Rename dropq directory/files as tbi and refactor run_nth_year_*_model functions

.coveragerc

@@ -4,6 +4,6 @@ omit =
     taxcalc/functions.py
     taxcalc/*.json
     taxcalc/cli/*
-    taxcalc/dropq/*
+    taxcalc/tbi/*
     taxcalc/tests/*
     taxcalc/validation/*

RELEASES.md

@@ -16,6 +16,9 @@ Release 0.12.0 on 2017-??-??
 - Remove arrays_not_lists argument from read_json_param_objects
   [[#1568](https://github.com/open-source-economics/Tax-Calculator/pull/1568)
   by Martin Holmer]
+- Rename dropq as tbi (taxbrain interface) and refactor run_nth_year_*_model functions
+  [[#1577](https://github.com/open-source-economics/Tax-Calculator/pull/1577)
+  by Martin Holmer]
 
 **New Features**
 - Add Calculator.reform_documentation that generates plain text documentation of a reform

read-the-docs/source/public_api.rst

@@ -52,12 +52,6 @@ taxcalc.decorators
 .. automodule:: taxcalc.decorators
    :members:
 
-taxcalc.dropq.dropq
--------------------
-
-.. automodule:: taxcalc.dropq.dropq
-   :members:
-
 taxcalc.functions
 -----------------
 
@@ -108,6 +102,12 @@ taxcalc.TaxCalcIO
 .. autoclass:: taxcalc.TaxCalcIO
    :members:
 
+taxcalc.tbi.tbi
+-------------------
+
+.. automodule:: taxcalc.tbi.tbi
+   :members:
+
 taxcalc.utils
 -------------
 

setup.py

@@ -26,7 +26,7 @@
     'cmdclass': cmdclass,
     'license': 'MIT',
     'packages': ['taxcalc', 'taxcalc.filings', 'taxcalc.filings.forms',
-                 'taxcalc.dropq', 'taxcalc.cli'],
+                 'taxcalc.tbi', 'taxcalc.cli'],
     'include_package_data': True,
     'name': 'taxcalc',
     'install_requires': ['numpy', 'pandas'],

taxcalc/__init__.py

@@ -9,7 +9,7 @@
 from taxcalc.taxcalcio import *
 from taxcalc.utils import *
 from taxcalc.macro_elasticity import *
-from taxcalc.dropq import *
+from taxcalc.tbi import *
 from taxcalc.cli import *
 
 from taxcalc._version import get_versions

taxcalc/macro_elasticity.py

@@ -6,7 +6,7 @@
 # pylint --disable=locally-disabled macro_elasticity.py
 
 
-def proportional_change_gdp(calc1, calc2, elasticity=0.0):
+def proportional_change_gdp(calc1, calc2, elasticity):
     '''
     This function harnesses econometric estimates of the historic relationship
     between tax policy and the macroeconomy to predict the effect of tax

taxcalc/records.py

@@ -173,7 +173,7 @@ def __init__(self,
     @staticmethod
     def cps_constructor(data=None,
                         exact_calculations=False,
-                        growfactors=Growfactors()):
+                        gfactors=Growfactors()):
         """
         Static method returns a Records object instantiated with CPS
         input data.  This works in a analogous way to Records(), which
@@ -188,7 +188,7 @@ def cps_constructor(data=None,
             data = os.path.join(Records.CUR_PATH, 'cps.csv.gz')
         return Records(data=data,
                        exact_calculations=exact_calculations,
-                       gfactors=growfactors,
+                       gfactors=gfactors,
                        weights=Records.CPS_WEIGHTS_FILENAME,
                        adjust_ratios=Records.CPS_RATIOS_FILENAME,
                        start_year=CPSCSV_YEAR)
@@ -213,7 +213,7 @@ def increment_year(self):
         Also, does extrapolation, reweighting, adjusting for new current year.
         """
         self._current_year += 1
-        # apply variable extrapolation growfactors
+        # apply variable extrapolation grow factors
         if self.gfactors is not None:
             self._blowup(self.current_year)
         # apply variable adjustment ratios

taxcalc/taxcalcio.py

@@ -228,11 +228,11 @@ def init(self, input_data, tax_year, reform, assump,
         if aging_input_data:
             if self.cps_input_data:
                 recs = Records.cps_constructor(
-                    growfactors=gfactors_ref,
+                    gfactors=gfactors_ref,
                     exact_calculations=exact_calculations
                 )
                 recs_clp = Records.cps_constructor(
-                    growfactors=gfactors_clp,
+                    gfactors=gfactors_clp,
                     exact_calculations=exact_calculations
                 )
             else:  # if not cps_input_data

taxcalc/tbi/__init__.py

@@ -0,0 +1,4 @@
+from taxcalc.tbi.tbi import (run_nth_year_tax_calc_model,
+                             run_nth_year_gdp_elast_model,
+                             create_dict_table,
+                             reform_warnings_errors)

taxcalc/dropq/dropq.py → taxcalc/tbi/tbi.py

@@ -1,24 +1,25 @@
 """
-The dropq functions are used by TaxBrain to call Tax-Calculator in order
-to maintain the privacy of the IRS-SOI PUF data being used by TaxBrain.
-This is done by "fuzzing" reform results for several randomly selected
+The tbi functions are used by TaxBrain to call Tax-Calculator in order
+to do distributed processing of TaxBrain runs and in order to maintain
+the privacy of the IRS-SOI PUF data being used by TaxBrain.  Maintaining
+privacy is done by "fuzzing" reform results for several randomly selected
 filing units in each table cell.  The filing units randomly selected
 differ for each policy reform and the "fuzzing" involves replacing the
 post-reform tax results for the selected units with their pre-reform
 tax results.
 """
 # CODING-STYLE CHECKS:
-# pep8 --ignore=E402 dropq.py
-# pylint --disable=locally-disabled dropq.py
+# pep8 --ignore=E402 tbi.py
+# pylint --disable=locally-disabled tbi.py
 
 from __future__ import print_function
 import time
 import numpy as np
 import pandas as pd
-from taxcalc.dropq.dropq_utils import (dropq_calculate,
-                                       random_seed,
-                                       dropq_summary,
-                                       AGGR_ROW_NAMES)
+from taxcalc.tbi.tbi_utils import (calculate,
+                                   random_seed,
+                                   summary,
+                                   AGGR_ROW_NAMES)
 from taxcalc import (results, DIST_TABLE_LABELS,
                      proportional_change_gdp, Growdiff, Growfactors, Policy)
 
@@ -45,7 +46,7 @@
 def reform_warnings_errors(user_mods):
     """
     The reform_warnings_errors function assumes user_mods is a dictionary
-    returned by the Calculator.read_json_parameter_files() function.
+    returned by the Calculator.read_json_param_objects() function.
 
     This function returns a dictionary containing two STR:STR pairs:
     {'warnings': '<empty-or-message(s)>', 'errors': '<empty-or-message(s)>'}
@@ -81,22 +82,27 @@ def reform_warnings_errors(user_mods):
 
 
 def run_nth_year_tax_calc_model(year_n, start_year,
-                                taxrec_df, user_mods,
-                                return_json=True):
+                                use_puf_not_cps,
+                                use_full_sample,
+                                user_mods,
+                                return_dict=True):
     """
-    The run_nth_year_tax_calc_model function assumes user_mods is a
-    dictionary returned by the Calculator.read_json_parameter_files()
-    function with an extra key:value pair that is specified as
-    'gdp_elasticity': {'value': <float_value>}.
+    The run_nth_year_tax_calc_model function assumes user_mods is a dictionary
+      returned by the Calculator.read_json_param_objects() function.
+    Setting use_puf_not_cps=True implies use puf.csv input file;
+      otherwise, use cps.csv input file.
+    Setting use_full_sample=False implies use sub-sample of input file;
+      otherwsie, use the complete sample.
     """
-    # pylint: disable=too-many-locals
+    # pylint: disable=too-many-arguments,too-many-locals
+
     start_time = time.time()
 
     # create calc1 and calc2 calculated for year_n and mask
-    (calc1, calc2, mask) = dropq_calculate(year_n, start_year,
-                                           taxrec_df, user_mods,
-                                           behavior_allowed=True,
-                                           mask_computed=True)
+    (calc1, calc2, mask) = calculate(year_n, start_year,
+                                     use_puf_not_cps, use_full_sample,
+                                     user_mods,
+                                     behavior_allowed=True)
 
     # extract raw results from calc1 and calc2
     rawres1 = results(calc1.records)
@@ -107,11 +113,8 @@ def run_nth_year_tax_calc_model(year_n, start_year,
     print('seed={}'.format(seed))
     np.random.seed(seed)  # pylint: disable=no-member
 
-    # construct dropq summary results from raw results
-    summ = dropq_summary(rawres1, rawres2, mask)
-
-    elapsed_time = time.time() - start_time
-    print('elapsed time for this run: ', elapsed_time)
+    # construct TaxBrain summary results from raw results
+    summ = summary(rawres1, rawres2, mask)
 
     def append_year(pdf):
         """
@@ -121,10 +124,12 @@ def append_year(pdf):
         return pdf
 
     # optionally return non-JSON results
-    if not return_json:
+    if not return_dict:
         res = dict()
         for tbl in summ:
             res[tbl] = append_year(summ[tbl])
+        elapsed_time = time.time() - start_time
+        print('elapsed time for this run: {:.1f}'.format(elapsed_time))
         return res
 
     # optionally construct JSON results tables for year n
@@ -147,41 +152,50 @@ def append_year(pdf):
     res = dict()
     for tbl in summ:
         if 'aggr' in tbl:
-            res_table = create_json_table(summ[tbl],
+            res_table = create_dict_table(summ[tbl],
                                           row_names=info[tbl]['row_names'])
             res[tbl] = dict((k, v[0]) for k, v in res_table.items())
         else:
-            res[tbl] = create_json_table(summ[tbl],
+            res[tbl] = create_dict_table(summ[tbl],
                                          row_names=info[tbl]['row_names'],
                                          column_types=info[tbl]['col_types'])
+    elapsed_time = time.time() - start_time
+    print('elapsed time for this run: {:.1f}'.format(elapsed_time))
     return res
 
 
 def run_nth_year_gdp_elast_model(year_n, start_year,
-                                 taxrec_df, user_mods,
-                                 return_json=True):
+                                 use_puf_not_cps,
+                                 use_full_sample,
+                                 user_mods,
+                                 gdp_elasticity,
+                                 return_dict=True):
     """
-    The run_nth_year_gdp_elast_model function assumes user_mods is a
-    dictionary returned by the Calculator.read_json_parameter_files()
-    function with an extra key:value pair that is specified as
-    'gdp_elasticity': {'value': <float_value>}.
+    The run_nth_year_gdp_elast_model function assumes user_mods is a dictionary
+      returned by the Calculator.read_json_param_objects() function.
+    Setting use_puf_not_cps=True implies use puf.csv input file;
+      otherwise, use cps.csv input file.
+    Setting use_full_sample=False implies use sub-sample of input file;
+      otherwsie, use the complete sample.
     """
+    # pylint: disable=too-many-arguments
+
     # create calc1 and calc2 calculated for year_n
-    (calc1, calc2, _) = dropq_calculate(year_n, start_year,
-                                        taxrec_df, user_mods,
-                                        behavior_allowed=False,
-                                        mask_computed=False)
+    (calc1, calc2, _) = calculate(year_n, start_year,
+                                  use_puf_not_cps,
+                                  use_full_sample,
+                                  user_mods,
+                                  behavior_allowed=False)
 
-    # compute GDP effect given assumed gdp elasticity
-    gdp_elasticity = user_mods['gdp_elasticity']['value']
+    # compute GDP effect given specified gdp_elasticity
     gdp_effect = proportional_change_gdp(calc1, calc2, gdp_elasticity)
 
     # return gdp_effect results
-    if return_json:
+    if return_dict:
         gdp_df = pd.DataFrame(data=[gdp_effect], columns=['col0'])
         gdp_elast_names_n = [x + '_' + str(year_n)
                              for x in GDP_ELAST_ROW_NAMES]
-        gdp_elast_total = create_json_table(gdp_df,
+        gdp_elast_total = create_dict_table(gdp_df,
                                             row_names=gdp_elast_names_n,
                                             num_decimals=5)
         gdp_elast_total = dict((k, v[0]) for k, v in gdp_elast_total.items())
@@ -190,10 +204,10 @@ def run_nth_year_gdp_elast_model(year_n, start_year,
         return gdp_effect
 
 
-def create_json_table(dframe, row_names=None, column_types=None,
+def create_dict_table(dframe, row_names=None, column_types=None,
                       num_decimals=2):
     """
-    Create and return dictionary with JSON-like contents from specified dframe.
+    Create and return dictionary with JSON-like content from specified dframe.
     """
     # embedded formatted_string function
     def formatted_string(val, _type, num_decimals):
@@ -216,7 +230,7 @@ def formatted_string(val, _type, num_decimals):
         except ValueError:
             # try making it a string - good luck!
             return str(val)
-    # high-level create_json_table function logic
+    # high-level create_dict_table function logic
     out = dict()
     if row_names is None:
         row_names = [str(x) for x in list(dframe.index)]