def test_ranges(bs: pd.DataFrame) -> None:
for (c, t) in [("recently bought this house", cla.InSet({True, False})),
("recently bought this house", cla.CoversRange(0, 1)),
("recently bought this house", cla.MeanBounds(0, 0.01)),
("recently bought this house", cla.MissingAtMost(0)),
("estrato", cla.InRange(0, 6)),
("estrato", cla.CoversRange(0, 3)),
("estrato", cla.MeanBounds(1.5, 2.5)),
("estrato", cla.MissingAtMost(0.02))]:
assert t.test(bs[c])
def test_Property_subclasses():
assert (cla.MissingAtMost(0.5).test(pd.Series([1, np.nan, 3])))
assert not (cla.MissingAtMost(0.5).test(pd.Series([1, np.nan, np.nan])))
for (val, result) in [(-1, False), (0, True), (0.5, True), (1, True),
(2, False), (np.nan, True)]:
assert cla.InRange(0, 1).test(pd.Series([val])) == result
assert cla.InSet({0, 0.5, 1}).test(pd.Series([val])) == result
assert ((cla.CoversRange(0, 10).test(pd.Series([0, 10]))) &
(cla.CoversRange(0, 10).test(pd.Series([0, 10]))) &
(not cla.CoversRange(0, 10).test(pd.Series([1, 9]))))
def test_ranges(df):
log = "test_ranges()\n"
inRange_spec = {
"25-broad-categs": cl.InRange(1, 25),
"big-hog": cl.InRange(0, 1),
"coicop": cl.InRange(1e6, 2e7),
# PITFALL: "freq-code"=11 <=> the purchase is never made.
# This corresponds to a "per month" value of np.nan.
"freq-code": cl.InRange(0, 10),
"household": cl.InRange(0, 1e6),
"is-purchase": cl.InRange(0, 1),
"per month": cl.InRange(1 / 36 - 0.001, 31),
"quantity": cl.InRange(0, 1e8),
"value": cl.InRange(0, 3e9),
# The special motorcycle tax, abusivelyed lump into the VAT table,
# means the max "vat" is 0.27 rather than 0.19.
"vat": cl.InRange(0, 0.3),
"vat frac": cl.InRange(0, 0.3 / 1.3),
}
for k, v in inRange_spec.items():
assert v.test(df[k])
coversRange_spec = {
"household": cl.CoversRange(2e5, 6e5),
"per month": cl.CoversRange(0.05, 30),
"quantity": cl.CoversRange(1, 100),
"value": cl.CoversRange(3, 1e6),
"weight": cl.CoversRange(10, 1000),
"where-got": cl.CoversRange(1, 25),
# The special motorcycle tax, abusively lump into the VAT table,
# means the max "vat" is 0.27 rather than 0.19.
# *However*, in the smaller samples,
# we can't be sure that whole range is covered:
# there might be no motorcycle purchases.
# That at least some purchase incurs a VAT of 0.19, though, is a safe bet.
"vat frac": cl.CoversRange(0, 0.19 / 1.19),
"vat paid": cl.CoversRange(0, 1e5),
"vat": cl.CoversRange(0, 0.19),
}
for k, v in coversRange_spec.items():
assert v.test(df[k])
return log
assert util.unique(out.columns)
assert util.unique(new_cols)
assert set.intersection(cols1, new_cols) == set()
assert set.union(cols1, new_cols) == cols2
assert set.difference(cols2, cols1) == new_cols
assert len(in_rows) == len(out)
assert util.near(len(out), misc.num_people / com.subsample, tol_frac=1 / 5)
per_cell_spec = {
"age-decile": cl.InRange(0, 9),
"income-decile": cl.InRange(0, 9),
"female head": cl.InRange(0, 1)
}
per_column_spec = {
"age-decile": cl.CoversRange(0, 9),
"income-decile": cl.CoversRange(0, 9),
"female head": cl.CoversRange(0, 1)
}
for k, v in per_cell_spec.items():
assert v.test(out[k])
for k, v in per_column_spec.items():
assert v.test(out[k])
oio.test_write(com.subsample, "people_2_buildings", "It worked.")
"value, tax, purchaselike non-VAT",
"value, tax, predial",
"value, tax, purchaselike non-predial non-VAT",
"transactions",
"value, non-purchase",
"value, purchase",
"value, spending",
"value, consumption",
"vat paid" } )
if com.subsample < 11: # The data is too sparse to test
# the smaller samples this way
for (c,ts) in [
( "transactions",
[ cla.MeanBounds ( 50 , 120 ),
cla.CoversRange ( 2 , 200 ),
cla.InRange ( 1 , 400 ),
cla.MissingAtMost ( 0 ) ] ),
( "value, tax, purchaselike non-VAT",
[ cla.MeanBounds (1e4 , 1e5),
cla.CoversRange (0 , 2e6),
cla.InRange (0 , 1.1e8), # someone pays a huge predial
cla.MissingAtMost (0) ] ),
( "value, tax, predial",
[ cla.MeanBounds (1e4 ,1e5),
cla.CoversRange (0 ,1e3),
cla.InRange (0 ,1.1e8),
cla.MissingAtMost (0) ] ),
assert ( merge[ merge["region-1"] == "SAN ANDRÉS" ]
["vat paid"].max() == 0 )
if True:
for k,v in {
"vat / purchase value" : cl.InRange( 0, 0.3 ),
# The special motorcycle tax, abusivelyed lump into the VAT table,
# means the max "vat" is 0.27 rather than 0.19.
"vat / income" : cl.InRange( 0, np.inf ),
"purchase value / income" : cl.InRange( 0, np.inf )
}.items():
assert v.test( merge[k] )
for k,v in {
# These bounds could be tighter,
# but the 1/1000 subsample has a small range.
"vat / purchase value" : cl.CoversRange( 0, 0.1 ),
"vat / income" : cl.CoversRange( 0, np.inf ),
"purchase value / income" : cl.CoversRange( 0.2, np.inf )
}.items():
assert v.test( merge[k] )
for k,v in {
"vat / purchase value" : cl.MeanBounds( 2.5e-2, 6e-2 ),
"vat / income" : cl.MeanBounds( np.inf, np.inf ),
"purchase value / income" : cl.MeanBounds( np.inf, np.inf )
}.items():
assert v.test( merge[k] )
for c in new_cols:
assert cl.MissingAtMost( 0.01 ) . test( merge[c] )
oio.test_write(
com.subsample,
def test_capitulo_c_data(df: pd.DataFrame):
for t in [cla.InRange(1, 25), cla.CoversRange(1, 25)]:
assert t.test(df["CODE"])
for col in ["vat", "vat, min", "vat, max"]:
assert (cla.InRange(0, 1).test(df[col]))
def test_coicop_data(df: pd.DataFrame):
for t in [cla.InRange(1e6, 2e7), cla.CoversRange(2e6, 1e7)]:
assert t.test(df["coicop"])
for col in ["vat", "vat, min", "vat, max"]:
assert (cla.InRange(0, 1).test(df[col]))