def parse_env(): filename = "rftghgemissions.xls" path = fileutils.getcache(filename, "uk") wb = xlrd.open_workbook(path) sheets = wb.sheets() tables = HybridTableCreator(config.SCHEMA) codes = tables.new_sector_codes(prefix="env_ind") codes.add_curated_codes({ "Manufacture of petrochemicals": "20.1[467]+20.6", "Manufacture of other basic metals & casting (excl. Nuclear fuel & Aluminium)": "24.4[^26]-5", "Rest of repair; Installation": "33.1[^56]", }) for sheet in sheets: series = sheet.name years = None for i in range(sheet.nrows): row = sheet.row_values(i) if len(row) < 3 or type(row[2]) is str and not len(row[2]): continue if years is None: if type(row[2]) is float: years = row for year in row[2:]: #envtable.add_env_table("env", year) tables.add_env_table(year) else: code = codes.set_code(row[0], row[1]) if code: for i in range(2, len(row)): tables.insert_env(years[i], code, series, row[i]) codes.update_codes()
def parse_env(): filename = "rftghgemissions.xls" path = fileutils.getcache(filename, "uk") wb = xlrd.open_workbook(path) sheets = wb.sheets() tables = HybridTableCreator(config.SCHEMA) codes = tables.new_sector_codes(prefix="env_ind") codes.add_curated_codes({ "Manufacture of petrochemicals": "20.1[467]+20.6", "Manufacture of other basic metals & casting (excl. Nuclear fuel & Aluminium)": "24.4[^26]-5", "Rest of repair; Installation": "33.1[^56]", }) for sheet in sheets: series = sheet.name years = None for i in range(sheet.nrows): row = sheet.row_values(i) if len(row) < 3 or type(row[2]) is str and not len(row[2]): continue if years is None: if type(row[2]) is float: years = row for year in row[2:]: #envtable.add_env_table("env", year) tables.add_env_table(year) else: code = codes.set_code(row[0], row[1]) if code: for i in range(2, len(row)): tables.insert_env(years[i], code, series, row[i]) codes.update_codes()
def parse_env(): files = { # 2005 only has 細分類 while 1990: "ei90187p.xls", 1995: "ei95186p.xls", 2000: "ei2000p104v01j.xls", 2005: "ei2005pc403jp_wt_bd.xlsx", } def series_names_from_rows(names, units): # since these tables are structured identically # we'll just do some hard coding series_names = [] for i in range(3, len(names)): if len(names[i]): name = "%s (%s)" % (names[i], units[i]) else: name = None series_names.append(name) return series_names tables = HybridTableCreator(config.SCHEMA) for (year, filename) in files.items(): tables.add_env_table(year, series_max_length=255) codes = tables.new_sector_codes(year, "env_ind") codes.curate_code_from_desc("総合計", "total") codes.blacklist_code("total") path = fileutils.getcache(filename, "jp", str(year)) if filename.endswith("xls"): wb = xlrd.open_workbook(path) # each xls file starts with ToC listing tables A-E. # E1: 部門別直接エネルギー消費量,エネルギー原単位を掲載 # E2: 部門別直接CO2排出量,CO2排出原単位を掲載 for sheetname in ("E1", "E2"): sheet = wb.sheet_by_name(sheetname) min_series_col = 4 # first col whose values interest us if sheetname == "E1": min_series_col = 3 # GDP - only want this once series_names = series_names_from_rows(sheet.row_values(0), sheet.row_values(1)) for i in range(2, sheet.nrows): row = sheet.row_values(i) code = row[1] if type(code) is float: code = str(int(code)).rjust(3, "0") code = codes.set_code(code, row[2]) if code: for (series, value) in zip(series_names, row[3:]): if type(value) is float: tables.insert_env(year, code, series, value) elif filename.endswith("xlsx"): wb = openpyxl.load_workbook(filename=path, use_iterators=True) # E: 部門別直接エネルギー消費量および各種GHG排出量, # エネルギー原単位およびGHG原単位を掲載 sheet = wb.get_sheet_by_name("E") rows = sheet.iter_rows() series_names = series_names_from_rows( [cell.internal_value for cell in next(rows)], [cell.internal_value for cell in next(rows)]) for row in rows: code = codes.set_code(row[1].internal_value, row[2].internal_value) if code: for (series, cell) in zip(series_names, row[3:]): if cell.internal_value is not None: tables.insert_env(year, code, series, cell.internal_value) codes.update_codes()
def parse_env(): files = { # 2005 only has 細分類 while 1990: "ei90187p.xls", 1995: "ei95186p.xls", 2000: "ei2000p104v01j.xls", 2005: "ei2005pc403jp_wt_bd.xlsx", } def series_names_from_rows(names, units): # since these tables are structured identically # we'll just do some hard coding series_names = [] for i in range(3, len(names)): if len(names[i]): name = "%s (%s)" % (names[i], units[i]) else: name = None series_names.append(name) return series_names tables = HybridTableCreator(config.SCHEMA) for (year, filename) in files.items(): tables.add_env_table(year, series_max_length=255) codes = tables.new_sector_codes(year, "env_ind") codes.curate_code_from_desc("総合計", "total") codes.blacklist_code("total") path = fileutils.getcache(filename, "jp", str(year)) if filename.endswith("xls"): wb = xlrd.open_workbook(path) # each xls file starts with ToC listing tables A-E. # E1: 部門別直接エネルギー消費量,エネルギー原単位を掲載 # E2: 部門別直接CO2排出量,CO2排出原単位を掲載 for sheetname in ("E1", "E2"): sheet = wb.sheet_by_name(sheetname) min_series_col = 4 # first col whose values interest us if sheetname == "E1": min_series_col = 3 # GDP - only want this once series_names = series_names_from_rows( sheet.row_values(0), sheet.row_values(1)) for i in range(2, sheet.nrows): row = sheet.row_values(i) code = row[1] if type(code) is float: code = str(int(code)).rjust(3, "0") code = codes.set_code(code, row[2]) if code: for (series, value) in zip(series_names, row[3:]): if type(value) is float: tables.insert_env(year, code, series, value) elif filename.endswith("xlsx"): wb = openpyxl.load_workbook(filename=path, use_iterators=True) # E: 部門別直接エネルギー消費量および各種GHG排出量, # エネルギー原単位およびGHG原単位を掲載 sheet = wb.get_sheet_by_name("E") rows = sheet.iter_rows() series_names = series_names_from_rows( [cell.internal_value for cell in next(rows)], [cell.internal_value for cell in next(rows)]) for row in rows: code = codes.set_code(row[1].internal_value, row[2].internal_value) if code: for (series, cell) in zip(series_names, row[3:]): if cell.internal_value is not None: tables.insert_env(year, code, series, cell.internal_value) codes.update_codes()