
| /Return/ReturnData/IRS990ScheduleJ/Form990ScheduleJPartII/CompBasedOnRelatedOrgs | 4 |
| /Return/ReturnData/IRS990ScheduleJ/Form990ScheduleJPartII/CompReportPrior990FilingOrg | 5 |
| /Return/ReturnData/IRS990ScheduleJ/Form990ScheduleJPartII/CompReportPrior990RelatedOrgs | 6 |
| /Return/ReturnData/IRS990ScheduleJ/Form990ScheduleJPartII/DeferredCompFilingOrg | 7 |
| /Return/ReturnData/IRS990ScheduleJ/Form990ScheduleJPartII/DeferredCompRelatedOrgs | 8 |
| /Return/ReturnData/IRS990ScheduleJ/Form990ScheduleJPartII/NameBusiness/BusinessNameLine1 | 9 |
| /Return/ReturnData/IRS990ScheduleJ/Form990ScheduleJPartII/NameBusiness/BusinessNameLine2 | 10 |
| /Return/ReturnData/IRS990ScheduleJ/Form990ScheduleJPartII/NamePerson | 11 |
| /Return/ReturnData/IRS990ScheduleJ/Form990ScheduleJPartII/NontaxableBenefitsFilingOrg | 12 |
| /Return/ReturnData/IRS990ScheduleJ/Form990ScheduleJPartII/NontaxableBenefitsRelatedOrgs | 13 |
| /Return/ReturnData/IRS990ScheduleJ/Form990ScheduleJPartII/OtherCompensationFilingOrg | 14 |
| /Return/ReturnData/IRS990ScheduleJ/Form990ScheduleJPartII/OtherCompensationRelatedOrgs | 15 |
| /Return/ReturnData/IRS990ScheduleJ/Form990ScheduleJPartII/Title | 16 |
| /Return/ReturnData/IRS990ScheduleJ/Form990ScheduleJPartII/TotalCompensationFilingOrg | 17 |
| /Return/ReturnData/IRS990ScheduleJ/Form990ScheduleJPartII/TotalCompensationRelatedOrgs | 18 |
| /Return/ReturnData/IRS990ScheduleJ/RltdOrgOfficerTrstKeyEmplGrp/BaseCompensationFilingOrgAmt | 19 |
| /Return/ReturnData/IRS990ScheduleJ/RltdOrgOfficerTrstKeyEmplGrp/BonusFilingOrganizationAmount | 20 |
| /Return/ReturnData/IRS990ScheduleJ/RltdOrgOfficerTrstKeyEmplGrp/BonusRelatedOrganizationsAmt | 21 |
| /Return/ReturnData/IRS990ScheduleJ/RltdOrgOfficerTrstKeyEmplGrp/BusinessName/BusinessNameLine1 | 22 |
| /Return/ReturnData/IRS990ScheduleJ/RltdOrgOfficerTrstKeyEmplGrp/BusinessName/BusinessNameLine1Txt | 23 |
| /Return/ReturnData/IRS990ScheduleJ/RltdOrgOfficerTrstKeyEmplGrp/BusinessName/BusinessNameLine2 | 24 |
| /Return/ReturnData/IRS990ScheduleJ/RltdOrgOfficerTrstKeyEmplGrp/BusinessName/BusinessNameLine2Txt | 25 |
| /Return/ReturnData/IRS990ScheduleJ/RltdOrgOfficerTrstKeyEmplGrp/CompReportPrior990FilingOrgAmt | 26 |
| /Return/ReturnData/IRS990ScheduleJ/RltdOrgOfficerTrstKeyEmplGrp/CompReportPrior990RltdOrgsAmt | 27 |
| /Return/ReturnData/IRS990ScheduleJ/RltdOrgOfficerTrstKeyEmplGrp/CompensationBasedOnRltdOrgsAmt | 28 |
| /Return/ReturnData/IRS990ScheduleJ/RltdOrgOfficerTrstKeyEmplGrp/DeferredCompRltdOrgsAmt | 29 |
| /Return/ReturnData/IRS990ScheduleJ/RltdOrgOfficerTrstKeyEmplGrp/DeferredCompensationFlngOrgAmt | 30 |
| /Return/ReturnData/IRS990ScheduleJ/RltdOrgOfficerTrstKeyEmplGrp/NontaxableBenefitsFilingOrgAmt | 31 |
| /Return/ReturnData/IRS990ScheduleJ/RltdOrgOfficerTrstKeyEmplGrp/NontaxableBenefitsRltdOrgsAmt | 32 |
| /Return/ReturnData/IRS990ScheduleJ/RltdOrgOfficerTrstKeyEmplGrp/OtherCompensationFilingOrgAmt | 33 |
| /Return/ReturnData/IRS990ScheduleJ/RltdOrgOfficerTrstKeyEmplGrp/OtherCompensationRltdOrgsAmt | 34 |
| /Return/ReturnData/IRS990ScheduleJ/RltdOrgOfficerTrstKeyEmplGrp/PersonNm | 35 |
| /Return/ReturnData/IRS990ScheduleJ/RltdOrgOfficerTrstKeyEmplGrp/TitleTxt | 36 |
| /Return/ReturnData/IRS990ScheduleJ/RltdOrgOfficerTrstKeyEmplGrp/TotalCompensationFilingOrgAmt | 37 |
| /Return/ReturnData/IRS990ScheduleJ/RltdOrgOfficerTrstKeyEmplGrp/TotalCompensationRltdOrgsAmt | 38 |
xpaths <- as.character( t.xpaths$xpath )
el <- create_edgelist_v1( xpaths )
nd <- FromDataFrameNetwork( network=el )
print( nd )## levelName
## 1 Return
## 2 °--ReturnData
## 3 °--IRS990ScheduleJ
## 4 ¦--Form990ScheduleJPartII
## 5 ¦ ¦--BaseCompensationFilingOrg
## 6 ¦ ¦--BonusFilingOrg
## 7 ¦ ¦--BonusRelatedOrgs
## 8 ¦ ¦--CompBasedOnRelatedOrgs
## 9 ¦ ¦--CompReportPrior990FilingOrg
## 10 ¦ ¦--CompReportPrior990RelatedOrgs
## 11 ¦ ¦--DeferredCompFilingOrg
## 12 ¦ ¦--DeferredCompRelatedOrgs
## 13 ¦ ¦--NameBusiness
## 14 ¦ ¦ ¦--BusinessNameLine1
## 15 ¦ ¦ °--BusinessNameLine2
## 16 ¦ ¦--NamePerson
## 17 ¦ ¦--NontaxableBenefitsFilingOrg
## 18 ¦ ¦--NontaxableBenefitsRelatedOrgs
## 19 ¦ ¦--OtherCompensationFilingOrg
## 20 ¦ ¦--OtherCompensationRelatedOrgs
## 21 ¦ ¦--Title
## 22 ¦ ¦--TotalCompensationFilingOrg
## 23 ¦ °--TotalCompensationRelatedOrgs
## 24 °--RltdOrgOfficerTrstKeyEmplGrp
## 25 ¦--BaseCompensationFilingOrgAmt
## 26 ¦--BonusFilingOrganizationAmount
## 27 ¦--BonusRelatedOrganizationsAmt
## 28 ¦--BusinessName
## 29 ¦ ¦--BusinessNameLine1
## 30 ¦ ¦--BusinessNameLine1Txt
## 31 ¦ ¦--BusinessNameLine2
## 32 ¦ °--BusinessNameLine2Txt
## 33 ¦--CompReportPrior990FilingOrgAmt
## 34 ¦--CompReportPrior990RltdOrgsAmt
## 35 ¦--CompensationBasedOnRltdOrgsAmt
## 36 ¦--DeferredCompRltdOrgsAmt
## 37 ¦--DeferredCompensationFlngOrgAmt
## 38 ¦--NontaxableBenefitsFilingOrgAmt
## 39 ¦--NontaxableBenefitsRltdOrgsAmt
## 40 ¦--OtherCompensationFilingOrgAmt
## 41 ¦--OtherCompensationRltdOrgsAmt
## 42 ¦--PersonNm
## 43 ¦--TitleTxt
## 44 ¦--TotalCompensationFilingOrgAmt
## 45 °--TotalCompensationRltdOrgsAmtSetGraphStyle( nd, rankdir = "LR")
SetEdgeStyle( nd, arrowhead = "vee", color = "grey20", penwidth = 2 )
SetNodeStyle( nd,
style = "filled,rounded",
shape = "box",
fillcolor = "LightBlue",
fontname = "helvetica",
fontcolor="black",
tooltip = GetDefaultTooltip )
# SetNodeStyle(acme$IT, fillcolor = "LightBlue", penwidth = "5px")
plot( nd )# old version
find_group_names( table.name )## [1] "//Form990ScheduleJPartII" "//RltdOrgOfficerTrstKeyEmplGrp"# new version
find_table_headers( table.name )## [1] "//Form990ScheduleJPartII/NameBusiness"
## [2] "//Form990ScheduleJPartII/NamePerson"
## [3] "//Form990ScheduleJPartII/Title"
## [4] "//Form990ScheduleJPartII/BaseCompensationFilingOrg"
## [5] "//Form990ScheduleJPartII/CompBasedOnRelatedOrgs"
## [6] "//Form990ScheduleJPartII/BonusFilingOrg"
## [7] "//Form990ScheduleJPartII/BonusRelatedOrgs"
## [8] "//Form990ScheduleJPartII/OtherCompensationFilingOrg"
## [9] "//Form990ScheduleJPartII/OtherCompensationRelatedOrgs"
## [10] "//Form990ScheduleJPartII/DeferredCompFilingOrg"
## [11] "//Form990ScheduleJPartII/DeferredCompRelatedOrgs"
## [12] "//Form990ScheduleJPartII/NontaxableBenefitsFilingOrg"
## [13] "//Form990ScheduleJPartII/NontaxableBenefitsRelatedOrgs"
## [14] "//Form990ScheduleJPartII/TotalCompensationFilingOrg"
## [15] "//Form990ScheduleJPartII/TotalCompensationRelatedOrgs"
## [16] "//Form990ScheduleJPartII/CompReportPrior990FilingOrg"
## [17] "//Form990ScheduleJPartII/CompReportPrior990RelatedOrgs"
## [18] "//RltdOrgOfficerTrstKeyEmplGrp/BusinessName"
## [19] "//RltdOrgOfficerTrstKeyEmplGrp/PersonNm"
## [20] "//RltdOrgOfficerTrstKeyEmplGrp/TitleTxt"
## [21] "//RltdOrgOfficerTrstKeyEmplGrp/BaseCompensationFilingOrgAmt"
## [22] "//RltdOrgOfficerTrstKeyEmplGrp/CompensationBasedOnRltdOrgsAmt"
## [23] "//RltdOrgOfficerTrstKeyEmplGrp/BonusFilingOrganizationAmount"
## [24] "//RltdOrgOfficerTrstKeyEmplGrp/BonusRelatedOrganizationsAmt"
## [25] "//RltdOrgOfficerTrstKeyEmplGrp/OtherCompensationFilingOrgAmt"
## [26] "//RltdOrgOfficerTrstKeyEmplGrp/OtherCompensationRltdOrgsAmt"
## [27] "//RltdOrgOfficerTrstKeyEmplGrp/DeferredCompensationFlngOrgAmt"
## [28] "//RltdOrgOfficerTrstKeyEmplGrp/DeferredCompRltdOrgsAmt"
## [29] "//RltdOrgOfficerTrstKeyEmplGrp/NontaxableBenefitsFilingOrgAmt"
## [30] "//RltdOrgOfficerTrstKeyEmplGrp/NontaxableBenefitsRltdOrgsAmt"
## [31] "//RltdOrgOfficerTrstKeyEmplGrp/TotalCompensationFilingOrgAmt"
## [32] "//RltdOrgOfficerTrstKeyEmplGrp/TotalCompensationRltdOrgsAmt"
## [33] "//RltdOrgOfficerTrstKeyEmplGrp/CompReportPrior990FilingOrgAmt"
## [34] "//RltdOrgOfficerTrstKeyEmplGrp/CompReportPrior990RltdOrgsAmt"# manual
if( ! is.null(table.headers) )
{table.headers}
# create new folder
dir.create( folder.name )
setwd( folder.name )
# create sample
set.seed( 1234 )
sample.index <- sample_n( index, sample.size )
write.csv( index, "sample-index.csv", row.names=F )
sample.urls <- sample.index$URL
# erase existing log files
file.create("XPATH-LOG.txt")
file.create("FAIL-LOG.txt")
start.build.time <- Sys.time() # --------------------
results.list <- list()
xpath.list <- list()
for( i in 1:length( sample.urls ) )
{
url <- sample.urls[i]
results.list[[i]] <-
build_rdb_table_v2( url,
table.name,
table.headers=table.headers )
xpath.list[[i]] <-
get_table_xpaths( url,
table.name,
table.headers=table.headers )
if( i %% 100 == 0 ){ print(i) }
}
end.build.time <- Sys.time() # --------------------
df <- dplyr::bind_rows( results.list )
fail.log <- readLines( "FAIL-LOG.txt" )
all.xpaths <- xpath.list %>% unlist() %>% unique() %>% sort()
cat( all.xpaths, sep="\n", file="XPATH-LOG.txt" )TABLE: SJ-P02-T01-COMPENSATION-DTK
## [1] "NUMBER OF RETURNS PROCESSED: 1000"
## [1] "TOTAL NUMBER OF TABLE ROWS: 4008"TOTAL RUN TIME:
## Time difference of 35.85313 mins
## Time difference of -0.5975521 hourswrite.csv( df, paste0( folder.name, "/", table.name, ".csv" ), row.names=F )
head(df) Are all names standardized?
names(df)## [1] "OBJECT_ID" "EIN"
## [3] "NAME" "TAXYR"
## [5] "FORMTYPE" "URL"
## [7] "SJ_02_COMP_DTK_NAME_PERS" "SJ_02_COMP_DTK_TITLE"
## [9] "SJ_02_COMP_DTK_BASE_ORG" "SJ_02_COMP_DTK_BASE_RLTD"
## [11] "SJ_02_COMP_DTK_BONUS_ORG" "SJ_02_COMP_DTK_BONUS_RLTD"
## [13] "SJ_02_COMP_DTK_OTH_ORG" "SJ_02_COMP_DTK_OTH_RLTD"
## [15] "SJ_02_COMP_DTK_DEFERRED_ORG" "SJ_02_COMP_DTK_DEFERRED_RLTD"
## [17] "SJ_02_COMP_DTK_BENFIT_ORG" "SJ_02_COMP_DTK_BENFIT_RLTD"
## [19] "SJ_02_COMP_DTK_TOT_ORG" "SJ_02_COMP_DTK_TOT_RLTD"
## [21] "SJ_02_COMP_DTK_PRIOR_990_ORG" "SJ_02_COMP_DTK_PRIOR_990_RLTD"
## [23] "SJ_02_COMP_DTK_NAME_ORG_L1"
Check for xpaths that were used in the tables but do not exist in the Concordance file.
c.table <- dplyr::filter( concordance, rdb_table == table.name )
xpath.concordance <- c.table$xpath
setdiff( all.xpaths, xpath.concordance )## [1] ""
## [2] "/Return/ReturnData/IRS990ScheduleJ/RltdOrgOfficerTrstKeyEmplGrp/BusinessName"Capture to update the Concordance file.
these <- setdiff( all.xpaths, xpath.concordance )
cat( these, sep="\n", file=paste0( folder.name, "/MISSING-XPATHS.txt" ) )Check the status of failed URLs.
if( length(fail.log) > 0 )
{
sapply( fail.log, get_message ) %>%
table() %>%
pander()
} else {
print("ALL URLs ARE VALID")
}## [1] "ALL URLs ARE VALID"
The create_edgelist() functions v1 and v2 are in R/utils.R.
V1 retains the root nodes Return and ReturnData.
V2 drops the root nodes and uses form versions “990” and “990EZ” as the root to visualize the sets of tables separately.
# KEEP ROOT NOTES Return & ReturnData
el <- create_edgelist_v1( all.xpaths )Edgelist format:
| V1 | V2 |
|---|---|
| Return | ReturnData |
| ReturnData | IRS990 |
| IRS990 | Form990PartVIISectionAGrp |
| Form990PartVIISectionAGrp | PersonNm |
| Form990PartVIISectionAGrp | TitleTxt |
| Form990PartVIISectionAGrp | AverageHoursPerWeekRt |
| Form990PartVIISectionAGrp | IndividualTrusteeOrDirectorInd |
| Form990PartVIISectionAGrp | OfficerInd |
| Form990PartVIISectionAGrp | ReportableCompFromOrgAmt |
| Form990PartVIISectionAGrp | ReportableCompFromRltdOrgAmt |
# library( data.tree )
nd <- FromDataFrameNetwork( network=el )
print( nd )## levelName
## 1 Return
## 2 °--ReturnData
## 3 °--IRS990ScheduleJ
## 4 °--RltdOrgOfficerTrstKeyEmplGrp
## 5 ¦--BaseCompensationFilingOrgAmt
## 6 ¦--BonusFilingOrganizationAmount
## 7 ¦--BonusRelatedOrganizationsAmt
## 8 ¦--BusinessName
## 9 ¦ °--BusinessNameLine1Txt
## 10 ¦--CompensationBasedOnRltdOrgsAmt
## 11 ¦--CompReportPrior990FilingOrgAmt
## 12 ¦--CompReportPrior990RltdOrgsAmt
## 13 ¦--DeferredCompensationFlngOrgAmt
## 14 ¦--DeferredCompRltdOrgsAmt
## 15 ¦--NontaxableBenefitsFilingOrgAmt
## 16 ¦--NontaxableBenefitsRltdOrgsAmt
## 17 ¦--OtherCompensationFilingOrgAmt
## 18 ¦--OtherCompensationRltdOrgsAmt
## 19 ¦--PersonNm
## 20 ¦--TitleTxt
## 21 ¦--TotalCompensationFilingOrgAmt
## 22 °--TotalCompensationRltdOrgsAmtSetGraphStyle( nd, rankdir = "LR")
SetEdgeStyle( nd, arrowhead = "vee", color = "grey20", penwidth = 2 )
SetNodeStyle( nd,
style = "filled,rounded",
shape = "box",
fillcolor = "LightBlue",
fontname = "helvetica",
fontcolor="black",
tooltip = GetDefaultTooltip )
# SetNodeStyle(acme$IT, fillcolor = "LightBlue", penwidth = "5px")
plot( nd )# library( networkD3 )
# net <- ToDataFrameNetwork( nd, "name" )
# simpleNetwork( net, fontSize = 12 )
simpleNetwork( el, fontSize = 12 )#plot with networkD3
radnet <- ToListExplicit( nd, unname = TRUE )
radialNetwork( radnet, fontSize = 12 )
t.xpaths <-
concordance %>%
filter( rdb_table == table.name ) %>%
select( xpath ) %>%
unique() %>%
arrange( xpath ) %>%
mutate( id=row_number() )
t.xpaths %>%
kable( align="l" )| xpath | id |
|---|---|
| /Return/ReturnData/IRS990ScheduleJ/Form990ScheduleJPartII/BaseCompensationFilingOrg | 1 |
| /Return/ReturnData/IRS990ScheduleJ/Form990ScheduleJPartII/BonusFilingOrg | 2 |
| /Return/ReturnData/IRS990ScheduleJ/Form990ScheduleJPartII/BonusRelatedOrgs | 3 |
| /Return/ReturnData/IRS990ScheduleJ/Form990ScheduleJPartII/CompBasedOnRelatedOrgs | 4 |
| /Return/ReturnData/IRS990ScheduleJ/Form990ScheduleJPartII/CompReportPrior990FilingOrg | 5 |
| /Return/ReturnData/IRS990ScheduleJ/Form990ScheduleJPartII/CompReportPrior990RelatedOrgs | 6 |
| /Return/ReturnData/IRS990ScheduleJ/Form990ScheduleJPartII/DeferredCompFilingOrg | 7 |
| /Return/ReturnData/IRS990ScheduleJ/Form990ScheduleJPartII/DeferredCompRelatedOrgs | 8 |
| /Return/ReturnData/IRS990ScheduleJ/Form990ScheduleJPartII/NameBusiness/BusinessNameLine1 | 9 |
| /Return/ReturnData/IRS990ScheduleJ/Form990ScheduleJPartII/NameBusiness/BusinessNameLine2 | 10 |
| /Return/ReturnData/IRS990ScheduleJ/Form990ScheduleJPartII/NamePerson | 11 |
| /Return/ReturnData/IRS990ScheduleJ/Form990ScheduleJPartII/NontaxableBenefitsFilingOrg | 12 |
| /Return/ReturnData/IRS990ScheduleJ/Form990ScheduleJPartII/NontaxableBenefitsRelatedOrgs | 13 |
| /Return/ReturnData/IRS990ScheduleJ/Form990ScheduleJPartII/OtherCompensationFilingOrg | 14 |
| /Return/ReturnData/IRS990ScheduleJ/Form990ScheduleJPartII/OtherCompensationRelatedOrgs | 15 |
| /Return/ReturnData/IRS990ScheduleJ/Form990ScheduleJPartII/Title | 16 |
| /Return/ReturnData/IRS990ScheduleJ/Form990ScheduleJPartII/TotalCompensationFilingOrg | 17 |
| /Return/ReturnData/IRS990ScheduleJ/Form990ScheduleJPartII/TotalCompensationRelatedOrgs | 18 |
| /Return/ReturnData/IRS990ScheduleJ/RltdOrgOfficerTrstKeyEmplGrp/BaseCompensationFilingOrgAmt | 19 |
| /Return/ReturnData/IRS990ScheduleJ/RltdOrgOfficerTrstKeyEmplGrp/BonusFilingOrganizationAmount | 20 |
| /Return/ReturnData/IRS990ScheduleJ/RltdOrgOfficerTrstKeyEmplGrp/BonusRelatedOrganizationsAmt | 21 |
| /Return/ReturnData/IRS990ScheduleJ/RltdOrgOfficerTrstKeyEmplGrp/BusinessName/BusinessNameLine1 | 22 |
| /Return/ReturnData/IRS990ScheduleJ/RltdOrgOfficerTrstKeyEmplGrp/BusinessName/BusinessNameLine1Txt | 23 |
| /Return/ReturnData/IRS990ScheduleJ/RltdOrgOfficerTrstKeyEmplGrp/BusinessName/BusinessNameLine2 | 24 |
| /Return/ReturnData/IRS990ScheduleJ/RltdOrgOfficerTrstKeyEmplGrp/BusinessName/BusinessNameLine2Txt | 25 |
| /Return/ReturnData/IRS990ScheduleJ/RltdOrgOfficerTrstKeyEmplGrp/CompReportPrior990FilingOrgAmt | 26 |
| /Return/ReturnData/IRS990ScheduleJ/RltdOrgOfficerTrstKeyEmplGrp/CompReportPrior990RltdOrgsAmt | 27 |
| /Return/ReturnData/IRS990ScheduleJ/RltdOrgOfficerTrstKeyEmplGrp/CompensationBasedOnRltdOrgsAmt | 28 |
| /Return/ReturnData/IRS990ScheduleJ/RltdOrgOfficerTrstKeyEmplGrp/DeferredCompRltdOrgsAmt | 29 |
| /Return/ReturnData/IRS990ScheduleJ/RltdOrgOfficerTrstKeyEmplGrp/DeferredCompensationFlngOrgAmt | 30 |
| /Return/ReturnData/IRS990ScheduleJ/RltdOrgOfficerTrstKeyEmplGrp/NontaxableBenefitsFilingOrgAmt | 31 |
| /Return/ReturnData/IRS990ScheduleJ/RltdOrgOfficerTrstKeyEmplGrp/NontaxableBenefitsRltdOrgsAmt | 32 |
| /Return/ReturnData/IRS990ScheduleJ/RltdOrgOfficerTrstKeyEmplGrp/OtherCompensationFilingOrgAmt | 33 |
| /Return/ReturnData/IRS990ScheduleJ/RltdOrgOfficerTrstKeyEmplGrp/OtherCompensationRltdOrgsAmt | 34 |
| /Return/ReturnData/IRS990ScheduleJ/RltdOrgOfficerTrstKeyEmplGrp/PersonNm | 35 |
| /Return/ReturnData/IRS990ScheduleJ/RltdOrgOfficerTrstKeyEmplGrp/TitleTxt | 36 |
| /Return/ReturnData/IRS990ScheduleJ/RltdOrgOfficerTrstKeyEmplGrp/TotalCompensationFilingOrgAmt | 37 |
| /Return/ReturnData/IRS990ScheduleJ/RltdOrgOfficerTrstKeyEmplGrp/TotalCompensationRltdOrgsAmt | 38 |
Identify all unique groups used in xpaths.
if( is.null(table.headers) )
{ find_table_headers( table.name ) } else
table.headers## [1] "//Form990ScheduleJPartII/NameBusiness"
## [2] "//Form990ScheduleJPartII/NamePerson"
## [3] "//Form990ScheduleJPartII/Title"
## [4] "//Form990ScheduleJPartII/BaseCompensationFilingOrg"
## [5] "//Form990ScheduleJPartII/CompBasedOnRelatedOrgs"
## [6] "//Form990ScheduleJPartII/BonusFilingOrg"
## [7] "//Form990ScheduleJPartII/BonusRelatedOrgs"
## [8] "//Form990ScheduleJPartII/OtherCompensationFilingOrg"
## [9] "//Form990ScheduleJPartII/OtherCompensationRelatedOrgs"
## [10] "//Form990ScheduleJPartII/DeferredCompFilingOrg"
## [11] "//Form990ScheduleJPartII/DeferredCompRelatedOrgs"
## [12] "//Form990ScheduleJPartII/NontaxableBenefitsFilingOrg"
## [13] "//Form990ScheduleJPartII/NontaxableBenefitsRelatedOrgs"
## [14] "//Form990ScheduleJPartII/TotalCompensationFilingOrg"
## [15] "//Form990ScheduleJPartII/TotalCompensationRelatedOrgs"
## [16] "//Form990ScheduleJPartII/CompReportPrior990FilingOrg"
## [17] "//Form990ScheduleJPartII/CompReportPrior990RelatedOrgs"
## [18] "//RltdOrgOfficerTrstKeyEmplGrp/BusinessName"
## [19] "//RltdOrgOfficerTrstKeyEmplGrp/PersonNm"
## [20] "//RltdOrgOfficerTrstKeyEmplGrp/TitleTxt"
## [21] "//RltdOrgOfficerTrstKeyEmplGrp/BaseCompensationFilingOrgAmt"
## [22] "//RltdOrgOfficerTrstKeyEmplGrp/CompensationBasedOnRltdOrgsAmt"
## [23] "//RltdOrgOfficerTrstKeyEmplGrp/BonusFilingOrganizationAmount"
## [24] "//RltdOrgOfficerTrstKeyEmplGrp/BonusRelatedOrganizationsAmt"
## [25] "//RltdOrgOfficerTrstKeyEmplGrp/OtherCompensationFilingOrgAmt"
## [26] "//RltdOrgOfficerTrstKeyEmplGrp/OtherCompensationRltdOrgsAmt"
## [27] "//RltdOrgOfficerTrstKeyEmplGrp/DeferredCompensationFlngOrgAmt"
## [28] "//RltdOrgOfficerTrstKeyEmplGrp/DeferredCompRltdOrgsAmt"
## [29] "//RltdOrgOfficerTrstKeyEmplGrp/NontaxableBenefitsFilingOrgAmt"
## [30] "//RltdOrgOfficerTrstKeyEmplGrp/NontaxableBenefitsRltdOrgsAmt"
## [31] "//RltdOrgOfficerTrstKeyEmplGrp/TotalCompensationFilingOrgAmt"
## [32] "//RltdOrgOfficerTrstKeyEmplGrp/TotalCompensationRltdOrgsAmt"
## [33] "//RltdOrgOfficerTrstKeyEmplGrp/CompReportPrior990FilingOrgAmt"
## [34] "//RltdOrgOfficerTrstKeyEmplGrp/CompReportPrior990RltdOrgsAmt"Groups can then be used to extract the 1:M RDB tables:
if( is.null(table.headers) )
{ table.headers <- find_table_headers( table.name ) }
demo.url <- "https://nccs-efile.s3.us-east-1.amazonaws.com/xml/201913079349300206_public.xml"
doc <- xml2::read_xml( demo.url )
xml2::xml_ns_strip( doc )
df.demo <- get_table_v2( doc, table.name, table.headers )
df.demo ## NULLMapping of xml variable names to concordance variable names:
get_var_map( table.name=table.name )A table with proper names:
v.map <- get_var_map( table.name=table.name )
if( ! is.null(df.demo) )
{re_name( df.demo, v.map ) %>% as.data.frame()}
Demo of functions - demo data only.
[[1]]
<Form990PartVIISectionAGrp>
<PersonNm>
{text}
<TitleTxt>
{text}
<AverageHoursPerWeekRt>
{text}
<IndividualTrusteeOrDirectorInd>
{text}
<OfficerInd>
{text}
<ReportableCompFromOrgAmt>
{text}
<ReportableCompFromRltdOrgAmt>
{text}
<OtherCompensationAmt>
{text}node.list[[1]] %>% xml_parent() %>% xmltools::xml_view_trees() (1) ------------
+-- Form990PartVIISectionAGrp
+-- PersonNm
+-- TitleTxt
+-- AverageHoursPerWeekRt
+-- IndividualTrusteeOrDirectorInd
+-- OfficerInd
+-- ReportableCompFromOrgAmt
+-- ReportableCompFromRltdOrgAmt
++-- OtherCompensationAmt
(2) ------------
+-- Form990PartVIISectionAGrp
+-- PersonNm
+-- TitleTxt
+-- AverageHoursPerWeekRt
+-- IndividualTrusteeOrDirectorInd
+-- OfficerInd
+-- ReportableCompFromOrgAmt
+-- ReportableCompFromRltdOrgAmt
++-- OtherCompensationAmt