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/IRS990ScheduleK/Form990ScheduleKPartII/AdequateBooksAndRecdsMaintaind | 1 |
| /Return/ReturnData/IRS990ScheduleK/Form990ScheduleKPartII/AdvanceRefunding | 2 |
| /Return/ReturnData/IRS990ScheduleK/Form990ScheduleKPartII/AmountBondDefeased | 3 |
| /Return/ReturnData/IRS990ScheduleK/Form990ScheduleKPartII/AmountDefeased | 4 |
| /Return/ReturnData/IRS990ScheduleK/Form990ScheduleKPartII/AmountInReserveFund | 5 |
| /Return/ReturnData/IRS990ScheduleK/Form990ScheduleKPartII/AmountRetired | 6 |
| /Return/ReturnData/IRS990ScheduleK/Form990ScheduleKPartII/AmountUnspent | 7 |
| /Return/ReturnData/IRS990ScheduleK/Form990ScheduleKPartII/BondReferenceCd | 8 |
| /Return/ReturnData/IRS990ScheduleK/Form990ScheduleKPartII/CapitalExpenditures | 9 |
| /Return/ReturnData/IRS990ScheduleK/Form990ScheduleKPartII/CapitalizedInterest | 10 |
| /Return/ReturnData/IRS990ScheduleK/Form990ScheduleKPartII/CreditEnhancement | 11 |
| /Return/ReturnData/IRS990ScheduleK/Form990ScheduleKPartII/CurrentRefunding | 12 |
| /Return/ReturnData/IRS990ScheduleK/Form990ScheduleKPartII/FinalAllocationMade | 13 |
| /Return/ReturnData/IRS990ScheduleK/Form990ScheduleKPartII/IssuanceCostsFromProceeds | 14 |
| /Return/ReturnData/IRS990ScheduleK/Form990ScheduleKPartII/OtherSpentProceeds | 15 |
| /Return/ReturnData/IRS990ScheduleK/Form990ScheduleKPartII/RefundingEscrow | 16 |
| /Return/ReturnData/IRS990ScheduleK/Form990ScheduleKPartII/TotalProceeds | 17 |
| /Return/ReturnData/IRS990ScheduleK/Form990ScheduleKPartII/WorkingCapitalExpenditures | 18 |
| /Return/ReturnData/IRS990ScheduleK/Form990ScheduleKPartII/YearOfSubstCompletion | 19 |
| /Return/ReturnData/IRS990ScheduleK/TaxExemptBondsProceedsGrp/AdequateBooksAndRecMaintInd | 20 |
| /Return/ReturnData/IRS990ScheduleK/TaxExemptBondsProceedsGrp/AdvanceRefundingInd | 21 |
| /Return/ReturnData/IRS990ScheduleK/TaxExemptBondsProceedsGrp/BondDefeasedAmt | 22 |
| /Return/ReturnData/IRS990ScheduleK/TaxExemptBondsProceedsGrp/BondReferenceCd | 23 |
| /Return/ReturnData/IRS990ScheduleK/TaxExemptBondsProceedsGrp/CapitalExpendituresAmt | 24 |
| /Return/ReturnData/IRS990ScheduleK/TaxExemptBondsProceedsGrp/CapitalizedInterestAmt | 25 |
| /Return/ReturnData/IRS990ScheduleK/TaxExemptBondsProceedsGrp/CreditEnhancementAmt | 26 |
| /Return/ReturnData/IRS990ScheduleK/TaxExemptBondsProceedsGrp/CurrentRefundingInd | 27 |
| /Return/ReturnData/IRS990ScheduleK/TaxExemptBondsProceedsGrp/FinalAllocationMadeInd | 28 |
| /Return/ReturnData/IRS990ScheduleK/TaxExemptBondsProceedsGrp/InReserveFundAmt | 29 |
| /Return/ReturnData/IRS990ScheduleK/TaxExemptBondsProceedsGrp/IssuanceCostsFromProceedsAmt | 30 |
| /Return/ReturnData/IRS990ScheduleK/TaxExemptBondsProceedsGrp/OtherSpentProceedsAmt | 31 |
| /Return/ReturnData/IRS990ScheduleK/TaxExemptBondsProceedsGrp/RefundingEscrowAmt | 32 |
| /Return/ReturnData/IRS990ScheduleK/TaxExemptBondsProceedsGrp/RetiredAmt | 33 |
| /Return/ReturnData/IRS990ScheduleK/TaxExemptBondsProceedsGrp/SubstantialCompletionYr | 34 |
| /Return/ReturnData/IRS990ScheduleK/TaxExemptBondsProceedsGrp/TotalProceedsAmt | 35 |
| /Return/ReturnData/IRS990ScheduleK/TaxExemptBondsProceedsGrp/UnspentAmt | 36 |
| /Return/ReturnData/IRS990ScheduleK/TaxExemptBondsProceedsGrp/WorkingCapitalExpendituresAmt | 37 |
xpaths <- as.character( t.xpaths$xpath )
el <- create_edgelist_v1( xpaths )
nd <- FromDataFrameNetwork( network=el )
print( nd )## levelName
## 1 Return
## 2 °--ReturnData
## 3 °--IRS990ScheduleK
## 4 ¦--Form990ScheduleKPartII
## 5 ¦ ¦--AdequateBooksAndRecdsMaintaind
## 6 ¦ ¦--AdvanceRefunding
## 7 ¦ ¦--AmountBondDefeased
## 8 ¦ ¦--AmountDefeased
## 9 ¦ ¦--AmountInReserveFund
## 10 ¦ ¦--AmountRetired
## 11 ¦ ¦--AmountUnspent
## 12 ¦ ¦--BondReferenceCd
## 13 ¦ ¦--CapitalExpenditures
## 14 ¦ ¦--CapitalizedInterest
## 15 ¦ ¦--CreditEnhancement
## 16 ¦ ¦--CurrentRefunding
## 17 ¦ ¦--FinalAllocationMade
## 18 ¦ ¦--IssuanceCostsFromProceeds
## 19 ¦ ¦--OtherSpentProceeds
## 20 ¦ ¦--RefundingEscrow
## 21 ¦ ¦--TotalProceeds
## 22 ¦ ¦--WorkingCapitalExpenditures
## 23 ¦ °--YearOfSubstCompletion
## 24 °--TaxExemptBondsProceedsGrp
## 25 ¦--AdequateBooksAndRecMaintInd
## 26 ¦--AdvanceRefundingInd
## 27 ¦--BondDefeasedAmt
## 28 ¦--BondReferenceCd
## 29 ¦--CapitalExpendituresAmt
## 30 ¦--CapitalizedInterestAmt
## 31 ¦--CreditEnhancementAmt
## 32 ¦--CurrentRefundingInd
## 33 ¦--FinalAllocationMadeInd
## 34 ¦--InReserveFundAmt
## 35 ¦--IssuanceCostsFromProceedsAmt
## 36 ¦--OtherSpentProceedsAmt
## 37 ¦--RefundingEscrowAmt
## 38 ¦--RetiredAmt
## 39 ¦--SubstantialCompletionYr
## 40 ¦--TotalProceedsAmt
## 41 ¦--UnspentAmt
## 42 °--WorkingCapitalExpendituresAmtSetGraphStyle( nd, rankdir = "LR")
SetEdgeStyle( nd, arrowhead = "vee", color = "grey20", penwidth = 2 )
SetNodeStyle( nd,
style = "filled,rounded",
shape = "box",
fillcolor = "LightBlue",
fontname = "helvetica",
fontcolor="black",
tooltip = GetDefaultTooltip )
# SetNodeStyle(acme$IT, fillcolor = "LightBlue", penwidth = "5px")
plot( nd )# old version
find_group_names( table.name )## [1] "//Form990ScheduleKPartII" "//TaxExemptBondsProceedsGrp"# new version
find_table_headers( table.name )## [1] "//Form990ScheduleKPartII/BondReferenceCd"
## [2] "//Form990ScheduleKPartII/AmountRetired"
## [3] "//Form990ScheduleKPartII/AmountBondDefeased"
## [4] "//Form990ScheduleKPartII/AmountDefeased"
## [5] "//Form990ScheduleKPartII/TotalProceeds"
## [6] "//Form990ScheduleKPartII/AmountInReserveFund"
## [7] "//Form990ScheduleKPartII/CapitalizedInterest"
## [8] "//Form990ScheduleKPartII/RefundingEscrow"
## [9] "//Form990ScheduleKPartII/IssuanceCostsFromProceeds"
## [10] "//Form990ScheduleKPartII/CreditEnhancement"
## [11] "//Form990ScheduleKPartII/WorkingCapitalExpenditures"
## [12] "//Form990ScheduleKPartII/CapitalExpenditures"
## [13] "//Form990ScheduleKPartII/OtherSpentProceeds"
## [14] "//Form990ScheduleKPartII/AmountUnspent"
## [15] "//Form990ScheduleKPartII/YearOfSubstCompletion"
## [16] "//Form990ScheduleKPartII/CurrentRefunding"
## [17] "//Form990ScheduleKPartII/AdvanceRefunding"
## [18] "//Form990ScheduleKPartII/FinalAllocationMade"
## [19] "//Form990ScheduleKPartII/AdequateBooksAndRecdsMaintaind"
## [20] "//TaxExemptBondsProceedsGrp/BondReferenceCd"
## [21] "//TaxExemptBondsProceedsGrp/RetiredAmt"
## [22] "//TaxExemptBondsProceedsGrp/BondDefeasedAmt"
## [23] "//TaxExemptBondsProceedsGrp/TotalProceedsAmt"
## [24] "//TaxExemptBondsProceedsGrp/InReserveFundAmt"
## [25] "//TaxExemptBondsProceedsGrp/CapitalizedInterestAmt"
## [26] "//TaxExemptBondsProceedsGrp/RefundingEscrowAmt"
## [27] "//TaxExemptBondsProceedsGrp/IssuanceCostsFromProceedsAmt"
## [28] "//TaxExemptBondsProceedsGrp/CreditEnhancementAmt"
## [29] "//TaxExemptBondsProceedsGrp/WorkingCapitalExpendituresAmt"
## [30] "//TaxExemptBondsProceedsGrp/CapitalExpendituresAmt"
## [31] "//TaxExemptBondsProceedsGrp/OtherSpentProceedsAmt"
## [32] "//TaxExemptBondsProceedsGrp/UnspentAmt"
## [33] "//TaxExemptBondsProceedsGrp/SubstantialCompletionYr"
## [34] "//TaxExemptBondsProceedsGrp/CurrentRefundingInd"
## [35] "//TaxExemptBondsProceedsGrp/AdvanceRefundingInd"
## [36] "//TaxExemptBondsProceedsGrp/FinalAllocationMadeInd"
## [37] "//TaxExemptBondsProceedsGrp/AdequateBooksAndRecMaintInd"# 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$URL
# erase existing log files
file.create("XPATH-LOG.txt")
file.create("FAIL-LOG.txt")
start.build.time <- Sys.time() # --------------------
results.list <- list()
xpath.list <- list()
for( i in 1:length( sample.urls ) )
{
url <- sample.urls[i]
results.list[[i]] <-
build_rdb_table_v2( url,
table.name,
table.headers=table.headers )
xpath.list[[i]] <-
get_table_xpaths( url,
table.name,
table.headers=table.headers )
if( i %% 100 == 0 ){ print(i) }
}
end.build.time <- Sys.time() # --------------------
df <- dplyr::bind_rows( results.list )
fail.log <- readLines( "FAIL-LOG.txt" )
all.xpaths <- xpath.list %>% unlist() %>% unique() %>% sort()
cat( all.xpaths, sep="\n", file="XPATH-LOG.txt" )TABLE: SK-P02-T01-BOND-PROCEEDS
## [1] "NUMBER OF RETURNS PROCESSED: 1000"
## [1] "TOTAL NUMBER OF TABLE ROWS: 2064"TOTAL RUN TIME:
## Time difference of 13.33343 hours
## Time difference of -13.33343 hourswrite.csv( df, paste0( folder.name, "/", table.name, ".csv" ), row.names=F )
head(df) Are all names standardized?
names(df)## [1] "OBJECT_ID" "EIN"
## [3] "NAME" "TAXYR"
## [5] "FORMTYPE" "URL"
## [7] "SK_02_BOND_ISSUE_REFERENCE_NUM" "SK_02_BOND_PROCEED_AMT_RETIRED"
## [9] "SK_02_BOND_PROCEED_AMT_DEFEASED" "SK_02_BOND_PROCEED_TOT"
## [11] "SK_02_BOND_PROCEED_RESERVE_FUND" "SK_02_BOND_PROCEED_INT_CAP"
## [13] "SK_02_BOND_PROCEED_REFUND_ESCROW" "SK_02_BOND_PROCEED_ISSUANCE_COST"
## [15] "SK_02_BOND_PROCEED_CREDIT_ENHANC" "SK_02_BOND_PROCEED_CAP_EXP_WORK"
## [17] "SK_02_BOND_PROCEED_CAP_EXP" "SK_02_BOND_PROCEED_OTH_SPENT"
## [19] "SK_02_BOND_PROCEED_OTH_UNSPENT" "SK_02_BOND_PROCEED_Y_COMPLETION."
## [21] "RefundingTaxExemptBondsInd" "RefundingTaxableBondsInd"
## [23] "SK_02_BOND_PROCEED_ALLOC_FINAL_X" "SK_02_BOND_PROCEED_BOOK_RECORD_X"
Check for xpaths that were used in the tables but do not exist in the Concordance file.
c.table <- dplyr::filter( concordance, rdb_table == table.name )
xpath.concordance <- c.table$xpath
setdiff( all.xpaths, xpath.concordance )## [1] ""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 °--IRS990ScheduleK
## 4 °--TaxExemptBondsProceedsGrp
## 5 ¦--AdequateBooksAndRecMaintInd
## 6 ¦--BondDefeasedAmt
## 7 ¦--BondReferenceCd
## 8 ¦--CapitalExpendituresAmt
## 9 ¦--CapitalizedInterestAmt
## 10 ¦--CreditEnhancementAmt
## 11 ¦--FinalAllocationMadeInd
## 12 ¦--InReserveFundAmt
## 13 ¦--IssuanceCostsFromProceedsAmt
## 14 ¦--OtherSpentProceedsAmt
## 15 ¦--RefundingEscrowAmt
## 16 ¦--RetiredAmt
## 17 ¦--SubstantialCompletionYr
## 18 ¦--TotalProceedsAmt
## 19 ¦--UnspentAmt
## 20 °--WorkingCapitalExpendituresAmtSetGraphStyle( 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/IRS990ScheduleK/Form990ScheduleKPartII/AdequateBooksAndRecdsMaintaind | 1 |
| /Return/ReturnData/IRS990ScheduleK/Form990ScheduleKPartII/AdvanceRefunding | 2 |
| /Return/ReturnData/IRS990ScheduleK/Form990ScheduleKPartII/AmountBondDefeased | 3 |
| /Return/ReturnData/IRS990ScheduleK/Form990ScheduleKPartII/AmountDefeased | 4 |
| /Return/ReturnData/IRS990ScheduleK/Form990ScheduleKPartII/AmountInReserveFund | 5 |
| /Return/ReturnData/IRS990ScheduleK/Form990ScheduleKPartII/AmountRetired | 6 |
| /Return/ReturnData/IRS990ScheduleK/Form990ScheduleKPartII/AmountUnspent | 7 |
| /Return/ReturnData/IRS990ScheduleK/Form990ScheduleKPartII/BondReferenceCd | 8 |
| /Return/ReturnData/IRS990ScheduleK/Form990ScheduleKPartII/CapitalExpenditures | 9 |
| /Return/ReturnData/IRS990ScheduleK/Form990ScheduleKPartII/CapitalizedInterest | 10 |
| /Return/ReturnData/IRS990ScheduleK/Form990ScheduleKPartII/CreditEnhancement | 11 |
| /Return/ReturnData/IRS990ScheduleK/Form990ScheduleKPartII/CurrentRefunding | 12 |
| /Return/ReturnData/IRS990ScheduleK/Form990ScheduleKPartII/FinalAllocationMade | 13 |
| /Return/ReturnData/IRS990ScheduleK/Form990ScheduleKPartII/IssuanceCostsFromProceeds | 14 |
| /Return/ReturnData/IRS990ScheduleK/Form990ScheduleKPartII/OtherSpentProceeds | 15 |
| /Return/ReturnData/IRS990ScheduleK/Form990ScheduleKPartII/RefundingEscrow | 16 |
| /Return/ReturnData/IRS990ScheduleK/Form990ScheduleKPartII/TotalProceeds | 17 |
| /Return/ReturnData/IRS990ScheduleK/Form990ScheduleKPartII/WorkingCapitalExpenditures | 18 |
| /Return/ReturnData/IRS990ScheduleK/Form990ScheduleKPartII/YearOfSubstCompletion | 19 |
| /Return/ReturnData/IRS990ScheduleK/TaxExemptBondsProceedsGrp/AdequateBooksAndRecMaintInd | 20 |
| /Return/ReturnData/IRS990ScheduleK/TaxExemptBondsProceedsGrp/AdvanceRefundingInd | 21 |
| /Return/ReturnData/IRS990ScheduleK/TaxExemptBondsProceedsGrp/BondDefeasedAmt | 22 |
| /Return/ReturnData/IRS990ScheduleK/TaxExemptBondsProceedsGrp/BondReferenceCd | 23 |
| /Return/ReturnData/IRS990ScheduleK/TaxExemptBondsProceedsGrp/CapitalExpendituresAmt | 24 |
| /Return/ReturnData/IRS990ScheduleK/TaxExemptBondsProceedsGrp/CapitalizedInterestAmt | 25 |
| /Return/ReturnData/IRS990ScheduleK/TaxExemptBondsProceedsGrp/CreditEnhancementAmt | 26 |
| /Return/ReturnData/IRS990ScheduleK/TaxExemptBondsProceedsGrp/CurrentRefundingInd | 27 |
| /Return/ReturnData/IRS990ScheduleK/TaxExemptBondsProceedsGrp/FinalAllocationMadeInd | 28 |
| /Return/ReturnData/IRS990ScheduleK/TaxExemptBondsProceedsGrp/InReserveFundAmt | 29 |
| /Return/ReturnData/IRS990ScheduleK/TaxExemptBondsProceedsGrp/IssuanceCostsFromProceedsAmt | 30 |
| /Return/ReturnData/IRS990ScheduleK/TaxExemptBondsProceedsGrp/OtherSpentProceedsAmt | 31 |
| /Return/ReturnData/IRS990ScheduleK/TaxExemptBondsProceedsGrp/RefundingEscrowAmt | 32 |
| /Return/ReturnData/IRS990ScheduleK/TaxExemptBondsProceedsGrp/RetiredAmt | 33 |
| /Return/ReturnData/IRS990ScheduleK/TaxExemptBondsProceedsGrp/SubstantialCompletionYr | 34 |
| /Return/ReturnData/IRS990ScheduleK/TaxExemptBondsProceedsGrp/TotalProceedsAmt | 35 |
| /Return/ReturnData/IRS990ScheduleK/TaxExemptBondsProceedsGrp/UnspentAmt | 36 |
| /Return/ReturnData/IRS990ScheduleK/TaxExemptBondsProceedsGrp/WorkingCapitalExpendituresAmt | 37 |
Identify all unique groups used in xpaths.
if( is.null(table.headers) )
{ find_table_headers( table.name ) } else
table.headers## [1] "//Form990ScheduleKPartII/BondReferenceCd"
## [2] "//Form990ScheduleKPartII/AmountRetired"
## [3] "//Form990ScheduleKPartII/AmountBondDefeased"
## [4] "//Form990ScheduleKPartII/AmountDefeased"
## [5] "//Form990ScheduleKPartII/TotalProceeds"
## [6] "//Form990ScheduleKPartII/AmountInReserveFund"
## [7] "//Form990ScheduleKPartII/CapitalizedInterest"
## [8] "//Form990ScheduleKPartII/RefundingEscrow"
## [9] "//Form990ScheduleKPartII/IssuanceCostsFromProceeds"
## [10] "//Form990ScheduleKPartII/CreditEnhancement"
## [11] "//Form990ScheduleKPartII/WorkingCapitalExpenditures"
## [12] "//Form990ScheduleKPartII/CapitalExpenditures"
## [13] "//Form990ScheduleKPartII/OtherSpentProceeds"
## [14] "//Form990ScheduleKPartII/AmountUnspent"
## [15] "//Form990ScheduleKPartII/YearOfSubstCompletion"
## [16] "//Form990ScheduleKPartII/CurrentRefunding"
## [17] "//Form990ScheduleKPartII/AdvanceRefunding"
## [18] "//Form990ScheduleKPartII/FinalAllocationMade"
## [19] "//Form990ScheduleKPartII/AdequateBooksAndRecdsMaintaind"
## [20] "//TaxExemptBondsProceedsGrp/BondReferenceCd"
## [21] "//TaxExemptBondsProceedsGrp/RetiredAmt"
## [22] "//TaxExemptBondsProceedsGrp/BondDefeasedAmt"
## [23] "//TaxExemptBondsProceedsGrp/TotalProceedsAmt"
## [24] "//TaxExemptBondsProceedsGrp/InReserveFundAmt"
## [25] "//TaxExemptBondsProceedsGrp/CapitalizedInterestAmt"
## [26] "//TaxExemptBondsProceedsGrp/RefundingEscrowAmt"
## [27] "//TaxExemptBondsProceedsGrp/IssuanceCostsFromProceedsAmt"
## [28] "//TaxExemptBondsProceedsGrp/CreditEnhancementAmt"
## [29] "//TaxExemptBondsProceedsGrp/WorkingCapitalExpendituresAmt"
## [30] "//TaxExemptBondsProceedsGrp/CapitalExpendituresAmt"
## [31] "//TaxExemptBondsProceedsGrp/OtherSpentProceedsAmt"
## [32] "//TaxExemptBondsProceedsGrp/UnspentAmt"
## [33] "//TaxExemptBondsProceedsGrp/SubstantialCompletionYr"
## [34] "//TaxExemptBondsProceedsGrp/CurrentRefundingInd"
## [35] "//TaxExemptBondsProceedsGrp/AdvanceRefundingInd"
## [36] "//TaxExemptBondsProceedsGrp/FinalAllocationMadeInd"
## [37] "//TaxExemptBondsProceedsGrp/AdequateBooksAndRecMaintInd"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