def get_people(self, year, geogs):
if isinstance(geogs, str):
geogs = [geogs]
geogs = ukpoputils.split_by_country(geogs)
alldata = pd.DataFrame()
for country in geogs:
# TODO variants...
if not geogs[country]: continue
if year < self.snpp.min_year(country):
data = self.mye.aggregate(["GENDER", "C_AGE"], geogs[country],
year)
elif year <= self.snpp.max_year(country):
data = self.snpp.aggregate(["GENDER", "C_AGE"], geogs[country],
year)
else:
print("%d population for %s is extrapolated" % (year, country))
data = self.snpp.extrapolagg(["GENDER", "C_AGE"], self.npp,
geogs[country], year)
alldata = alldata.append(data, ignore_index=True, sort=False)
alldata = alldata.rename({
"OBS_VALUE": "PEOPLE"
}, axis=1).drop("PROJECTED_YEAR_NAME", axis=1)
# print(data.head())
# print(len(data))
return alldata
def test_utils(self):
year_range = range(2018, 2050)
(in_range, ex_range) = utils.split_range(year_range, self.snpp.max_year(utils.EN))
self.assertEqual(min(in_range), min(year_range))
self.assertEqual(max(in_range), 2029)
self.assertEqual(min(ex_range), 2030)
self.assertEqual(max(ex_range), max(year_range))
self.assertEqual(utils.trim_range(2011, 1991, 2016), [2011])
self.assertEqual(utils.trim_range(2011.0, 1991, 2016), [2011])
self.assertEqual(utils.trim_range([2011], 1991, 2016), [2011])
self.assertEqual(utils.trim_range([2011.0], 1991, 2016), [2011])
self.assertEqual(utils.trim_range(np.array([1995, 2005, 2019]), 2001, 2011), [2005])
self.assertEqual(utils.trim_range([1969, 2111], 1991, 2016), [])
self.assertEqual(utils.trim_range(range(1969, 2111), 2011, 2016), list(range(2011, 2017)))
codes = "E09000001"
self.assertTrue(utils.country(codes) == ["en"])
codes = ['E06000002', 'E09000001']
self.assertTrue(utils.country(codes) == ["en"])
codes = ['E06000002', 'N09000001', 'S12000033', 'W06000011']
self.assertTrue(utils.country(codes) == ['en', 'ni', 'sc', 'wa'])
codes = ['E06000001', 'E06000002', 'N09000001', 'S12000033', 'W06000011']
self.assertTrue(utils.country(codes) == ['en', 'ni', 'sc', 'wa'])
codes = ['E06000001', 'W06000011', 'X06000002', 'Y09000001', 'Z12000033']
self.assertTrue(utils.country(codes) == ["en", "wa"])
codes = 'A06000001'
self.assertTrue(utils.country(codes) == [])
codes = ['E06000001', 'E06000002', 'N09000001', 'S12000033', 'W06000011']
split = utils.split_by_country(codes)
self.assertTrue(split[utils.EN] == ['E06000001', 'E06000002'])
self.assertTrue(split[utils.WA] == ['W06000011'])
self.assertTrue(split[utils.SC] == ['S12000033'])
self.assertTrue(split[utils.NI] == ['N09000001'])
# naively, each element would be rounded down, making the total 10
fractional = np.array([0.1, 0.2, 0.3, 0.4]) * 11
integral = utils.integerise(fractional)
self.assertTrue(np.array_equal(integral, [1, 2, 3, 5]))
# 1.51 is NOT increased because 4.5 has a larger fractional part when total is rescaled to 17 from 16.91
fractional = np.array([1.1, 3.9, 4.5, 5.9, 1.51])
integral = utils.integerise(fractional)
self.assertTrue(np.array_equal(integral, [1, 4, 5, 6, 1]))
# another example that preserves sum
fractional = np.array([1.01] * 100)
integral = utils.integerise(fractional)
self.assertTrue(sum(integral) == 1.01 * 100)
self.assertTrue(np.array_equal(np.unique(integral), [1, 2]))
def get_households(self, year, geogs):
geogs = ukpoputils.split_by_country(geogs)
allsnhp = pd.DataFrame()
for country in geogs:
if not geogs[country]: continue
max_year = self.snhp.max_year(country)
if year <= max_year:
snhp = self.snhp.aggregate(geogs[country], year).rename(
{"OBS_VALUE": "HOUSEHOLDS"}, axis=1)
else:
print("%d households for %s is extrapolated" % (year, country))
#print(self.snhp.aggregate(geogs[country], max_year))
snhp = self.snhp.aggregate(geogs[country], max_year - 1).merge(
self.snhp.aggregate(geogs[country], max_year),
left_on="GEOGRAPHY_CODE",
right_on="GEOGRAPHY_CODE")
snhp["HOUSEHOLDS"] = snhp.OBS_VALUE_y + (
snhp.OBS_VALUE_y - snhp.OBS_VALUE_x) * (year - max_year)
snhp["PROJECTED_YEAR_NAME"] = year
snhp.drop([
"PROJECTED_YEAR_NAME_x", "OBS_VALUE_x",
"PROJECTED_YEAR_NAME_y", "OBS_VALUE_y"
],
axis=1,
inplace=True)
# aggregate census-merged LADs 'E06000053' 'E09000001'
snhp.loc[snhp.GEOGRAPHY_CODE == "E09000033",
"HOUSEHOLDS"] = snhp[snhp.GEOGRAPHY_CODE.isin(
["E09000001", "E09000033"])].HOUSEHOLDS.sum()
snhp.loc[snhp.GEOGRAPHY_CODE == "E06000052",
"HOUSEHOLDS"] = snhp[snhp.GEOGRAPHY_CODE.isin(
["E06000052", "E06000053"])].HOUSEHOLDS.sum()
allsnhp = allsnhp.append(snhp, ignore_index=True, sort=False)
return allsnhp
def extrapolate(self, npp, geog_codes, year_range):
if isinstance(geog_codes, str):
geog_codes = [geog_codes]
geog_codes = utils.split_by_country(geog_codes)
all_codes_all_years = pd.DataFrame()
for country in geog_codes:
if not geog_codes[country]: continue
max_year = self.max_year(country)
last_year = self.filter(geog_codes[country], max_year)
(in_range, ex_range) = utils.split_range(year_range, max_year)
# years that dont need to be extrapolated
all_years = self.filter(geog_codes[country],
in_range) if in_range else pd.DataFrame()
for year in ex_range:
data = last_year.copy()
scaling = npp.year_ratio("ppp", country, max_year, year)
data = data.merge(scaling[["GENDER", "C_AGE", "OBS_VALUE"]],
on=["GENDER", "C_AGE"])
data["OBS_VALUE"] = data.OBS_VALUE_x * data.OBS_VALUE_y
data.PROJECTED_YEAR_NAME = year
all_years = all_years.append(data.drop(
["OBS_VALUE_x", "OBS_VALUE_y"], axis=1),
ignore_index=True,
sort=False)
all_codes_all_years = all_codes_all_years.append(all_years,
ignore_index=True,
sort=False)
return all_codes_all_years