Move all randomness to data package for deterministic country package

household_counts.txt

@@ -0,0 +1,12 @@
+L0 Value | Household Count
+---------|----------------
+4.9999e-07 | 7,977
+4.999e-07 | 8,005
+5.0000078125e-07 | 7,784
+5.000015625e-07 | 7,617
+5.00003125e-07 | 8,069
+5.0000625e-07 | 7,908
+5.000125e-07 | 7,937
+5.00025e-07 | 7,889
+5.0005e-07 | 7,935
+5.002e-07 | 7,897

policyengine_us_data/datasets/cps/cps.py

@@ -14,6 +14,7 @@
 )
 from microimpute.models.qrf import QRF
 import logging
+from policyengine_us_data.parameters import load_take_up_rate
 
 
 test_lite = os.environ.get("TEST_LITE") == "true"
@@ -207,25 +208,58 @@ def add_takeup(self):
     from policyengine_us import system, Microsimulation
 
     baseline = Microsimulation(dataset=self)
-    parameters = baseline.tax_benefit_system.parameters(self.time_period)
 
+    # Generate all stochastic take-up decisions using take-up rates from parameter files
+    # This keeps the country package purely deterministic
     generator = np.random.default_rng(seed=100)
 
-    eitc_takeup_rates = parameters.gov.irs.credits.eitc.takeup
+    # Load take-up rates from parameter files
+    eitc_rates_by_children = load_take_up_rate("eitc", self.time_period)
+    dc_ptc_rate = load_take_up_rate("dc_ptc", self.time_period)
+    snap_rate = load_take_up_rate("snap", self.time_period)
+    aca_rate = load_take_up_rate("aca", self.time_period)
+    medicaid_rate = load_take_up_rate("medicaid", self.time_period)
+    head_start_rate = load_take_up_rate("head_start", self.time_period)
+    early_head_start_rate = load_take_up_rate("early_head_start", self.time_period)
+
+    # EITC: varies by number of children
     eitc_child_count = baseline.calculate("eitc_child_count").values
-    eitc_takeup_rate = eitc_takeup_rates.calc(eitc_child_count)
+    eitc_takeup_rate = np.array(
+        [eitc_rates_by_children.get(min(int(c), 3), 0.85) for c in eitc_child_count]
+    )
     data["takes_up_eitc"] = (
         generator.random(len(data["tax_unit_id"])) < eitc_takeup_rate
     )
-    dc_ptc_takeup_rate = parameters.gov.states.dc.tax.income.credits.ptc.takeup
+
+    # DC Property Tax Credit
     data["takes_up_dc_ptc"] = (
-        generator.random(len(data["tax_unit_id"])) < dc_ptc_takeup_rate
+        generator.random(len(data["tax_unit_id"])) < dc_ptc_rate
     )
-    generator = np.random.default_rng(seed=100)
 
-    data["snap_take_up_seed"] = generator.random(len(data["spm_unit_id"]))
-    data["aca_take_up_seed"] = generator.random(len(data["tax_unit_id"]))
-    data["medicaid_take_up_seed"] = generator.random(len(data["person_id"]))
+    # SNAP
+    data["takes_up_snap_if_eligible"] = (
+        generator.random(len(data["spm_unit_id"])) < snap_rate
+    )
+
+    # ACA
+    data["takes_up_aca_if_eligible"] = (
+        generator.random(len(data["tax_unit_id"])) < aca_rate
+    )
+
+    # Medicaid
+    data["takes_up_medicaid_if_eligible"] = (
+        generator.random(len(data["person_id"])) < medicaid_rate
+    )
+
+    # Head Start
+    data["takes_up_head_start_if_eligible"] = (
+        generator.random(len(data["person_id"])) < head_start_rate
+    )
+
+    # Early Head Start
+    data["takes_up_early_head_start_if_eligible"] = (
+        generator.random(len(data["person_id"])) < early_head_start_rate
+    )
 
     self.save_dataset(data)
 

policyengine_us_data/parameters/__init__.py

@@ -0,0 +1,53 @@
+"""
+Take-up rate parameters for stochastic simulation.
+
+These parameters are stored in the data package to keep the country package
+as a purely deterministic rules engine.
+"""
+import yaml
+from pathlib import Path
+
+PARAMETERS_DIR = Path(__file__).parent
+
+
+def load_take_up_rate(variable_name: str, year: int = 2018) -> float:
+    """Load take-up rate from YAML parameter files.
+
+    Args:
+        variable_name: Name of the take-up parameter file (without .yaml)
+        year: Year for which to get the rate
+
+    Returns:
+        Take-up rate as a float between 0 and 1
+    """
+    yaml_path = PARAMETERS_DIR / "take_up" / f"{variable_name}.yaml"
+
+    with open(yaml_path) as f:
+        data = yaml.safe_load(f)
+
+    # Handle EITC special case (has rates_by_children instead of values)
+    if "rates_by_children" in data:
+        return data["rates_by_children"]  # Return the dict
+
+    # Find the applicable value for the year
+    values = data["values"]
+    applicable_value = None
+
+    for date_key, value in sorted(values.items()):
+        # Handle both string and datetime.date objects from YAML
+        if hasattr(date_key, "year"):
+            # It's a datetime.date object
+            date_year = date_key.year
+        else:
+            # It's a string
+            date_year = int(date_key.split("-")[0])
+
+        if date_year <= year:
+            applicable_value = value
+        else:
+            break
+
+    if applicable_value is None:
+        raise ValueError(f"No take-up rate found for {variable_name} in {year}")
+
+    return applicable_value

policyengine_us_data/parameters/take_up/aca.yaml

@@ -0,0 +1,10 @@
+description: Percentage of eligible people who do enroll in Affordable Care Act coverage, if eligible.
+metadata:
+  label: ACA takeup rate
+  unit: /1
+  period: year
+  reference:
+    - title: KFF "A Closer Look at the Remaining Uninsured Population Eligible for Medicaid and CHIP"
+      href: https://www.kff.org/uninsured/issue-brief/a-closer-look-at-the-remaining-uninsured-population-eligible-for-medicaid-and-chip/#:~:text=the%20uninsured%20rate%20dropped%20to,States%20began%20the
+values:
+  2018-01-01: 0.672

policyengine_us_data/parameters/take_up/dc_ptc.yaml

@@ -0,0 +1,11 @@
+description: The share of eligible individuals who claim the DC property tax credit.
+metadata:
+  unit: /1
+  label: DC property tax credit takeup rate
+  period: year
+  reference:
+    - title: District of Columbia Tax Expenditure Report, 2024
+      href: https://ora-cfo.dc.gov/sites/default/files/dc/sites/ora-cfo/publication/attachments/2024%20Tax%20Expenditure%20Report.pdf#page=234
+values:
+  # 37,133 (from 2024 Tax Expenditure Report) / 131,791,388 (PolicyEngine DC PTC value estimate)
+  2021-01-01: 0.32

policyengine_us_data/parameters/take_up/early_head_start.yaml

@@ -0,0 +1,9 @@
+description: Percentage of eligible infants and toddlers who enroll in Early Head Start.
+metadata:
+  label: Early Head Start take-up rate
+  unit: /1
+  reference:
+    - title: NIEER State(s) of Head Start and Early Head Start Report
+      href: https://nieer.org/research-library/states-head-start-early-head-start
+values:
+  2020-09-01: 0.09

policyengine_us_data/parameters/take_up/eitc.yaml

@@ -0,0 +1,12 @@
+description: The share of eligible individuals who claim the EITC (by number of children).
+metadata:
+  label: EITC take-up rate by number of children
+  reference:
+    - title: National Taxpayer Advocate Special Report to Congress 2020 | IRS
+      href: https://www.taxpayeradvocate.irs.gov/wp-content/uploads/2020/08/JRC20_Volume3.pdf#page=62
+# Maps number of children to take-up rate
+rates_by_children:
+  0: 0.65
+  1: 0.86
+  2: 0.85
+  3: 0.85  # Assume same as 2

policyengine_us_data/parameters/take_up/head_start.yaml

@@ -0,0 +1,10 @@
+description: Percentage of eligible children who enroll in Head Start.
+metadata:
+  label: Head Start take-up rate
+  unit: /1
+  reference:
+    - title: NIEER State(s) of Head Start and Early Head Start Report
+      href: https://nieer.org/research-library/states-head-start-early-head-start
+values:
+  2020-09-01: 0.40
+  2021-09-01: 0.30

policyengine_us_data/parameters/take_up/medicaid.yaml

@@ -0,0 +1,10 @@
+description: Percentage of people who do enroll in Medicaid, if eligible.
+metadata:
+  label: Medicaid takeup rate
+  unit: /1
+  period: year
+  reference:
+    - title: KFF "A Closer Look at the Remaining Uninsured Population Eligible for Medicaid and CHIP"
+      href: https://www.kff.org/uninsured/issue-brief/a-closer-look-at-the-remaining-uninsured-population-eligible-for-medicaid-and-chip/#:~:text=the%20uninsured%20rate%20dropped%20to,States%20began%20the
+values:
+  2018-01-01: 0.93

policyengine_us_data/parameters/take_up/snap.yaml

@@ -0,0 +1,9 @@
+description: Percentage of eligible SNAP recipients who claim SNAP.
+metadata:
+  label: SNAP takeup rate
+  unit: /1
+  reference:
+    - title: USDA
+      href: https://www.fns.usda.gov/usamap
+values:
+  2018-01-01: 0.82