def test_compare_sheets_to_IPP(): # WIP. for now it only generates the first two sheets, to be compared to Agrégats IPP df = get_tidy_data(2012) variables_CN1 = generate_CN1_variables(2012) variables_CN2 = generate_CN2_variables(2012) values_CN1_2012, formulas_CN1 = get_or_construct_data(df, variables_CN1, range(1949, 2013)) values_CN2_2012, formulas_CN2 = get_or_construct_data(df, variables_CN2, range(1949, 2013)) return values_CN1_2012, values_CN2_2012
def test_compare_sheets_to_IPP( ): # WIP. for now it only generates the first two sheets, to be compared to Agrégats IPP df = get_tidy_data(2012) variables_CN1 = generate_CN1_variables(2012) variables_CN2 = generate_CN2_variables(2012) values_CN1_2012, formulas_CN1 = get_or_construct_data( df, variables_CN1, range(1949, 2013)) values_CN2_2012, formulas_CN2 = get_or_construct_data( df, variables_CN2, range(1949, 2013)) return values_CN1_2012, values_CN2_2012
def test_get_or_construct_data_CN1(): # copied on the one in cn_test df = get_comptes_nationaux_data(2013) values_CN1_target = read_CN1(2013) variables_CN1 = generate_CN1_variables(2013) values_CN1, formulas_CN1 = get_or_construct_data(df, variables_CN1, range(1949, 2014)) assert_frame_equal(values_CN1, values_CN1_target)
def test_CN1(year): df = get_tidy_data(year) values_CN1_target = read_CN1(year) variables_CN1 = generate_CN1_variables(year) values_CN1, formulas_CN1 = get_or_construct_data(df, variables_CN1, range(1949, year + 1)) assert_frame_equal(values_CN1, values_CN1_target)
def test_profits_societes(): df = get_tidy_data(2013) values_profits_societes_target = read_profits_societes() dict_profits_societes = create_dict_profits() values_profits_societes = get_or_construct_data(df, dict_profits_societes)[0] assert_frame_equal(values_profits_societes, values_profits_societes_target)
def create_and_save_CN1(year): # NB : should no longer be executed - already saved file_path = (os.path.join(tests_data, 'values_CN1_{}.h5'.format(year))) assert not os.path.exists(file_path), 'CN1 sheet with {} data already generated and saved'.format(year) df = get_tidy_data(year) variables_CN1 = generate_CN1_variables(year) values_CN1, formulas_CN1 = get_or_construct_data(df, variables_CN1, range(1949, year + 1)) values_CN1.to_hdf(file_path, 'CN1')
def test_CN1(year): df = get_tidy_data(year) values_CN1_target = read_CN1(year) variables_CN1 = generate_CN1_variables(year) values_CN1, formulas_CN1 = get_or_construct_data(df, variables_CN1, range(1949, year + 1)) assert_frame_equal(values_CN1, values_CN1_target)
def test_profits_societes(): df = get_tidy_data(2013) values_profits_societes_target = read_profits_societes() dict_profits_societes = create_dict_profits() values_profits_societes = get_or_construct_data(df, dict_profits_societes)[0] assert_frame_equal(values_profits_societes, values_profits_societes_target)
def test_get_or_construct_data_profits(): # copied on the one in cn_test df = get_comptes_nationaux_data(2013) values_profits_societes_target = read_profits_societes() dict_profits = create_dict_profits() values_profits_societes = get_or_construct_data(df, dict_profits)[0] assert_frame_equal(values_profits_societes, values_profits_societes_target)
def test_get_or_construct_data_CN1(): # copied on the one in cn_test df = get_comptes_nationaux_data(2013) values_CN1_target = read_CN1(2013) variables_CN1 = generate_CN1_variables(2013) values_CN1, formulas_CN1 = get_or_construct_data(df, variables_CN1, range(1949, 2014)) print values_CN1.columns print values_CN1_target.columns assert_frame_equal(values_CN1, values_CN1_target)
def create_and_save_CN1( year): # NB : should no longer be executed - already saved file_path = (os.path.join(tests_data, 'values_CN1_{}.h5'.format(year))) assert not os.path.exists( file_path ), 'CN1 sheet with {} data already generated and saved'.format(year) df = get_tidy_data(year) variables_CN1 = generate_CN1_variables(year) values_CN1, formulas_CN1 = get_or_construct_data(df, variables_CN1, range(1949, year + 1)) values_CN1.to_hdf(file_path, 'CN1')
def tests_get_or_construct_data(): df = get_tidy_data(2013) double_dict = create_double_dict() dict_revenus_rdm = create_dict_revenus_rdm() dict_with_squares = create_dict_w_squares() dict_profits = create_dict_profits() dict_sal_cot_soc = create_dict_sal_cot_soc() mult_dict_with_formula = create_mult_dict_formula() values_double, formulas_double = get_or_construct_data(df, double_dict) values_double_w_formula, formulas_double_w_formula = get_or_construct_data( df, mult_dict_with_formula) values_complex, formulas_complex = get_or_construct_data( df, dict_with_squares) values_profits_societes, formulas_profits_societes = get_or_construct_data( df, dict_profits) values_revenus_reste_du_monde, formulas_revenus_reste_du_monde = get_or_construct_data( df, dict_revenus_rdm, range(1949, 2014)) values_sal_cs, formulas_sal_cs = get_or_construct_data(df, dict_sal_cot_soc, years=range( 1949, 2014)) return (values_double, values_double_w_formula, values_complex, values_profits_societes, values_revenus_reste_du_monde)
def tests_get_or_construct_data(): df = get_tidy_data(2013) double_dict = create_double_dict() dict_revenus_rdm = create_dict_revenus_rdm() dict_with_squares = create_dict_w_squares() dict_profits = create_dict_profits() dict_sal_cot_soc = create_dict_sal_cot_soc() mult_dict_with_formula = create_mult_dict_formula() values_double, formulas_double = get_or_construct_data(df, double_dict) values_double_w_formula, formulas_double_w_formula = get_or_construct_data(df, mult_dict_with_formula) values_complex, formulas_complex = get_or_construct_data(df, dict_with_squares) values_profits_societes, formulas_profits_societes = get_or_construct_data(df, dict_profits) values_revenus_reste_du_monde, formulas_revenus_reste_du_monde = get_or_construct_data( df, dict_revenus_rdm, range(1949, 2014) ) values_sal_cs, formulas_sal_cs = get_or_construct_data(df, dict_sal_cot_soc, years = range(1949, 2014)) return ( values_double, values_double_w_formula, values_complex, values_profits_societes, values_revenus_reste_du_monde )
# -*- coding: utf-8 -*- import os import pkg_resources from ipp_macro_series_parser.config import Config from ipp_macro_series_parser.comptes_nationaux.parser_main import get_comptes_nationaux_data from ipp_macro_series_parser.data_extraction import get_or_construct_data from ipp_macro_series_parser.comptes_nationaux.sheets_lists import variables_CN1, variables_CN2 parser = Config() cn_directory = parser.get('data', 'cn_directory') cn_hdf = parser.get('data', 'cn_hdf_directory') cn_csv = parser.get('data', 'cn_csv_directory') tests_directory = parser.get('data', 'tests_directory') tests_data = os.path.join( pkg_resources.get_distribution('ipp-macro-series-parser').location, 'ipp_macro_series_parser/tests/data') df = get_comptes_nationaux_data(2013) values_CN1, formulas_CN1 = get_or_construct_data(df, variables_CN1, range(1949, 2014)) values_CN2, formulas_CN2 = get_or_construct_data(df, variables_CN2, range(1949, 2014))
def generate_CN6(year): df = get_tidy_data(year) variables_CN6 = generate_CN6_variables(year) values_CN6, formulas_CN6 = get_or_construct_data(df, variables_CN6, range(1949, year + 1)) return values_CN6, formulas_CN6
# -*- coding: utf-8 -*- import os import pandas import pkg_resources from ipp_macro_series_parser.config import Config from ipp_macro_series_parser.comptes_nationaux.parser_main import get_comptes_nationaux_data from ipp_macro_series_parser.data_extraction import ( look_many, look_up, get_or_construct_value, get_or_construct_data) from ipp_macro_series_parser.comptes_nationaux.sheets_lists import variables_CN1, variables_CN2 parser = Config( config_files_directory = os.path.join(pkg_resources.get_distribution('ipp-macro-series-parser').location) ) cn_directory = parser.get('data', 'cn_directory') cn_hdf = parser.get('data', 'cn_hdf_directory') cn_csv = parser.get('data', 'cn_csv_directory') tests_directory = parser.get('data', 'tests_directory') tests_data = os.path.join( pkg_resources.get_distribution('ipp-macro-series-parser').location, 'ipp_macro_series_parser/tests/data') df = get_comptes_nationaux_data(2013) values_CN1, formulas_CN1 = get_or_construct_data(df, variables_CN1, range(1949, 2014)) values_CN2, formulas_CN2 = get_or_construct_data(df, variables_CN2, range(1949, 2014))
def generate_CN6(year): df = get_tidy_data(year) variables_CN6 = generate_CN6_variables(year) values_CN6, formulas_CN6 = get_or_construct_data(df, variables_CN6, range(1949, year + 1)) return values_CN6, formulas_CN6