def parse_map():
table = SQLTable("%s.code_map" % config.SCHEMA,
["from_code", "to_code", "env_code",
"harmonized", "description"],
["varchar(3)", "varchar(6)", "varchar(31)",
"char(3)", "text"]).create()
table.truncate()
filename = "code_map.xls"
path = fileutils.getdatapath(filename, "uk")
wb = xlrd.open_workbook(path)
sheet = wb.sheet_by_index(0)
def sanitize_code(code):
if type(code) is float:
code = str(int(code))
if not len(code):
code = None
return code
for i in range(1, sheet.nrows):
row = sheet.row_values(i)
from_code = sanitize_code(row[0])
to_code = sanitize_code(row[2])
env_code = sanitize_code(row[4])
harmonized = sanitize_code(row[6])
desc = row[7].strip()
table.insert([from_code, to_code, env_code, harmonized, desc])
def create_make_table(self, year):
print("creating make table for %s..." % year)
tablename = "%s.make_%s" % (config.IO_SCHEMA, year)
self.make_table = SQLTable(tablename,
["industry", "commodity", "thousands"],
["varchar(6)", "varchar(6)", "bigint"])
self.make_table.create()
self.make_table.truncate()
def __init__(self, codetablename, mode="r"):
self.mode = mode
self.codetable = SQLTable(codetablename, ["code", "description"],
["varchar(15)", "varchar(255)"])
self.code_dict = {}
self.reverse_code_dict = {}
self.setup()
def parse_codes():
path = fileutils.getdatapath("sector_map.xls", "tw-env")
wb = xlrd.open_workbook(path)
sheets = wb.sheets()
for sheet in sheets:
year = int(sheet.name)
tablename = "%s.sector_map_%d" % (config.SCHEMA, year)
if year > 2006: # CxI only, need map between commods and inds
colnames = ["io_sector", "env_sector", "harmonized_env",
"io_commod", "io_ind"]
coltypes = ["varchar(255)"]*5
else:
colnames = ["io_sector", "env_sector", "harmonized_env"]
coltypes = ["varchar(255)"]*3
table = SQLTable(tablename, colnames, coltypes)
table.create()
table.truncate()
for i in range(sheet.nrows):
row = sheet.row_values(i)
io_sector = row[0].strip()
env_sector = row[1].strip()
harmonized_env = row[2]
if type(harmonized_env) is float:
harmonized_env = str(int(harmonized_env))
harmonized_env = harmonized_env.strip()
if year > 2006:
io_commod = row[4].strip()
io_ind = row[5].strip()
table.insert([io_sector, env_sector, harmonized_env,
io_commod, io_ind])
else:
table.insert([io_sector, env_sector, harmonized_env])
def __init__(self):
self.gdp_deflators = {}
self.pce_deflators = {}
table = SQLTable(TABLE_NAME, ["year", "gdp", "pce"],
["int", "float", "float"])
result = table.getall()
for row in result:
year = row[0]
self.gdp_deflators[year] = row[1]
self.pce_deflators[year] = row[2]
def __init__(self):
self.gdp_deflators = {}
self.pce_deflators = {}
table = SQLTable(TABLE_NAME,
["year", "gdp", "pce"],
["int", "float", "float"])
result = table.getall()
for row in result:
year = row[0]
self.gdp_deflators[year] = row[1]
self.pce_deflators[year] = row[2]
def create_use_table(self, year, has_margins=False):
print("creating use table for %s..." % year)
cols = ["commodity", "industry", "thousands"]
coltypes = ["varchar(6)", "varchar(6)", "bigint"]
if has_margins:
for field in bea.use_table_margins:
cols.append(field)
coltypes.append("int")
tablename = "%s.use_%s" % (config.IO_SCHEMA, year)
self.use_table = SQLTable(tablename, cols, coltypes)
self.use_table.create()
self.use_table.truncate()
class TableStateTracker:
def __init__(self):
self.xact = None
self.table = None
def drop_table(self, tablename, cascade=False):
self.table = SQLTable(tablename)
self.table.drop(cascade)
def create_table(self, tablename, cols, coltypes, cascade=False):
self.flush()
self.table = SQLTable(tablename, cols, coltypes)
self.table.drop(cascade)
self.table.create()
self.warmup()
def insert_row(self, values):
self.table.insert(values)
#self.current_stmt(*values)
def warmup(self):
self.xact = db.xact(mode="READ WRITE")
self.xact.begin()
def flush(self):
if self.xact is not None:
self.xact.commit()
class TableStateTracker:
def __init__(self):
self.xact = None
self.table = None
def drop_table(self, tablename, cascade=False):
self.table = SQLTable(tablename)
self.table.drop(cascade)
def create_table(self, tablename, cols, coltypes, cascade=False):
self.flush()
self.table = SQLTable(tablename, cols, coltypes)
self.table.drop(cascade)
self.table.create()
self.warmup()
def insert_row(self, values):
self.table.insert(values)
#self.current_stmt(*values)
def warmup(self):
self.xact = db.xact(mode="READ WRITE")
self.xact.begin()
def flush(self):
if self.xact is not None:
self.xact.commit()
def __init__(self, name):
self.name = name
self.table = SQLTable(
"%s.%s" % (config.WIOD_SCHEMA, name),
["code", "description"],
["varchar(15)", "varchar(255)"])
self.code_dict = None
def activate():
TradeResultsTable.__active = True
TradeResultsTable.__sqltable = SQLTable(
"trade_results",
["year", "country", "is_export", "industry", "value"],
["int", "char(3)", "bool", "varchar(15)", "float"])
TradeResultsTable.__sqltable.create()
TradeResultsTable.__sqltable.truncate()
def parse_codes():
## manually curated sector map
table = SQLTable("%s.sector_map" % config.WIOD_SCHEMA,
["io_code", "env_code", "description"],
["varchar(15)", "varchar(15)", "text"]).create()
table.truncate()
sector_map = fileutils.getdatapath("sector_map.csv", "wiod")
fh = open(sector_map, "r")
csvf = csv.reader(fh)
header = next(csvf)
for row in csvf:
io_code = row[0].strip()
if not len(io_code):
io_code = None
env_code = row[1].strip()
if not len(env_code):
env_code = None
desc = row[2].strip()
table.insert([io_code, env_code, desc])
## current exchange rates
table = SQLTable("%s.exchange_rates" % config.WIOD_SCHEMA,
["country", "year", "rate"],
["char(3)", "int", "float"]).create()
table.truncate()
path = fileutils.getcache("exr_wiod.xls", "wiod")
wb = xlrd.open_workbook(path)
sheet = wb.sheet_by_name("EXR")
year_list = None
for i in range(sheet.nrows):
row = sheet.row_values(i)
if len(row) < 2:
continue
if year_list is None:
if type(row[0]) is str and row[0].strip() == "Country":
year_list = [int(cell.strip("_ ")) for cell in row[2:]]
else:
if type(row[1]) is str and len(row[1].strip()) == 3:
country = row[1]
if country == "GER":
country = "DEU"
for (year, value) in zip(year_list, row[2:]):
table.insert([country, year, value])
def create_make_table(self, year):
print("creating make table for %s..." % year)
tablename = "%s.make_%s" % (config.IO_SCHEMA, year)
self.make_table = SQLTable(tablename,
["industry", "commodity", "thousands"],
["varchar(6)", "varchar(6)", "bigint"])
self.make_table.create()
self.make_table.truncate()
class CodeTracker:
def __init__(self, name):
self.name = name
self.table = SQLTable(
"%s.%s" % (config.WIOD_SCHEMA, name),
["code", "description"],
["varchar(15)", "varchar(255)"])
self.code_dict = None
def setup(self):
self.table.create()
self.get_codes()
# get existing codes from db
def get_codes(self):
if self.code_dict is None:
self.code_dict = {}
for (code, desc) in self.table.getall():
self.code_dict[code] = desc
def get_desc_for_code(self, code):
if code in self.code_dict:
return self.code_dict[code]
return None
# returns the code used if it was recognized, false otherwise
def set_code(self, code, desc):
if type(code) is str:
code = code.strip()
elif type(code) is float:
code = str(int(code))
if type(desc) is str:
desc = desc.strip()
if code is None or not len(code):
if desc is None or not len(desc): # ignore empty args
return False
elif desc in config.fd_sectors: # choose manual codes
code = config.fd_sectors[desc]
elif desc in config.va_sectors: # choose manual codes
code = config.va_sectors[desc]
else:
return False
elif code in config.code_blacklist: # ignore invalid values for codes
return False
if code in self.code_dict and self.code_dict[code] != desc:
print(self.code_dict[code], desc)
self.code_dict[code] = desc
return code
def update_codes(self):
self.table.truncate()
for code in sorted(self.code_dict.keys()):
desc = self.code_dict[code]
self.table.insert([code, desc])
def doparse():
country_dict = dict((v, k) for k, v in config.countries.items())
country_dict["Slovakia"] = "SVK"
sources = ["total", "nuclear", "thermal", "renewable",
"geothermal", "solar", "wind", "biomass"]
measurements = ["capacity", "consumption"]
tablename = "%s.world_power" % ("eia")
table = SQLTable(
tablename,
["year", "country", "source", "units", "value"],
["int", "char(3)", "varchar(15)", "varchar(4)", "float"])
table.create()
table.truncate()
for source in sources:
for measure in measurements:
if measure == "consumption":
if source in ("geothermal", "solar", "wind", "biomass"):
continue
units = "bkWh"
elif measure == "capacity":
units = "MkW"
filename = source + "_" + measure + ".xls"
path = fileutils.getcache(filename, "eia")
wb = xlrd.open_workbook(path)
sheet = wb.sheet_by_index(0)
header = None
for i in range(sheet.nrows):
row = sheet.row_values(i)
if header is None:
if len(row) > 2 and type(row[2]) is float:
header = []
for cell in row:
if type(cell) is float:
header.append(int(cell))
else:
header.append(None)
header_len = len(header)
elif len(row) > 2:
country_name = row[0]
if country_name in country_dict:
country = country_dict[country_name]
for i in range(2, header_len):
value = row[i]
year = header[i]
if type(value) is float and value > 0:
table.insert(
[year, country, source, units, value])
def __init__(self, codetablename, mode="r"):
self.mode = mode
self.codetable = SQLTable(
codetablename,
["code", "description"],
["varchar(15)", "varchar(255)"])
self.code_dict = {}
self.reverse_code_dict = {}
self.setup()
def add_io_table(self, year, sector_max_length=15):
year = self.valid_year(year)
if year not in self.io_tables:
tablename = "%s.%s_%d" % (self.schema, self.io_prefix, year)
colnames = ["from_sector", "to_sector", "value"]
coltypes = [
"varchar(%d)" % sector_max_length,
"varchar(%d)" % sector_max_length, "float"
]
self.io_tables[year] = SQLTable(tablename, colnames,
coltypes).create()
self.io_tables[year].truncate()
def parse_env():
tables = {}
for year in config.STUDY_YEARS:
tablename = "%s.env_%d" % (config.WIOD_SCHEMA, year)
colnames = ["country", "industry", "measurement", "value"]
coltypes = ["char(3)", "varchar(15)", "varchar(31)", "float"]
tables[year] = SQLTable(tablename, colnames, coltypes).create()
tables[year].truncate()
countries = sorted(config.countries.keys())
countries.append("ROW") # rest of world
for (series, attribs) in config.env_series.items():
if "dir" in attribs:
subdir = attribs["dir"]
else:
subdir = series
subdir = os.path.join("wiod", subdir)
skip_name = "skip_name" in attribs and attribs["skip_name"]
for country in config.countries.keys():
filename = "%s_%s_May12.xls" % (country, series)
print(filename)
path = fileutils.getcache(filename, subdir)
wb = xlrd.open_workbook(path)
for year in config.STUDY_YEARS:
sheet = wb.sheet_by_name("%d" % year)
measurements = sheet.row_values(0)
if series == "EU":
measurements = [m + " - Gross" for m in measurements]
elif series == "CO2":
measurements = ["CO2 - " + m for m in measurements]
for i in range(1, sheet.nrows):
row = sheet.row_values(i)
if len(row[0].strip()):
if skip_name:
ind_code = row[0]
first_col = 1
else:
ind_name = row[0]
ind_code = row[1]
industry_tracker.set_code(ind_code, ind_name)
first_col = 2
for j in range(first_col, len(row)):
value = row[j]
if type(value) is float and value != 0:
measurement = measurements[j]
tables[year].insert(
[country, ind_code, measurement, value])
def parse_map():
table = SQLTable(
"%s.code_map" % config.SCHEMA,
["from_code", "to_code", "env_code", "harmonized", "description"],
["varchar(3)", "varchar(6)", "varchar(31)", "char(3)", "text"
]).create()
table.truncate()
filename = "code_map.xls"
path = fileutils.getdatapath(filename, "uk")
wb = xlrd.open_workbook(path)
sheet = wb.sheet_by_index(0)
def sanitize_code(code):
if type(code) is float:
code = str(int(code))
if not len(code):
code = None
return code
for i in range(1, sheet.nrows):
row = sheet.row_values(i)
from_code = sanitize_code(row[0])
to_code = sanitize_code(row[2])
env_code = sanitize_code(row[4])
harmonized = sanitize_code(row[6])
desc = row[7].strip()
table.insert([from_code, to_code, env_code, harmonized, desc])
def parse_codes():
comcodes = parserutils.add_tracker("%s.com_codes" % config.SCHEMA, "w")
filename = fileutils.getdatapath("commodities.csv", "ca")
with open(filename, "r") as fh:
csvf = csv.reader(fh)
for row in csvf:
if len(row) and regexes.is_num(row[0]):
comcodes.set_code(row[0], row[1])
comcodes.update_codes()
maptable = SQLTable("%s.sector_map" % config.SCHEMA,
["io_code", "env_code", "harmonized"],
["varchar(15)", "varchar(15)", "varchar(15)"]).create()
indcodes = parserutils.add_tracker("%s.ind_codes" % config.SCHEMA, "w")
filename = fileutils.getdatapath("industries.csv", "ca")
with open(filename, "r") as fh:
csvf = csv.reader(fh)
for row in csvf:
if len(row) >= 5:
io_code = row[0]
if not len(io_code):
io_code = None
elif len(row[1]):
indcodes.set_code(io_code, row[1])
env_code = row[2]
if not len(env_code):
env_code = None
elif len(row[3]):
indcodes.set_code(env_code, row[3])
harmonized = row[4]
if len(harmonized) and regexes.is_num(harmonized):
indcodes.set_code(harmonized, row[5])
maptable.insert([io_code, env_code, harmonized])
indcodes.update_codes()
def create_use_table(self, year, has_margins=False):
print("creating use table for %s..." % year)
cols = ["commodity", "industry", "thousands"]
coltypes = ["varchar(6)", "varchar(6)", "bigint"]
if has_margins:
for field in bea.use_table_margins:
cols.append(field)
coltypes.append("int")
tablename = "%s.use_%s" % (config.IO_SCHEMA, year)
self.use_table = SQLTable(tablename, cols, coltypes)
self.use_table.create()
self.use_table.truncate()
def parse_codes():
path = fileutils.getdatapath("sector_map.xls", "tw-env")
wb = xlrd.open_workbook(path)
sheets = wb.sheets()
for sheet in sheets:
year = int(sheet.name)
tablename = "%s.sector_map_%d" % (config.SCHEMA, year)
if year > 2006: # CxI only, need map between commods and inds
colnames = [
"io_sector", "env_sector", "harmonized_env", "io_commod",
"io_ind"
]
coltypes = ["varchar(255)"] * 5
else:
colnames = ["io_sector", "env_sector", "harmonized_env"]
coltypes = ["varchar(255)"] * 3
table = SQLTable(tablename, colnames, coltypes)
table.create()
table.truncate()
for i in range(sheet.nrows):
row = sheet.row_values(i)
io_sector = row[0].strip()
env_sector = row[1].strip()
harmonized_env = row[2]
if type(harmonized_env) is float:
harmonized_env = str(int(harmonized_env))
harmonized_env = harmonized_env.strip()
if year > 2006:
io_commod = row[4].strip()
io_ind = row[5].strip()
table.insert(
[io_sector, env_sector, harmonized_env, io_commod, io_ind])
else:
table.insert([io_sector, env_sector, harmonized_env])
def create_simple_transaction_table(self, year, filename, factor=1):
print("creating transations table for %s..." % year)
tablename = "%s.transactions_%s" % (config.IO_SCHEMA, year)
xtable = SQLTable(tablename, ["producer", "consumer", "thousands"],
["varchar(6)", "varchar(6)", "int"])
xtable.create()
xtable.truncate()
insert_count = 0
with open(fileutils.getcache(filename), "r") as f:
for line in f:
cols = line.split()
if len(cols) >= 3:
value = float(cols[2]) * factor
if (value != 0):
xtable.insert([cols[0], cols[1], int(value)])
insert_count += 1
print("%d rows inserted" % insert_count)
def parse_sut(sheet_name, table_prefix):
tables = {}
colnames = ["country", "commodity", "industry", "value"]
coltypes = ["char(3)", "varchar(15)", "varchar(15)", "float"]
for year in config.STUDY_YEARS:
tablename = "%s_%d" % (table_prefix, year)
tables[year] = SQLTable(tablename, colnames, coltypes).create()
tables[year].truncate()
for country in config.countries.keys():
# TODO: more automated way to get this
if country in ("AUS", "DEU", "GBR", "USA"):
filename = "%s_SUT_Feb12.xls" % country
else:
filename = "%s_SUT_Jan12.xls" % country
subdir = os.path.join("wiod", "suts")
path = fileutils.getcache(filename, subdir)
wb = xlrd.open_workbook(path)
# extract supply and use tables at fob prices
sheet = wb.sheet_by_name(sheet_name)
industry_row = sheet.row_values(0)
row = sheet.row_values(1)
industry_codes = []
for (code, desc) in zip(industry_row, row):
industry_codes.append(industry_tracker.set_code(code, desc))
for i in range(2, sheet.nrows):
row = sheet.row_values(i)
if not len(row[0].strip()):
continue
year = int(row[0])
if year not in config.STUDY_YEARS:
continue
com_code = commodity_tracker.set_code(row[1], row[2])
if not com_code:
continue
for j in range(3, len(row)):
value = row[j]
ind_code = industry_codes[j]
if value != 0 and ind_code:
# commodity first
tables[year].insert(
[country, com_code, ind_code, value])
def create_simple_transaction_table(self, year, filename, factor=1):
print("creating transations table for %s..." % year)
tablename = "%s.transactions_%s" % (config.IO_SCHEMA, year)
xtable = SQLTable(tablename,
["producer", "consumer", "thousands"],
["varchar(6)", "varchar(6)", "int"])
xtable.create()
xtable.truncate()
insert_count = 0
with open(fileutils.getcache(filename), "r") as f:
for line in f:
cols = line.split()
if len(cols) >= 3:
value = float(cols[2]) * factor
if (value != 0):
xtable.insert([cols[0], cols[1], int(value)])
insert_count += 1
print ("%d rows inserted" % insert_count)
def doparse():
table = SQLTable("%s.mdg_emissions" % config.UN_SCHEMA,
["country", "year", "value"],
["char(3)", "int", "float"]).create()
table.truncate()
country_dict = dict((v, k) for k, v in config.countries.items())
country_dict["Slovakia"] = "SVK"
country_dict["Russian Federation"] = "RUS"
year_pat = re.compile("[12]\d{3}")
path = fileutils.getdatapath("mdg_emissions.csv", "un")
with open(path, "r") as fh:
csvf = csv.reader(fh)
header = next(csvf)
header_index = {}
years = []
for i in range(len(header)):
header_index[header[i]] = i
if year_pat.match(header[i]):
years.append(header[i])
for row in csvf:
if len(row) <= header_index["SeriesCode"] or \
row[header_index["SeriesCode"]] != "749":
continue
country_name = row[header_index["Country"]]
if country_name not in country_dict:
continue
country = country_dict[country_name]
for year in years:
value = row[header_index[year]].strip()
if len(value):
table.insert([country, int(year), float(value)])
def doparse():
# ppp rank from
# https://www.cia.gov/library/publications/the-world-factbook/rankorder/2004rank.html
countries = {
"LUX": {"fips": "LU", "ppp": 3},
"USA": {"fips": "US", "ppp": 11},
"NLD": {"fips": "NL", "ppp": 17},
"AUT": {"fips": "AU", "ppp": 18},
"SWE": {"fips": "SW", "ppp": 21},
"CAN": {"fips": "CA", "ppp": 20},
"AUS": {"fips": "AS", "ppp": 22},
"IRL": {"fips": "EI", "ppp": 23},
"DEU": {"fips": "GM", "ppp": 26},
"TWN": {"fips": "TW", "ppp": 27},
"BEL": {"fips": "BE", "ppp": 28},
"DNK": {"fips": "DK", "ppp": 29},
"FIN": {"fips": "FI", "ppp": 32},
"GBR": {"fips": "UK", "ppp": 33},
"FRA": {"fips": "FR", "ppp": 35},
"JPN": {"fips": "JA", "ppp": 36},
"KOR": {"fips": "KS", "ppp": 40},
"ESP": {"fips": "SP", "ppp": 43},
"ITA": {"fips": "IT", "ppp": 44},
"CYP": {"fips": "CY", "ppp": 46},
"SVN": {"fips": "SI", "ppp": 47},
"CZE": {"fips": "EZ", "ppp": 50}, # EZ??
"GRC": {"fips": "GR", "ppp": 52},
"MLT": {"fips": "MT", "ppp": 53},
"PRT": {"fips": "PO", "ppp": 57},
"SVK": {"fips": "LO", "ppp": 58},
"POL": {"fips": "PL", "ppp": 60},
"EST": {"fips": "EN", "ppp": 61},
"HUN": {"fips": "HU", "ppp": 63},
"LTU": {"fips": "LH", "ppp": 65},
"RUS": {"fips": "RS", "ppp": 71},
"LVA": {"fips": "LG", "ppp": 75},
"MEX": {"fips": "MX", "ppp": 85},
"TUR": {"fips": "TU", "ppp": 86},
"BRA": {"fips": "BR", "ppp": 92},
"ROU": {"fips": "RO", "ppp": 97},
"BGR": {"fips": "BU", "ppp": 101},
"CHN": {"fips": "CH", "ppp": 121},
"IDN": {"fips": "ID", "ppp": 156},
"IND": {"fips": "IN", "ppp": 164},
}
tablename = "world_supplement"
table = SQLTable(tablename,
["year", "country", "pop", "gdp", "ppp"],
["int", "char(3)", "int", "float", "float"]).create()
table.truncate()
country_fips = {}
data = {}
for (country, info) in countries.items():
data[country] = {}
country_fips[info["fips"]] = country
# this file spec is documented in the xlsx file from the archive
thisyear = datetime.datetime.now().year
path = fileutils.getcache("IDBext001.txt", "wsupp")
with open(path, "r") as fh:
for line in fh:
fields = line.split("|")
if len(fields) == 3:
fips = fields[0]
if fips in country_fips:
year = int(fields[1])
if year >= thisyear: # we don't want future projections
continue
country = country_fips[fips]
data[country][year] = {"pop": int(fields[2])}
worldbank = {
"ppp": "NY.GNP.PCAP.PP.CD_Indicator_MetaData_en_EXCEL.xls",
"gdp": "NY.GDP.PCAP.CD_Indicator_MetaData_en_EXCEL.xls",
}
for (indicator, filename) in worldbank.items():
path = fileutils.getcache(filename, "wsupp")
wb = xlrd.open_workbook(path)
sheet = wb.sheet_by_index(0)
header = [int(x) for x in sheet.row_values(0)[2:]]
for i in range(1, sheet.nrows):
row = sheet.row_values(i)
if row[1] in countries:
country = row[1]
for (year, value) in zip(header, row[2:]):
# this discards years where we don't have population
if year in data[country] and \
type(value) is float and value != 0:
data[country][year][indicator] = value
for (country, country_data) in data.items():
for (year, year_data) in country_data.items():
ppp = None
gdp = None
pop = year_data["pop"]
if "gdp" in year_data:
gdp = year_data["gdp"]
if "ppp" in year_data:
ppp = year_data["ppp"]
table.insert([year, country, pop, gdp, ppp])
def parse_codes():
# parse sector maps
path = fileutils.getdatapath("io_env_map.xls", "jp")
wb = xlrd.open_workbook(path)
io_tables = {}
env_tables = {}
harmonized_sectors = {}
harmonized_table = SQLTable("%s.harmonized_codes" % config.SCHEMA,
["code", "description"],
["char(3)", "varchar(63)"]).create()
for year in config.STUDY_YEARS:
# all io codes are in one sheet, parse afterward
io_tables[year] = SQLTable(
"%s.io_map_%d" % (config.SCHEMA, year),
["io_sector", "description", "harmonized"],
["char(3)", "varchar(63)", "char(3)"]).create()
io_tables[year].truncate()
# parse env codes
env_table = SQLTable(
"%s.env_map_%d" % (config.SCHEMA, year),
["env_sector", "description", "harmonized"],
["varchar(7)", "varchar(63)", "char(3)"]).create()
env_table.truncate()
sheet = wb.sheet_by_name(str(year))
for i in range(1, sheet.nrows):
row = sheet.row_values(i)
code = row[0]
if type(code) is float:
# 2005 codes are 5 or more digits so this just trims .0
code = str(int(code)).rjust(3, "0")
desc = row[1]
h_code = row[2]
if type(h_code) is float:
h_code = str(int(h_code)).rjust(3, "0")
env_table.insert([code, desc, h_code])
if h_code not in harmonized_sectors:
h_desc = row[3]
harmonized_sectors[h_code] = 1
harmonized_table.insert([h_code, h_desc])
sheet = wb.sheet_by_name("io")
positions = {}
header = sheet.row_values(0)
for i in range(len(header)):
if type(header[i]) is float:
positions[int(header[i])] = i
elif header[i] == "harmonized":
positions["harmonized"] = i
for i in range(1, sheet.nrows):
row = sheet.row_values(i)
for year in config.STUDY_YEARS:
code = row[positions[year]]
if type(code) is float:
code = str(int(code)).rjust(3, "0")
if code is None or not len(code):
continue
desc = row[positions[year] + 1]
h_code = row[positions["harmonized"]]
if type(h_code) is float:
h_code = str(int(h_code)).rjust(3, "0")
io_tables[year].insert([code, desc, h_code])
def create_table(self, tablename, cols, coltypes, cascade=False):
self.flush()
self.table = SQLTable(tablename, cols, coltypes)
self.table.drop(cascade)
self.table.create()
self.warmup()
def parse_io():
io_files = {
1996: "410281134571.xls",
1999: "4102715414971.xls",
2001: "4122111363671.xls",
2004: "611239581071.xls",
2006: "9121414285971.xls",
2007: "1139203871.xls",
2008: "1139204871.xls",
2009: "11229101502.xls",
2010: "1122910141371.xls",
}
for (year, filename) in io_files.items():
tablename = "%s.io_%d" % (config.SCHEMA, year)
# millions are in NTD
table = SQLTable(tablename,
["from_sector", "to_sector", "millions"],
["varchar(255)", "varchar(255)", "float"])
table.create()
table.truncate()
path = fileutils.getcache(filename, "tw/%d" % year)
wb = xlrd.open_workbook(path)
sheet = wb.sheets()[0]
to_codes = sheet.row_values(0)
to_names = sheet.row_values(1)
for rowindex in range(2, sheet.nrows):
row = sheet.row_values(rowindex)
from_code = row[0].strip()
from_name = row[1].strip()
for i in range(2, len(to_names)):
to_name = to_names[i].strip()
value = row[i]
table.insert([from_name, to_name, value])
if year == 2010:
strings = {
"viewname": "%s.io_view_%d" % (config.SCHEMA, year),
"tablename": tablename,
"maptable": "%s.sector_map_%d" % (config.SCHEMA, year),
"to_blacklist": sqlhelper.set_repr(config.to_blacklists[year]),
"from_blacklist":
sqlhelper.set_repr(config.from_blacklists[year]),
}
sql = """CREATE OR REPLACE VIEW %(viewname)s AS
SELECT from_map.io_sector AS from_sector,
to_map.io_sector as to_sector,
sum(millions) as millions
FROM %(tablename)s io,
(SELECT DISTINCT io_sector, io_commod
FROM %(maptable)s) from_map,
(SELECT DISTINCT io_sector, io_ind
FROM %(maptable)s) to_map
WHERE io.to_sector NOT IN %(to_blacklist)s
AND io.from_sector NOT IN %(from_blacklist)s
AND from_map.io_commod = io.from_sector
AND to_map.io_ind = io.to_sector
GROUP BY from_map.io_sector, to_map.io_sector""" % strings
print(sql)
db.execute(sql)
def doparse():
for year in (1972, 1977):
table = SQLTable("%s.codes_%d" % (config.IO_SCHEMA, year),
["code", "description"],
["char(6)", "text"]).create()
table.truncate()
filepath = fileutils.getdatapath("io_sectors_%d.csv" % year, "usa")
with open(filepath, "r") as fh:
csvf = csv.reader(fh)
for row in csvf:
if len(row) and len(row[0]):
table.insert([row[0], row[1]])
if year == 1972:
# this is stated in the rtf file for both 1972 and 1977
# but this code never appears in 1977, the documentation
# was probably not properly updated
table.insert(["870000", "total value added"])
writer = dbsetup.IOCodeTableWriter()
writer.set_year(1982, "Io-code.doc")
with open(writer.get_filename()) as f:
for line in f:
if len(line) > 8:
code = line[:6]
desc = line[8:]
writer.writerow(code, desc)
writer.set_year(1987, "SIC-IO.DOC")
with open(writer.get_filename()) as f:
pattern = re.compile('\s*(\d{1,2})\.(\d{4})\s+([^0-9\*]+)')
for line in f:
match = pattern.match(line)
if match:
code = match.group(1).rjust(2, '0') + match.group(2)
desc = match.group(3).strip('(. \r\n')
writer.writerow(code, desc)
writer.set_year(1992, "io-code.txt")
with open(writer.get_filename()) as f:
for line in f:
if len(line) > 7:
code = line[:6]
desc = line[7:]
writer.writerow(code, desc)
writer.set_year(1997, "IO-CodeDetail.txt")
with open(writer.get_filename()) as f:
csvf = csv.reader(f)
for row in csvf:
if len(row) == 2:
writer.writerow(row[0], row[1])
writer.set_year(2002, "REV_NAICSUseDetail 4-24-08.txt")
with open(writer.get_filename()) as f:
valid_line = re.compile("[A-Z0-9]{6}\s")
line = f.readline().strip().replace("GasPipeVal", "GasPipe ")
fields = dbsetup.get_header_locations(dbsetup.replace_tabs(line))
codemap = {}
for line in f:
if valid_line.match(line):
row = dbsetup.get_values_for_fields(dbsetup.replace_tabs(line),
fields)
codemap[row["Commodity"]] = row["CommodityDescription"]
codemap[row["Industry"]] = row["IndustryDescription"]
for (code, desc) in codemap.items():
writer.writerow(code, desc)
writer.flush()
class IOTableStateTracker(TableStateTracker):
def __init__(self):
TableStateTracker.__init__(self)
self.make_table = None
self.use_table = None
self.make_insert_count = 0
self.use_insert_count = 0
def flush(self):
TableStateTracker.flush(self)
if self.make_insert_count:
print("%d rows inserted to make table" % self.make_insert_count)
self.make_insert_count = 0
if self.use_insert_count:
print("%d rows inserted to use table" % self.use_insert_count)
self.use_insert_count = 0
def create_make_table(self, year):
print("creating make table for %s..." % year)
tablename = "%s.make_%s" % (config.IO_SCHEMA, year)
self.make_table = SQLTable(tablename,
["industry", "commodity", "thousands"],
["varchar(6)", "varchar(6)", "bigint"])
self.make_table.create()
self.make_table.truncate()
def create_use_table(self, year, has_margins=False):
print("creating use table for %s..." % year)
cols = ["commodity", "industry", "thousands"]
coltypes = ["varchar(6)", "varchar(6)", "bigint"]
if has_margins:
for field in bea.use_table_margins:
cols.append(field)
coltypes.append("int")
tablename = "%s.use_%s" % (config.IO_SCHEMA, year)
self.use_table = SQLTable(tablename, cols, coltypes)
self.use_table.create()
self.use_table.truncate()
def insert_make(self, indus, commod, makeval, factor=1):
value = float(makeval) * factor
if (value != 0):
self.make_table.insert([indus.strip(), commod.strip(), int(value)])
self.make_insert_count += 1
def insert_use(self, commod, indus, useval, margins={}, factor=1):
useval = float(useval) * factor
nonzero = useval
values = [commod.strip(), indus.strip(), int(useval)]
if len(margins) > 0:
for margin_field in bea.use_table_margins:
value = 0
if margin_field in margins:
value = float(margins[margin_field]) * factor
if value:
nonzero += value
values.append(value)
if nonzero != 0:
self.use_table.insert(values)
self.use_insert_count += 1
# this is for years with no distinction between
# make and use tables
def create_simple_transaction_table(self, year, filename, factor=1):
print("creating transations table for %s..." % year)
tablename = "%s.transactions_%s" % (config.IO_SCHEMA, year)
xtable = SQLTable(tablename, ["producer", "consumer", "thousands"],
["varchar(6)", "varchar(6)", "int"])
xtable.create()
xtable.truncate()
insert_count = 0
with open(fileutils.getcache(filename), "r") as f:
for line in f:
cols = line.split()
if len(cols) >= 3:
value = float(cols[2]) * factor
if (value != 0):
xtable.insert([cols[0], cols[1], int(value)])
insert_count += 1
print("%d rows inserted" % insert_count)
# this is for years that have make and use but no margins
def create_simple_make_use(self, year, filename, factor=1):
self.create_make_table(year)
self.create_use_table(year, has_margins=False)
with open(fileutils.getcache(filename), "r") as f:
for line in f:
cols = line.split()
if len(cols) == 4:
input_ind = cols[0] # comm consumed (producing ind)
output_ind = cols[1] # consuming ind (comm produced)
use_dollars = cols[2] # use in producers' prices
make_dollars = cols[3] # make in producers' prices
self.insert_make(input_ind, output_ind, make_dollars, factor)
self.insert_use(commod=input_ind,
indus=output_ind,
useval=use_dollars,
factor=factor)
class SectorCodes:
def __init__(self, codetablename, mode="r"):
self.mode = mode
self.codetable = SQLTable(codetablename, ["code", "description"],
["varchar(15)", "varchar(255)"])
self.code_dict = {}
self.reverse_code_dict = {}
self.setup()
def setup(self):
if self.mode == "w":
# invalid codes or codes that we don't want to record
self.code_blacklist = []
# if we want to override the code provided with something
# we make up (or from another set) based on the description
self.manual_codes = {}
self.codetable.create()
# get existing codes from db
for (code, desc) in self.codetable.getall():
self.code_dict[code] = desc
self.reverse_code_dict[desc] = code
return self
# for write mode
def blacklist_code(self, code):
self.code_blacklist.append(code)
if code in self.code_dict:
del self.code_dict[code]
def set_blacklist(self, code_blacklist):
self.code_blacklist = []
for code in code_blacklist:
self.blacklist_code(code)
def curate_code_from_desc(self, desc, code):
self.manual_codes[desc] = code
self.code_dict[code] = desc
self.reverse_code_dict[desc] = code
def add_curated_codes(self, curated_codes):
for (desc, code) in curated_codes.items():
self.curate_code_from_desc(desc, code)
# returns the code used if it was recognized, false otherwise
def set_code(self, code, desc):
if type(code) is str:
code = code.strip()
elif type(code) is float:
code = str(int(code))
if type(desc) is str:
desc = desc.strip()
if desc in self.manual_codes:
code = self.manual_codes[desc]
if code is None or not len(code):
if desc is None or not len(desc): # ignore empty args
return False
else:
return False
elif code in self.code_blacklist:
return False
if code in self.code_dict and self.code_dict[code] != desc:
# this is to check for blatant differences
print(self.code_dict[code], "=>", desc)
self.code_dict[code] = desc
# there may be more than one description for the same code
self.reverse_code_dict[desc] = code
return code
def has_code(self, code):
return code in self.code_dict
def get_code_for_title(self, desc):
if desc in self.reverse_code_dict:
return self.reverse_code_dict[desc]
def get_title_for_code(self, code):
if self.has_code(code):
return self.code_dict[code]
return False
def update_codes(self):
if self.mode != "w":
raise Exception("SectorCodes created in read-only mode")
self.codetable.truncate()
for code in sorted(self.code_dict.keys()):
desc = self.code_dict[code]
self.codetable.insert([code, desc])
def parse_codes():
# parse sector maps
path = fileutils.getdatapath("io_env_map.xls", "jp")
wb = xlrd.open_workbook(path)
io_tables = {}
env_tables = {}
harmonized_sectors = {}
harmonized_table = SQLTable(
"%s.harmonized_codes" % config.SCHEMA,
["code", "description"],
["char(3)", "varchar(63)"]).create()
for year in config.STUDY_YEARS:
# all io codes are in one sheet, parse afterward
io_tables[year] = SQLTable(
"%s.io_map_%d" % (config.SCHEMA, year),
["io_sector", "description", "harmonized"],
["char(3)", "varchar(63)", "char(3)"]).create()
io_tables[year].truncate()
# parse env codes
env_table = SQLTable(
"%s.env_map_%d" % (config.SCHEMA, year),
["env_sector", "description", "harmonized"],
["varchar(7)", "varchar(63)", "char(3)"]).create()
env_table.truncate()
sheet = wb.sheet_by_name(str(year))
for i in range(1, sheet.nrows):
row = sheet.row_values(i)
code = row[0]
if type(code) is float:
# 2005 codes are 5 or more digits so this just trims .0
code = str(int(code)).rjust(3, "0")
desc = row[1]
h_code = row[2]
if type(h_code) is float:
h_code = str(int(h_code)).rjust(3, "0")
env_table.insert([code, desc, h_code])
if h_code not in harmonized_sectors:
h_desc = row[3]
harmonized_sectors[h_code] = 1
harmonized_table.insert([h_code, h_desc])
sheet = wb.sheet_by_name("io")
positions = {}
header = sheet.row_values(0)
for i in range(len(header)):
if type(header[i]) is float:
positions[int(header[i])] = i
elif header[i] == "harmonized":
positions["harmonized"] = i
for i in range(1, sheet.nrows):
row = sheet.row_values(i)
for year in config.STUDY_YEARS:
code = row[positions[year]]
if type(code) is float:
code = str(int(code)).rjust(3, "0")
if code is None or not len(code):
continue
desc = row[positions[year] + 1]
h_code = row[positions["harmonized"]]
if type(h_code) is float:
h_code = str(int(h_code)).rjust(3, "0")
io_tables[year].insert([code, desc, h_code])
def create_table(self, tablename, cols, coltypes, cascade=False):
self.flush()
self.table = SQLTable(tablename, cols, coltypes)
self.table.drop(cascade)
self.table.create()
self.warmup()
def create_table(self, tablename, cols, coltypes, cascade=False):
table = SQLTable(tablename, cols, coltypes)
table.drop(cascade)
table.create()
self.tables[tablename] = table
def drop_table(self, tablename, cascade=False):
self.table = SQLTable(tablename)
self.table.drop(cascade)
def doparse():
tablename = "%s.world_supplement" % config.WIOD_SCHEMA
table = SQLTable(tablename, ["year", "country", "measurement", "value"],
["int", "char(3)", "varchar(8)", "float"])
table.create()
table.truncate()
# census data has more complete population counts
country_fips = {
"LU": "LUX",
"US": "USA",
"NL": "NLD",
"AU": "AUT",
"SW": "SWE",
"CA": "CAN",
"AS": "AUS",
"EI": "IRL",
"GM": "DEU",
"BE": "BEL",
"TW": "TWN",
"DA": "DNK",
"UK": "GBR",
"FR": "FRA",
"JA": "JPN",
"KS": "KOR",
"SP": "ESP",
"CY": "CYP",
"SI": "SVN",
"EZ": "CZE",
"GR": "GRC",
"MT": "MLT",
"PO": "PRT",
"LO": "SVK",
"PL": "POL",
"EN": "EST",
"HU": "HUN",
"LH": "LTU",
"LG": "LVA",
"MX": "MEX",
"TU": "TUR",
"BR": "BRA",
"RO": "ROU",
"BU": "BGR",
"CH": "CHN",
"ID": "IDN",
"IN": "IND",
"RS": "RUS",
"FI": "FIN",
"IT": "ITA",
}
# this file spec is documented in the xlsx file from the archive
path = fileutils.getcache("IDBext001.txt", "wsupp")
with open(path, "r") as fh:
for line in fh:
fields = line.split("|")
if len(fields) == 3:
fips = fields[0]
if fips in country_fips:
year = int(fields[1])
country = country_fips[fips]
table.insert([year, country, "pop", int(fields[2])])
# worldbank data has some deflator data that imf doesn't
worldbank = {
"ppp_pc": "NY.GDP.PCAP.PP.KD_Indicator_MetaData_en_EXCEL.xls",
#"gdp_pc": "NY.GDP.PCAP.CD_Indicator_MetaData_en_EXCEL.xls",
#"dec": "PA.NUS.ATLS_Indicator_MetaData_en_EXCEL.xls",
#"pppratio": "PA.NUS.PPPC.RF_Indicator_MetaData_en_EXCEL.xls",
"deflator": "NY.GDP.DEFL.ZS_Indicator_MetaData_en_EXCEL.xls",
}
for (indicator, filename) in worldbank.items():
path = fileutils.getcache(filename, "wsupp")
wb = xlrd.open_workbook(path)
sheet = wb.sheet_by_index(0)
header = [int(x) for x in sheet.row_values(0)[2:]]
for i in range(1, sheet.nrows):
row = sheet.row_values(i)
if row[1] in config.countries:
country = row[1]
for (year, value) in zip(header, row[2:]):
if type(value) is float and value != 0:
table.insert([year, country, indicator, value])
imf_fields = (
"LP", # population
"PPPPC", # ppp per capita
"NGDPRPC", # gdp per capita in constant prices
"NGDP_D", # gdp deflator
)
# this is actually a csv file despite what it's called
path = fileutils.getcache("WEOApr2012all.xls", "wsupp")
with codecs.open(path, "r", "cp1252") as fh:
csvf = csv.reader(fh, dialect=csv.excel_tab)
header = next(csvf)
year_cols = {}
valid_year = re.compile("\d{4}")
valid_float = re.compile("-*[\d\.,]+")
for i in range(len(header)):
if header[i] == "ISO":
country_col = i
elif header[i] == "WEO Subject Code":
subject_col = i
elif valid_year.match(header[i]):
year_cols[int(header[i])] = i
elif header[i] == "Estimates Start After":
last_year_col = i
for row in csvf:
if len(row) > subject_col and row[subject_col] in imf_fields:
field = row[subject_col]
country = row[country_col]
if country not in config.countries:
continue
if valid_year.match(row[last_year_col]):
last_year = int(row[last_year_col])
else:
# not clear if this means all values are estimated
last_year = 9999
for (year, colnum) in year_cols.items():
value = row[colnum]
if valid_float.match(value): #and year < last_year:
table.insert([
year, country, field,
float(value.replace(",", ""))
])
def parse_env():
cache_dirs = fileutils.getcachecontents("cn")
for adir in cache_dirs:
if regexes.is_num(adir):
year = int(adir)
else:
continue
db_table = SQLTable("cn.emissions_%d" % year,
["industry_zh", "industry_en",
"pollutant", "amount"],
["varchar(1023)", "varchar(1023)",
"varchar(1023)", "float"])
db_table.drop()
db_table.create()
def insert_row(rowdata, columns, max_sector_column):
if max_sector_column == 0:
(ind_zh, ind_en) = split_english(rowdata[0])
else:
ind_zh = rowdata[0]
ind_en = rowdata[1]
for (pollutant, amount) in zip(columns[max_sector_column+1:],
rowdata[max_sector_column+1:]):
if (len(amount)):
db_table.insert([ind_zh, ind_en, pollutant, amount])
xact = db.xact(mode="READ WRITE")
xact.begin()
subdir = os.path.join("cn", adir)
files = fileutils.getcachecontents(subdir)
for filename in files:
filepath = fileutils.getcache(filename, subdir)
fh = open(filepath, "rb") # binary b/c of non-utf encoding
html = fh.read()
fh.close()
soup = BeautifulSoup(html)
print(adir, filename)
title = soup.title.string
# mad maaad nested tables!
# we'll just have to find one with a large number of rows
# and hope that's the right one
table = None
for test_table in soup.find_all("table"):
if test_table.tbody:
test_table = test_table.tbody
num_rows = len(list(filter(is_row, test_table.children)))
if num_rows > 10:
table = test_table
break
columns = None
did_have_numbers = False # true after we've parsed through
max_sector_column = 0 # 1 if english separate, 0 otherwise
prev_rowdata = None
prev_rowspans = None
data = []
# long cell values are often expanded into the cell directly
# below (multiple rows) resulting in rows that are blank
# except in cells that contain overflow.
# this necessitates to keep state using heuristics.
insert_later = None
insert_now = None
for row in table.children:
if not is_tag(row) or row.name != "tr":
continue
rowspans = []
rowdata = []
# multi-row cells precede sub-parts of the pollutant
# which can't be distinguished without their parent
prefix = None
cells = list(filter(is_cell, row.children))
rowlen = len(cells)
for cellpos in range(rowlen):
cell = cells[cellpos]
rowspan = 1
if "rowspan" in cell.attrs:
rowspan = int(cell["rowspan"])
cellvalue = cell.text.strip().strip(".")\
.replace('…', '').replace('\xa0', '')
# use previous rowspan if we have one of the buggy blank
# cells at the end, which don't have the proper rowspan
if cellpos == rowlen - 1 and \
len(cellvalue) == 0 and len(rowspans) > 0:
rowspan = rowspans[-1]
# if the cell directly before us in the previous row
# spanned multiple rows, create a blank space in this row.
# the abs difference below is used for counting down:
# if rowspan in previous column was 6 and current is 1
# the difference is -5, on the next row that will
# be subtracted again
if prev_rowspans is not None:
i = len(rowdata)
while i < len(prev_rowspans) and \
abs(prev_rowspans[i]) > rowspan:
rowdata.append('')
rowspans.append(-abs(
abs(rowspan) - abs(prev_rowspans[i])))
i = len(rowdata)
rowdata.append(cellvalue)
rowspans.append(rowspan)
# count any multi-row cells that were at the end
if prev_rowdata is not None:
for i in range(len(rowdata), len(prev_rowdata)):
if prev_rowspans[i] > rowspan: # span of last cell
rowdata.append(prev_rowdata[i])
rowspans.append(rowspan)
# remove blank cells at the end - these appear to be bugs
while len(rowdata) and len(rowdata[-1]) == 0 and \
(columns is None or len(rowdata) != len(columns)):
rowdata.pop()
rowspans.pop()
# end of rowdata manipulation
prev_rowdata = rowdata
prev_rowspans = rowspans
if len(rowdata) == 0:
continue
# ignore rows that they put above the column headers
# we'll just special case anything we find
if columns is None and rowdata[0].startswith("单位"):
prev_rowdata = None
prev_rowspans = None
continue
lengths = [len(x) for x in rowdata]
if sum(lengths) == 0: # all blank strings
continue
# if we're sure we have columns, clean up rowdata so
# the multirow rules don't get applied anymore
if sum(rowspans) == rowspan * len(rowspans):
rowspans = [1]*len(rowspans)
has_numbers = False
for field in rowdata:
if regexes.is_num(field):
has_numbers = True
did_have_numbers = True
break
if has_numbers or insert_later is None:
insert_now = insert_later
insert_later = rowdata
else:
# decide whether this row is an overflow
# already know sum(lengths) > 0
if len(rowdata) >= len(insert_later) and \
(lengths[0] == 0 or lengths[-1] == 0):
# we shouldn't see overflow on both sides
# because rowdata[0] should happen in a header row
# and rowdata[-1] must happen in a data row
for i in range(len(insert_later)):
# don't want to append to "hang ye" or "Sector"
if not did_have_numbers \
and i > max_sector_column + 1 \
and len(insert_later[i]) == 0:
# blank above, assume "multirow" to the left
insert_later[i] = insert_later[i-1] + " - "
if lengths[i]:
insert_later[i] += " " + rowdata[i]
# if we knocked blank cells off the previous row but
# we know it's actually longer from the current row
for i in range(len(insert_later), len(rowdata)):
insert_later.append(rowdata[i])
#if not has_numbers and not did_have_numbers: # near BOF
if insert_now is not None and columns is None:
columns = insert_now
insert_now = None
for i in range(len(columns)):
columns[i] = columns[i].replace("\n", " ")
# figure out if english names are separate or not
if len(columns) > 1 and columns[1].strip() == "Sector":
max_sector_column = 1
elif insert_now is not None and len(insert_now) == len(columns):
insert_row(insert_now, columns, max_sector_column)
insert_now = None
else:
# we don't want to get here - debug
if insert_now is not None:
print(len(insert_now), len(columns), insert_now)
# close the loop
if insert_later is not None and len(insert_later) == len(columns):
insert_row(insert_later, columns, max_sector_column)
print(columns)
xact.commit()
def parse_int():
for year in config.STUDY_YEARS:
tablename = "%s.int_use_%d" % (config.WIOD_SCHEMA, year)
colnames = [
"from_country", "to_country", "commodity", "industry", "value"
]
coltypes = [
"char(3)", "char(3)", "varchar(15)", "varchar(15)", "float"
]
use_table = SQLTable(tablename, colnames, coltypes).create()
tablename = "%s.int_make_%d" % (config.WIOD_SCHEMA, year)
colnames = ["country", "industry", "commodity", "value"]
coltypes = ["char(3)", "varchar(15)", "varchar(15)", "float"]
make_table = SQLTable(tablename, colnames, coltypes).create()
filename = "IntSUT%s_row_Apr12.xls" % str(year)[2:4]
subdir = os.path.join("wiod", "intsuts_analytic")
path = fileutils.getcache(filename, subdir)
wb = xlrd.open_workbook(path)
for country in config.countries.keys():
sheet = wb.sheet_by_name("USE_%s" % country)
industry_row = sheet.row_values(0)
row = sheet.row_values(1)
industry_codes = []
for (code, desc) in zip(industry_row, row):
industry_codes.append(industry_tracker.set_code(code, desc))
for i in range(2, sheet.nrows):
row = sheet.row_values(i)
# notes say Use tables are broken down by origin
from_country = row[1]
# stupid hack so i don't have to change char(3)
if from_country == "ZROW":
from_country = "RoW"
com_code = commodity_tracker.set_code(row[2], row[3])
if not com_code:
continue
for j in range(4, len(row)):
value = row[j]
ind_code = industry_codes[j]
if value != 0 and ind_code:
# commodity first
use_table.insert(
[from_country, country, com_code, ind_code, value])
sheet = wb.sheet_by_name("SUP_%s" % country)
industry_row = sheet.row_values(0)
row = sheet.row_values(1)
industry_codes = []
for (code, desc) in zip(industry_row, row):
industry_codes.append(industry_tracker.set_code(code, desc))
for i in range(2, sheet.nrows):
row = sheet.row_values(i)
com_code = commodity_tracker.set_code(row[1], row[2])
if not com_code:
continue
for j in range(3, len(row)):
value = row[j]
ind_code = industry_codes[j]
if value != 0 and ind_code:
# industry first
make_table.insert([country, ind_code, com_code, value])
def parse_env():
# parse english env files
# TODO: might want to use the energy table as well.
# it is very comprehensive, but formatted differently and only has 2001
sector_whitelist = ("Household Consumption", "Fixed Capital Formation")
eng_env_years = [1999, 2001, 2004]
eng_env_files = {
"air_pol": {
"filename": "IO_air.xls",
"columns": ["TSP", "PM10", "SOx", "NOx", "NMHC", "CO", "Pb"],
},
"water_pol": {
"filename": "IO_pol_water.xls",
"columns": ["BOD", "COD", "SS"],
},
"waste_pol": {
"filename":
"IO_waste.xls",
"columns": [
"Total waste", "General waste", "Hazardous waste",
"Total waste - improper disposal",
"General waste - improper disposal",
"Hazardous waste - improper disposal"
],
},
"water_use": {
"filename": "IO_res_water.xls",
"columns": ["Natural water", "Abstracted water"],
},
}
tables_by_year = {}
for year in eng_env_years:
if year not in tables_by_year:
tablename = "%s.env_%d" % (config.SCHEMA, year)
table = SQLTable(tablename, ["sector", "series", "value"],
["varchar(55)", "varchar(255)", "float"])
table.create()
table.truncate()
tables_by_year[year] = table
else:
table = tables_by_year[year]
first_file = True
for (tkey, tdata) in eng_env_files.items():
path = fileutils.getdatapath(tdata["filename"], "tw-env")
wb = xlrd.open_workbook(path)
sheet = wb.sheet_by_name("year %d" % year)
for rowindex in range(sheet.nrows):
row = sheet.row_values(rowindex)
if len(row) > 1 and \
(regexes.is_num(row[0]) or row[1] in sector_whitelist):
sector = row[1].strip()
if first_file: # these columns are repeated in every file
table.insert([sector, "Total Output", row[2]])
table.insert([sector, "Total Input", row[3]])
table.insert([sector, "GDP", row[4]])
first_file = False
for i in range(len(tdata["columns"])):
table.insert([sector, tdata["columns"][i], row[i + 5]])
# parse chinese env tables
# this is file that we created by compiling older chinse data and
# manually copying info from latest (2010) pdf files
# skip 2001 because the english version is better
sheetnames_by_year = {
2000: ["89年空汙", "89年廢棄物"],
2002: ["91年空汙", "91年廢棄物"],
2003: ["92年空汙", "92年廢棄物"],
2010: ["99年空汙", "99年水汙", "99年廢棄物"],
}
path = fileutils.getdatapath("sheets.xls", "tw-env")
wb = xlrd.open_workbook(path)
for (year, sheetnames) in sheetnames_by_year.items():
tablename = "%s.env_%d" % (config.SCHEMA, year)
table = SQLTable(tablename, ["sector", "series", "value"],
["varchar(55)", "varchar(255)", "float"])
table.create()
table.truncate()
for sheetname in sheetnames:
sheet = wb.sheet_by_name(sheetname)
header = sheet.row_values(0)
# the 2010 tables have several rows that we don't want
should_parse = (year != 2010)
for i in range(1, sheet.nrows):
row = sheet.row_values(i)
if should_parse:
sector = row[0].strip()
for i in range(1, len(header)):
measurement = header[i].strip()
value = row[i]
table.insert([sector, measurement, value])
elif row[0] in ("依行業分", "依部門分"):
should_parse = True
def doparse():
carrier_countries = {
#"-": "", # Unknown
"1I": "USA", # Sky Trek International Airlines
"2T": "CAN", # Canada 3000 Airlines Ltd.
"3Z": "USA", # Tatonduk Outfitters Limited d/b/a Everts Air Alaska and Everts Air Cargo
"5X": "USA", # United Parcel Service
"5Y": "USA", # Atlas Air Inc.
"6F": "GBR", # Laker Airways Inc.
#"6U": "", # Air Ukraine
#"6Y": "", # Nicaraguense De Aviacion Sa
#"7P": "", # Apa International Air S.A. (dominican rep)
#"7Z": "", # Lb Limited
"8C": "USA", # Air Transport International
"AA": "USA", # American Airlines Inc.
"AC": "CAN", # Air Canada
#"ADB": "", # Antonov Company (ukraine)
"AF": "FRA", # Compagnie Nat'l Air France
"AI": "IND", # National Aviation Company of India Limited d/b/a Air India
"AM": "MEX", # Aeromexico
#"AQQ": "", # Air Charter (Safa)
#"AR": "", # Aerolineas Argentinas
"AS": "USA", # Alaska Airlines Inc.
#"AT": "", # Royal Air Maroc (morocco)
#"AV": "", # Aerovias Nac'l De Colombia
"AY": "FIN", # Finnair Oy
"AZ": "ITA", # Compagnia Aerea Italiana
#"All Rows": "", # All Rows (including those not displayed)
"BA": "GBR", # British Airways Plc
#"BBQ": "", # Balair Ag (swiss)
"BCQ": "CAN", # Bradley Air Services Ltd.
#"BG": "", # Biman Bangladesh Airlines
"BQ": "MEX", # Aeromar C. Por A.
"BR": "TWN", # Eva Airways Corporation
#"BW": "", # Caribbean Airlines Limited (trinidad and tobago)
"BY": "GBR", # Britannia Airways Ltd.
"CA": "CHN", # Air China
#"CC": "", # Air Atlanta Icelandic
"CDQ": "USA", # Kitty Hawk International
#"CF": "", # Compan. De Aviacion Faucett (peru)
"CI": "TWN", # China Airlines Ltd.
#"CLQ": "", # Aero Transcolombiana
#"CM": "", # Compania Panamena (Copa)
"CO": "USA", # Continental Air Lines Inc.
"CP (1)": "CAN", # Canadian Airlines International Ltd.
"CS": "USA", # Continental Micronesia
"CV": "LUX", # Cargolux Airlines International S.A
#"CVQ": "", # Caraven S.A.
#"CX": "", # Cathay Pacific Airways Ltd. (hong kong, includes pre 1997)
"CYQ": "FRA", # Corse Air International (assuming corsair)
"CZ": "CHN", # China Southern Airlines
"DE": "DEU", # Condor Flugdienst
"DHQ": "GBR", # DHL Aero Expresso
"DL": "USA", # Delta Air Lines Inc.
#"ED": "", # Andes (ecuador or argentina)
"EH": "ESP", # Saeta Airlines
"EI": "IRL", # Aer Lingus Plc
#"EOQ": "", # Aeroservicios Ecuatorianos
"ER": "USA", # Astar USA, LLC
#"EU": "", # Ecuatoriana De Aviacion
#"EXQ": "", # Export Air Del Peru S.A.
"EZ": "TWN", # Evergreen International Inc.
"F9": "USA", # Frontier Airlines Inc.
"FCQ": "USA", # Falcon Air Express
#"FF": "", # Tower Air Inc.
#"FI": "", # Icelandair
#"FJ": "", # Air Pacific Ltd. (fiji)
"FNQ": "USA", # Fine Airlines Inc.
#"FQ": "", # Air Aruba
#"FS": "", # Serv De Trans Aereos Fuegui (argentina)
"FX": "USA", # Federal Express Corporation
#"G3": "", # Aerochago S.A.
"GA": "IDN", # P.T. Garuda Indonesian Arwy
"GD": "MEX", # Transp. Aereos Ejecutivos
#"GF": "", # Gulf Air Company (bahrain)
#"GH": "", # Ghana Airways Corporation
"GJ (1)": "MEX", # Mexicargo
"GL": "USA", # Miami Air International
"GR": "USA", # Gemini Air Cargo Airways
#"GU": "", # Aviateca (guatemala)
#"GY": "", # Guyana Airways Corporation
"H2": "BEL", # City Bird
"H5": "RUS", # Magadan Airlines
"HA": "USA", # Hawaiian Airlines Inc.
"HAQ": "DEU", # Hapag Lloyd Flug.
"HCQ": "USA", # Av Atlantic
#"HFQ": "", # Haiti Air Freight Intl
"HLQ": "AUS", # Heavylift Cargo Airlines Lt
"HP": "USA", # America West Airlines Inc. (Merged with US Airways 9/05. Stopped reporting 10/07.)
#"HY": "", # Uzbekistan Airways
"IB": "ESP", # Iberia Air Lines Of Spain
#"ITQ": "", # Interamericana De Aviacion (uruguay)
"IW": "FRA", # Air Liberte Aka Aom Minerve
#"JAQ": "", # Jamaica Air Freighters
"JD": "JPN", # Japan Air System Co. Ltd.
"JI (1)": "USA", # Midway Airlines Inc.
"JK": "ESP", # Spanair S.A.
"JKQ": "USA", # Express One International Inc.
"JL": "JPN", # Japan Air Lines Co. Ltd.
#"JM": "", # Air Jamaica Limited
"JR": "USA", # Aero California
"JW": "CAN", # Arrow Air Inc.
"JZ": "JPN", # Japan Air Charter Co. Ltd.
"K8 (1)": "NLD", # Dutch Caribbean Airlines
"KE": "KOR", # Korean Air Lines Co. Ltd.
"KH": "USA", # Aloha Air Cargo
#"KI": "", # Time Air Ltd. (south africa)
"KL": "NLD", # Klm Royal Dutch Airlines
#"KP": "", # Kiwi International
"KR": "USA", # Kitty Hawk Aircargo
"KTQ": "TUR", # Turks Air Ltd.
#"KU": "", # Kuwait Airways Corp.
"KW": "USA", # Carnival Air Lines Inc.
#"KX": "", # Cayman Airways Limited
"KZ": "JPN", # Nippon Cargo Airlines
#"LA": "", # Lan-Chile Airlines
#"LB": "", # Lloyd Aereo Boliviano S. A.
"LGQ": "MEX", # Lineas Aereas Allegro
"LH": "DEU", # Lufthansa German Airlines
"LO": "POL", # Polskie Linie Lotnicze
#"LR": "", # Lacsa (costa rica)
#"LSQ": "", # Lineas Aereas Suramerican (colombia)
"LT": "DEU", # Luftransport-Unternehmen
#"LU": "", # Air Atlantic Dominicana
#"LY": "", # El Al Israel Airlines Ltd.
"LZ": "BGR", # Balkan Bulgarian Airlines
"M6": "USA", # Amerijet International
"M7": "MEX", # Aerotransportes Mas De Crga
"MA": "HUN", # Malev Hungarian Airlines
"MG": "USA", # Champion Air
#"MH": "", # Malaysian Airline System
#"ML": "", # Aero Costa Rica
"MP": "NLD", # Martinair Holland N.V.
#"MS": "", # Egyptair
"MT": "GBR", # Thomas Cook Airlines Uk Ltd.
"MT (1)": "GBR", # Flying Colours Airlines Ltd.
"MU": "CHN", # China Eastern Airlines
#"MUQ": "", # Aerolineas Mundo (columbia)
"MX": "MEX", # Compania Mexicana De Aviaci
#"MYQ": "", # Lineas Aereas Mayas (Lamsa)
#"N5 (1)": "", # Nations Air Express Inc.
"NA": "USA", # North American Airlines
"NG": "DEU", # Lauda Air Luftfahrt Ag
"NH": "JPN", # All Nippon Airways Co.
"NK": "USA", # Spirit Air Lines
"NW": "USA", # Northwest Airlines Inc.
"NWQ": "USA", # N. W. Territorial Airways
#"NZ": "", # Air New Zealand
"OA": "GRC", # Olympic Airways
#"OI": "", # Prestige Airways (uae)
"OK": "CZE", # Czech Airlines
#"ON": "", # Air Nauru
"OS": "AUT", # Austrian Airlines
"OW": "USA", # Executive Airlines
"OZ": "KOR", # Asiana Airlines Inc.
"PA (2)": "USA", # Pan American World Airways
"PCQ": "USA", # Pace Airlines
#"PIQ": "", # Pacific International Airlines (ambiguous: usa, panama)
#"PK": "", # Pakistan International Airlines
#"PL": "", # Aero Peru
"PNQ": "USA", # Panagra Airways
"PO": "USA", # Polar Air Cargo Airways
#"PR": "", # Philippine Airlines Inc.
"PRQ": "USA", # Florida West Airlines Inc.
"PT": "USA", # Capital Cargo International
#"PY": "", # Surinam Airways Limited
"Q7": "BEL", # Sobelair
"QF": "AUS", # Qantas Airways Ltd.
"QK": "CAN", # Jazz Aviation LP
#"QN": "", # Royal Air (ambiguous)
"QO": "MEX", # Aeromexpress
"QQ": "USA", # Reno Air Inc.
#"QT": "", # Transportes Aereos Mercantiles Panamericanos S.A (colombia)
"QTQ": "IRL", # Aer Turas Teoranta
"QX": "USA", # Horizon Air
"RD": "USA", # Ryan International Airlines
"REQ": "USA", # Renown Aviation
"RG": "BRA", # Varig S. A.
#"RJ": "", # Alia-(The) Royal Jordanian
#"RK": "", # Air Afrique
"RNQ": "GBR", # Mytravel Airways
"RO": "ROU", # Tarom Romanian Air Transpor
#"SA": "", # South African Airways
"SAQ": "USA", # Southern Air Transport Inc.
"SEQ": "GBR", # Sky Service F.B.O.
"SIQ": "LUX", # Premiair
"SK": "SWE", # Scandinavian Airlines Sys.
"SM": "USA", # Sunworld International Airlines
"SN (1)": "BEL", # Sabena Belgian World Air.
"SPQ": "USA", # Sun Pacific International
#"SQ": "", # Singapore Airlines Ltd.
#"SR": "", # Swissair Transport Co. Ltd.
"SU": "RUS", # Aeroflot Russian Airlines
#"SV": "", # Saudi Arabian Airlines Corp
"SX (1)": "MEX", # Aeroejecutivo S.A.
"SY": "USA", # Sun Country Airlines d/b/a MN Airlines
"T9": "USA", # TransMeridian Airlines
#"TA": "", # Taca International Airlines (el savador)
"TCQ": "USA", # Express.Net Airlines
#"TG": "", # Thai Airways International Ltd.
"TK": "TUR", # Turk Hava Yollari A.O.
"TKQ": "USA", # Trans-Air-Link Corporation
"TNQ": "USA", # Emery Worldwide Airlines
"TP": "PRT", # Tap-Portuguese Airlines
"TR": "BRA", # Transbrasil S.A.
"TRQ": "SWE", # Blue Scandinavia Ab
"TS": "CAN", # Air Transat
"TW": "USA", # Trans World Airways LLC
#"TZ": "", # ATA Airlines d/b/a ATA (iran)
"TZQ": "GBR", # First Choice Airways
"U7": "USA", # USA Jet Airlines Inc.
"UA": "USA", # United Air Lines Inc.
#"UD": "", # Fast Air Carrier Ltd.
"UN": "RUS", # Transaero Airlines
#"UP": "", # Bahamasair Holding Limited
"US": "USA", # US Airways Inc. (Merged with America West 9/05. Reporting for both starting 10/07.)
"UX": "ESP", # Air Europa
#"UYQ": "", # Aerolineas Uruguayas S.A.
#"VA (1)": "", # Venezuelan International Airways
#"VC": "", # Servicios Avensa (venezuela)
#"VE": "", # Aerovias Venezolanas-Avensa
"VIQ": "RUS", # Volga-Dnepr Airlines
"VP": "BRA", # Viacao Aerea Sao Paulo
#"VR": "", # Transportes Aereos De Cabo (cape verde)
"VS": "GBR", # Virgin Atlantic Airways
#"VX (1)": "", # Aces Airlines (colombia)
#"W7": "", # Western Pacific Airlines (solomon islands)
#"WD": "", # Halisa Air (haiti)
"WE": "USA", # Centurion Cargo Inc.
"WO": "USA", # World Airways Inc.
#"XC": "", # Air Caribbean (1)
"XE": "USA", # ExpressJet Airlines Inc. (1)
"XJ": "USA", # Mesaba Airlines
"XP": "USA", # Casino Express
"YX (1)": "USA", # Midwest Airline, Inc.
"ZB": "USA", # Monarch Airlines
#"ZUQ": "", # Zuliana De Aviacion (venezuela)
"ZX (1)": "CAN", # Airbc Ltd.
}
tablename = "air_carriers"
table = SQLTable(
tablename,
["year", "carrier", "series", "value"],
["int", "varchar(15)", "varchar(15)", "int"])
table.create()
table.truncate()
carriers = {}
for year in config.STUDY_YEARS:
for filestem in ["freight", "passengers"]:
filename = filestem + str(year) + ".csv"
path = fileutils.getcache(filename, "bts")
with open(path) as fh:
csvf = csv.reader(fh)
next(csvf)
header = next(csvf)
for row in csvf:
if len(row) == 3:
carrier = row[0]
#carrier_name = row[1]
if carrier in carrier_countries:
country = carrier_countries[carrier]
value = int(row[2])
table.insert([year, country, filestem, value])
def doparse():
for year in (1972, 1977):
table = SQLTable("%s.codes_%d" % (config.IO_SCHEMA, year),
["code", "description"],
["char(6)", "text"]).create()
table.truncate()
filepath = fileutils.getdatapath("io_sectors_%d.csv" % year, "usa")
with open(filepath, "r") as fh:
csvf = csv.reader(fh)
for row in csvf:
if len(row) and len(row[0]):
table.insert([row[0], row[1]])
if year == 1972:
# this is stated in the rtf file for both 1972 and 1977
# but this code never appears in 1977, the documentation
# was probably not properly updated
table.insert(["870000", "total value added"])
writer = dbsetup.IOCodeTableWriter()
writer.set_year(1982, "Io-code.doc")
with open(writer.get_filename()) as f:
for line in f:
if len(line) > 8:
code = line[:6]
desc = line[8:]
writer.writerow(code, desc)
writer.set_year(1987, "SIC-IO.DOC")
with open(writer.get_filename()) as f:
pattern = re.compile('\s*(\d{1,2})\.(\d{4})\s+([^0-9\*]+)')
for line in f:
match = pattern.match(line)
if match:
code = match.group(1).rjust(2, '0') + match.group(2)
desc = match.group(3).strip('(. \r\n')
writer.writerow(code, desc)
writer.set_year(1992, "io-code.txt")
with open(writer.get_filename()) as f:
for line in f:
if len(line) > 7:
code = line[:6]
desc = line[7:]
writer.writerow(code, desc)
writer.set_year(1997, "IO-CodeDetail.txt")
with open(writer.get_filename()) as f:
csvf = csv.reader(f)
for row in csvf:
if len(row) == 2:
writer.writerow(row[0], row[1])
writer.set_year(2002, "REV_NAICSUseDetail 4-24-08.txt")
with open(writer.get_filename()) as f:
valid_line = re.compile("[A-Z0-9]{6}\s")
line = f.readline().strip().replace("GasPipeVal", "GasPipe ")
fields = dbsetup.get_header_locations(dbsetup.replace_tabs(line))
codemap = {}
for line in f:
if valid_line.match(line):
row = dbsetup.get_values_for_fields(
dbsetup.replace_tabs(line), fields)
codemap[row["Commodity"]] = row["CommodityDescription"]
codemap[row["Industry"]] = row["IndustryDescription"]
for (code, desc) in codemap.items():
writer.writerow(code, desc)
writer.flush()
def parse_env():
cache_dirs = fileutils.getcachecontents("cn")
for adir in cache_dirs:
if regexes.is_num(adir):
year = int(adir)
else:
continue
db_table = SQLTable(
"cn.emissions_%d" % year,
["industry_zh", "industry_en", "pollutant", "amount"],
["varchar(1023)", "varchar(1023)", "varchar(1023)", "float"])
db_table.drop()
db_table.create()
def insert_row(rowdata, columns, max_sector_column):
if max_sector_column == 0:
(ind_zh, ind_en) = split_english(rowdata[0])
else:
ind_zh = rowdata[0]
ind_en = rowdata[1]
for (pollutant, amount) in zip(columns[max_sector_column + 1:],
rowdata[max_sector_column + 1:]):
if (len(amount)):
db_table.insert([ind_zh, ind_en, pollutant, amount])
xact = db.xact(mode="READ WRITE")
xact.begin()
subdir = os.path.join("cn", adir)
files = fileutils.getcachecontents(subdir)
for filename in files:
filepath = fileutils.getcache(filename, subdir)
fh = open(filepath, "rb") # binary b/c of non-utf encoding
html = fh.read()
fh.close()
soup = BeautifulSoup(html)
print(adir, filename)
title = soup.title.string
# mad maaad nested tables!
# we'll just have to find one with a large number of rows
# and hope that's the right one
table = None
for test_table in soup.find_all("table"):
if test_table.tbody:
test_table = test_table.tbody
num_rows = len(list(filter(is_row, test_table.children)))
if num_rows > 10:
table = test_table
break
columns = None
did_have_numbers = False # true after we've parsed through
max_sector_column = 0 # 1 if english separate, 0 otherwise
prev_rowdata = None
prev_rowspans = None
data = []
# long cell values are often expanded into the cell directly
# below (multiple rows) resulting in rows that are blank
# except in cells that contain overflow.
# this necessitates to keep state using heuristics.
insert_later = None
insert_now = None
for row in table.children:
if not is_tag(row) or row.name != "tr":
continue
rowspans = []
rowdata = []
# multi-row cells precede sub-parts of the pollutant
# which can't be distinguished without their parent
prefix = None
cells = list(filter(is_cell, row.children))
rowlen = len(cells)
for cellpos in range(rowlen):
cell = cells[cellpos]
rowspan = 1
if "rowspan" in cell.attrs:
rowspan = int(cell["rowspan"])
cellvalue = cell.text.strip().strip(".")\
.replace('…', '').replace('\xa0', '')
# use previous rowspan if we have one of the buggy blank
# cells at the end, which don't have the proper rowspan
if cellpos == rowlen - 1 and \
len(cellvalue) == 0 and len(rowspans) > 0:
rowspan = rowspans[-1]
# if the cell directly before us in the previous row
# spanned multiple rows, create a blank space in this row.
# the abs difference below is used for counting down:
# if rowspan in previous column was 6 and current is 1
# the difference is -5, on the next row that will
# be subtracted again
if prev_rowspans is not None:
i = len(rowdata)
while i < len(prev_rowspans) and \
abs(prev_rowspans[i]) > rowspan:
rowdata.append('')
rowspans.append(
-abs(abs(rowspan) - abs(prev_rowspans[i])))
i = len(rowdata)
rowdata.append(cellvalue)
rowspans.append(rowspan)
# count any multi-row cells that were at the end
if prev_rowdata is not None:
for i in range(len(rowdata), len(prev_rowdata)):
if prev_rowspans[i] > rowspan: # span of last cell
rowdata.append(prev_rowdata[i])
rowspans.append(rowspan)
# remove blank cells at the end - these appear to be bugs
while len(rowdata) and len(rowdata[-1]) == 0 and \
(columns is None or len(rowdata) != len(columns)):
rowdata.pop()
rowspans.pop()
# end of rowdata manipulation
prev_rowdata = rowdata
prev_rowspans = rowspans
if len(rowdata) == 0:
continue
# ignore rows that they put above the column headers
# we'll just special case anything we find
if columns is None and rowdata[0].startswith("单位"):
prev_rowdata = None
prev_rowspans = None
continue
lengths = [len(x) for x in rowdata]
if sum(lengths) == 0: # all blank strings
continue
# if we're sure we have columns, clean up rowdata so
# the multirow rules don't get applied anymore
if sum(rowspans) == rowspan * len(rowspans):
rowspans = [1] * len(rowspans)
has_numbers = False
for field in rowdata:
if regexes.is_num(field):
has_numbers = True
did_have_numbers = True
break
if has_numbers or insert_later is None:
insert_now = insert_later
insert_later = rowdata
else:
# decide whether this row is an overflow
# already know sum(lengths) > 0
if len(rowdata) >= len(insert_later) and \
(lengths[0] == 0 or lengths[-1] == 0):
# we shouldn't see overflow on both sides
# because rowdata[0] should happen in a header row
# and rowdata[-1] must happen in a data row
for i in range(len(insert_later)):
# don't want to append to "hang ye" or "Sector"
if not did_have_numbers \
and i > max_sector_column + 1 \
and len(insert_later[i]) == 0:
# blank above, assume "multirow" to the left
insert_later[i] = insert_later[i - 1] + " - "
if lengths[i]:
insert_later[i] += " " + rowdata[i]
# if we knocked blank cells off the previous row but
# we know it's actually longer from the current row
for i in range(len(insert_later), len(rowdata)):
insert_later.append(rowdata[i])
#if not has_numbers and not did_have_numbers: # near BOF
if insert_now is not None and columns is None:
columns = insert_now
insert_now = None
for i in range(len(columns)):
columns[i] = columns[i].replace("\n", " ")
# figure out if english names are separate or not
if len(columns) > 1 and columns[1].strip() == "Sector":
max_sector_column = 1
elif insert_now is not None and len(insert_now) == len(
columns):
insert_row(insert_now, columns, max_sector_column)
insert_now = None
else:
# we don't want to get here - debug
if insert_now is not None:
print(len(insert_now), len(columns), insert_now)
# close the loop
if insert_later is not None and len(insert_later) == len(columns):
insert_row(insert_later, columns, max_sector_column)
print(columns)
xact.commit()
def parse_io():
io_files = {
1996: "410281134571.xls",
1999: "4102715414971.xls",
2001: "4122111363671.xls",
2004: "611239581071.xls",
2006: "9121414285971.xls",
2007: "1139203871.xls",
2008: "1139204871.xls",
2009: "11229101502.xls",
2010: "1122910141371.xls",
}
for (year, filename) in io_files.items():
tablename = "%s.io_%d" % (config.SCHEMA, year)
# millions are in NTD
table = SQLTable(tablename, ["from_sector", "to_sector", "millions"],
["varchar(255)", "varchar(255)", "float"])
table.create()
table.truncate()
path = fileutils.getcache(filename, "tw/%d" % year)
wb = xlrd.open_workbook(path)
sheet = wb.sheets()[0]
to_codes = sheet.row_values(0)
to_names = sheet.row_values(1)
for rowindex in range(2, sheet.nrows):
row = sheet.row_values(rowindex)
from_code = row[0].strip()
from_name = row[1].strip()
for i in range(2, len(to_names)):
to_name = to_names[i].strip()
value = row[i]
table.insert([from_name, to_name, value])
if year == 2010:
strings = {
"viewname": "%s.io_view_%d" % (config.SCHEMA, year),
"tablename": tablename,
"maptable": "%s.sector_map_%d" % (config.SCHEMA, year),
"to_blacklist": sqlhelper.set_repr(config.to_blacklists[year]),
"from_blacklist":
sqlhelper.set_repr(config.from_blacklists[year]),
}
sql = """CREATE OR REPLACE VIEW %(viewname)s AS
SELECT from_map.io_sector AS from_sector,
to_map.io_sector as to_sector,
sum(millions) as millions
FROM %(tablename)s io,
(SELECT DISTINCT io_sector, io_commod
FROM %(maptable)s) from_map,
(SELECT DISTINCT io_sector, io_ind
FROM %(maptable)s) to_map
WHERE io.to_sector NOT IN %(to_blacklist)s
AND io.from_sector NOT IN %(from_blacklist)s
AND from_map.io_commod = io.from_sector
AND to_map.io_ind = io.to_sector
GROUP BY from_map.io_sector, to_map.io_sector""" % strings
print(sql)
db.execute(sql)
class SectorCodes:
def __init__(self, codetablename, mode="r"):
self.mode = mode
self.codetable = SQLTable(
codetablename,
["code", "description"],
["varchar(15)", "varchar(255)"])
self.code_dict = {}
self.reverse_code_dict = {}
self.setup()
def setup(self):
if self.mode == "w":
# invalid codes or codes that we don't want to record
self.code_blacklist = []
# if we want to override the code provided with something
# we make up (or from another set) based on the description
self.manual_codes = {}
self.codetable.create()
# get existing codes from db
for (code, desc) in self.codetable.getall():
self.code_dict[code] = desc
self.reverse_code_dict[desc] = code
return self
# for write mode
def blacklist_code(self, code):
self.code_blacklist.append(code)
if code in self.code_dict:
del self.code_dict[code]
def set_blacklist(self, code_blacklist):
self.code_blacklist = []
for code in code_blacklist:
self.blacklist_code(code)
def curate_code_from_desc(self, desc, code):
self.manual_codes[desc] = code
self.code_dict[code] = desc
self.reverse_code_dict[desc] = code
def add_curated_codes(self, curated_codes):
for (desc, code) in curated_codes.items():
self.curate_code_from_desc(desc, code)
# returns the code used if it was recognized, false otherwise
def set_code(self, code, desc):
if type(code) is str:
code = code.strip()
elif type(code) is float:
code = str(int(code))
if type(desc) is str:
desc = desc.strip()
if desc in self.manual_codes:
code = self.manual_codes[desc]
if code is None or not len(code):
if desc is None or not len(desc): # ignore empty args
return False
else:
return False
elif code in self.code_blacklist:
return False
if code in self.code_dict and self.code_dict[code] != desc:
# this is to check for blatant differences
print(self.code_dict[code], "=>", desc)
self.code_dict[code] = desc
# there may be more than one description for the same code
self.reverse_code_dict[desc] = code
return code
def has_code(self, code):
return code in self.code_dict
def get_code_for_title(self, desc):
if desc in self.reverse_code_dict:
return self.reverse_code_dict[desc]
def get_title_for_code(self, code):
if self.has_code(code):
return self.code_dict[code]
return False
def update_codes(self):
if self.mode != "w":
raise Exception("SectorCodes created in read-only mode")
self.codetable.truncate()
for code in sorted(self.code_dict.keys()):
desc = self.code_dict[code]
self.codetable.insert([code, desc])
def parse_codes():
## manually curated sector map
table = SQLTable("%s.sector_map" % config.WIOD_SCHEMA,
["io_code", "env_code", "description"],
["varchar(15)", "varchar(15)", "text"]).create()
table.truncate()
sector_map = fileutils.getdatapath("sector_map.csv", "wiod")
fh = open(sector_map, "r")
csvf = csv.reader(fh)
header = next(csvf)
for row in csvf:
io_code = row[0].strip()
if not len(io_code):
io_code = None
env_code = row[1].strip()
if not len(env_code):
env_code = None
desc = row[2].strip()
table.insert([io_code, env_code, desc])
## current exchange rates
table = SQLTable("%s.exchange_rates" % config.WIOD_SCHEMA,
["country", "year", "rate"],
["char(3)", "int", "float"]).create()
table.truncate()
path = fileutils.getcache("exr_wiod.xls", "wiod")
wb = xlrd.open_workbook(path)
sheet = wb.sheet_by_name("EXR")
year_list = None
for i in range(sheet.nrows):
row = sheet.row_values(i)
if len(row) < 2:
continue
if year_list is None:
if type(row[0]) is str and row[0].strip() == "Country":
year_list = [int(cell.strip("_ ")) for cell in row[2:]]
else:
if type(row[1]) is str and len(row[1].strip()) == 3:
country = row[1]
if country == "GER":
country = "DEU"
for (year, value) in zip(year_list, row[2:]):
table.insert([country, year, value])
def doparse():
# ppp rank from
# https://www.cia.gov/library/publications/the-world-factbook/rankorder/2004rank.html
countries = {
"LUX": {
"fips": "LU",
"ppp": 3
},
"USA": {
"fips": "US",
"ppp": 11
},
"NLD": {
"fips": "NL",
"ppp": 17
},
"AUT": {
"fips": "AU",
"ppp": 18
},
"SWE": {
"fips": "SW",
"ppp": 21
},
"CAN": {
"fips": "CA",
"ppp": 20
},
"AUS": {
"fips": "AS",
"ppp": 22
},
"IRL": {
"fips": "EI",
"ppp": 23
},
"DEU": {
"fips": "GM",
"ppp": 26
},
"TWN": {
"fips": "TW",
"ppp": 27
},
"BEL": {
"fips": "BE",
"ppp": 28
},
"DNK": {
"fips": "DK",
"ppp": 29
},
"FIN": {
"fips": "FI",
"ppp": 32
},
"GBR": {
"fips": "UK",
"ppp": 33
},
"FRA": {
"fips": "FR",
"ppp": 35
},
"JPN": {
"fips": "JA",
"ppp": 36
},
"KOR": {
"fips": "KS",
"ppp": 40
},
"ESP": {
"fips": "SP",
"ppp": 43
},
"ITA": {
"fips": "IT",
"ppp": 44
},
"CYP": {
"fips": "CY",
"ppp": 46
},
"SVN": {
"fips": "SI",
"ppp": 47
},
"CZE": {
"fips": "EZ",
"ppp": 50
}, # EZ??
"GRC": {
"fips": "GR",
"ppp": 52
},
"MLT": {
"fips": "MT",
"ppp": 53
},
"PRT": {
"fips": "PO",
"ppp": 57
},
"SVK": {
"fips": "LO",
"ppp": 58
},
"POL": {
"fips": "PL",
"ppp": 60
},
"EST": {
"fips": "EN",
"ppp": 61
},
"HUN": {
"fips": "HU",
"ppp": 63
},
"LTU": {
"fips": "LH",
"ppp": 65
},
"RUS": {
"fips": "RS",
"ppp": 71
},
"LVA": {
"fips": "LG",
"ppp": 75
},
"MEX": {
"fips": "MX",
"ppp": 85
},
"TUR": {
"fips": "TU",
"ppp": 86
},
"BRA": {
"fips": "BR",
"ppp": 92
},
"ROU": {
"fips": "RO",
"ppp": 97
},
"BGR": {
"fips": "BU",
"ppp": 101
},
"CHN": {
"fips": "CH",
"ppp": 121
},
"IDN": {
"fips": "ID",
"ppp": 156
},
"IND": {
"fips": "IN",
"ppp": 164
},
}
tablename = "world_supplement"
table = SQLTable(tablename, ["year", "country", "pop", "gdp", "ppp"],
["int", "char(3)", "int", "float", "float"]).create()
table.truncate()
country_fips = {}
data = {}
for (country, info) in countries.items():
data[country] = {}
country_fips[info["fips"]] = country
# this file spec is documented in the xlsx file from the archive
thisyear = datetime.datetime.now().year
path = fileutils.getcache("IDBext001.txt", "wsupp")
with open(path, "r") as fh:
for line in fh:
fields = line.split("|")
if len(fields) == 3:
fips = fields[0]
if fips in country_fips:
year = int(fields[1])
if year >= thisyear: # we don't want future projections
continue
country = country_fips[fips]
data[country][year] = {"pop": int(fields[2])}
worldbank = {
"ppp": "NY.GNP.PCAP.PP.CD_Indicator_MetaData_en_EXCEL.xls",
"gdp": "NY.GDP.PCAP.CD_Indicator_MetaData_en_EXCEL.xls",
}
for (indicator, filename) in worldbank.items():
path = fileutils.getcache(filename, "wsupp")
wb = xlrd.open_workbook(path)
sheet = wb.sheet_by_index(0)
header = [int(x) for x in sheet.row_values(0)[2:]]
for i in range(1, sheet.nrows):
row = sheet.row_values(i)
if row[1] in countries:
country = row[1]
for (year, value) in zip(header, row[2:]):
# this discards years where we don't have population
if year in data[country] and \
type(value) is float and value != 0:
data[country][year][indicator] = value
for (country, country_data) in data.items():
for (year, year_data) in country_data.items():
ppp = None
gdp = None
pop = year_data["pop"]
if "gdp" in year_data:
gdp = year_data["gdp"]
if "ppp" in year_data:
ppp = year_data["ppp"]
table.insert([year, country, pop, gdp, ppp])
def parse_int():
for year in config.STUDY_YEARS:
tablename = "%s.int_use_%d" % (config.WIOD_SCHEMA, year)
colnames = [
"from_country", "to_country", "commodity", "industry", "value"]
coltypes = [
"char(3)", "char(3)", "varchar(15)", "varchar(15)", "float"]
use_table = SQLTable(tablename, colnames, coltypes).create()
tablename = "%s.int_make_%d" % (config.WIOD_SCHEMA, year)
colnames = ["country", "industry", "commodity", "value"]
coltypes = ["char(3)", "varchar(15)", "varchar(15)", "float"]
make_table = SQLTable(tablename, colnames, coltypes).create()
filename = "IntSUT%s_row_Apr12.xls" % str(year)[2:4]
subdir = os.path.join("wiod", "intsuts_analytic")
path = fileutils.getcache(filename, subdir)
wb = xlrd.open_workbook(path)
for country in config.countries.keys():
sheet = wb.sheet_by_name("USE_%s" % country)
industry_row = sheet.row_values(0)
row = sheet.row_values(1)
industry_codes = []
for (code, desc) in zip(industry_row, row):
industry_codes.append(industry_tracker.set_code(code, desc))
for i in range(2, sheet.nrows):
row = sheet.row_values(i)
# notes say Use tables are broken down by origin
from_country = row[1]
# stupid hack so i don't have to change char(3)
if from_country == "ZROW":
from_country = "RoW"
com_code = commodity_tracker.set_code(row[2], row[3])
if not com_code:
continue
for j in range(4, len(row)):
value = row[j]
ind_code = industry_codes[j]
if value != 0 and ind_code:
# commodity first
use_table.insert(
[from_country, country, com_code, ind_code, value])
sheet = wb.sheet_by_name("SUP_%s" % country)
industry_row = sheet.row_values(0)
row = sheet.row_values(1)
industry_codes = []
for (code, desc) in zip(industry_row, row):
industry_codes.append(industry_tracker.set_code(code, desc))
for i in range(2, sheet.nrows):
row = sheet.row_values(i)
com_code = commodity_tracker.set_code(row[1], row[2])
if not com_code:
continue
for j in range(3, len(row)):
value = row[j]
ind_code = industry_codes[j]
if value != 0 and ind_code:
# industry first
make_table.insert(
[country, ind_code, com_code, value])
def drop_table(self, tablename, cascade=False):
self.table = SQLTable(tablename)
self.table.drop(cascade)
def parse_io():
### for ind x ind tables
tables = {}
colnames = ["country", "from_ind", "to_ind", "is_import", "value"]
coltypes = ["char(3)", "varchar(15)", "varchar(15)", "bool", "float"]
for year in config.STUDY_YEARS:
tablename = "%s.niot_%d" % (config.WIOD_SCHEMA, year)
tables[year] = SQLTable(tablename, colnames, coltypes) #.create()
tables[year].drop()
tables[year].create()
tables[year].truncate()
va_sectors = set(config.va_sectors.values())
for country in config.countries.keys():
filename = "%s_NIOT_ROW_Apr12.xlsx" % country
subdir = os.path.join("wiod", "niot")
path = fileutils.getcache(filename, subdir)
wb = openpyxl.load_workbook(filename=path, use_iterators=True)
for year in config.STUDY_YEARS:
imports = {}
sheet = wb.get_sheet_by_name("%d" % year)
rows = sheet.iter_rows()
industry_row = None
for row in rows:
cell = row[0]
if cell.internal_value == "(industry-by-industry)":
industry_row = row
break
row = next(rows) # industry names
industry_codes = []
for (code_cell, desc_cell) in zip(industry_row, row):
code = code_cell.internal_value
desc = desc_cell.internal_value
industry_codes.append(industry_tracker.set_code(code, desc))
for row in rows:
from_code = None
from_desc = None
is_import = False
for (to_code, value_cell) in zip(industry_codes, row):
column = value_cell.column
value = value_cell.internal_value
# excel columns use letters
if column == "A":
from_code = value_cell.internal_value
elif column == "B":
from_desc = value_cell.internal_value
elif column == "C":
from_code = industry_tracker.set_code(
from_code, from_desc)
if not from_code:
break
if type(value) is str and value == "Imports":
is_import = True
elif (column > "D" or len(column) > 1) \
and to_code and value != 0:
tables[year].insert(
[country, from_code, to_code, is_import, value])
### for supply and use tables
def parse_sut(sheet_name, table_prefix):
tables = {}
colnames = ["country", "commodity", "industry", "value"]
coltypes = ["char(3)", "varchar(15)", "varchar(15)", "float"]
for year in config.STUDY_YEARS:
tablename = "%s_%d" % (table_prefix, year)
tables[year] = SQLTable(tablename, colnames, coltypes).create()
tables[year].truncate()
for country in config.countries.keys():
# TODO: more automated way to get this
if country in ("AUS", "DEU", "GBR", "USA"):
filename = "%s_SUT_Feb12.xls" % country
else:
filename = "%s_SUT_Jan12.xls" % country
subdir = os.path.join("wiod", "suts")
path = fileutils.getcache(filename, subdir)
wb = xlrd.open_workbook(path)
# extract supply and use tables at fob prices
sheet = wb.sheet_by_name(sheet_name)
industry_row = sheet.row_values(0)
row = sheet.row_values(1)
industry_codes = []
for (code, desc) in zip(industry_row, row):
industry_codes.append(industry_tracker.set_code(code, desc))
for i in range(2, sheet.nrows):
row = sheet.row_values(i)
if not len(row[0].strip()):
continue
year = int(row[0])
if year not in config.STUDY_YEARS:
continue
com_code = commodity_tracker.set_code(row[1], row[2])
if not com_code:
continue
for j in range(3, len(row)):
value = row[j]
ind_code = industry_codes[j]
if value != 0 and ind_code:
# commodity first
tables[year].insert(
[country, com_code, ind_code, value])
# make tables
parse_sut("SUP_bas", "%s.make" % config.WIOD_SCHEMA)
# use tables
parse_sut("USE_bas", "%s.use" % config.WIOD_SCHEMA)
def create_table(self, tablename, cols, coltypes, cascade=False):
table = SQLTable(tablename, cols, coltypes)
table.drop(cascade)
table.create()
self.tables[tablename] = table
class IOTableStateTracker(TableStateTracker):
def __init__(self):
TableStateTracker.__init__(self)
self.make_table = None
self.use_table = None
self.make_insert_count = 0
self.use_insert_count = 0
def flush(self):
TableStateTracker.flush(self)
if self.make_insert_count:
print("%d rows inserted to make table"
% self.make_insert_count)
self.make_insert_count = 0
if self.use_insert_count:
print("%d rows inserted to use table"
% self.use_insert_count)
self.use_insert_count = 0
def create_make_table(self, year):
print("creating make table for %s..." % year)
tablename = "%s.make_%s" % (config.IO_SCHEMA, year)
self.make_table = SQLTable(tablename,
["industry", "commodity", "thousands"],
["varchar(6)", "varchar(6)", "bigint"])
self.make_table.create()
self.make_table.truncate()
def create_use_table(self, year, has_margins=False):
print("creating use table for %s..." % year)
cols = ["commodity", "industry", "thousands"]
coltypes = ["varchar(6)", "varchar(6)", "bigint"]
if has_margins:
for field in bea.use_table_margins:
cols.append(field)
coltypes.append("int")
tablename = "%s.use_%s" % (config.IO_SCHEMA, year)
self.use_table = SQLTable(tablename, cols, coltypes)
self.use_table.create()
self.use_table.truncate()
def insert_make(self, indus, commod, makeval, factor=1):
value = float(makeval) * factor
if (value != 0):
self.make_table.insert([indus.strip(),commod.strip(), int(value)])
self.make_insert_count += 1
def insert_use(self, commod, indus, useval,
margins={}, factor=1):
useval = float(useval) * factor
nonzero = useval
values = [commod.strip(), indus.strip(), int(useval)]
if len(margins) > 0:
for margin_field in bea.use_table_margins:
value = 0
if margin_field in margins:
value = float(margins[margin_field]) * factor
if value:
nonzero += value
values.append(value)
if nonzero != 0:
self.use_table.insert(values)
self.use_insert_count += 1
# this is for years with no distinction between
# make and use tables
def create_simple_transaction_table(self, year, filename, factor=1):
print("creating transations table for %s..." % year)
tablename = "%s.transactions_%s" % (config.IO_SCHEMA, year)
xtable = SQLTable(tablename,
["producer", "consumer", "thousands"],
["varchar(6)", "varchar(6)", "int"])
xtable.create()
xtable.truncate()
insert_count = 0
with open(fileutils.getcache(filename), "r") as f:
for line in f:
cols = line.split()
if len(cols) >= 3:
value = float(cols[2]) * factor
if (value != 0):
xtable.insert([cols[0], cols[1], int(value)])
insert_count += 1
print ("%d rows inserted" % insert_count)
# this is for years that have make and use but no margins
def create_simple_make_use(self, year, filename, factor=1):
self.create_make_table(year)
self.create_use_table(year, has_margins=False)
with open(fileutils.getcache(filename), "r") as f:
for line in f:
cols = line.split()
if len(cols) == 4:
input_ind = cols[0] # comm consumed (producing ind)
output_ind = cols[1] # consuming ind (comm produced)
use_dollars = cols[2] # use in producers' prices
make_dollars = cols[3] # make in producers' prices
self.insert_make(input_ind, output_ind, make_dollars, factor)
self.insert_use(commod=input_ind, indus=output_ind,
useval=use_dollars, factor=factor)
def doparse():
tablename = "%s.world_supplement" % config.WIOD_SCHEMA
table = SQLTable(tablename,
["year", "country", "measurement", "value"],
["int", "char(3)", "varchar(8)", "float"])
table.create()
table.truncate()
# census data has more complete population counts
country_fips = {
"LU": "LUX", "US": "USA", "NL": "NLD", "AU": "AUT", "SW": "SWE",
"CA": "CAN", "AS": "AUS", "EI": "IRL", "GM": "DEU", "BE": "BEL",
"TW": "TWN", "DA": "DNK", "UK": "GBR", "FR": "FRA", "JA": "JPN",
"KS": "KOR", "SP": "ESP", "CY": "CYP", "SI": "SVN", "EZ": "CZE",
"GR": "GRC", "MT": "MLT", "PO": "PRT", "LO": "SVK", "PL": "POL",
"EN": "EST", "HU": "HUN", "LH": "LTU", "LG": "LVA", "MX": "MEX",
"TU": "TUR", "BR": "BRA", "RO": "ROU", "BU": "BGR", "CH": "CHN",
"ID": "IDN", "IN": "IND", "RS": "RUS", "FI": "FIN", "IT": "ITA",
}
# this file spec is documented in the xlsx file from the archive
path = fileutils.getcache("IDBext001.txt", "wsupp")
with open(path, "r") as fh:
for line in fh:
fields = line.split("|")
if len(fields) == 3:
fips = fields[0]
if fips in country_fips:
year = int(fields[1])
country = country_fips[fips]
table.insert([year, country, "pop", int(fields[2])])
# worldbank data has some deflator data that imf doesn't
worldbank = {
"ppp_pc": "NY.GDP.PCAP.PP.KD_Indicator_MetaData_en_EXCEL.xls",
#"gdp_pc": "NY.GDP.PCAP.CD_Indicator_MetaData_en_EXCEL.xls",
#"dec": "PA.NUS.ATLS_Indicator_MetaData_en_EXCEL.xls",
#"pppratio": "PA.NUS.PPPC.RF_Indicator_MetaData_en_EXCEL.xls",
"deflator": "NY.GDP.DEFL.ZS_Indicator_MetaData_en_EXCEL.xls",
}
for (indicator, filename) in worldbank.items():
path = fileutils.getcache(filename, "wsupp")
wb = xlrd.open_workbook(path)
sheet = wb.sheet_by_index(0)
header = [int(x) for x in sheet.row_values(0)[2:]]
for i in range(1, sheet.nrows):
row = sheet.row_values(i)
if row[1] in config.countries:
country = row[1]
for (year, value) in zip(header, row[2:]):
if type(value) is float and value != 0:
table.insert([year, country, indicator, value])
imf_fields = (
"LP", # population
"PPPPC", # ppp per capita
"NGDPRPC", # gdp per capita in constant prices
"NGDP_D", # gdp deflator
)
# this is actually a csv file despite what it's called
path = fileutils.getcache("WEOApr2012all.xls", "wsupp")
with codecs.open(path, "r", "cp1252") as fh:
csvf = csv.reader(fh, dialect=csv.excel_tab)
header = next(csvf)
year_cols = {}
valid_year = re.compile("\d{4}")
valid_float = re.compile("-*[\d\.,]+")
for i in range(len(header)):
if header[i] == "ISO":
country_col = i
elif header[i] == "WEO Subject Code":
subject_col = i
elif valid_year.match(header[i]):
year_cols[int(header[i])] = i
elif header[i] == "Estimates Start After":
last_year_col = i
for row in csvf:
if len(row) > subject_col and row[subject_col] in imf_fields:
field = row[subject_col]
country = row[country_col]
if country not in config.countries:
continue
if valid_year.match(row[last_year_col]):
last_year = int(row[last_year_col])
else:
# not clear if this means all values are estimated
last_year = 9999
for (year, colnum) in year_cols.items():
value = row[colnum]
if valid_float.match(value): #and year < last_year:
table.insert([year, country, field,
float(value.replace(",", ""))])
def parse_env():
# parse english env files
# TODO: might want to use the energy table as well.
# it is very comprehensive, but formatted differently and only has 2001
sector_whitelist = ("Household Consumption", "Fixed Capital Formation")
eng_env_years = [1999, 2001, 2004]
eng_env_files = {
"air_pol": {
"filename": "IO_air.xls",
"columns": ["TSP", "PM10", "SOx", "NOx", "NMHC", "CO", "Pb"],
},
"water_pol": {
"filename": "IO_pol_water.xls",
"columns": ["BOD", "COD", "SS"],
},
"waste_pol": {
"filename": "IO_waste.xls",
"columns": ["Total waste", "General waste",
"Hazardous waste", "Total waste - improper disposal",
"General waste - improper disposal",
"Hazardous waste - improper disposal"],
},
"water_use": {
"filename": "IO_res_water.xls",
"columns": ["Natural water", "Abstracted water"],
},
}
tables_by_year = {}
for year in eng_env_years:
if year not in tables_by_year:
tablename = "%s.env_%d" % (config.SCHEMA, year)
table = SQLTable(tablename,
["sector", "series", "value"],
["varchar(55)", "varchar(255)", "float"])
table.create()
table.truncate()
tables_by_year[year] = table
else:
table = tables_by_year[year]
first_file = True
for (tkey, tdata) in eng_env_files.items():
path = fileutils.getdatapath(tdata["filename"], "tw-env")
wb = xlrd.open_workbook(path)
sheet = wb.sheet_by_name("year %d" % year)
for rowindex in range(sheet.nrows):
row = sheet.row_values(rowindex)
if len(row) > 1 and \
(regexes.is_num(row[0]) or row[1] in sector_whitelist):
sector = row[1].strip()
if first_file: # these columns are repeated in every file
table.insert([sector, "Total Output", row[2]])
table.insert([sector, "Total Input", row[3]])
table.insert([sector, "GDP", row[4]])
first_file = False
for i in range(len(tdata["columns"])):
table.insert([sector, tdata["columns"][i], row[i+5]])
# parse chinese env tables
# this is file that we created by compiling older chinse data and
# manually copying info from latest (2010) pdf files
# skip 2001 because the english version is better
sheetnames_by_year = {
2000: ["89年空汙", "89年廢棄物"],
2002: ["91年空汙", "91年廢棄物"],
2003: ["92年空汙", "92年廢棄物"],
2010: ["99年空汙", "99年水汙", "99年廢棄物"],
}
path = fileutils.getdatapath("sheets.xls", "tw-env")
wb = xlrd.open_workbook(path)
for (year, sheetnames) in sheetnames_by_year.items():
tablename = "%s.env_%d" % (config.SCHEMA, year)
table = SQLTable(tablename,
["sector", "series", "value"],
["varchar(55)", "varchar(255)", "float"])
table.create()
table.truncate()
for sheetname in sheetnames:
sheet = wb.sheet_by_name(sheetname)
header = sheet.row_values(0)
# the 2010 tables have several rows that we don't want
should_parse = (year != 2010)
for i in range(1, sheet.nrows):
row = sheet.row_values(i)
if should_parse:
sector = row[0].strip()
for i in range (1, len(header)):
measurement = header[i].strip()
value = row[i]
table.insert([sector, measurement, value])
elif row[0] in ("依行業分", "依部門分"):
should_parse = True
