Skip to content
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

Jump to bottom

Update Medicare and Medicaid values in cps.csv.gz file #185

Merged
merged 10 commits into from
Aug 10, 2018
Merged

Update Medicare and Medicaid values in cps.csv.gz file #185

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
10 commits
Select commit Hold shift + click to select a range
f39e307
update medicare and medicaid values
andersonfrailey Apr 26, 2018
38235fe
Merge branch 'master' into medicaremedicaid
andersonfrailey Apr 26, 2018
d7a6f33
update to master
andersonfrailey Apr 26, 2018
5f6472f
fix typo
andersonfrailey Apr 26, 2018
5a1432f
implement suggestions from Max and Amy
andersonfrailey Apr 27, 2018
3ef0fe4
update to master
andersonfrailey May 11, 2018
d50af17
change medicare/caid methodology
andersonfrailey Jun 25, 2018
85df884
Merge branch 'master' into medicaremedicaid
andersonfrailey Jun 25, 2018
f928932
update to master
andersonfrailey Aug 10, 2018
71f21a9
update tests
andersonfrailey Aug 10, 2018
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
Binary file modified cps_data/cps.csv.gz
View file
Open in desktop
Binary file not shown.
19 changes: 18 additions & 1 deletion cps_data/finalprep.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -341,8 +341,25 @@ def adjust(data, targets):
def benefits(data, other_ben):
"""
Distribute benefits from non-models benefit programs and create total
benefits variable
benefits variable.
Replaces Medicare and Medicaid values with set amounts
"""
# replace medicare and medicaid
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This code should run faster than lines 348-354:

medicare_cols = 'MCARE_VAL' + pd.Series((np.arange(16) + 1).astype(str))
medicaid_cols = 'MCAID_VAL' + pd.Series((np.arange(16) + 1).astype(str))

count_medicare = data[medicare_cols].astype(bool).sum(axis=1)
count_medicaid = data[medicaid_cols].astype(bool).sum(axis=1)

See https://drive.google.com/file/d/1Fw8rcvcERKs9llMf6dfOVAPuqwuqUUah for an example.

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks for the tip!

medicare_cols = 'MCARE_VAL' + pd.Series((np.arange(15) + 1).astype(str))
medicaid_cols = 'MCAID_VAL' + pd.Series((np.arange(15) + 1).astype(str))
count_medicare = data[medicare_cols].astype(bool).sum(axis=1)
count_medicaid = data[medicaid_cols].astype(bool).sum(axis=1)
weighted_count_mcare = (count_medicare * data['s006']).sum()
weighted_count_mcaid = (count_medicaid * data['s006']).sum()
weighted_mcare = (data['mcare_ben'] * data['s006']).sum()
weighted_mcaid = (data['mcaid_ben'] * data['s006']).sum()
mcare_amt = weighted_mcare / weighted_count_mcare
mcaid_amt = weighted_mcaid / weighted_count_mcaid
data[medicare_cols] = data[medicare_cols].astype(bool) * mcare_amt
data[medicaid_cols] = data[medicaid_cols].astype(bool) * mcaid_amt
data['mcare_ben'] = data[medicare_cols].sum(axis=1)
data['mcaid_ben'] = data[medicaid_cols].sum(axis=1)

other_ben['2014_cost'] *= 1e6

# Distribute other benefits
Expand Down
6 changes: 3 additions & 3 deletions tests/cps_agg_expected.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -51,15 +51,15 @@ filer 437439 0 1
fips 12469516 1 56
h_seq 22850538907 1 99461
housing_ben 60379435 0 53253
mcaid_ben 904042846 0 692753
mcare_ben 1700697749 0 691961
mcaid_ben 888211102 0 98440
mcare_ben 1778073024 0 92976
n1820 36555 0 6
n21 711316 0 11
n24 226097 0 10
nu05 45400 0 4
nu13 163487 0 10
nu18 281400 0 12
other_ben 512349609 0 232456
other_ben 507328438 0 53790
s006 16296813000 100 561900
snap_ben 141713659 0 26569
ssi_ben 103019670 0 64378
Expand Down
18 changes: 9 additions & 9 deletions tests/test_data.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -181,27 +181,27 @@ def check_cps_benefits(data):
expect_ben_stat = dict()
# .. maximum value per filing unit for benefit
expect_ben_stat['max'] = {
'mcare': 691961, # <--- will be fixed after switch to actuarial value
'mcaid': 692753, # <--- will be fixed after switch to actuarial value
'mcare': 92976,
'mcaid': 98440,
'ssi': 64378,
'snap': 26569,
'wic': 4972,
'tanf': 159407, # <--- SEEMS ABSURD ($13,284/month)
'housing': 53253,
'vet': 169920, # <--- HIGH ($14,160/month)VA hospital costs or what?
'other': 232456 # <--- SEEMS ABSURD ($19,371/month)
'other': 53790
}
# .. minimum value per filing unit for positive benefit
expect_ben_stat['min'] = {
'mcare': 1, # <--- will be fixed after switch to actuarial value
'mcaid': 2, # <--- will be fixed after switch to actuarial value
'mcare': 11622,
'mcaid': 7031,
'ssi': 1, # <--- SEEMS LOW
'snap': 9, # <--- SEEMS LOW
'wic': 241,
'tanf': 1, # <--- SEEMS LOW
'housing': 1265,
'vet': 9890, # <--- is this actuarial value of VA hospital costs?
'other': 1 # <--- SEEMS LOW
'other': 3
}
# .. mean value per filing unit of positive benefit
expect_ben_stat['avg'] = {
Expand All @@ -213,7 +213,7 @@ def check_cps_benefits(data):
'tanf': 9117,
'housing': 7048,
'vet': 29912,
'other': 4323
'other': 4321
}
# compare actual and expected benefit statistics
error_msg = ''
Expand All @@ -237,9 +237,9 @@ def check_cps_benefits(data):
exp_maxben = expect_ben_stat['max'][bname]
if not np.allclose([maxben], [exp_maxben], rtol=0, atol=0.1):
msg = '\nCPS {}_ben maxben={} != {}'
error_msg += msg.format(bname, minben, exp_maxben)
error_msg += msg.format(bname, maxben, exp_maxben)
expect_avgben = expect_ben_stat['avg'][bname]
if not np.allclose([avgben], [expect_avgben], rtol=0, atol=0.5):
if not np.allclose([avgben], [expect_avgben], rtol=0, atol=0.6):
msg = '\nCPS {}_ben avgben={:.2f} != {:.2f}'
error_msg += msg.format(bname, avgben, expect_avgben)
if error_msg:
Expand Down