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/IRS990ScheduleH/Form990ScheduleHPartV/Address/AddressForeign/AddressLine1 | 1 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartV/Address/AddressForeign/AddressLine2 | 2 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartV/Address/AddressForeign/City | 3 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartV/Address/AddressForeign/Country | 4 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartV/Address/AddressForeign/PostalCode | 5 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartV/Address/AddressForeign/ProvinceOrState | 6 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartV/Address/AddressLine1 | 7 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartV/Address/AddressLine2 | 8 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartV/Address/AddressUS/AddressLine1 | 9 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartV/Address/AddressUS/AddressLine2 | 10 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartV/Address/AddressUS/City | 11 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartV/Address/AddressUS/State | 12 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartV/Address/AddressUS/ZIPCode | 13 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartV/Address/City | 14 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartV/Address/State | 15 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartV/Address/ZIPCode | 16 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartV/ChildrensHospital | 17 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartV/CriticalAccessHospital | 18 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartV/Er24Hours | 19 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartV/ErOther | 20 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartV/GeneralMedicalAndSurgical | 21 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartV/LicensedHospital | 22 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartV/Name/BusinessNameLine1 | 23 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartV/Name/BusinessNameLine2 | 24 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartV/Other | 25 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartV/ResearchFacility | 26 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartV/TeachingHospital | 27 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartVSectionA/Address/AddressLine1 | 28 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartVSectionA/Address/AddressLine2 | 29 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartVSectionA/Address/City | 30 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartVSectionA/Address/State | 31 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartVSectionA/Address/ZIPCode | 32 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartVSectionA/ChildrensHospital | 33 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartVSectionA/CriticalAccessHospital | 34 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartVSectionA/Er24Hours | 35 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartVSectionA/ErOther | 36 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartVSectionA/FacilityReportingGroup | 37 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartVSectionA/GeneralMedicalAndSurgical | 38 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartVSectionA/LicensedHospital | 39 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartVSectionA/Name/BusinessNameLine1 | 40 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartVSectionA/Name/BusinessNameLine2 | 41 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartVSectionA/Other | 42 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartVSectionA/ResearchFacility | 43 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartVSectionA/TeachingHospital | 44 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartVSectionA/WebsiteAddress | 45 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/BusinessName/BusinessNameLine1 | 46 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/BusinessName/BusinessNameLine1Txt | 47 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/BusinessName/BusinessNameLine2 | 48 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/BusinessName/BusinessNameLine2Txt | 49 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/ChildrensHospitalInd | 50 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/CriticalAccessHospitalInd | 51 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/EmergencyRoom24HrsInd | 52 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/EmergencyRoomOtherInd | 53 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/FacilityReportingGroupCd | 54 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/GeneralMedicalAndSurgicalInd | 55 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/LicensedHospitalInd | 56 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/OtherDesc | 57 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/ResearchFacilityInd | 58 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/StateLicenseNum | 59 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/SubordinateHospitalEIN | 60 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/SubordinateHospitalName/BusinessNameLine1Txt | 61 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/SubordinateHospitalName/BusinessNameLine2Txt | 62 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/TeachingHospitalInd | 63 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/USAddress/AddressLine1 | 64 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/USAddress/AddressLine1Txt | 65 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/USAddress/AddressLine2 | 66 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/USAddress/AddressLine2Txt | 67 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/USAddress/City | 68 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/USAddress/CityNm | 69 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/USAddress/State | 70 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/USAddress/StateAbbreviationCd | 71 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/USAddress/ZIPCd | 72 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/USAddress/ZIPCode | 73 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/WebsiteAddressTxt | 74 |
xpaths <- as.character( t.xpaths$xpath )
el <- create_edgelist_v1( xpaths )
nd <- FromDataFrameNetwork( network=el )
print( nd )## levelName
## 1 Return
## 2 °--ReturnData
## 3 °--IRS990ScheduleH
## 4 ¦--Form990ScheduleHPartV
## 5 ¦ ¦--Address
## 6 ¦ ¦ ¦--AddressForeign
## 7 ¦ ¦ ¦ ¦--AddressLine1
## 8 ¦ ¦ ¦ ¦--AddressLine2
## 9 ¦ ¦ ¦ ¦--City
## 10 ¦ ¦ ¦ ¦--Country
## 11 ¦ ¦ ¦ ¦--PostalCode
## 12 ¦ ¦ ¦ °--ProvinceOrState
## 13 ¦ ¦ ¦--AddressLine1
## 14 ¦ ¦ ¦--AddressLine2
## 15 ¦ ¦ ¦--AddressUS
## 16 ¦ ¦ ¦ ¦--AddressLine1
## 17 ¦ ¦ ¦ ¦--AddressLine2
## 18 ¦ ¦ ¦ ¦--City
## 19 ¦ ¦ ¦ ¦--State
## 20 ¦ ¦ ¦ °--ZIPCode
## 21 ¦ ¦ ¦--City
## 22 ¦ ¦ ¦--State
## 23 ¦ ¦ °--ZIPCode
## 24 ¦ ¦--ChildrensHospital
## 25 ¦ ¦--CriticalAccessHospital
## 26 ¦ ¦--Er24Hours
## 27 ¦ ¦--ErOther
## 28 ¦ ¦--GeneralMedicalAndSurgical
## 29 ¦ ¦--LicensedHospital
## 30 ¦ ¦--Name
## 31 ¦ ¦ ¦--BusinessNameLine1
## 32 ¦ ¦ °--BusinessNameLine2
## 33 ¦ ¦--Other
## 34 ¦ ¦--ResearchFacility
## 35 ¦ °--TeachingHospital
## 36 ¦--Form990ScheduleHPartVSectionA
## 37 ¦ ¦--Address
## 38 ¦ ¦ ¦--AddressForeign
## 39 ¦ ¦ ¦ ¦--AddressLine1
## 40 ¦ ¦ ¦ ¦--AddressLine2
## 41 ¦ ¦ ¦ ¦--City
## 42 ¦ ¦ ¦ ¦--Country
## 43 ¦ ¦ ¦ ¦--PostalCode
## 44 ¦ ¦ ¦ °--ProvinceOrState
## 45 ¦ ¦ ¦--AddressLine1
## 46 ¦ ¦ ¦--AddressLine2
## 47 ¦ ¦ ¦--AddressUS
## 48 ¦ ¦ ¦ ¦--AddressLine1
## 49 ¦ ¦ ¦ ¦--AddressLine2
## 50 ¦ ¦ ¦ ¦--City
## 51 ¦ ¦ ¦ ¦--State
## 52 ¦ ¦ ¦ °--ZIPCode
## 53 ¦ ¦ ¦--City
## 54 ¦ ¦ ¦--State
## 55 ¦ ¦ °--ZIPCode
## 56 ¦ ¦--ChildrensHospital
## 57 ¦ ¦--CriticalAccessHospital
## 58 ¦ ¦--Er24Hours
## 59 ¦ ¦--ErOther
## 60 ¦ ¦--FacilityReportingGroup
## 61 ¦ ¦--GeneralMedicalAndSurgical
## 62 ¦ ¦--LicensedHospital
## 63 ¦ ¦--Name
## 64 ¦ ¦ ¦--BusinessNameLine1
## 65 ¦ ¦ °--BusinessNameLine2
## 66 ¦ ¦--Other
## 67 ¦ ¦--ResearchFacility
## 68 ¦ ¦--TeachingHospital
## 69 ¦ °--WebsiteAddress
## 70 °--HospitalFacilitiesGrp
## 71 ¦--BusinessName
## 72 ¦ ¦--BusinessNameLine1
## 73 ¦ ¦--BusinessNameLine1Txt
## 74 ¦ ¦--BusinessNameLine2
## 75 ¦ °--BusinessNameLine2Txt
## 76 ¦--ChildrensHospitalInd
## 77 ¦--CriticalAccessHospitalInd
## 78 ¦--EmergencyRoom24HrsInd
## 79 ¦--EmergencyRoomOtherInd
## 80 ¦--FacilityReportingGroupCd
## 81 ¦--GeneralMedicalAndSurgicalInd
## 82 ¦--LicensedHospitalInd
## 83 ¦--OtherDesc
## 84 ¦--ResearchFacilityInd
## 85 ¦--StateLicenseNum
## 86 ¦--SubordinateHospitalEIN
## 87 ¦--SubordinateHospitalName
## 88 ¦ ¦--BusinessNameLine1Txt
## 89 ¦ °--BusinessNameLine2Txt
## 90 ¦--TeachingHospitalInd
## 91 ¦--USAddress
## 92 ¦ ¦--AddressLine1
## 93 ¦ ¦--AddressLine1Txt
## 94 ¦ ¦--AddressLine2
## 95 ¦ ¦--AddressLine2Txt
## 96 ¦ ¦--City
## 97 ¦ ¦--CityNm
## 98 ¦ ¦--State
## 99 ¦ ¦--StateAbbreviationCd
## 100 ¦ °--... 2 nodes w/ 0 sub
## 101 °--... 1 nodes w/ 2 subSetGraphStyle( 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] "//Form990ScheduleHPartV" "//Form990ScheduleHPartVSectionA"
## [3] "//HospitalFacilitiesGrp"# new version
find_table_headers( table.name )## [1] "//Form990ScheduleHPartV/Address"
## [2] "//Form990ScheduleHPartV/Name"
## [3] "//Form990ScheduleHPartV/LicensedHospital"
## [4] "//Form990ScheduleHPartV/GeneralMedicalAndSurgical"
## [5] "//Form990ScheduleHPartV/ChildrensHospital"
## [6] "//Form990ScheduleHPartV/TeachingHospital"
## [7] "//Form990ScheduleHPartV/CriticalAccessHospital"
## [8] "//Form990ScheduleHPartV/ResearchFacility"
## [9] "//Form990ScheduleHPartV/Er24Hours"
## [10] "//Form990ScheduleHPartV/ErOther"
## [11] "//Form990ScheduleHPartV/Other"
## [12] "//Form990ScheduleHPartVSectionA/Address"
## [13] "//Form990ScheduleHPartVSectionA/Name"
## [14] "//Form990ScheduleHPartVSectionA/WebsiteAddress"
## [15] "//Form990ScheduleHPartVSectionA/LicensedHospital"
## [16] "//Form990ScheduleHPartVSectionA/GeneralMedicalAndSurgical"
## [17] "//Form990ScheduleHPartVSectionA/ChildrensHospital"
## [18] "//Form990ScheduleHPartVSectionA/TeachingHospital"
## [19] "//Form990ScheduleHPartVSectionA/CriticalAccessHospital"
## [20] "//Form990ScheduleHPartVSectionA/ResearchFacility"
## [21] "//Form990ScheduleHPartVSectionA/Er24Hours"
## [22] "//Form990ScheduleHPartVSectionA/ErOther"
## [23] "//Form990ScheduleHPartVSectionA/Other"
## [24] "//Form990ScheduleHPartVSectionA/FacilityReportingGroup"
## [25] "//Form990ScheduleHPartVSectionA/FacilityNumber"
## [26] "//HospitalFacilitiesGrp/USAddress"
## [27] "//HospitalFacilitiesGrp/BusinessName"
## [28] "//HospitalFacilitiesGrp/StateLicenseNum"
## [29] "//HospitalFacilitiesGrp/SubordinateHospitalEIN"
## [30] "//HospitalFacilitiesGrp/SubordinateHospitalName"
## [31] "//HospitalFacilitiesGrp/WebsiteAddressTxt"
## [32] "//HospitalFacilitiesGrp/LicensedHospitalInd"
## [33] "//HospitalFacilitiesGrp/GeneralMedicalAndSurgicalInd"
## [34] "//HospitalFacilitiesGrp/ChildrensHospitalInd"
## [35] "//HospitalFacilitiesGrp/TeachingHospitalInd"
## [36] "//HospitalFacilitiesGrp/CriticalAccessHospitalInd"
## [37] "//HospitalFacilitiesGrp/ResearchFacilityInd"
## [38] "//HospitalFacilitiesGrp/EmergencyRoom24HrsInd"
## [39] "//HospitalFacilitiesGrp/EmergencyRoomOtherInd"
## [40] "//HospitalFacilitiesGrp/OtherDesc"
## [41] "//HospitalFacilitiesGrp/FacilityReportingGroupCd"
## [42] "//HospitalFacilitiesGrp/FacilityNum"# 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$URL
# erase existing log files
file.create("XPATH-LOG.txt")
file.create("FAIL-LOG.txt")
start.build.time <- Sys.time() # --------------------
results.list <- list()
xpath.list <- list()
for( i in 1:length( sample.urls ) )
{
url <- sample.urls[i]
results.list[[i]] <-
build_rdb_table_v2( url,
table.name,
table.headers=table.headers )
xpath.list[[i]] <-
get_table_xpaths( url,
table.name,
table.headers=table.headers )
if( i %% 100 == 0 ){ print(i) }
}
end.build.time <- Sys.time() # --------------------
df <- dplyr::bind_rows( results.list )
fail.log <- readLines( "FAIL-LOG.txt" )
all.xpaths <- xpath.list %>% unlist() %>% unique() %>% sort()
cat( all.xpaths, sep="\n", file="XPATH-LOG.txt" )TABLE: SH-P05-T01-HOSPITAL-FACILITY
## [1] "NUMBER OF RETURNS PROCESSED: 1000"
## [1] "TOTAL NUMBER OF TABLE ROWS: 1613"TOTAL RUN TIME:
## Time difference of 37.91935 mins
## Time difference of -0.6319892 hourswrite.csv( df, paste0( folder.name, "/", table.name, ".csv" ), row.names=F )
head(df) Are all names standardized?
names(df)## [1] "OBJECT_ID" "EIN"
## [3] "NAME" "TAXYR"
## [5] "FORMTYPE" "URL"
## [7] "FacilityNum" "SH_05_HOSPITAL_WEBSITE"
## [9] "SH_05_HOSPITAL_STATE_LIC_NUM" "SH_05_HOSPITAL_LIC_X"
## [11] "SH_05_HOSPITAL_MEDICAL_X" "SH_05_HOSPITAL_TEACHING_X"
## [13] "SH_05_HOSPITAL_ER_24HOURS_X" "SH_05_HOSPITAL_FACILITY_GROUP"
## [15] "SH_05_HOSPITAL_NAME_L1" "SH_05_HOSPITAL_ADDR_L1"
## [17] "SH_05_HOSPITAL_ADDR_CITY" "SH_05_HOSPITAL_ADDR_STATE"
## [19] "SH_05_HOSPITAL_ADDR_ZIP" "SH_05_HOSPITAL_CHILDREN_X"
## [21] "SH_05_HOSPITAL_OTH" "SH_05_HOSPITAL_RSRCH_FACILITY_X"
## [23] "SH_05_HOSPITAL_CRITICAL_ACCESS_X" "SH_05_HOSPITAL_ADDR_L2"
## [25] "SH_05_HOSPITAL_ER_OTH_X" "SH_05_HOSPITAL_SUBORD_EIN"
## [27] "SH_05_HOSPITAL_NAME_L1.1" "SH_05_HOSPITAL_NAME_L2"
Check for xpaths that were used in the tables but do not exist in the Concordance file.
c.table <- dplyr::filter( concordance, rdb_table == table.name )
xpath.concordance <- c.table$xpath
setdiff( all.xpaths, xpath.concordance )## [1] "/Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/BusinessName"
## [2] "/Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/FacilityNum"
## [3] "/Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/SubordinateHospitalName"
## [4] "/Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/USAddress"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 °--IRS990ScheduleH
## 4 °--HospitalFacilitiesGrp
## 5 ¦--BusinessName
## 6 ¦ ¦--BusinessNameLine1Txt
## 7 ¦ °--BusinessNameLine2Txt
## 8 ¦--ChildrensHospitalInd
## 9 ¦--CriticalAccessHospitalInd
## 10 ¦--EmergencyRoom24HrsInd
## 11 ¦--EmergencyRoomOtherInd
## 12 ¦--FacilityNum
## 13 ¦--FacilityReportingGroupCd
## 14 ¦--GeneralMedicalAndSurgicalInd
## 15 ¦--LicensedHospitalInd
## 16 ¦--OtherDesc
## 17 ¦--ResearchFacilityInd
## 18 ¦--StateLicenseNum
## 19 ¦--SubordinateHospitalEIN
## 20 ¦--SubordinateHospitalName
## 21 ¦ °--BusinessNameLine1Txt
## 22 ¦--TeachingHospitalInd
## 23 ¦--USAddress
## 24 ¦ ¦--AddressLine1Txt
## 25 ¦ ¦--AddressLine2Txt
## 26 ¦ ¦--CityNm
## 27 ¦ ¦--StateAbbreviationCd
## 28 ¦ °--ZIPCd
## 29 °--WebsiteAddressTxtSetGraphStyle( 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/IRS990ScheduleH/Form990ScheduleHPartV/Address/AddressForeign/AddressLine1 | 1 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartV/Address/AddressForeign/AddressLine2 | 2 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartV/Address/AddressForeign/City | 3 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartV/Address/AddressForeign/Country | 4 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartV/Address/AddressForeign/PostalCode | 5 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartV/Address/AddressForeign/ProvinceOrState | 6 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartV/Address/AddressLine1 | 7 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartV/Address/AddressLine2 | 8 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartV/Address/AddressUS/AddressLine1 | 9 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartV/Address/AddressUS/AddressLine2 | 10 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartV/Address/AddressUS/City | 11 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartV/Address/AddressUS/State | 12 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartV/Address/AddressUS/ZIPCode | 13 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartV/Address/City | 14 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartV/Address/State | 15 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartV/Address/ZIPCode | 16 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartV/ChildrensHospital | 17 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartV/CriticalAccessHospital | 18 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartV/Er24Hours | 19 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartV/ErOther | 20 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartV/GeneralMedicalAndSurgical | 21 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartV/LicensedHospital | 22 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartV/Name/BusinessNameLine1 | 23 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartV/Name/BusinessNameLine2 | 24 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartV/Other | 25 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartV/ResearchFacility | 26 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartV/TeachingHospital | 27 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartVSectionA/Address/AddressLine1 | 28 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartVSectionA/Address/AddressLine2 | 29 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartVSectionA/Address/City | 30 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartVSectionA/Address/State | 31 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartVSectionA/Address/ZIPCode | 32 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartVSectionA/ChildrensHospital | 33 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartVSectionA/CriticalAccessHospital | 34 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartVSectionA/Er24Hours | 35 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartVSectionA/ErOther | 36 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartVSectionA/FacilityReportingGroup | 37 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartVSectionA/GeneralMedicalAndSurgical | 38 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartVSectionA/LicensedHospital | 39 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartVSectionA/Name/BusinessNameLine1 | 40 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartVSectionA/Name/BusinessNameLine2 | 41 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartVSectionA/Other | 42 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartVSectionA/ResearchFacility | 43 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartVSectionA/TeachingHospital | 44 |
| /Return/ReturnData/IRS990ScheduleH/Form990ScheduleHPartVSectionA/WebsiteAddress | 45 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/BusinessName/BusinessNameLine1 | 46 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/BusinessName/BusinessNameLine1Txt | 47 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/BusinessName/BusinessNameLine2 | 48 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/BusinessName/BusinessNameLine2Txt | 49 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/ChildrensHospitalInd | 50 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/CriticalAccessHospitalInd | 51 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/EmergencyRoom24HrsInd | 52 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/EmergencyRoomOtherInd | 53 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/FacilityReportingGroupCd | 54 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/GeneralMedicalAndSurgicalInd | 55 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/LicensedHospitalInd | 56 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/OtherDesc | 57 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/ResearchFacilityInd | 58 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/StateLicenseNum | 59 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/SubordinateHospitalEIN | 60 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/SubordinateHospitalName/BusinessNameLine1Txt | 61 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/SubordinateHospitalName/BusinessNameLine2Txt | 62 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/TeachingHospitalInd | 63 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/USAddress/AddressLine1 | 64 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/USAddress/AddressLine1Txt | 65 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/USAddress/AddressLine2 | 66 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/USAddress/AddressLine2Txt | 67 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/USAddress/City | 68 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/USAddress/CityNm | 69 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/USAddress/State | 70 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/USAddress/StateAbbreviationCd | 71 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/USAddress/ZIPCd | 72 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/USAddress/ZIPCode | 73 |
| /Return/ReturnData/IRS990ScheduleH/HospitalFacilitiesGrp/WebsiteAddressTxt | 74 |
Identify all unique groups used in xpaths.
if( is.null(table.headers) )
{ find_table_headers( table.name ) } else
table.headers## [1] "//Form990ScheduleHPartV/Address"
## [2] "//Form990ScheduleHPartV/Name"
## [3] "//Form990ScheduleHPartV/LicensedHospital"
## [4] "//Form990ScheduleHPartV/GeneralMedicalAndSurgical"
## [5] "//Form990ScheduleHPartV/ChildrensHospital"
## [6] "//Form990ScheduleHPartV/TeachingHospital"
## [7] "//Form990ScheduleHPartV/CriticalAccessHospital"
## [8] "//Form990ScheduleHPartV/ResearchFacility"
## [9] "//Form990ScheduleHPartV/Er24Hours"
## [10] "//Form990ScheduleHPartV/ErOther"
## [11] "//Form990ScheduleHPartV/Other"
## [12] "//Form990ScheduleHPartVSectionA/Address"
## [13] "//Form990ScheduleHPartVSectionA/Name"
## [14] "//Form990ScheduleHPartVSectionA/WebsiteAddress"
## [15] "//Form990ScheduleHPartVSectionA/LicensedHospital"
## [16] "//Form990ScheduleHPartVSectionA/GeneralMedicalAndSurgical"
## [17] "//Form990ScheduleHPartVSectionA/ChildrensHospital"
## [18] "//Form990ScheduleHPartVSectionA/TeachingHospital"
## [19] "//Form990ScheduleHPartVSectionA/CriticalAccessHospital"
## [20] "//Form990ScheduleHPartVSectionA/ResearchFacility"
## [21] "//Form990ScheduleHPartVSectionA/Er24Hours"
## [22] "//Form990ScheduleHPartVSectionA/ErOther"
## [23] "//Form990ScheduleHPartVSectionA/Other"
## [24] "//Form990ScheduleHPartVSectionA/FacilityReportingGroup"
## [25] "//Form990ScheduleHPartVSectionA/FacilityNumber"
## [26] "//HospitalFacilitiesGrp/USAddress"
## [27] "//HospitalFacilitiesGrp/BusinessName"
## [28] "//HospitalFacilitiesGrp/StateLicenseNum"
## [29] "//HospitalFacilitiesGrp/SubordinateHospitalEIN"
## [30] "//HospitalFacilitiesGrp/SubordinateHospitalName"
## [31] "//HospitalFacilitiesGrp/WebsiteAddressTxt"
## [32] "//HospitalFacilitiesGrp/LicensedHospitalInd"
## [33] "//HospitalFacilitiesGrp/GeneralMedicalAndSurgicalInd"
## [34] "//HospitalFacilitiesGrp/ChildrensHospitalInd"
## [35] "//HospitalFacilitiesGrp/TeachingHospitalInd"
## [36] "//HospitalFacilitiesGrp/CriticalAccessHospitalInd"
## [37] "//HospitalFacilitiesGrp/ResearchFacilityInd"
## [38] "//HospitalFacilitiesGrp/EmergencyRoom24HrsInd"
## [39] "//HospitalFacilitiesGrp/EmergencyRoomOtherInd"
## [40] "//HospitalFacilitiesGrp/OtherDesc"
## [41] "//HospitalFacilitiesGrp/FacilityReportingGroupCd"
## [42] "//HospitalFacilitiesGrp/FacilityNum"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