Add MI under-age-1 reproducer for state dataset undercount (#135)

us/poverty/michigan_under_age_1.ipynb

@@ -0,0 +1,191 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "intro",
+   "metadata": {},
+   "source": [
+    "# Number of Children Under Age 1 in Michigan\n",
+    "\n",
+    "Calculates the weighted count of persons with `age < 1` in Michigan.\n",
+    "\n",
+    "**Two approaches compared:**\n",
+    "1. State-specific dataset (`MI.h5`)\n",
+    "2. National dataset filtered to Michigan via `state_code`\n",
+    "\n",
+    "Result: the state dataset significantly undercounts MI population (~4.1M vs actual ~10M), so the national dataset gives the realistic figure."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "imports",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2026-05-18T19:49:56.996452Z",
+     "iopub.status.busy": "2026-05-18T19:49:56.996452Z",
+     "iopub.status.idle": "2026-05-18T19:50:15.838852Z",
+     "shell.execute_reply": "2026-05-18T19:50:15.838852Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "from policyengine_us import Microsimulation\n",
+    "from huggingface_hub import hf_hub_download\n",
+    "\n",
+    "YEAR = 2026"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "md-state",
+   "metadata": {},
+   "source": [
+    "## Approach 1: State-specific MI.h5 dataset"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "state",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2026-05-18T19:50:15.841743Z",
+     "iopub.status.busy": "2026-05-18T19:50:15.841743Z",
+     "iopub.status.idle": "2026-05-18T19:50:16.968247Z",
+     "shell.execute_reply": "2026-05-18T19:50:16.968247Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "MI total population (state dataset): 4,104,577\n",
+      "MI children under age 1 (state dataset): 43,689\n"
+     ]
+    }
+   ],
+   "source": [
+    "mi_path = hf_hub_download(\n",
+    "    repo_id=\"policyengine/policyengine-us-data\",\n",
+    "    filename=\"states/MI.h5\",\n",
+    "    repo_type=\"model\",\n",
+    ")\n",
+    "sim_state = Microsimulation(dataset=mi_path)\n",
+    "age_state = sim_state.calculate(\"age\", YEAR)\n",
+    "\n",
+    "# (boolean_series).sum() applies weights once -> weighted count of True rows\n",
+    "state_total = (age_state >= 0).sum()\n",
+    "state_under_1 = (age_state < 1).sum()\n",
+    "print(f\"MI total population (state dataset): {state_total:,.0f}\")\n",
+    "print(f\"MI children under age 1 (state dataset): {state_under_1:,.0f}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "md-nat",
+   "metadata": {},
+   "source": [
+    "## Approach 2: National dataset filtered to Michigan"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "national",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2026-05-18T19:50:16.971253Z",
+     "iopub.status.busy": "2026-05-18T19:50:16.970256Z",
+     "iopub.status.idle": "2026-05-18T19:50:17.298029Z",
+     "shell.execute_reply": "2026-05-18T19:50:17.298029Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "MI total population (national dataset): 10,106,712\n",
+      "MI children under age 1 (national dataset): 101,162\n"
+     ]
+    }
+   ],
+   "source": [
+    "sim_nat = Microsimulation()\n",
+    "age_nat = sim_nat.calculate(\"age\", YEAR).values\n",
+    "weight_nat = sim_nat.calculate(\"person_weight\", YEAR).values\n",
+    "state_code_person = sim_nat.calculate(\"state_code\", YEAR, map_to=\"person\").values\n",
+    "\n",
+    "in_mi = state_code_person == \"MI\"\n",
+    "mi_total = float(weight_nat[in_mi].sum())\n",
+    "mi_under_1 = float(weight_nat[(age_nat < 1) & in_mi].sum())\n",
+    "print(f\"MI total population (national dataset): {mi_total:,.0f}\")\n",
+    "print(f\"MI children under age 1 (national dataset): {mi_under_1:,.0f}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "md-cmp",
+   "metadata": {},
+   "source": [
+    "## Comparison"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "compare",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2026-05-18T19:50:17.301058Z",
+     "iopub.status.busy": "2026-05-18T19:50:17.300058Z",
+     "iopub.status.idle": "2026-05-18T19:50:17.304642Z",
+     "shell.execute_reply": "2026-05-18T19:50:17.304642Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Source                                     MI total      Age < 1\n",
+      "----------------------------------------------------------------\n",
+      "State MI.h5 dataset                       4,104,577       43,689\n",
+      "National dataset (filter to MI)          10,106,712      101,162\n",
+      "Census / MDHHS (real-world)             ~10,100,000     ~104,000\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(f\"{'Source':<35} {'MI total':>15} {'Age < 1':>12}\")\n",
+    "print(\"-\" * 64)\n",
+    "print(f\"{'State MI.h5 dataset':<35} {state_total:>15,.0f} {state_under_1:>12,.0f}\")\n",
+    "print(f\"{'National dataset (filter to MI)':<35} {mi_total:>15,.0f} {mi_under_1:>12,.0f}\")\n",
+    "print(f\"{'Census / MDHHS (real-world)':<35} {'~10,100,000':>15} {'~104,000':>12}\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

us/searchlight_institute/reform_1_10year_budgetary_impact.csv

@@ -0,0 +1,11 @@
+Year,Budgetary Impact
+2026,-154164001783.69482
+2027,-157864084761.3623
+2028,-164597276521.37793
+2029,-167287528290.4707
+2030,-175556385052.03516
+2031,-169573356121.84375
+2032,-176599302199.34863
+2033,-178463440201.4834
+2034,-177017552448.71387
+2035,-180123710118.63232