taxcalc 4.2.1__py3-none-any.whl → 4.2.2__py3-none-any.whl

taxcalc/validation/taxsim35/expected_differences/a21-taxdiffs-expect.csv

@@ -0,0 +1,25 @@
+,# of differing records,max_diff,max_diff_index,max_diff_taxsim_val,max_diff_taxcalc_val
+iitax,0,0.0,no diff,no diff,no diff
+statetax,0,0.0,no diff,no diff,no diff
+payrolltax,0,0.0,no diff,no diff,no diff
+mtr_inctax,1,80.1,150,30.9,111.0
+mtr_state,0,0.0,no diff,no diff,no diff
+c00100,0,0.0,no diff,no diff,no diff
+e02300,0,0.0,no diff,no diff,no diff
+c02500,0,0.0,no diff,no diff,no diff
+post_phase_out_pe,0,0.0,no diff,no diff,no diff
+phased_out_pe,0,0.0,no diff,no diff,no diff
+c21040,0,0.0,no diff,no diff,no diff
+c04470,0,0.0,no diff,no diff,no diff
+c04800,0,0.0,no diff,no diff,no diff
+taxbc,0,0.0,no diff,no diff,no diff
+exemption_surtax,0,0.0,no diff,no diff,no diff
+gen_tax_credit,0,0.0,no diff,no diff,no diff
+non_refundable_child_odep_credit,0,0.0,no diff,no diff,no diff
+c11070,0,0.0,no diff,no diff,no diff
+c07180,0,0.0,no diff,no diff,no diff
+eitc,0,0.0,no diff,no diff,no diff
+c62100,0,0.0,no diff,no diff,no diff
+amt_liability,0,0.0,no diff,no diff,no diff
+iitax_before_credits_ex_AMT,0,0.0,no diff,no diff,no diff
+recovery_rebate_credit,0,0.0,no diff,no diff,no diff

taxcalc/validation/taxsim35/expected_differences/b17-taxdiffs-expect.csv

@@ -0,0 +1,25 @@
+,# of differing records,max_diff,max_diff_index,max_diff_taxsim_val,max_diff_taxcalc_val
+iitax,496,-3122.13,464,346693.19,343571.06
+statetax,0,0,no diff,no diff,no diff
+payrolltax,944,15766.13,464,42759.4,58525.53
+mtr_inctax,371,-13.87,644,41.87,28
+mtr_state,0,0,no diff,no diff,no diff
+c00100,563,-7884.17,464,1028327.24,1020443.07
+e02300,0,0,no diff,no diff,no diff
+c02500,0,0,no diff,no diff,no diff
+post_phase_out_pe,24,566.75,739,3913.52,4480.27
+phased_out_pe,30,-566.75,739,12286.48,11719.73
+c21040,0,0,no diff,no diff,no diff
+c04470,0,0,no diff,no diff,no diff
+c04800,560,-8221.45,141,399715.05,391493.6
+taxbc,984,-8184.83,454,243008.07,234823.24
+exemption_surtax,0,0,no diff,no diff,no diff
+gen_tax_credit,0,0,no diff,no diff,no diff
+non_refundable_child_odep_credit,0,0,no diff,no diff,no diff
+c11070,0,0,no diff,no diff,no diff
+c07180,0,0,no diff,no diff,no diff
+eitc,0,0,no diff,no diff,no diff
+c62100,563,-7884.17,464,1028327.24,1020443.07
+amt_liability,26,233.2,644,0,233.2
+iitax_before_credits_ex_AMT,509,-3122.13,464,346047.19,342925.06
+recovery_rebate_credit,0,0,no diff,no diff,no diff

taxcalc/validation/taxsim35/expected_differences/b18-taxdiffs-expect.csv

@@ -0,0 +1,25 @@
+,# of differing records,max_diff,max_diff_index,max_diff_taxsim_val,max_diff_taxcalc_val
+iitax,1000,-27543.059999999998,239,422043.45,394500.39
+statetax,0,0.0,no diff,no diff,no diff
+payrolltax,942,15897.89,861,43904.8,59802.69
+mtr_inctax,395,-18.090000000000003,114,42.09,24.0
+mtr_state,0,0.0,no diff,no diff,no diff
+c00100,567,-7949.869999999995,861,984467.76,976517.89
+e02300,0,0.0,no diff,no diff,no diff
+c02500,0,0.0,no diff,no diff,no diff
+post_phase_out_pe,0,0.0,no diff,no diff,no diff
+phased_out_pe,0,0.0,no diff,no diff,no diff
+c21040,0,0.0,no diff,no diff,no diff
+c04470,0,0.0,no diff,no diff,no diff
+c04800,1000,-74440.69999999995,239,1308141.76,1233701.06
+taxbc,1000,-31100.119999999995,221,467556.97,436456.85
+exemption_surtax,0,0.0,no diff,no diff,no diff
+gen_tax_credit,0,0.0,no diff,no diff,no diff
+non_refundable_child_odep_credit,15,311.75,930,1355.76,1667.51
+c11070,0,0.0,no diff,no diff,no diff
+c07180,0,0.0,no diff,no diff,no diff
+eitc,0,0.0,no diff,no diff,no diff
+c62100,1000,-74440.69999999995,239,1332141.76,1257701.06
+amt_liability,0,0.0,no diff,no diff,no diff
+iitax_before_credits_ex_AMT,1000,-27543.059999999998,239,419991.45,392448.39
+recovery_rebate_credit,0,0.0,no diff,no diff,no diff

taxcalc/validation/taxsim35/expected_differences/b19-taxdiffs-expect.csv

@@ -0,0 +1,25 @@
+,# of differing records,max_diff,max_diff_index,max_diff_taxsim_val,max_diff_taxcalc_val
+iitax,1000,-27824.47999999998,956,292614.24,264789.76
+statetax,0,0.0,no diff,no diff,no diff
+payrolltax,946,16470.230000000003,583,42555.56,59025.79
+mtr_inctax,361,-19.07,476,43.07,24.0
+mtr_state,0,0.0,no diff,no diff,no diff
+c00100,535,-8235.959999999963,583,1095818.15,1087582.19
+e02300,0,0.0,no diff,no diff,no diff
+c02500,0,0.0,no diff,no diff,no diff
+post_phase_out_pe,0,0.0,no diff,no diff,no diff
+phased_out_pe,0,0.0,no diff,no diff,no diff
+c21040,0,0.0,no diff,no diff,no diff
+c04470,0,0.0,no diff,no diff,no diff
+c04800,1000,-75201.29999999993,956,960616.86,885415.56
+taxbc,1000,-30819.72000000003,600,394678.94,363859.22
+exemption_surtax,0,0.0,no diff,no diff,no diff
+gen_tax_credit,0,0.0,no diff,no diff,no diff
+non_refundable_child_odep_credit,9,389.85000000000014,113,908.31,1298.16
+c11070,0,0.0,no diff,no diff,no diff
+c07180,0,0.0,no diff,no diff,no diff
+eitc,0,0.0,no diff,no diff,no diff
+c62100,1000,-75201.29999999993,956,986316.86,911115.56
+amt_liability,0,0.0,no diff,no diff,no diff
+iitax_before_credits_ex_AMT,1000,-27824.47999999998,956,291018.24,263193.76
+recovery_rebate_credit,0,0.0,no diff,no diff,no diff

taxcalc/validation/taxsim35/expected_differences/b20-taxdiffs-expect.csv

@@ -0,0 +1,25 @@
+,# of differing records,max_diff,max_diff_index,max_diff_taxsim_val,max_diff_taxcalc_val
+iitax,1000,-27821.880000000005,957,252485.92,224664.04
+statetax,0,0.0,no diff,no diff,no diff
+payrolltax,939,17066.6,860,50776.77,67843.37
+mtr_inctax,387,-21.15,159,50.15,29.0
+mtr_state,0,0.0,no diff,no diff,no diff
+c00100,546,-8534.540000000037,860,1450796.75,1442262.21
+e02300,1,10000.0,905,0.0,10000.0
+c02500,0,0.0,no diff,no diff,no diff
+post_phase_out_pe,0,0.0,no diff,no diff,no diff
+phased_out_pe,0,0.0,no diff,no diff,no diff
+c21040,0,0.0,no diff,no diff,no diff
+c04470,0,0.0,no diff,no diff,no diff
+c04800,1000,-75194.26000000001,957,856997.08,781802.82
+taxbc,1000,-30928.869999999995,903,446385.24,415456.37
+exemption_surtax,0,0.0,no diff,no diff,no diff
+gen_tax_credit,0,0.0,no diff,no diff,no diff
+non_refundable_child_odep_credit,7,-60.12000000000012,562,1812.92,1752.8
+c11070,0,0.0,no diff,no diff,no diff
+c07180,0,0.0,no diff,no diff,no diff
+eitc,0,0.0,no diff,no diff,no diff
+c62100,1000,-75194.26000000001,957,883097.08,807902.82
+amt_liability,0,0.0,no diff,no diff,no diff
+iitax_before_credits_ex_AMT,1000,-27821.880000000005,957,251687.92,223866.04
+recovery_rebate_credit,3,1568.03,613,0.0,1568.03

taxcalc/validation/taxsim35/expected_differences/b21-taxdiffs-expect.csv

@@ -0,0 +1,25 @@
+,# of differing records,max_diff,max_diff_index,max_diff_taxsim_val,max_diff_taxcalc_val
+iitax,1000,-27772.820000000007,557,254981.5,227208.68
+statetax,0,0.0,no diff,no diff,no diff
+payrolltax,927,17673.559999999998,359,38169.65,55843.21
+mtr_inctax,403,-25.15,252,25.15,0.0
+mtr_state,0,0.0,no diff,no diff,no diff
+c00100,588,-8838.319999999949,359,923028.96,914190.64
+e02300,0,0.0,no diff,no diff,no diff
+c02500,0,0.0,no diff,no diff,no diff
+post_phase_out_pe,0,0.0,no diff,no diff,no diff
+phased_out_pe,0,0.0,no diff,no diff,no diff
+c21040,0,0.0,no diff,no diff,no diff
+c04470,0,0.0,no diff,no diff,no diff
+c04800,1000,-75061.65999999992,557,863181.07,788119.41
+taxbc,1000,-31201.459999999992,11,236011.88,204810.42
+exemption_surtax,0,0.0,no diff,no diff,no diff
+gen_tax_credit,0,0.0,no diff,no diff,no diff
+non_refundable_child_odep_credit,6,255.17999999999984,202,1305.4,1560.58
+c11070,6,255.17999999999984,202,1305.4,1560.58
+c07180,0,0.0,no diff,no diff,no diff
+eitc,0,0.0,no diff,no diff,no diff
+c62100,1000,-75061.65999999992,557,888281.07,813219.41
+amt_liability,1,2058.18,252,0.0,2058.18
+iitax_before_credits_ex_AMT,1000,-27772.820000000007,557,253689.5,225916.68
+recovery_rebate_credit,0,0.0,no diff,no diff,no diff

taxcalc/validation/taxsim35/expected_differences/c17-taxdiffs-expect.csv

@@ -0,0 +1,25 @@
+,# of differing records,max_diff,max_diff_index,max_diff_taxsim_val,max_diff_taxcalc_val
+iitax,497,-3189.62,663,323202.99,320013.37
+statetax,0,0,no diff,no diff,no diff
+payrolltax,948,15766.12,464,44198.22,59964.34
+mtr_inctax,375,-15.12,629,43.12,28
+mtr_state,0,0,no diff,no diff,no diff
+c00100,574,-7884.17,464,1069778.22,1061894.05
+e02300,0,0,no diff,no diff,no diff
+c02500,0,0,no diff,no diff,no diff
+post_phase_out_pe,27,610.65,68,3079.35,3690
+phased_out_pe,30,-610.65,68,13120.65,12510
+c21040,651,-40340.92,328,40340.92,0
+c04470,356,23110.41,676,0,23110.41
+c04800,549,-13416.95,676,334915.13,321498.18
+taxbc,984,-8184.83,454,277251.56,269066.73
+exemption_surtax,0,0,no diff,no diff,no diff
+gen_tax_credit,0,0,no diff,no diff,no diff
+non_refundable_child_odep_credit,0,0,no diff,no diff,no diff
+c11070,0,0,no diff,no diff,no diff
+c07180,0,0,no diff,no diff,no diff
+eitc,0,0,no diff,no diff,no diff
+c62100,574,-16579.42,948,893325.42,876746
+amt_liability,47,4515.24,676,4171.03,8686.27
+iitax_before_credits_ex_AMT,511,-4427.59,676,90033.49,85605.9
+recovery_rebate_credit,0,0,no diff,no diff,no diff

taxcalc/validation/taxsim35/expected_differences/c18-taxdiffs-expect.csv

@@ -0,0 +1,25 @@
+,# of differing records,max_diff,max_diff_index,max_diff_taxsim_val,max_diff_taxcalc_val
+iitax,1000,-27840.640000000014,246,246001.89,218161.25
+statetax,0,0.0,no diff,no diff,no diff
+payrolltax,939,15897.900000000001,861,39167.24,55065.14
+mtr_inctax,384,-21.490000000000002,17,50.49,29.0
+mtr_state,0,0.0,no diff,no diff,no diff
+c00100,573,-7949.859999999986,861,963275.51,955325.65
+e02300,0,0.0,no diff,no diff,no diff
+c02500,0,0.0,no diff,no diff,no diff
+post_phase_out_pe,0,0.0,no diff,no diff,no diff
+phased_out_pe,0,0.0,no diff,no diff,no diff
+c21040,0,0.0,no diff,no diff,no diff
+c04470,0,0.0,no diff,no diff,no diff
+c04800,1000,-75244.97999999998,246,828115.91,752870.93
+taxbc,1000,-32292.660000000003,956,229141.22,196848.56
+exemption_surtax,0,0.0,no diff,no diff,no diff
+gen_tax_credit,0,0.0,no diff,no diff,no diff
+non_refundable_child_odep_credit,12,234.75,561,1293.63,1528.38
+c11070,0,0.0,no diff,no diff,no diff
+c07180,0,0.0,no diff,no diff,no diff
+eitc,0,0.0,no diff,no diff,no diff
+c62100,1000,-75244.97999999998,246,854715.91,779470.93
+amt_liability,0,0.0,no diff,no diff,no diff
+iitax_before_credits_ex_AMT,1000,-27840.640000000014,246,245271.89,217431.25
+recovery_rebate_credit,0,0.0,no diff,no diff,no diff

taxcalc/validation/taxsim35/expected_differences/c19-taxdiffs-expect.csv

@@ -0,0 +1,25 @@
+,# of differing records,max_diff,max_diff_index,max_diff_taxsim_val,max_diff_taxcalc_val
+iitax,1000,-27608.780000000028,837,312222.07,284613.29
+statetax,0,0.0,no diff,no diff,no diff
+payrolltax,942,16454.309999999998,873,46662.91,63117.22
+mtr_inctax,366,-19.259999999999998,130,48.26,29.0
+mtr_state,0,0.0,no diff,no diff,no diff
+c00100,550,-8228.23999999999,873,1128648.72,1120420.48
+e02300,0,0.0,no diff,no diff,no diff
+c02500,0,0.0,no diff,no diff,no diff
+post_phase_out_pe,0,0.0,no diff,no diff,no diff
+phased_out_pe,0,0.0,no diff,no diff,no diff
+c21040,0,0.0,no diff,no diff,no diff
+c04470,0,0.0,no diff,no diff,no diff
+c04800,1000,-74618.33999999997,837,1015746.15,941127.81
+taxbc,1000,-29988.790000000037,837,313966.08,283977.29
+exemption_surtax,0,0.0,no diff,no diff,no diff
+gen_tax_credit,0,0.0,no diff,no diff,no diff
+non_refundable_child_odep_credit,10,382.96000000000004,3,3128.1,3511.06
+c11070,0,0.0,no diff,no diff,no diff
+c07180,0,0.0,no diff,no diff,no diff
+eitc,0,0.0,no diff,no diff,no diff
+c62100,1000,-74618.33999999997,837,1025746.15,951127.81
+amt_liability,0,0.0,no diff,no diff,no diff
+iitax_before_credits_ex_AMT,1000,-27608.780000000028,837,311586.07,283977.29
+recovery_rebate_credit,0,0.0,no diff,no diff,no diff

taxcalc/validation/taxsim35/input_setup.py

@@ -0,0 +1,67 @@
+"""
+Generates TAXSIM-35 `.in` input files, downloads `.in.out-taxsim` output files,
+prepares files for Tax Calculator and zips them
+"""
+
+import os
+import glob
+import taxsim_input
+
+
+def get_ftp_output(letter, year):
+    """
+    Uses `curl` to upload assumption set input files
+    and save taxsim-35 output files
+
+    Args:
+        letter (character): letter denoting assumption set to generate data
+        year (int): year data will represent
+        offset (int): offset to alter the random number seed
+
+    Returns:
+        None
+    """
+    f = str(letter + str(year) + ".in")
+    file_out = f + ".out-taxsim"
+    os.system(
+        f"ssh -T -o StrictHostKeyChecking=no -o UserKnownHostsFile=/dev/null taxsim35@taxsim35.nber.org <{f} >{file_out}"
+    )
+
+
+def change_delim(letter, year):
+    """ "
+    This function changes the delimeter in the taxsim output files from
+    a comma to a space
+
+    This is necessary because taxsim output seems to vary - for some years
+    the separator is a comma and for others (seemingly before 2020) it's a space
+
+    Args:
+        letter (character): letter denoting assumption set to generate data
+        year (int): year data will represent
+        offset (int): offset to alter the random number seed
+
+    Returns:
+        None
+    """
+    f = str(letter + str(year) + ".in")
+    file_out = f + ".out-taxsim"
+    # Read in the file
+    with open(file_out, "r") as fin:
+        filedata = fin.read()
+
+    # Replace the target string
+    # filedata = filedata.replace(",", " ")
+    filedata = filedata.replace(" ", "")
+
+    # Write the file out again
+    with open(file_out, "w") as fout:
+        fout.write(filedata)
+
+
+def taxsim_io(assump_set, years):
+    for letter in assump_set:
+        for year in years:
+            taxsim_input.generate_datasets(letter, year)
+            get_ftp_output(letter, year)
+            change_delim(letter, year)

taxcalc/validation/taxsim35/main_comparison.py

@@ -0,0 +1,183 @@
+# DESCRIPTIONS of variable outputs can be found on the TAXSIM-35 website near
+# the bottom of the page
+# URL: https://users.nber.org/~taxsim/taxsim35/
+
+import sys
+import os
+import pandas as pd
+import numpy as np
+import tc_sims
+
+CUR_PATH = os.path.abspath(os.path.dirname(__file__))
+# check if directory exists, if not create it
+if not os.path.isdir(os.path.join(CUR_PATH, "actual_differences")):
+    os.mkdir(os.path.join(CUR_PATH, "actual_differences"))
+
+
+def main(letter, year):
+
+    test_passed = False  # set boolean to False, change in tests pass
+    # (1) generate TAXSIM-35-formatted output using Tax-Calculator tc CLI
+    tc_sims.io(letter, year)
+
+    # (2) generate tax differences
+    print("Trying to read ", f"{letter}{year}.in.out-taxsim")
+    taxsim_df = pd.read_csv(
+        f"{letter}{year}.in.out-taxsim",
+        # skipinitialspace=True,
+        # delim_whitespace=True,
+        index_col=False,
+    )
+    # taxsim_df = taxsim_df.iloc[:, 0:28]
+    taxcalc_df = pd.read_csv(
+        f"{letter}{year}.in.out-taxcalc",
+        # skipinitialspace=True,
+        index_col=0,
+    )
+
+    taxsim_out_cols_map = {
+        "taxsimid": "RECID",
+        "year": "FLPDYR",
+        "state": "state",
+        "fiitax": "iitax",
+        "siitax": "statetax",
+        "fica": "payrolltax",
+        "frate": "mtr_inctax",
+        "srate": "mtr_state",
+        # "ficar": "mtr_paytax",  # not sure why, but this is always zero from taxsim
+        # "tfica": "ptax_oasdi",  # I don't understand how fica and tfica differ in taxsim
+        "v10": "c00100",  # federal agi
+        "v11": "e02300",  # UI in federal AGI
+        "v12": "c02500",  # social security in AGI
+        # "v13": "zero_bracket_amount", # zero bracket amount (for itemizers) -- always set to zero in taxcalc output
+        "v14": "post_phase_out_pe",  # personal exemptions
+        "v15": "phased_out_pe",  # exemption phaseout
+        "v16": "c21040",  # deduction phaseout
+        "v17": "c04470",  # itemized deductions
+        "v18": "c04800",  # federal taxable income
+        "v19": "taxbc",  # tax on taxable income (no special cap gains rates)
+        "v20": "exemption_surtax",  # exemption surtax  -- always set to zero in taxcalc output
+        "v21": "gen_tax_credit",  # general tax credit  -- always set to zero in taxcalc output
+        "v22": "non_refundable_child_odep_credit",  # child tax credit (as adjusted)  # Is this right?? Should it be c07220 only?
+        "v23": "c11070",  # additional child tax credit (refundable)
+        "v24": "c07180",  # child care credit
+        "v25": "eitc",  # earned income credit (total federal)
+        "v26": "c62100",  # income for amt
+        "v27": "amt_liability",  # AMT liability
+        "v28": "iitax_before_credits_ex_AMT",  # federal tax before credits
+        # "v29": , # FICA -- is this not the same as "fica" above?
+        # state calculations all zeros since we don't do state calculations
+        # "v30": ,  #state household income
+        # "v31": , # state rent expense
+        # "v32": , # state AGI
+        # "v33": , # state exemption amount
+        # "v34": , # state standard deduction
+        # "v35": , # state itemized deductions
+        # "v36": , # state taxable income
+        # "v37": , # state property tax credit
+        # "v38": , # state child care tax credit
+        # "v39": , # state EIC
+        # "v40": , # state total credits
+        # "v41": , # state bracket rate
+        # "v42": , # earned self-employed income for FICA
+        # "v43": , # medicare tax on unearned income
+        # "v44": , # medicare tax on earned income
+        "v45": "recovery_rebate_credit",  # CARES act Recovery Rebates
+        # "v46": ,
+        # "v47": ,
+    }
+
+    # give tax-calculator variable names to taxsim output variables
+    taxsim_df.rename(columns=taxsim_out_cols_map, inplace=True)
+    taxsim_df = taxsim_df[list(taxsim_out_cols_map.values())]
+
+    diff_dict = {
+        "# of differing records": [],
+        "max_diff": [],
+        "max_diff_index": [],
+        "max_diff_taxsim_val": [],
+        "max_diff_taxcalc_val": [],
+    }
+    diff_df = taxcalc_df - taxsim_df
+    input_df = pd.read_csv(
+        f"{letter}{year}.in",
+        # skipinitialspace=True,
+        # delim_whitespace=True,
+        index_col=False,
+    )
+    with pd.ExcelWriter(
+        os.path.join(
+            CUR_PATH, "actual_differences", f"{letter}{year}differences.xlsx"
+        )
+    ) as writer:
+        # use to_excel function and specify the sheet_name and index
+        # to store the dataframe in specified sheet
+        taxsim_df.to_excel(writer, sheet_name="taxsim", index=False)
+        taxcalc_df.to_excel(writer, sheet_name="taxcalc", index=False)
+        diff_df.to_excel(writer, sheet_name="differences", index=False)
+        input_df.to_excel(writer, sheet_name="inputs", index=False)
+
+    for col in taxsim_df.columns[3:]:
+        df_diff = pd.DataFrame({"a": taxsim_df[col], "b": taxcalc_df[col]})
+        df_diff_recs = df_diff[df_diff["a"] != df_diff["b"]]
+        diff_dict["# of differing records"].append(df_diff_recs.shape[0])
+
+        ind, max_val = max(
+            enumerate(
+                abs(x - y)
+                for x, y in zip(taxcalc_df.loc[:, col], taxsim_df.loc[:, col])
+            ),
+            key=lambda x: x[1],
+        )
+
+        diff_dict["max_diff"].append(
+            taxcalc_df.loc[ind, col] - taxsim_df.loc[ind, col]
+        )
+        if max_val != 0:
+            diff_dict["max_diff_index"].append(ind)
+            diff_dict["max_diff_taxsim_val"].append(taxsim_df.loc[ind, col])
+            diff_dict["max_diff_taxcalc_val"].append(taxcalc_df.loc[ind, col])
+        else:
+            diff_dict["max_diff_index"].append("no diff")
+            diff_dict["max_diff_taxsim_val"].append("no diff")
+            diff_dict["max_diff_taxcalc_val"].append("no diff")
+
+    actual_df = pd.DataFrame(diff_dict, index=taxsim_df.columns[3:])
+    print(
+        f"Difference in dataframes for assumption set {letter} in year {year}"
+    )
+    print(actual_df)
+
+    # (3) check for difference between LYY.taxdiffs-actual and LYY.taxdiffs-expect
+    expected_file_name = os.path.join(
+        CUR_PATH, "expected_differences", f"{letter}{year}-taxdiffs-expect.csv"
+    )
+    if os.path.isfile(expected_file_name):
+        expect_df = pd.read_csv(expected_file_name, index_col=0)
+        print(actual_df.eq(expect_df))
+        test_passed = np.allclose(
+            actual_df[["# of differing records", "max_diff"]].values,
+            expect_df[["# of differing records", "max_diff"]].values
+                      )
+
+        print(
+            "Above, True values mean the element is the same between the ACTUAL and EXPECT dataframes. "
+            + "(EXPECT files are used for debugging purposes.)"
+        )
+    else:
+        print("This EXPECT file doesn't exist.")
+
+    # (4) Write the created df to *.taxdiffs-actual
+    actual_df.to_csv(
+        os.path.join(
+            CUR_PATH,
+            "actual_differences",
+            f"{letter}{year}-taxdiffs-actual.csv",
+        )
+    )
+
+    return test_passed
+
+
+if __name__ == "__main__":
+    sys.exit(main())

taxcalc/validation/taxsim35/prepare_taxcalc_input.py

@@ -0,0 +1,161 @@
+"""
+Translates TAXSIM-35 input file to Tax-Calculator tc input file.
+"""
+
+# CODING-STYLE CHECKS:
+# pycodestyle prepare_tc_input.py
+# pylint --disable=locally-disabled prepare_tc_input.py
+
+import argparse
+import os
+import sys
+import numpy as np
+import pandas as pd
+
+
+TAXSIM_TC_MAP = {
+    "taxsimid": "RECID",
+    "year": "FLPDYR",
+    # 'state': # no Tax-Calculator use of TAXSIM variable 3, state code
+    # 'mstat', # Tax-Calculator MARS differs from TAXSIM mstat
+    "page": "age_head",
+    "sage": "age_spouse",
+    # 'depx': "", # no Tax-Calculator variable for total number of dependents
+    "dep13": "nu13",
+    "dep17": "nu18",
+    # 'dep18': "n24", #"f2441", # no direct Tax-Calculator use of number EIC qualified dependents
+    "pwages": "e00200p",
+    "swages": "e00200s",
+    "psemp": "e00900p",
+    "ssemp": "e00900s",
+    "dividends": "e00650",
+    "intrec": "e00300",
+    "stcg": "p22250",
+    "ltcg": "p23250",
+    "otherprop": "e02000",
+    "nonprop": "e00800",
+    "pensions": "e01700",
+    "gssi": "e02400",
+    # 'ui': 'e02300',  # For TAXSIM-35, UI is separated between primary and secondary filers
+    # 'transfers': # no Tax-Calculator use of TAXSIM variable 22, non-taxable transfers
+    # 'rentpaid' # no Tax-Calculator use of TAXSIM variable 23, rent paid
+    "proptax": "e18500",
+    "otheritem": "e18400",
+    "childcare": "e32800",
+    "mortgage": "e19200",
+    "scorp": "e26270",
+    # 'pbusinc': 'e00900p', # Not perfect match for this in Tax-Calculator -- will add to e00900s below
+    # 'pprofinc': # no direct analog in Tax-Calculator
+    # 'sbusinc': 'e00900s', # Not perfect match for this in Tax-Calculator -- will add to e00900s below
+    # 'sprofinc':# no direct analog in Tax-Calculator
+}
+
+
+def main(file_in_name, file_out_name):
+    """
+    Translates TAXSIM-35 input file into a Tax-Calculator CSV-formatted
+    tc input file. Any pre-existing OUTPUT file contents are overwritten.
+    For details on Internet TAXSIM version 32 INPUT format, go to
+    https://users.nber.org/~taxsim/taxsim35/
+
+    Args:
+        file_in_name (string): name of input file to run taxcalc with
+        file_out_name (string): name of file to save taxcalc output to
+
+    Returns:
+        None
+    """
+    print("File in and out names: ", file_in_name, file_out_name)
+    # check INPUT filename
+    if not os.path.isfile(file_in_name):
+        emsg = "INPUT file named {} does not exist".format(file_in_name)
+        sys.stderr.write("ERROR: {}\n".format(emsg))
+        assert False
+    # check OUTPUT filename
+    if file_out_name == "":
+        sys.stderr.write("ERROR: must specify OUTPUT file name\n")
+        assert False
+    if os.path.isfile(file_out_name):
+        os.remove(file_out_name)
+    # read TAXSIM-35 INPUT file into a pandas DataFrame
+    ivar = pd.read_csv(file_in_name, header=0, index_col=False)
+    # Drop 'idtl' – used to generate detailed output
+    ivar.drop(columns=["idtl"], inplace=True)
+    # translate INPUT variables into OUTPUT variables
+    invar = translate(ivar)
+    # write OUTPUT file containing Tax-Calculator input variables
+    invar.to_csv(file_out_name, index=False)
+    # return no-error exit code
+    return 0
+
+
+# end of main function code
+
+
+def translate(ivar):
+    """
+    Translate TAXSIM-35 input variables into Tax-Calculator input variables.
+    Both ivar and returned invar are pandas DataFrame objects.
+    """
+    assert isinstance(ivar, pd.DataFrame)
+    # Rename variables to be consistent with Tax-Calculator naming conventions
+    invar = ivar.rename(TAXSIM_TC_MAP, axis=1)
+    invar["n24"] = ivar["dep17"]
+    # Create variables for Tax-Calculator that aren't directly represented in TAXSIM
+    invar["e02000"] += invar[
+        "e26270"
+    ]  # add active scorp income to "otherprop" income from taxsim
+    mstat = ivar["mstat"]
+    assert np.all(np.logical_or(mstat == 1, mstat == 2))
+    num_deps = ivar["depx"]
+    mars = np.where(mstat == 1, np.where(num_deps > 0, 4, 1), 2)
+    assert np.all(
+        np.logical_or(mars == 1, np.logical_or(mars == 2, mars == 4))
+    )
+    invar["MARS"] = mars
+    num_eitc_qualified_kids = ivar["dep18"]
+    invar["f2441"] = invar["nu13"]
+    invar["EIC"] = np.minimum(num_eitc_qualified_kids, 3)
+    num_taxpayers = np.where(mars == 2, 2, 1)
+    invar["XTOT"] = num_taxpayers + num_deps
+    invar["e00200"] = invar["e00200p"] + invar["e00200s"]
+    invar["e00900p"] += invar["pbusinc"]
+    invar["e00900s"] += invar[
+        "sbusinc"
+    ]  # NB: will need to check this later because in TAXSIM, the e00900 does not include QBI, but businc does...
+    invar["e00900"] = invar["e00900p"] + invar["e00900s"]
+    invar["e00600"] = invar["e00650"]
+    invar["e01500"] = invar["e01700"]
+    invar["e02300"] = invar["pui"] + invar["sui"]
+    # variables for QBID calculation
+    invar["PT_SSTB_income"] = (
+        0  # np.where(invar['pprofinc'] + invar['sprofinc'] > 0, 1, 0)
+    )
+    invar["PT_SSTB_income"] = (
+        0  # np.where(invar['e26270'] > 0, 1, invar['PT_SSTB_income'])
+    )
+
+    # Drop TAXSIM variables not used in Tax-Calculator
+    invar.drop(
+        columns=[
+            "state",
+            "mstat",
+            "depx",
+            # "dep18",
+            "transfers",
+            "rentpaid",
+            "pprofinc",
+            "pbusinc",
+            "sbusinc",
+            "sprofinc",
+            "pui",
+            "sui",
+        ],
+        inplace=True,
+    )
+
+    return invar
+
+
+if __name__ == "__main__":
+    sys.exit(main())