Add summary file

tax_microdata_benchmarking/create_summary_file.py

@@ -0,0 +1,32 @@
+from tax_microdata_benchmarking.create_flat_file import taxcalc_extension
+from policyengine_us import Simulation
+import pandas as pd
+from pathlib import Path
+
+sim = Simulation(reform=taxcalc_extension, situation={"person_id": 1})
+taxcalc_cps = pd.read_csv("cps.csv.gz")
+
+summary_file = """# PolicyEngine US Tax-Calculator flat file
+
+This file contains a summary of the Tax-Calculator microdata file. It is intended to be used as a reference for the Tax-Calculator microdata file.
+"""
+
+added_columns = []
+
+variables = sim.tax_benefit_system.variables
+for variable in variables.values():
+    if variable.name.startswith("tc_"):
+        added_columns.append(variable.name[3:])
+
+# Add 'The flat file currently has X out of Y (Z%) columns in the Tax-Calculator CPS microdata file'.
+
+summary_file += f"\nThe flat file currently has {len(added_columns)} out of 68 ({len(added_columns) / len(taxcalc_cps.columns):.0%}) columns in the Tax-Calculator CPS microdata file.\n"
+
+for variable in variables.values():
+    if variable.name.startswith("tc_"):
+        summary_file += f"\n## {variable.name[3:]}\n\n{variable.label}\n\n"
+
+FOLDER = Path(__file__).parent
+
+with open(FOLDER / "summary.md", "w") as file:
+    file.write(summary_file)

tax_microdata_benchmarking/summary.md

@@ -0,0 +1,105 @@
+# PolicyEngine US Tax-Calculator flat file
+
+This file contains a summary of the Tax-Calculator microdata file. It is intended to be used as a reference for the Tax-Calculator microdata file.
+
+The flat file currently has 20 out of 68 (29%) columns in the Tax-Calculator CPS microdata file.
+
+## RECID
+
+record ID
+
+
+## MARS
+
+filing status
+
+
+## e00200p
+
+wages less pension contributions (filer)
+
+
+## e00200s
+
+wages less pension contributions (spouse)
+
+
+## e00200
+
+TaxCalc Variable Alias
+
+
+## age_head
+
+age of head of tax unit
+
+
+## age_spouse
+
+age of spouse of head of tax unit
+
+
+## blind_head
+
+blindness of head of tax unit
+
+
+## blind_spouse
+
+blindness of spouse of head of tax unit
+
+
+## fips
+
+FIPS state code
+
+
+## s006
+
+tax unit weight
+
+
+## FLPDYR
+
+tax year to calculate for
+
+
+## EIC
+
+EITC-qualifying children
+
+
+## nu18
+
+number of people under 18
+
+
+## n1820
+
+number of people 18-20
+
+
+## nu13
+
+number of people under 13
+
+
+## nu06
+
+number of people under 6
+
+
+## n24
+
+number of people eligible for the CTC
+
+
+## elderly_dependents
+
+number of elderly dependents
+
+
+## f2441
+
+CDCC-qualifying children
+