def run_calc(self): """ Creates baseline, reform, and + $1 Tax-Calculator objects Returns: self.calc1: Calculator object for current law self.calc_reform: Calculator object for reform self.calc_mtr: Calculator object for + $1 """ year = self.data.iloc[0][1] year = year.item() recs = tc.Records(data=self.data, start_year=year) self.calc1 = tc.Calculator(policy=self.pol, records=recs) self.calc1.advance_to_year(year) self.calc1.calc_all() self.calc_reform = tc.Calculator(policy=self.pol2, records=recs) self.calc_reform.advance_to_year(year) self.calc_reform.calc_all() recs_mtr = tc.Records(data=self.data_mtr, start_year=year) self.calc_mtr = tc.Calculator(policy=self.pol2, records=recs_mtr) self.calc_mtr.advance_to_year(year) self.calc_mtr.calc_all() return self.calc1, self.calc_reform, self.calc_mtr
def _make_calculators(self): """ This function creates the baseline and reform calculators used when the `run()` method is called """ # Create two microsimulation calculators gd_base = tc.GrowDiff() gf_base = tc.GrowFactors() # apply user specified growdiff if self.params["growdiff_baseline"]: gd_base.update_growdiff(self.params["growdiff_baseline"]) gd_base.apply_to(gf_base) # Baseline calculator if self.use_cps: records = tc.Records.cps_constructor(data=self.microdata, gfactors=gf_base) else: records = tc.Records(self.microdata, gfactors=gf_base) policy = tc.Policy(gf_base) if self.params["base_policy"]: update_policy(policy, self.params["base_policy"]) base_calc = tc.Calculator(policy=policy, records=records, verbose=self.verbose) # Reform calculator # Initialize a policy object gd_reform = tc.GrowDiff() gf_reform = tc.GrowFactors() if self.params["growdiff_response"]: gd_reform.update_growdiff(self.params["growdiff_response"]) gd_reform.apply_to(gf_reform) if self.use_cps: records = tc.Records.cps_constructor(data=self.microdata, gfactors=gf_reform) else: records = tc.Records(self.microdata, gfactors=gf_reform) policy = tc.Policy(gf_reform) if self.params["base_policy"]: update_policy(policy, self.params["base_policy"]) update_policy(policy, self.params["policy"]) # Initialize Calculator reform_calc = tc.Calculator(policy=policy, records=records, verbose=self.verbose) # delete all unneeded variables del gd_base, gd_reform, records, gf_base, gf_reform, policy return base_calc, reform_calc
def calc_mtr(self, reform_file): """ Calculates income tax, payroll tax, and combined marginal rates """ year = self.invar["FLPDYR"][0] year = int(year.item()) recs_base = tc.Records( data=self.invar, start_year=year, gfactors=None, weights=None, adjust_ratios=None, ) if reform_file is None: pol = tc.Policy() else: pol = self.get_pol(reform_file) calc_base = tc.Calculator(policy=pol, records=recs_base) calc_base.advance_to_year(year) calc_base.calc_all() payrolltax_base = calc_base.array("payrolltax") incometax_base = calc_base.array("iitax") combined_taxes_base = incometax_base + payrolltax_base recs_marg = tc.Records( data=self.invar_marg, start_year=year, gfactors=None, weights=None, adjust_ratios=None, ) calc_marg = tc.Calculator(policy=pol, records=recs_marg) calc_marg.advance_to_year(year) calc_marg.calc_all() payrolltax_marg = calc_marg.array("payrolltax") incometax_marg = calc_marg.array("iitax") combined_taxes_marg = incometax_marg + payrolltax_marg payrolltax_diff = payrolltax_marg - payrolltax_base incometax_diff = incometax_marg - incometax_base combined_diff = combined_taxes_marg - combined_taxes_base mtr_payrolltax = payrolltax_diff / FINITE_DIFF mtr_incometax = incometax_diff / FINITE_DIFF mtr_combined = combined_diff / FINITE_DIFF return (mtr_payrolltax, mtr_incometax, mtr_combined)
def test_sub_effect_independence(stcg): """ Ensure that LTCG amount does not affect magnitude of substitution effect. """ # pylint: disable=too-many-locals # specify reform that raises top-bracket marginal tax rate refyear = 2020 reform = {'II_rt7': {refyear: 0.70}} # specify a substitution effect behavioral response elasticity elasticities_dict = {'sub': 0.25} # specify several high-earning filing units num_recs = 9 input_csv = (u'RECID,MARS,e00200,e00200p,p22250,p23250\n' u'1,2,1000000,1000000,stcg, 0\n' u'2,2,1000000,1000000,stcg, 4800\n' u'3,2,1000000,1000000,stcg, 3600\n' u'4,2,1000000,1000000,stcg, 2400\n' u'5,2,1000000,1000000,stcg, 1200\n' u'6,2,1000000,1000000,stcg, 0\n' u'7,2,1000000,1000000,stcg,-1200\n' u'8,2,1000000,1000000,stcg,-2400\n' u'9,2,1000000,1000000,stcg,-3600\n') inputcsv = input_csv.replace('stcg', str(stcg)) input_dataframe = pd.read_csv(StringIO(inputcsv)) assert len(input_dataframe.index) == num_recs recs = tc.Records(data=input_dataframe, start_year=refyear, gfactors=None, weights=None) pol = tc.Policy() calc1 = tc.Calculator(records=recs, policy=pol) assert calc1.current_year == refyear pol.implement_reform(reform) calc2 = tc.Calculator(records=recs, policy=pol) assert calc2.current_year == refyear del pol df1, df2 = response(calc1, calc2, elasticities_dict) del calc1 del calc2 # compute change in taxable income for each of the filing units chg_funit = dict() for rid in range(1, num_recs + 1): idx = rid - 1 chg_funit[rid] = df2['c04800'][idx] - df1['c04800'][idx] del df1 del df2 # confirm reform reduces taxable income when assuming substitution effect emsg = '' for rid in range(1, num_recs + 1): if not chg_funit[rid] < 0: txt = '\nFAIL: stcg={} : chg[{}]={:.2f} is not negative' emsg += txt.format(stcg, rid, chg_funit[rid]) # confirm change in taxable income is same for all filing units for rid in range(2, num_recs + 1): if not np.allclose(chg_funit[rid], chg_funit[1]): txt = '\nFAIL: stcg={} : chg[{}]={:.2f} != chg[1]={:.2f}' emsg += txt.format(stcg, rid, chg_funit[rid], chg_funit[1]) del chg_funit if emsg: raise ValueError(emsg)
def create_table(self, reform_file=None): """ Creates table of liabilities. Default is current law, but user may specify a policy reform which is read and implemented below in get_pol() The reform_file argument can be the name of a reform file in the Tax-Calculator reforms folder, a file path to a custom JSON reform file, or a dictionary with a policy reform. Returns: df_res: a Pandas dataframe. Each observation is a separate tax filer """ pol = self.get_pol(reform_file) year = self.invar['FLPDYR'][0] year = year.item() recs = tc.Records(data=self.invar, start_year=year) calc = tc.Calculator(policy=pol, records=recs) calc.advance_to_year(year) calc.calc_all() calcs = calc.dataframe(self.tc_vars) mtr = calc.mtr(wrt_full_compensation=False) mtr_df = pd.DataFrame(data=mtr).transpose() df_res = pd.concat([calcs, mtr_df], axis=1) df_res.columns = self.labels df_res.index = range(self.rows) return df_res
def _make_stacked_objects(self): """ This method makes the base calculator and policy and records objects for stacked reforms. The difference between this and the standard _make_calcuators method is that this method only fully creates the baseline calculator. For the reform, it creates policy and records objects and implements any growth assumptions provided by the user. """ # Create two microsimulation calculators gd_base = tc.GrowDiff() gf_base = tc.GrowFactors() # apply user specified growdiff if self.params["growdiff_baseline"]: gd_base.update_growdiff(self.params["growdiff_baseline"]) gd_base.apply_to(gf_base) # Baseline calculator if self.use_cps: records = tc.Records.cps_constructor(data=self.microdata, gfactors=gf_base) else: records = tc.Records(self.microdata, gfactors=gf_base) policy = tc.Policy(gf_base) if self.params["base_policy"]: update_policy(policy, self.params["base_policy"]) base_calc = tc.Calculator(policy=policy, records=records, verbose=self.verbose) # Reform calculator # Initialize a policy object gd_reform = tc.GrowDiff() gf_reform = tc.GrowFactors() if self.params["growdiff_response"]: gd_reform.update_growdiff(self.params["growdiff_response"]) gd_reform.apply_to(gf_reform) if self.use_cps: records = tc.Records.cps_constructor(data=self.microdata, gfactors=gf_reform) else: records = tc.Records(self.microdata, gfactors=gf_reform) policy = tc.Policy(gf_reform) return base_calc, policy, records
def initiate_itax_calculator(self): """ Creates and calculates an itax.Calculator object for START_YEAR """ calc = itax.Calculator(policy=self.itax_policy, records=itax.Records(data=self.records_data), verbose=False) calc.advance_to_year(START_YEAR) calc.calc_all() return calc
def __init__(self, start_year, end_year=LAST_BUDGET_YEAR, microdata=None, use_cps=False, reform=None, behavior=None, assump=None, verbose=False): """ Constructor for the TaxBrain class Parameters ---------- start_year: First year in the analysis. Must be no earlier than the first year allowed in Tax-Calculator. end_year: Last year in the analysis. Must be no later than the last year allowed in Tax-Calculator. microdata: Either a path to a micro-data file or a Pandas DataFrame containing micro-data. use_cps: A boolean value to indicate whether or not the analysis should be run using the CPS file included in Tax-Calculator. Note: use_cps cannot be True if a file was also specified with the microdata parameter. reform: Individual income tax policy reform. Can be either a string pointing to a JSON reform file, or the contents of a JSON file. behavior: Individual behavior assumptions use by the Behavior-Response package. assump: A string pointing to a JSON file containing user specified economic assumptions. verbose: A boolean value indicated whether or not to write model progress reports. """ if not use_cps and microdata is None: raise ValueError("Must specify microdata or set 'use_cps' to True") assert isinstance(start_year, int) & isinstance(end_year, int), ( "Start and end years must be integers") assert start_year <= end_year, ( f"Specified end year, {end_year}, is before specified start year, " f"{start_year}.") assert TaxBrain.FIRST_BUDGET_YEAR <= start_year, ( f"Specified start_year, {start_year}, comes before first known " f"budget year, {TaxBrain.FIRST_BUDGET_YEAR}.") assert end_year <= TaxBrain.LAST_BUDGET_YEAR, ( f"Specified end_year, {end_year}, comes after last known " f"budget year, {TaxBrain.LAST_BUDGET_YEAR}.") self.use_cps = use_cps self.start_year = start_year self.end_year = end_year self.base_data = {yr: {} for yr in range(start_year, end_year + 1)} self.reform_data = {yr: {} for yr in range(start_year, end_year + 1)} self.verbose = verbose # Process user inputs early to throw any errors quickly self.params = self._process_user_mods(reform, assump) self.params["behavior"] = behavior # Create two microsimulation calculators gd_base = tc.GrowDiff() gf_base = tc.GrowFactors() # apply user specified growdiff if self.params["growdiff_baseline"]: gd_base.update_growdiff(self.params["growdiff_baseline"]) gd_base.apply_to(gf_base) # Baseline calculator if use_cps: records = tc.Records.cps_constructor(data=microdata, gfactors=gf_base) else: records = tc.Records(microdata, gfactors=gf_base) self.base_calc = tc.Calculator(policy=tc.Policy(gf_base), records=records, verbose=self.verbose) # Reform calculator # Initialize a policy object gd_reform = tc.GrowDiff() gf_reform = tc.GrowFactors() if self.params["growdiff_response"]: gd_reform.update_growdiff(self.params["growdiff_response"]) gd_reform.apply_to(gf_reform) if use_cps: records = tc.Records.cps_constructor(data=microdata, gfactors=gf_reform) else: records = tc.Records(microdata, gfactors=gf_reform) policy = tc.Policy(gf_reform) policy.implement_reform(self.params['policy']) # Initialize Calculator self.reform_calc = tc.Calculator(policy=policy, records=records, verbose=self.verbose)
# AGI groups to target separately IRS_AGI_STUBS = [-9e99, 1.0, 5e3, 10e3, 15e3, 20e3, 25e3, 30e3, 40e3, 50e3, 75e3, 100e3, 200e3, 500e3, 1e6, 1.5e6, 2e6, 5e6, 10e6, 9e99] HT2_AGI_STUBS = [-9e99, 1.0, 10e3, 25e3, 50e3, 75e3, 100e3, 200e3, 500e3, 1e6, 9e99] # %% create objects gfactor = tc.GrowFactors(GF_NAME) dir(gfactor) puf = pd.read_csv(PUF_NAME) recs = tc.Records(data=puf, start_year=2011, gfactors=gfactor, weights=WEIGHTS_NAME, adjust_ratios=None) # don't use puf_ratios # recs = tc.Records(data=mypuf, # start_year=2011, # gfactors=gfactor, # weights=WEIGHTS_NAME) # apply built-in puf_ratios.csv # %% advance the file pol = tc.Policy() calc = tc.Calculator(policy=pol, records=recs) CYR = 2018 calc.advance_to_year(CYR) calc.calc_all()
def report(): """ Generate TaxData history report """ parser = argparse.ArgumentParser() parser.add_argument( "prs", help=( "prs is a list of prs that were used for this report. " "Enter them as a string separated by commas" ), default="", type=str, ) parser.add_argument( "--desc", help=( "File path to a text or markdown file with additonal information " "that will appear at the beginning of the report" ), default="", type=str, ) parser.add_argument( "--basepuf", help=( "File path to the previous puf.csv file. Use when the proposed " "changes affect puf.csv" ), ) args = parser.parse_args() desc = args.desc base_puf_path = args.basepuf if desc: desc = Path(args.desc).open("r").read() plot_paths = [] date = datetime.today().date() template_args = {"date": date, "desc": desc} pull_str = "* [#{}: {}]({})" _prs = args.prs.split(",") session = HTMLSession() prs = [] for pr in _prs: url = f"https://github.com/PSLmodels/taxdata/pull/{pr}" # extract PR title r = session.get(url) elm = r.html.find("span.js-issue-title")[0] title = elm.text prs.append(pull_str.format(pr, title, url)) template_args["prs"] = prs # CBO projection comparisons cbo_projections = [] cur_cbo = pd.read_csv(CBO_URL, index_col=0) new_cbo = pd.read_csv(CBO_PATH, index_col=0) cbo_years = new_cbo.columns.astype(int) last_year = cbo_years.max() first_year = last_year - 9 if new_cbo.equals(cur_cbo): cbo_projections.append("No changes to CBO projections.") else: # we're only going to include the final ten years in our bar chart keep_years = [str(year) for year in range(first_year, last_year + 1)] cur_cbo = cur_cbo.filter(keep_years, axis=1).transpose().reset_index() cur_cbo["Projections"] = "Current" new_cbo = new_cbo.filter(keep_years, axis=1).transpose().reset_index() new_cbo["Projections"] = "New" cbo_data = pd.concat([cur_cbo, new_cbo], axis=0) for col in cbo_data.columns: if col == "index" or col == "Projections": continue chart = cbo_bar_chart(cbo_data, col, CBO_LABELS[col]) img_path = Path(CUR_PATH, f"{col}.png") chart.save(str(img_path)) plot_paths.append(img_path) cbo_projections.append(f"![]({str(img_path)})" + "{.center}") template_args["cbo_projections"] = cbo_projections # changes in data availability cur_meta = pd.read_json(META_URL, orient="index") new_meta = pd.read_json(META_PATH, orient="index") puf_added, puf_removed = compare_vars(cur_meta, new_meta, "puf") cps_added, cps_removed = compare_vars(cur_meta, new_meta, "cps") template_args["puf_added"] = puf_added template_args["puf_removed"] = puf_removed template_args["cps_added"] = cps_added template_args["cps_removed"] = cps_removed # growth rate changes growth_rate_projections = [] cur_grow = pd.read_csv(GROW_FACTORS_URL) new_grow = pd.read_csv(GROW_FACTORS_PATH) if new_grow.equals(cur_grow): growth_rate_projections.append("No changes to growth rate projections") else: new_grow = new_grow[ (new_grow["YEAR"] >= first_year) & (new_grow["YEAR"] <= last_year) ] cur_grow = cur_grow[ (cur_grow["YEAR"] >= first_year) & (cur_grow["YEAR"] <= last_year) ] new_grow["Growth Factors"] = "New" cur_grow["Growth Factors"] = "Current" growth_data = pd.concat([new_grow, cur_grow]) rows = list(growth_data.columns) rows.remove("YEAR"), rows.remove("Growth Factors") n = len(rows) // 3 chart1 = growth_scatter_plot(growth_data, rows[:n]) img_path = Path(CUR_PATH, "growth_factors1.png") chart1.save(str(img_path)) plot_paths.append(img_path) growth_rate_projections.append(f"![]({str(img_path)})" + "{.center}") chart2 = growth_scatter_plot(growth_data, rows[n : 2 * n]) img_path = Path(CUR_PATH, "growth_factors2.png") chart2.save(str(img_path)) plot_paths.append(img_path) growth_rate_projections.append(f"![]({str(img_path)})" + "{.center}") chart3 = growth_scatter_plot(growth_data, rows[2 * n :]) img_path = Path(CUR_PATH, "growth_factors3.png") chart3.save(str(img_path)) plot_paths.append(img_path) growth_rate_projections.append(f"![]({str(img_path)})" + "{.center}") template_args["growth_rate_projections"] = growth_rate_projections # compare tax calculator projections # baseline CPS calculator base_cps = tc.Calculator(records=tc.Records.cps_constructor(), policy=tc.Policy()) base_cps.advance_to_year(first_year) base_cps.calc_all() # updated CPS calculator cps = pd.read_csv(Path(CUR_PATH, "..", "data", "cps.csv.gz"), index_col=None) cps_weights = pd.read_csv( Path(CUR_PATH, "..", "cps_stage2", "cps_weights.csv.gz"), index_col=None ) new_cps = tc.Calculator( records=tc.Records( data=cps, weights=cps_weights, adjust_ratios=None, start_year=2014 ), policy=tc.Policy(), ) new_cps.advance_to_year(first_year) new_cps.calc_all() template_args, plot_paths = compare_calcs( base_cps, new_cps, "cps", template_args, plot_paths ) # PUF comparison if base_puf_path and PUF_AVAILABLE: template_args["puf_msg"] = None # base puf calculator base_puf = tc.Calculator( records=tc.Records(data=base_puf_path), policy=tc.Policy() ) base_puf.advance_to_year(first_year) base_puf.calc_all() # updated puf calculator puf_weights = pd.read_csv( Path(CUR_PATH, "..", "puf_stage2", "puf_weights.csv.gz"), index_col=None ) puf_ratios = pd.read_csv( Path(CUR_PATH, "..", "puf_stage3", "puf_ratios.csv"), index_col=0 ).transpose() new_records = tc.Records( data=str(PUF_PATH), weights=puf_weights, adjust_ratios=puf_ratios ) new_puf = tc.Calculator(records=new_records, policy=tc.Policy()) new_puf.advance_to_year(first_year) new_puf.calc_all() template_args, plot_paths = compare_calcs( base_puf, new_puf, "puf", template_args, plot_paths ) else: msg = "PUF comparisons are not included in this report." template_args["puf_msg"] = msg template_args["puf_agg_plot"] = None template_args["puf_combined_table"] = None template_args["puf_income_table"] = None template_args["puf_payroll_table"] = None # # distribution plots # dist_vars = [ # ("c00100", "AGI Distribution"), # ("combined", "Tax Liability Distribution"), # ] # dist_plots = [] # for var, title in dist_vars: # plot = distplot(calcs, calc_labels, var, title=title) # img_path = Path(CUR_PATH, f"{var}_dist.png") # plot.save(str(img_path)) # plot_paths.append(img_path) # dist_plots.append(f"![]({str(img_path)})" + "{.center}") # template_args["cps_dist_plots"] = dist_plots # # aggregate totals # aggs = defaultdict(list) # var_list = ["payrolltax", "iitax", "combined", "standard", "c04470"] # for year in range(first_year, tc.Policy.LAST_BUDGET_YEAR + 1): # base_aggs = run_calc(base_cps, year, var_list) # new_aggs = run_calc(new_cps, year, var_list) # aggs["Tax Liability"].append(base_aggs["payrolltax"]) # aggs["Tax"].append("Current Payroll") # aggs["Year"].append(year) # aggs["Tax Liability"].append(new_aggs["payrolltax"]) # aggs["Tax"].append("New Payroll") # aggs["Year"].append(year) # aggs["Tax Liability"].append(base_aggs["iitax"]) # aggs["Tax"].append("Current Income") # aggs["Year"].append(year) # aggs["Tax Liability"].append(new_aggs["iitax"]) # aggs["Tax"].append("New Income") # aggs["Year"].append(year) # aggs["Tax Liability"].append(base_aggs["combined"]) # aggs["Tax"].append("Current Combined") # aggs["Year"].append(year) # aggs["Tax Liability"].append(new_aggs["combined"]) # aggs["Tax"].append("New Combined") # aggs["Year"].append(year) # agg_df = pd.DataFrame(aggs) # title = "Aggregate Tax Liability by Year" # agg_chart = ( # alt.Chart(agg_df, title=title) # .mark_line() # .encode( # x=alt.X( # "Year:O", # axis=alt.Axis(labelAngle=0, titleFontSize=20, labelFontSize=15), # ), # y=alt.Y( # "Tax Liability", # title="Tax Liability (Billions)", # axis=alt.Axis(titleFontSize=20, labelFontSize=15), # ), # color=alt.Color( # "Tax", # legend=alt.Legend(symbolSize=150, labelFontSize=15, titleFontSize=20), # ), # ) # .properties(width=800, height=350) # .configure_title(fontSize=24) # ) # img_path = Path(CUR_PATH, "agg_plot.png") # agg_chart.save(str(img_path)) # plot_paths.append(img_path) # template_args["agg_plot"] = f"![]({str(img_path)})" + "{.center}" # # create tax liability tables # template_args["combined_table"] = agg_liability_table(agg_df, "Combined") # template_args["payroll_table"] = agg_liability_table(agg_df, "Payroll") # template_args["income_table"] = agg_liability_table(agg_df, "Income") # write report and delete images used output_path = Path(CUR_PATH, "reports", f"taxdata_report_{date}.pdf") write_page(output_path, TEMPLATE_PATH, **template_args) for path in plot_paths: path.unlink()
def response(calc_1, calc_2, elasticities, dump=False): """ Implements TaxBrain "Partial Equilibrium Simulation" dynamic analysis returning results as a tuple of Pandas DataFrame objects (df1, df2) where: df1 is extracted from a baseline-policy calc_1 copy, and df2 is extracted from a reform-policy calc_2 copy that incorporates the behavioral responses given by the nature of the baseline-to-reform change in policy and elasticities in the specified behavior dictionary. Note: this function internally modifies a copy of calc_2 records to account for behavioral responses that arise from the policy reform that involves moving from calc1 policy to calc2 policy. Neither calc_1 nor calc_2 need to have had calc_all() executed before calling the response function. And neither calc_1 nor calc_2 are affected by this response function. The elasticities argument is a dictionary containing the assumed response elasticities. Omitting an elasticity key:value pair in the dictionary implies the omitted elasticity is assumed to be zero. Here is the full dictionary content and each elasticity's internal name: be_sub = elasticities['sub'] Substitution elasticity of taxable income. Defined as proportional change in taxable income divided by proportional change in marginal net-of-tax rate (1-MTR) on taxpayer earnings caused by the reform. Must be zero or positive. be_inc = elasticities['inc'] Income elasticity of taxable income. Defined as dollar change in taxable income divided by dollar change in after-tax income caused by the reform. Must be zero or negative. be_cg = elasticities['cg'] Semi-elasticity of long-term capital gains. Defined as change in logarithm of long-term capital gains divided by change in marginal tax rate (MTR) on long-term capital gains caused by the reform. Must be zero or negative. Read response function documentation (see below) for discussion of appropriate values. The optional dump argument controls the number of variables included in the two returned DataFrame objects. When dump=False (its default value), the variables in the two returned DataFrame objects include just the variables in the Tax-Calculator DIST_VARIABLES list, which is sufficient for constructing the standard Tax-Calculator tables. When dump=True, the variables in the two returned DataFrame objects include all the Tax-Calculator input and calculated output variables, which is the same output as produced by the Tax-Calculator tc --dump option except for one difference: the tc --dump option provides two calculated variables, mtr_inctax and mtr_paytax, that are replaced in the dump output of this response function by mtr_combined, which is the sum of mtr_inctax and mtr_paytax. Note: the use here of a dollar-change income elasticity (rather than a proportional-change elasticity) is consistent with Feldstein and Feenberg, "The Taxation of Two Earner Families", NBER Working Paper No. 5155 (June 1995). A proportional-change elasticity was used by Gruber and Saez, "The elasticity of taxable income: evidence and implications", Journal of Public Economics 84:1-32 (2002) [see equation 2 on page 10]. Note: the nature of the capital-gains elasticity used here is similar to that used in Joint Committee on Taxation, "New Evidence on the Tax Elasticity of Capital Gains: A Joint Working Paper of the Staff of the Joint Committee on Taxation and the Congressional Budget Office", (JCX-56-12), June 2012. In particular, the elasticity use here is equivalent to the term inside the square brackets on the right-hand side of equation (4) on page 11 --- not the epsilon variable on the left-hand side of equation (4), which is equal to the elasticity used here times the weighted average marginal tax rate on long-term capital gains. So, the JCT-CBO estimate of -0.792 for the epsilon elasticity (see JCT-CBO, Table 5) translates into a much larger absolute value for the be_cg semi-elasticity used by Tax-Calculator. To calculate the elasticity from a semi-elasticity, we multiply by MTRs from TC and weight by shares of taxable gains. To avoid those with zero MTRs, we restrict this to the top 40% of tax units by AGI. Using this function, a semi-elasticity of -3.45 corresponds to a tax rate elasticity of -0.792. """ # pylint: disable=too-many-locals,too-many-statements,too-many-branches # Check function argument types and elasticity values calc1 = copy.deepcopy(calc_1) calc2 = copy.deepcopy(calc_2) assert isinstance(calc1, tc.Calculator) assert isinstance(calc2, tc.Calculator) assert isinstance(elasticities, dict) be_sub = elasticities['sub'] if 'sub' in elasticities else 0.0 be_inc = elasticities['inc'] if 'inc' in elasticities else 0.0 be_cg = elasticities['cg'] if 'cg' in elasticities else 0.0 assert be_sub >= 0.0 assert be_inc <= 0.0 assert be_cg <= 0.0 # Begin nested functions used only in this response function def _update_ordinary_income(taxinc_change, calc): """ Implement total taxable income change induced by behavioral response. """ # compute AGI minus itemized deductions, agi_m_ided agi = calc.array('c00100') ided = np.where( calc.array('c04470') < calc.array('standard'), 0., calc.array('c04470')) agi_m_ided = agi - ided # assume behv response only for filing units with positive agi_m_ided pos = np.array(agi_m_ided > 0., dtype=bool) delta_income = np.where(pos, taxinc_change, 0.) # allocate delta_income into three parts # pylint: disable=unsupported-assignment-operation winc = calc.array('e00200') delta_winc = np.zeros_like(agi) delta_winc[pos] = delta_income[pos] * winc[pos] / agi_m_ided[pos] oinc = agi - winc delta_oinc = np.zeros_like(agi) delta_oinc[pos] = delta_income[pos] * oinc[pos] / agi_m_ided[pos] delta_ided = np.zeros_like(agi) delta_ided[pos] = delta_income[pos] * ided[pos] / agi_m_ided[pos] # confirm that the three parts are consistent with delta_income assert np.allclose(delta_income, delta_winc + delta_oinc - delta_ided) # add the three parts to different records variables embedded in calc calc.incarray('e00200', delta_winc) calc.incarray('e00200p', delta_winc) calc.incarray('e00300', delta_oinc) calc.incarray('e19200', delta_ided) return calc def _update_cap_gain_income(cap_gain_change, calc): """ Implement capital gain change induced by behavioral responses. """ calc.incarray('p23250', cap_gain_change) return calc def _mtr12(calc__1, calc__2, mtr_of='e00200p', tax_type='combined'): """ Computes marginal tax rates for Calculator objects calc__1 and calc__2 for specified mtr_of income type and specified tax_type. """ assert tax_type in ('combined', 'iitax') _, iitax1, combined1 = calc__1.mtr(mtr_of, wrt_full_compensation=True) _, iitax2, combined2 = calc__2.mtr(mtr_of, wrt_full_compensation=True) if tax_type == 'combined': return (combined1, combined2) return (iitax1, iitax2) # End nested functions used only in this response function # Begin main logic of response function calc1.calc_all() calc2.calc_all() assert calc1.array_len == calc2.array_len assert calc1.current_year == calc2.current_year mtr_cap = 0.99 if dump: recs_vinfo = tc.Records(data=None) # contains records VARINFO only dvars = list(recs_vinfo.USABLE_READ_VARS | recs_vinfo.CALCULATED_VARS) # Calculate sum of substitution and income effects if be_sub == 0.0 and be_inc == 0.0: zero_sub_and_inc = True if dump: wage_mtr1 = np.zeros(calc1.array_len) wage_mtr2 = np.zeros(calc2.array_len) else: zero_sub_and_inc = False # calculate marginal combined tax rates on taxpayer wages+salary # (e00200p is taxpayer's wages+salary) wage_mtr1, wage_mtr2 = _mtr12(calc1, calc2, mtr_of='e00200p', tax_type='combined') # calculate magnitude of substitution effect if be_sub == 0.0: sub = np.zeros(calc1.array_len) else: # proportional change in marginal net-of-tax rates on earnings mtr1 = np.where(wage_mtr1 > mtr_cap, mtr_cap, wage_mtr1) mtr2 = np.where(wage_mtr2 > mtr_cap, mtr_cap, wage_mtr2) pch = ((1. - mtr2) / (1. - mtr1)) - 1. # Note: c04800 is filing unit's taxable income sub = be_sub * pch * calc1.array('c04800') # calculate magnitude of income effect if be_inc == 0.0: inc = np.zeros(calc1.array_len) else: # dollar change in after-tax income # Note: combined is f.unit's income+payroll tax liability dch = calc1.array('combined') - calc2.array('combined') inc = be_inc * dch # calculate sum of substitution and income effects si_chg = sub + inc # Calculate long-term capital-gains effect if be_cg == 0.0: ltcg_chg = np.zeros(calc1.array_len) else: # calculate marginal tax rates on long-term capital gains # p23250 is filing units' long-term capital gains ltcg_mtr1, ltcg_mtr2 = _mtr12(calc1, calc2, mtr_of='p23250', tax_type='iitax') rch = ltcg_mtr2 - ltcg_mtr1 exp_term = np.exp(be_cg * rch) new_ltcg = calc1.array('p23250') * exp_term ltcg_chg = new_ltcg - calc1.array('p23250') # Extract dataframe from calc1 if dump: df1 = calc1.dataframe(dvars) df1.drop('mtr_inctax', axis='columns', inplace=True) df1.drop('mtr_paytax', axis='columns', inplace=True) df1['mtr_combined'] = wage_mtr1 * 100 else: df1 = calc1.dataframe(tc.DIST_VARIABLES) del calc1 # Add behavioral-response changes to income sources calc2_behv = copy.deepcopy(calc2) del calc2 if not zero_sub_and_inc: calc2_behv = _update_ordinary_income(si_chg, calc2_behv) calc2_behv = _update_cap_gain_income(ltcg_chg, calc2_behv) # Recalculate post-reform taxes incorporating behavioral responses calc2_behv.calc_all() # Extract dataframe from calc2_behv if dump: df2 = calc2_behv.dataframe(dvars) df2.drop('mtr_inctax', axis='columns', inplace=True) df2.drop('mtr_paytax', axis='columns', inplace=True) df2['mtr_combined'] = wage_mtr2 * 100 else: df2 = calc2_behv.dataframe(tc.DIST_VARIABLES) del calc2_behv # Return the two dataframes return (df1, df2)
def create_table( self, reform_file=None, tc_vars=None, tc_labels=None, include_mtr=True, be_sub=0, be_inc=0, be_cg=0, ): """ Creates table of liabilities. Default is current law with no behavioral response (i.e. static analysis). User may specify a policy reform which is read and implemented below in get_pol() and/or or may specify elasticities for partial- equilibrium behavioral responses. reform_file: name of a reform file in the Tax-Calculator reforms folder, a file path to a custom JSON reform file, or a dictionary with a policy reform. tc_vars: list of Tax-Calculator output variables. tc_labels: list of labels for output table include_mtr: include MTR calculations in output table be_sub: Substitution elasticity of taxable income. Defined as proportional change in taxable income divided by proportional change in marginal net-of-tax rate (1-MTR) on taxpayer earnings caused by the reform. Must be zero or positive. be_inc: Income elasticity of taxable income. Defined as dollar change in taxable income divided by dollar change in after-tax income caused by the reform. Must be zero or negative. be_cg: Semi-elasticity of long-term capital gains. Defined as change in logarithm of long-term capital gains divided by change in marginal tax rate (MTR) on long-term capital gains caused by the reform. Must be zero or negative. Returns: df_res: a Pandas dataframe. Each observation is a separate tax filer """ year = self.invar["FLPDYR"][0] year = int(year.item()) recs = tc.Records( data=self.invar, start_year=year, gfactors=None, weights=None, adjust_ratios=None, ) # if tc_vars and tc_labels are not specified, defaults are used if tc_vars is None: tc_vars = self.TC_VARS if tc_labels is None: tc_labels = self.TC_LABELS assert len(tc_vars) > 0 assert len(tc_vars) == len(tc_labels) # if no reform file is passed, table will show current law values if reform_file is None: pol = tc.Policy() assert be_sub == be_inc == be_cg == 0 calc = tc.Calculator(policy=pol, records=recs) calc.advance_to_year(year) calc.calc_all() calcs = calc.dataframe(tc_vars) # if a reform file is passed, table will show reform values else: pol = self.get_pol(reform_file) calc = tc.Calculator(policy=pol, records=recs) pol_base = tc.Policy() calc_base = tc.Calculator(policy=pol_base, records=recs) response_elasticities = {"sub": be_sub, "inc": be_inc, "cg": be_cg} _, df2br = br.response(calc_base, calc, response_elasticities, dump=True) calcs = df2br[tc_vars] # if include_mtr is True, the tables includes three columns with MTRs if include_mtr: mtr = self.calc_mtr(reform_file) mtr_df = pd.DataFrame(data=mtr).transpose() df_res = pd.concat([calcs, mtr_df], axis=1) col_labels = tc_labels + self.MTR_LABELS df_res.columns = col_labels df_res.index = range(self.rows) else: df_res = calcs df_res.columns = tc_labels df_res.index = range(self.rows) return df_res
def create_table(self, reform_file=None): """ Creates table of liabilities. Default is current law, but user may specify a policy reform. The reform_file argument can be the name of a reform file in the Tax-Calculator reforms folder, a file path to a custom JSON reform file, or a dictionary with a policy reform. Returns: df_res: a Pandas dataframe. Each observation is a separate tax filer """ REFORMS_URL = ("https://raw.githubusercontent.com/" "PSLmodels/Tax-Calculator/master/taxcalc/reforms/") CURRENT_PATH = os.path.abspath(os.path.dirname(__file__)) # if a reform file is not specified, the default policy is current law if reform_file == None: pol = tc.Policy() else: # check to see if file path to reform_file exists if isinstance(reform_file, str) and os.path.isfile( os.path.join(CURRENT_PATH, reform_file)): reform = tc.Calculator.read_json_param_objects( reform_file, None) # try reform_file as dictionary elif isinstance(reform_file, dict): reform = reform_file # if file path does not exist, check Tax-Calculator reforms file else: try: reform_url = REFORMS_URL + reform_file reform = tc.Calculator.read_json_param_objects( reform_url, None) except: raise 'Reform file does not exist' pol = tc.Policy() pol.implement_reform(reform["policy"]) df_res = [] # create Tax-Calculator records object from each row of csv file and # run calculator for r in range(self.rows): unit = self.invar.iloc[r] unit = pd.DataFrame(unit).transpose() year = unit.iloc[0][1] year = year.item() recs = tc.Records(data=unit, start_year=year) calc = tc.Calculator(policy=pol, records=recs) calc.calc_all() calcs = calc.dataframe(self.tc_vars) # calculate marginal tax rate for each unit mtr = calc.mtr(wrt_full_compensation=False) # income tax MTR, payroll tax MTR mtr_df = pd.DataFrame(data=[mtr[1], mtr[0]]).transpose() table = pd.concat([calcs, mtr_df], axis=1) df_res.append(table) df_res = pd.concat(df_res) df_res.columns = self.labels df_res.index = range(self.rows) return df_res
import numpy as np import pandas as pd import taxcalc as tc from .impute_pencon import impute_pension_contributions from .constants import UNUSED_READ_VARS from pathlib import Path CUR_PATH = Path(__file__).resolve().parent USABLE_VARS = tc.Records(data=None).USABLE_READ_VARS USABLE_VARS.add("filer") def finalprep(data): """ Contains all the logic of the puf_data/finalprep.py script. """ # - Check the PUF year max_flpdyr = max(data["flpdyr"]) if max_flpdyr == 2008: data = transform_2008_varnames_to_2009_varnames(data) else: # if PUF year is 2009+ data = age_consistency(data) # - Make recid variable be a unique integer key: data = create_new_recid(data) # - Make several variable names be uppercase as in SOI PUF: data = capitalize_varnames(data) # - Impute cmbtp variable to estimate income on Form 6251 but not in AGI: cmbtp_standard = data["e62100"] - data["e00100"] + data["e00700"]