Created
April 1, 2014 21:32
-
-
Save davidfauth/9923640 to your computer and use it in GitHub Desktop.
Pig job to create the DocGraph structure
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
filteredNPIData = FOREACH npiData GENERATE | |
REPLACE(NPI, '\\"','') as npiRX, | |
REPLACE(Provider_Business_Mailing_Address_State_Name, '\\"','') as NPIState, | |
REPLACE(Healthcare_Provider_Taxonomy_Code_1, '\\"','') as NPITaxonomy, | |
REPLACE(Provider_Organization_Name_Legal_Business_Name, '\\"','') as NPIOrgName, | |
CONCAT(CONCAT(REPLACE(Provider_First_Name,'\\"',''),' '), REPLACE(Provider_Last_Name_Legal_Name,'\\"','')) as docName; | |
--join the filtered set to the NPI data to get the NPI information | |
joinReferred = JOIN docGraphRXData BY referringDoc, filteredNPIData by npiRX; | |
joinReferredTo = JOIN joinReferred BY referredDoc, filteredNPIData by npiRX; | |
-- join the set to the NUCC codes | |
joinReferredNUCC = JOIN joinReferredTo BY joinReferred::filteredNPIData::NPITaxonomy, nucc_codes by nuccCode; | |
joinReferredToNUCC = JOIN joinReferredNUCC BY joinReferredTo::filteredNPIData::NPITaxonomy, nucc_codes by nuccCode; | |
prunedDocGraphRXData = FOREACH joinReferredToNUCC GENERATE | |
joinReferredNUCC::joinReferredTo::joinReferred::docGraphRXData::referringDoc as referringDoc, | |
joinReferredNUCC::joinReferredTo::joinReferred::docGraphRXData::referredDoc as referredToDoc, | |
joinReferredNUCC::joinReferredTo::joinReferred::docGraphRXData::sharedTransactionCount as sharedTransactionCount, | |
joinReferredNUCC::joinReferredTo::joinReferred::docGraphRXData::patientTotal as patientTotal, | |
joinReferredNUCC::joinReferredTo::joinReferred::docGraphRXData::sameDayTotal as sameDayTotal, | |
(float)(joinReferredNUCC::joinReferredTo::joinReferred::docGraphRXData::sameDayTotal / joinReferredNUCC::joinReferredTo::joinReferred::docGraphRXData::sharedTransactionCount) as pctSameDayTotal, | |
(float)(joinReferredNUCC::joinReferredTo::joinReferred::docGraphRXData::patientTotal / joinReferredNUCC::joinReferredTo::joinReferred::docGraphRXData::sharedTransactionCount) as pctTransactions, | |
joinReferredNUCC::joinReferredTo::joinReferred::filteredNPIData::npiRX as referringDocNPI, | |
joinReferredNUCC::joinReferredTo::joinReferred::filteredNPIData::NPIState as referringDocState, | |
joinReferredNUCC::joinReferredTo::joinReferred::filteredNPIData::NPITaxonomy as referringDocTaxonomy, | |
joinReferredNUCC::joinReferredTo::joinReferred::filteredNPIData::NPIOrgName as referringDocOrgName, | |
joinReferredNUCC::joinReferredTo::joinReferred::filteredNPIData::docName as referringDocName, | |
joinReferredNUCC::joinReferredTo::filteredNPIData::npiRX as referredToDocNPI, | |
joinReferredNUCC::joinReferredTo::filteredNPIData::NPIState as referredToDocState, | |
joinReferredNUCC::joinReferredTo::filteredNPIData::NPITaxonomy as referredToDocTaxonomy, | |
joinReferredNUCC::joinReferredTo::filteredNPIData::NPIOrgName as referredToDocOrgName, | |
joinReferredNUCC::joinReferredTo::filteredNPIData::docName as referredToDocName, | |
joinReferredNUCC::nucc_codes::nuccCode as referringDocNUCCCode, | |
joinReferredNUCC::nucc_codes::nuccType as referringDocNUCCType, | |
nucc_codes::nuccCode as referredToDocNUCCCode, | |
nucc_codes::nuccType as referredToDocNUCCType; |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment