Skip to content

Make the batch size and number of batches also reflective of number o… #157

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
tjann merged 2 commits into from
Sep 16, 2020
Merged

Make the batch size and number of batches also reflective of number o… #157

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
69a1a26
Make the batch size and number of batches also reflective of number o…
tjann Sep 16, 2020
a3bf7eb
Update comment to use constant instead of number.
tjann Sep 16, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
93 changes: 78 additions & 15 deletions datacommons/examples/stat_vars.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -130,27 +130,90 @@ def call_str(pvs):
try:
dc.get_stat_all(
dc.get_places_in(['country/USA'], 'County')['country/USA'], [
'Count_Person_Unemployed', 'Median_Age_Person', 'Count_Death',
'Count_Death_CertainInfectiousParasiticDiseases',
'Count_UnemploymentInsuranceClaim_StateUnemploymentInsurance',
'Count_Worker_NAICSAccommodationFoodServices',
'Count_Household_With0AvailableVehicles',
'Count_Person_WhiteAlone', 'Count_Person_WorkedFullTime',
'Count_Person_Employed', 'Count_Person_EnrolledInSchool',
'Count_Person', 'LandAreaSqMeter',
'PopulationDensityPerSqMeter',
'Count_Person_BlackOrAfricanAmericanAlone',
'PercentBlackOrAfricanAmericanAlone', 'Count_Person_Female',
'Count_Person_Male',
'Count_Person_AmericanIndianAndAlaskaNativeAlone',
'Count_Person_AmericanIndianAndAlaskaNativeAloneOrInCombinationWithOneOrMoreOtherRaces',
'Count_Person_AmericanIndianOrAlaskaNativeAlone',
'Count_Person_AsianAlone',
'Count_Person_AsianAloneOrInCombinationWithOneOrMoreOtherRaces',
'Count_Person_BlackOrAfricanAmericanAloneOrInCombinationWithOneOrMoreOtherRaces',
'Count_Person_HispanicOrLatino',
'Count_Person_NativeHawaiianAndOtherPacificIslanderAlone',
'Count_Person_NativeHawaiianAndOtherPacificIslanderAloneOrInCombinationWithOneOrMoreOtherRaces',
'Count_Person_NativeHawaiianOrOtherPacificIslanderAlone',
'Count_Person_SomeOtherRaceAlone',
'Count_Person_SomeOtherRaceAloneOrInCombinationWithOneOrMoreOtherRaces',
'Count_Person_TwoOrMoreRaces', 'Count_Person_WhiteAlone',
'Count_Person_WhiteAloneNotHispanicOrLatino',
'Count_Person_WhiteAloneOrInCombinationWithOneOrMoreOtherRaces',
'Count_Person_Upto5Years', 'Count_Person_Upto18Years',
'Count_Person_65OrMoreYears', 'Count_Person_75OrMoreYears',
'Count_Person_ForeignBorn',
'Count_Person_USCitizenByNaturalization',
'Count_Person_NotAUSCitizen', 'Count_Person_Nonveteran',
'Count_Person_Veteran', 'Count_Person_NotWorkedFullTime',
'Count_Person_WorkedFullTime', 'Count_Person_Employed',
'Count_Person_Unemployed', 'Count_Person_InLaborForce',
'Count_Person_IncomeOf10000To14999USDollar',
'Count_Person_IncomeOf15000To24999USDollar',
'Count_Person_IncomeOf25000To34999USDollar',
'Count_Person_IncomeOf35000To49999USDollar',
'Count_Person_IncomeOf50000To64999USDollar',
'Count_Person_IncomeOf65000To74999USDollar',
'Count_Person_IncomeOf75000OrMoreUSDollar',
'Count_Person_IncomeOfUpto9999USDollar',
'Count_Person_EnrolledInSchool',
'Count_Person_NotEnrolledInSchool',
'Count_Person_EnrolledInCollegeUndergraduateYears',
'Count_Person_EnrolledInGrade1ToGrade4',
'Count_Person_EnrolledInGrade5ToGrade8',
'Count_Person_EnrolledInGrade9ToGrade12',
'Count_Person_ResidesInGroupQuarters',
'Count_Person_NowMarried',
'RetailDrugDistribution_DrugDistribution_DMethamphetamine',
'Count_Household_With2Person',
'Count_Person_EnrolledInKindergarten',
'Count_Person_EnrolledInNurserySchoolPreschool',
'Count_Person_GraduateOrProfessionalSchool',
'Count_Person_EducationalAttainment10ThGrade',
'Count_Person_EducationalAttainment11ThGrade',
'Count_Person_EducationalAttainment12ThGradeNoDiploma',
'Count_Person_EducationalAttainment1StGrade',
'Count_Person_EducationalAttainment2NdGrade',
'Count_Person_EducationalAttainment3RdGrade',
'Count_Person_EducationalAttainment4ThGrade',
'Count_Person_EducationalAttainment5ThGrade',
'Count_Person_EducationalAttainment6ThGrade',
'Count_Person_EducationalAttainment7ThGrade',
'Count_Person_EducationalAttainment8ThGrade',
'Count_Person_EducationalAttainment9ThGrade',
'Count_Person_EducationalAttainmentAssociatesDegree',
'Count_Person_EducationalAttainmentBachelorsDegree',
'Count_Person_EducationalAttainmentBachelorsDegreeOrHigher',
'Count_Person_EducationalAttainmentDoctorateDegree',
'Count_Person_EducationalAttainmentGedOrAlternativeCredential',
'Count_Person_EducationalAttainmentKindergarten',
'Count_Person_EducationalAttainmentMastersDegree',
'Count_Person_EducationalAttainmentNoSchoolingCompleted',
'Count_Person_EducationalAttainmentNurserySchool',
'Count_Person_EducationalAttainmentPrimarySchool',
'Count_Person_EducationalAttainmentProfessionalSchoolDegree',
'Count_Person_EducationalAttainmentRegularHighSchoolDiploma',
'Count_Person_EducationalAttainmentSomeCollege1OrMoreYearsNoDegree',
'Count_Person_EducationalAttainmentSomeCollegeLessThan1Year',
'Count_Person_Divorced', 'Count_Person_MarriedAndNotSeparated',
'Count_Person_NeverMarried', 'Count_Person_Separated',
'Count_Person_Widowed', 'Count_Person_NowMarried',
'Count_Person_AbovePovertyLevelInThePast12Months',
'Count_Person_BelowPovertyLevelInThePast12Months',
'Percent_Person_20OrMoreYears_WithDiabetes',
'Percent_Person_20OrMoreYears_Obesity',
'Percent_Person_20OrMoreYears_PhysicalInactivity',
'Percent_Person_Upto64Years_NoHealthInsurance',
'Median_Age_Person', 'Median_Income_Person', 'Count_Death',
'Count_Death_CertainInfectiousParasiticDiseases',
'Count_Death_DiseasesOfBloodAndBloodFormingOrgansAndImmuneDisorders',
'Count_Household_NoComputer',
'Median_Income_Household_HouseholderRaceHispanicOrLatino,',
'Count_HousingUnit_RenterOccupied',
'Count_Worker_NAICSInformation'
'Count_Death_DiseasesOfTheRespiratorySystem'
])
except ValueError:
print('Stress test for get_stat_all FAILED!')
Expand Down
19 changes: 13 additions & 6 deletions datacommons/stat_vars.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,6 +25,9 @@

import datacommons.utils as utils

# stat_var specific batch size.
_STAT_BATCH_SIZE = 2000


def get_stat_value(place,
stat_var,
Expand Down Expand Up @@ -203,20 +206,24 @@ def get_stat_all(places, stat_vars):
}
"""
url = utils._API_ROOT + utils._API_ENDPOINTS['get_stat_all']
# Cast iterable-like to list.
places = list(places)
stat_vars = list(stat_vars)

# Aiming for _STAT_BATCH_SIZE entries total.
# _STAT_BATCH_SIZE = num places x num stat_vars, so aim for
# _STAT_BATCH_SIZE/len(stat_vars) places per batch.
places_per_batch = _STAT_BATCH_SIZE // len(stat_vars)
# Get number of batches via an arithmetic ceiling trick:
# 11//10 rounds down to 1.
# -11//10 rounds down to -2.
# We can divide with, then remove the negative to get the ceiling.
batches = -(-len(places) // utils._QUERY_BATCH_SIZE)
batches = -(-len(places) // places_per_batch)
res = {}
for i in range(batches):
req_json = {
'stat_vars':
stat_vars,
'places':
places[i * utils._QUERY_BATCH_SIZE:(i + 1) *
utils._QUERY_BATCH_SIZE]
'stat_vars': stat_vars,
'places': places[i * places_per_batch:(i + 1) * places_per_batch]
}
# Send the request
res_json = utils._send_request(url,
Expand Down