Increase Python version for env and tests

.github/workflows/check_black.yml

@@ -7,9 +7,9 @@ jobs:
   lint:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v5
       - uses: actions/setup-python@v2
       - uses: psf/black@stable
         with:
-          options: " --check"
+          options: "-l 79 --check"
           src: "."

.github/workflows/deploy_docs.yml

@@ -9,16 +9,16 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@v2 # If you're using actions/checkout@v2 you must set persist-credentials to false in most cases for the deployment to work correctly.
+        uses: actions/checkout@v5
         with:
           persist-credentials: false
 
       - name: Setup Miniconda
-        uses: conda-incubator/setup-miniconda@v2
+        uses: conda-incubator/setup-miniconda@v3
         with:
           activate-environment: taxdata-dev
           environment-file: environment.yml
-          python-version: 3.7
+          python-version: 3.13
           auto-activate-base: false
 
       - name: Build # Build Jupyter Book

.github/workflows/docs_check.yml

@@ -6,16 +6,16 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@v2 # If you're using actions/checkout@v2 you must set persist-credentials to false in most cases for the deployment to work correctly.
+        uses: actions/checkout@v5
         with:
           persist-credentials: false
 
       - name: Setup Miniconda
-        uses: conda-incubator/setup-miniconda@v2
+        uses: conda-incubator/setup-miniconda@v3
         with:
           activate-environment: taxdata-dev
           environment-file: environment.yml
-          python-version: 3.7
+          python-version: 3.13
           auto-activate-base: false
 
       - name: Build # Build Jupyter Book

.github/workflows/test.yml

@@ -1,21 +1,23 @@
-name: Test data
+name: Test source code
 
 on: [push, pull_request]
 
 jobs:
   build:
-    runs-on: ubuntu-latest
+    runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        python-version: [3.7]
+        os: [ubuntu-latest, windows-latest]
+        python-version: ['3.11', '3.12', '3.13']
+
     steps:
       - name: checkout
         uses: actions/checkout@master
         with:
           persist-credentials: false
 
       - name: Setup Miniconda using Python ${{ matrix.python-version }}
-        uses: conda-incubator/setup-miniconda@v2
+        uses: conda-incubator/setup-miniconda@v3
         with:
           activate-environment: taxdata-dev
           environment-file: environment.yml

cps_stage2/dataprep.py

@@ -24,10 +24,16 @@ def target(target_val, pop, factor, value):
         weights * factors["APOPSNR"][year],
         weights * factors["ARETS"][year],
     )
-    single_returns = np.where((data["mars"] == 1) & (data["filer"] == 1), s006, 0)
-    joint_returns = np.where((data["mars"] == 2) & (data["filer"] == 1), s006, 0)
+    single_returns = np.where(
+        (data["mars"] == 1) & (data["filer"] == 1), s006, 0
+    )
+    joint_returns = np.where(
+        (data["mars"] == 2) & (data["filer"] == 1), s006, 0
+    )
     hh_returns = np.where((data["mars"] == 4) & (data["filer"] == 1), s006, 0)
-    returns_w_ss = np.where((data["e02400"] > 0) & (data["filer"] == 1), s006, 0)
+    returns_w_ss = np.where(
+        (data["e02400"] > 0) & (data["filer"] == 1), s006, 0
+    )
     dep_exemptions = (
         np.where(data["mars"] == 2, data["XTOT"] - 2, data["XTOT"] - 1) * s006
     )
@@ -45,27 +51,39 @@ def target(target_val, pop, factor, value):
     # wage distribution
     wage1 = np.where(data["agi"] <= 10000, data["e00200"], 0) * s006
     wage2 = (
-        np.where((data["agi"] > 10000) & (data["agi"] <= 20000), data["e00200"], 0)
+        np.where(
+            (data["agi"] > 10000) & (data["agi"] <= 20000), data["e00200"], 0
+        )
         * s006
     )
     wage3 = (
-        np.where((data["agi"] > 20000) & (data["agi"] <= 30000), data["e00200"], 0)
+        np.where(
+            (data["agi"] > 20000) & (data["agi"] <= 30000), data["e00200"], 0
+        )
         * s006
     )
     wage4 = (
-        np.where((data["agi"] > 30000) & (data["agi"] <= 40000), data["e00200"], 0)
+        np.where(
+            (data["agi"] > 30000) & (data["agi"] <= 40000), data["e00200"], 0
+        )
         * s006
     )
     wage5 = (
-        np.where((data["agi"] > 40000) & (data["agi"] <= 50000), data["e00200"], 0)
+        np.where(
+            (data["agi"] > 40000) & (data["agi"] <= 50000), data["e00200"], 0
+        )
         * s006
     )
     wage6 = (
-        np.where((data["agi"] > 50000) & (data["agi"] <= 75000), data["e00200"], 0)
+        np.where(
+            (data["agi"] > 50000) & (data["agi"] <= 75000), data["e00200"], 0
+        )
         * s006
     )
     wage7 = (
-        np.where((data["agi"] > 75000) & (data["agi"] <= 100_000), data["e00200"], 0)
+        np.where(
+            (data["agi"] > 75000) & (data["agi"] <= 100_000), data["e00200"], 0
+        )
         * s006
     )
     wage8 = np.where(data["agi"] > 100_000, data["e00200"], 0) * s006
@@ -118,15 +136,27 @@ def target(target_val, pop, factor, value):
     target_name = "SS_return"
     rhs_vars["returns_w_ss"] = targets[year][target_name] - returns_w_ss.sum()
     target_name = "Dep_return"
-    rhs_vars["dep_exemptions"] = targets[year][target_name] - dep_exemptions.sum()
-    rhs_vars["interest"] = target(targets[year]["INTS"], apopn, aints, interest.sum())
-    rhs_vars["dividend"] = target(targets[year]["DIVS"], apopn, adivs, dividend.sum())
+    rhs_vars["dep_exemptions"] = (
+        targets[year][target_name] - dep_exemptions.sum()
+    )
+    rhs_vars["interest"] = target(
+        targets[year]["INTS"], apopn, aints, interest.sum()
+    )
+    rhs_vars["dividend"] = target(
+        targets[year]["DIVS"], apopn, adivs, dividend.sum()
+    )
     rhs_vars["biz_income"] = target(
         targets[year]["SCHCI"], apopn, aschci, biz_income.sum()
     )
-    rhs_vars["biz_loss"] = target(targets[year]["SCHCL"], apopn, aschcl, biz_loss.sum())
-    rhs_vars["cap_gain"] = target(targets[year]["CGNS"], apopn, acgns, cap_gain.sum())
-    rhs_vars["pension"] = target(targets[year]["Pension"], apopn, atxpy, pension.sum())
+    rhs_vars["biz_loss"] = target(
+        targets[year]["SCHCL"], apopn, aschcl, biz_loss.sum()
+    )
+    rhs_vars["cap_gain"] = target(
+        targets[year]["CGNS"], apopn, acgns, cap_gain.sum()
+    )
+    rhs_vars["pension"] = target(
+        targets[year]["Pension"], apopn, atxpy, pension.sum()
+    )
     rhs_vars["sch_e_income"] = target(
         targets[year]["SCHEI"], apopn, aschei, sch_e_income.sum()
     )
@@ -136,15 +166,33 @@ def target(target_val, pop, factor, value):
     rhs_vars["ss_income"] = target(
         targets[year]["SS"], apopsnr, asocsec, ss_income.sum()
     )
-    rhs_vars["ucomp"] = target(targets[year]["UCOMP"], apopn, aucomp, ucomp.sum())
-    rhs_vars["wage1"] = target(targets[year]["wage1"], apopn, awage, wage1.sum())
-    rhs_vars["wage2"] = target(targets[year]["wage2"], apopn, awage, wage2.sum())
-    rhs_vars["wage3"] = target(targets[year]["wage3"], apopn, awage, wage3.sum())
-    rhs_vars["wage4"] = target(targets[year]["wage4"], apopn, awage, wage4.sum())
-    rhs_vars["wage5"] = target(targets[year]["wage5"], apopn, awage, wage5.sum())
-    rhs_vars["wage6"] = target(targets[year]["wage6"], apopn, awage, wage6.sum())
-    rhs_vars["wage7"] = target(targets[year]["wage7"], apopn, awage, wage7.sum())
-    rhs_vars["wage8"] = target(targets[year]["wage8"], apopn, awage, wage8.sum())
+    rhs_vars["ucomp"] = target(
+        targets[year]["UCOMP"], apopn, aucomp, ucomp.sum()
+    )
+    rhs_vars["wage1"] = target(
+        targets[year]["wage1"], apopn, awage, wage1.sum()
+    )
+    rhs_vars["wage2"] = target(
+        targets[year]["wage2"], apopn, awage, wage2.sum()
+    )
+    rhs_vars["wage3"] = target(
+        targets[year]["wage3"], apopn, awage, wage3.sum()
+    )
+    rhs_vars["wage4"] = target(
+        targets[year]["wage4"], apopn, awage, wage4.sum()
+    )
+    rhs_vars["wage5"] = target(
+        targets[year]["wage5"], apopn, awage, wage5.sum()
+    )
+    rhs_vars["wage6"] = target(
+        targets[year]["wage6"], apopn, awage, wage6.sum()
+    )
+    rhs_vars["wage7"] = target(
+        targets[year]["wage7"], apopn, awage, wage7.sum()
+    )
+    rhs_vars["wage8"] = target(
+        targets[year]["wage8"], apopn, awage, wage8.sum()
+    )
 
     model_vars = [
         "single_returns",

cps_stage2/stage2.py

@@ -63,7 +63,9 @@ def main():
     for year in range(START_YEAR, END_YEAR + 1):
         try:
             factor_match = _factors[year].equals(CUR_FACTORS[year])
-            target_match = stage_2_targets[f"{year}"].equals(CUR_TARGETS[f"{year}"])
+            target_match = stage_2_targets[f"{year}"].equals(
+                CUR_TARGETS[f"{year}"]
+            )
             if files_match and factor_match and target_match:
                 print(f"Skipping {year}")
                 skipped_years.append(year)

createpuf.py

@@ -49,13 +49,18 @@ def dataprep(data):
     """
     # we use a slightly modified version of mars for matching.
     # _mars = 1 if single, 3 if HoH, 2 any type of joint filer
-    data["_mars"] = np.where(data["mars"] == 1, 1, np.where(data["mars"] == 4, 3, 2))
+    data["_mars"] = np.where(
+        data["mars"] == 1, 1, np.where(data["mars"] == 4, 3, 2)
+    )
     data["const"] = 1
     data["bil"] = np.maximum(0, data["e00900"])
     data["fil"] = np.maximum(0, data["e02100"])
     data["tpi"] = data[INC_VARS].sum(axis=1)
     data["wage_share"] = np.divide(
-        data["e00200"], data["tpi"], out=np.zeros(data.shape[0]), where=data["tpi"] != 0
+        data["e00200"],
+        data["tpi"],
+        out=np.zeros(data.shape[0]),
+        where=data["tpi"] != 0,
     )
     data["cap_inc"] = data[CAP_VARS].sum(axis=1)
     data["cap_share"] = np.divide(
@@ -73,25 +78,33 @@ def dataprep(data):
         ),
         0,
     )
-    data["people"] = np.where(data["_mars"] == 2, data["depne"] + 2, data["depne"] + 1)
+    data["people"] = np.where(
+        data["_mars"] == 2, data["depne"] + 2, data["depne"] + 1
+    )
     data["people"] = np.minimum(5, data["people"])
     wage_flag = (data["e00200"] != 0).astype(int)
     # self employment flag
-    se_flag = np.logical_or(data["e00900"] != 0, data["e02100"] != 0).astype(int)
+    se_flag = np.logical_or(data["e00900"] != 0, data["e02100"] != 0).astype(
+        int
+    )
     # income source flags
     data["se1"] = np.where(wage_flag & ~se_flag, 1, 0)
     data["se2"] = np.where(~wage_flag & se_flag, 1, 0)
     data["se3"] = np.where(wage_flag & se_flag, 1, 0)
     data["_depne"] = np.where(
-        np.logical_and(data["mars"] == 3, data["_depne"] == 0), 1, data["_depne"]
+        np.logical_and(data["mars"] == 3, data["_depne"] == 0),
+        1,
+        data["_depne"],
     )
 
     return data
 
 
 # create CPS tax units
 print("Creating CPS tax units")
-raw_cps = cps.create(DATA_PATH, exportpkl=True, cps_files=[CPS_YEAR], benefits=False)
+raw_cps = cps.create(
+    DATA_PATH, exportpkl=True, cps_files=[CPS_YEAR], benefits=False
+)
 # minor PUF prep
 print("Prepping PUF")
 puf2011 = pd.read_csv(Path(DATA_PATH, "puf2011.csv"))
@@ -158,7 +171,9 @@ def dataprep(data):
 
 # merge all the data together
 print("Merging matched data")
-data = pd.merge(raw_puf, match_index, how="inner", left_on="recid", right_on="recip")
+data = pd.merge(
+    raw_puf, match_index, how="inner", left_on="recid", right_on="recip"
+)
 data = pd.merge(
     data,
     filers,

environment.yml

@@ -2,11 +2,11 @@ name: taxdata-dev
 channels:
 - conda-forge
 dependencies:
-- python>=3.6.5
-- numpy>=1.12.1
-- pandas>=0.20.3
+- "python>=3.11, <3.14"
+- "numpy>=1.26"
+- "pandas>=2.2"
+- "bokeh>=3.7"
 - scipy>=0.18.1
-- bokeh>=0.12.3
 - statsmodels
 - pytest
 - pulp
@@ -21,9 +21,9 @@ dependencies:
 - python-chromedriver-binary
 - tabulate
 - pre-commit
-- taxcalc>=3.5.0
 - pip
 - pip:
   - requests-html
   - black
+  - taxcalc>=5.3.0
   - jupyter-book>=0.9.1