Merge pull request #162 from PSLmodels/fix-warnings

Avoid deprecation warnings in uprate_puf.py code

.github/workflows/pr.yml

@@ -29,8 +29,8 @@ jobs:
         env:
           POLICYENGINE_GITHUB_MICRODATA_AUTH_TOKEN: ${{ secrets.POLICYENGINE_GITHUB_MICRODATA_AUTH_TOKEN}}
           PSL_TAX_MICRODATA_RELEASE_AUTH_TOKEN: ${{ secrets.PSL_TAX_MICRODATA_RELEASE_AUTH_TOKEN}}
-      - name: Generate datasets
-        run: make flat-file
+      - name: Generate tmd files
+        run: make tmd_files
       - name: Run tests
         run: make test
       - name: Test documentation builds

.github/workflows/push.yml

@@ -32,8 +32,8 @@ jobs:
         env:
           POLICYENGINE_GITHUB_MICRODATA_AUTH_TOKEN: ${{ secrets.POLICYENGINE_GITHUB_MICRODATA_AUTH_TOKEN}}
           PSL_TAX_MICRODATA_RELEASE_AUTH_TOKEN: ${{ secrets.PSL_TAX_MICRODATA_RELEASE_AUTH_TOKEN}}
-      - name: Generate datasets
-        run: make flat-file
+      - name: Generate tmd files
+        run: make tmd_files
       - name: Run tests
         run: make test
       - name: Build documentation
@@ -44,4 +44,3 @@ jobs:
           token: ${{ secrets.GITHUB_TOKEN }}
           branch: gh-pages
           folder: docs/book/_build/html
-

Makefile

@@ -1,27 +1,66 @@
+.PHONY=clean
+clean:
+	rm -f tax_microdata_benchmarking/storage/output/*
+
+.PHONY=install
 install:
 	pip install -e .
 	python tax_microdata_benchmarking/download_prerequisites.py
 
-test:
-	pytest . -v
-
-format:
-	black . -l 79
-
-flat-file:
+tax_microdata_benchmarking/storage/output/tmd.csv.gz: \
+  tax_microdata_benchmarking/imputation_assumptions.py \
+  tax_microdata_benchmarking/datasets/tmd.py \
+  tax_microdata_benchmarking/datasets/puf.py \
+  tax_microdata_benchmarking/datasets/cps.py \
+  tax_microdata_benchmarking/datasets/taxcalc_dataset.py \
+  tax_microdata_benchmarking/utils/taxcalc_utils.py \
+  tax_microdata_benchmarking/utils/imputation.py \
+  tax_microdata_benchmarking/utils/is_tax_filer.py \
+  tax_microdata_benchmarking/utils/pension_contributions.py \
+  tax_microdata_benchmarking/utils/soi_replication.py \
+  tax_microdata_benchmarking/utils/soi_targets.py \
+  tax_microdata_benchmarking/utils/reweight.py \
+  tax_microdata_benchmarking/utils/trace.py \
+  tax_microdata_benchmarking/create_taxcalc_input_variables.py
 	python tax_microdata_benchmarking/create_taxcalc_input_variables.py
+
+tax_microdata_benchmarking/storage/output/tmd_growfactors.csv: \
+  tax_microdata_benchmarking/storage/input/puf_growfactors.csv \
+  tax_microdata_benchmarking/create_taxcalc_growth_factors.py
 	python tax_microdata_benchmarking/create_taxcalc_growth_factors.py
+
+tax_microdata_benchmarking/storage/output/tmd_weights.csv.gz: \
+  tax_microdata_benchmarking/storage/input/cbo_population_forecast.yaml \
+  tax_microdata_benchmarking/storage/output/tmd.csv.gz \
+  tax_microdata_benchmarking/create_taxcalc_sampling_weights.py
 	python tax_microdata_benchmarking/create_taxcalc_sampling_weights.py
 
-data: install flat-file test
+.PHONY=tmd_files
+tmd_files: tax_microdata_benchmarking/storage/output/tmd.csv.gz \
+  tax_microdata_benchmarking/storage/output/tmd_growfactors.csv \
+  tax_microdata_benchmarking/storage/output/tmd_weights.csv.gz
+
+.PHONY=test
+test: tmd_files
+	pytest . -v
+
+.PHONY=data
+data: install tmd_files test
+
+.PHONY=format
+format:
+	black . -l 79
 
+.PHONY=documentation
 documentation:
 	jb build docs/book
 
+.PHONY=reweighting-visualisation
 reweighting-visualisation:
 	tensorboard --logdir=tax_microdata_benchmarking/storage/output/reweighting
 
-tax-expenditures-report: flat-file
+.PHONY=tax-expenditures-report
+tax-expenditures-report: tmd_files
 	-pytest . --disable-warnings -m taxexp
 	diff tax_microdata_benchmarking/storage/output/tax_expenditures \
              tax_microdata_benchmarking/examination/tax_expenditures

tax_microdata_benchmarking/datasets/uprate_puf.py

@@ -156,12 +156,12 @@ def uprate_puf(puf, from_year, to_year):
     for variable in SOI_TO_PUF_POS_ONLY_RENAMES:
         growth = get_growth(variable, from_year, to_year)
         puf_variable = SOI_TO_PUF_POS_ONLY_RENAMES[variable]
-        puf[puf_variable][puf[puf_variable] > 0] *= growth
+        puf.loc[puf[puf_variable] > 0, puf_variable] *= growth
 
     for variable in SOI_TO_PUF_NEG_ONLY_RENAMES:
         growth = get_growth(variable, from_year, to_year)
         puf_variable = SOI_TO_PUF_NEG_ONLY_RENAMES[variable]
-        puf[puf_variable][puf[puf_variable] < 0] *= growth
+        puf.loc[puf[puf_variable] < 0, puf_variable] *= growth
 
     # Remaining variables, uprate purely by AGI growth
     # (for now, because I'm not sure how to handle the deductions,

tests/test_flat_file.py → tests/test_tmd_files.py

@@ -1,7 +1,7 @@
 """
-This module adds basic sanity tests for each TC-input flat file,
-checking that the totals of each variable are within the ballpark
-of the Tax-Data 2023 PUF's totals.
+This module adds basic tests for several tmd file variables,
+checking that the variable total is within the ballpark of
+the Tax-Data 2023 PUF's totals.
 """
 
 import os
@@ -21,9 +21,11 @@
     get_tax_expenditure_results,
 )
 
-warnings.filterwarnings("ignore")
 
-test_mode = os.environ.get("TEST_MODE", "lite")
+# include this test only to gather warnings information
+def test_create_taxcalc_tmd_file():
+    create_variable_file(write_file=False)
+
 
 FOLDER = Path(__file__).parent
 
@@ -159,10 +161,6 @@ def test_tax_expenditure_estimates(
     )
 
 
-def test_create_taxcalc_tmd_file():
-    create_variable_file(write_file=False)
-
-
 @pytest.mark.parametrize(
     "flat_file", datasets_to_test, ids=dataset_names_to_test
 )