def test_latent_class_full_data(swissmetro_raw_df):
dfs = larch.DataFrames(swissmetro_raw_df, alt_codes=[1, 2, 3])
m1 = larch.Model(dataservice=dfs)
m1.availability_co_vars = {
1: "TRAIN_AV_SP",
2: "SM_AV",
3: "CAR_AV_SP",
}
m1.choice_co_code = 'CHOICE'
m1.utility_co[1] = P("ASC_TRAIN") + X("TRAIN_CO*(GA==0)") * P("B_COST")
m1.utility_co[2] = X("SM_CO*(GA==0)") * P("B_COST")
m1.utility_co[3] = P("ASC_CAR") + X("CAR_CO") * P("B_COST")
m2 = larch.Model(dataservice=dfs)
m2.availability_co_vars = {
1: "TRAIN_AV_SP",
2: "SM_AV",
3: "CAR_AV_SP",
}
m2.choice_co_code = 'CHOICE'
m2.utility_co[1] = P("ASC_TRAIN") + X("TRAIN_TT") * P("B_TIME") + X(
"TRAIN_CO*(GA==0)") * P("B_COST")
m2.utility_co[
2] = X("SM_TT") * P("B_TIME") + X("SM_CO*(GA==0)") * P("B_COST")
m2.utility_co[3] = P(
"ASC_CAR") + X("CAR_TT") * P("B_TIME") + X("CAR_CO") * P("B_COST")
km = larch.Model(dataservice=dfs, alts=[1, 2])
km.utility_co[2] = P.W_OTHER
from larch.model.latentclass import LatentClassModel
m = LatentClassModel(km, {1: m1, 2: m2})
m.load_data()
m.set_value(P.ASC_CAR, 0.125 / 2)
m.set_value(P.ASC_TRAIN, -0.398 / 2)
m.set_value(P.B_COST, -.0126 / 2)
m.set_value(P.B_TIME, -0.028 / 2)
m.set_value(P.W_OTHER, 1.095 / 2)
check1 = m.check_d_loglike()
assert dict(check1.data.analytic) == approx({
'ASC_CAR': -81.69736186616234,
'ASC_TRAIN': -613.131371089499,
'B_COST': -6697.31706964777,
'B_TIME': -40104.940072046316,
'W_OTHER': 245.43145056623683,
})
def test_latent_class_mixed_data(swissmetro_raw_df):
dfs = larch.DataFrames(swissmetro_raw_df, alt_codes=[1, 2, 3])
m1 = larch.Model(dataservice=dfs)
m1.availability_co_vars = {
1: "TRAIN_AV_SP",
2: "SM_AV",
3: "CAR_AV_SP",
}
m1.choice_co_code = 'CHOICE'
m1.utility_co[1] = P("ASC_TRAIN") + X("TRAIN_CO*(GA==0)") * P("B_COST")
m1.utility_co[2] = X("SM_CO*(GA==0)") * P("B_COST")
m1.utility_co[3] = P("ASC_CAR") + X("CAR_CO") * P("B_COST")
m2 = larch.Model(dataservice=dfs)
m2.availability_co_vars = {
1: "TRAIN_AV_SP",
2: "SM_AV",
3: "CAR_AV_SP",
}
m2.choice_co_code = 'CHOICE'
m2.utility_co[1] = P("ASC_TRAIN") + X("TRAIN_TT") * P("B_TIME") + X(
"TRAIN_CO*(GA==0)") * P("B_COST")
m2.utility_co[
2] = X("SM_TT") * P("B_TIME") + X("SM_CO*(GA==0)") * P("B_COST")
m2.utility_co[3] = P(
"ASC_CAR") + X("CAR_TT") * P("B_TIME") + X("CAR_CO") * P("B_COST")
dfs2 = larch.DataFrames(swissmetro_raw_df, alt_codes=[1, 2])
km = larch.Model(dataservice=dfs2)
km.utility_co[2] = P.W_OTHER
from larch.model.latentclass import LatentClassModel
with raises(ValueError):
m = LatentClassModel(km, {1: m1, 2: m2})
def test_ch_av_summary_output():
skims = larch.OMX(larch.exampville.files.skims, mode='r')
hh = pandas.read_csv(larch.exampville.files.hh)
pp = pandas.read_csv(larch.exampville.files.person)
tour = pandas.read_csv(larch.exampville.files.tour)
pp_col = [
'PERSONID', 'HHID', 'HHIDX', 'AGE', 'WORKS', 'N_WORK_TOURS',
'N_OTHER_TOURS', 'N_TOURS', 'N_TRIPS', 'N_TRIPS_HBW', 'N_TRIPS_HBO',
'N_TRIPS_NHB'
]
raw = tour.merge(hh, on='HHID').merge(pp[pp_col], on=('HHID', 'PERSONID'))
raw["HOMETAZi"] = raw["HOMETAZ"] - 1
raw["DTAZi"] = raw["DTAZ"] - 1
raw = raw[raw.TOURPURP == 1]
f_tour = raw.join(skims.get_rc_dataframe(
raw.HOMETAZi,
raw.DTAZi,
))
DA = 1
SR = 2
Walk = 3
Bike = 4
Transit = 5
dfs = larch.DataFrames(
co=f_tour,
alt_codes=[DA, SR, Walk, Bike, Transit],
alt_names=['DA', 'SR', 'Walk', 'Bike', 'Transit'],
)
m = larch.Model(dataservice=dfs)
m.title = "Exampville Work Tour Mode Choice v1"
m.utility_co[DA] = (
+P.InVehTime * X.AUTO_TIME + P.Cost * X.AUTO_COST # dollars per mile
)
m.utility_co[SR] = (
+P.ASC_SR + P.InVehTime * X.AUTO_TIME + P.Cost *
(X.AUTO_COST * 0.5) # dollars per mile, half share
+ P("HighInc:SR") * X("INCOME>75000"))
m.utility_co[Walk] = (+P.ASC_Walk + P.NonMotorTime * X.WALK_TIME +
P("HighInc:Walk") * X("INCOME>75000"))
m.utility_co[Bike] = (+P.ASC_Bike + P.NonMotorTime * X.BIKE_TIME +
P("HighInc:Bike") * X("INCOME>75000"))
m.utility_co[Transit] = (+P.ASC_Transit + P.InVehTime * X.TRANSIT_IVTT +
P.OutVehTime * X.TRANSIT_OVTT +
P.Cost * X.TRANSIT_FARE +
P("HighInc:Transit") * X("INCOME>75000"))
# No choice or avail data set
m.load_data()
q = m.dataframes.choice_avail_summary()
assert numpy.array_equal(q.columns, ['name', 'chosen', 'available'])
assert q.index.identical(
pandas.Index([1, 2, 3, 4, 5, '< Total All Alternatives >'],
dtype='object'))
assert numpy.array_equal(q.values, [
['DA', None, None],
['SR', None, None],
['Walk', None, None],
['Bike', None, None],
['Transit', None, None],
['', 0, ''],
])
# Reasonable choice and avail data set
m.choice_co_code = 'TOURMODE'
m.availability_co_vars = {
DA: 'AGE >= 16',
SR: '1',
Walk: 'WALK_TIME < 60',
Bike: 'BIKE_TIME < 60',
Transit: 'TRANSIT_FARE>0',
}
m.load_data()
q = m.dataframes.choice_avail_summary()
assert numpy.array_equal(q.columns, ['name', 'chosen', 'available'])
assert q.index.identical(
pandas.Index([1, 2, 3, 4, 5, '< Total All Alternatives >'],
dtype='object'))
assert numpy.array_equal(q['name'].values,
['DA', 'SR', 'Walk', 'Bike', 'Transit', ''])
assert numpy.array_equal(q['chosen'].values,
[6052., 810., 196., 72., 434., 7564.])
assert numpy.array_equal(
q['available'].values,
numpy.array([7564.0, 7564.0, 4179.0, 7564.0, 4199.0, ''],
dtype=object))
# Unreasonable choice and avail data set
m.choice_co_code = 'TOURMODE'
m.availability_co_vars = {
DA: 'AGE >= 26',
SR: '1',
Walk: 'WALK_TIME < 60',
Bike: 'BIKE_TIME < 60',
Transit: 'TRANSIT_FARE>0',
}
m.load_data()
q = m.dataframes.choice_avail_summary()
assert numpy.array_equal(
q.columns, ['name', 'chosen', 'available', 'chosen but not available'])
assert q.index.identical(
pandas.Index([1, 2, 3, 4, 5, '< Total All Alternatives >'],
dtype='object'))
assert numpy.array_equal(q['name'].values,
['DA', 'SR', 'Walk', 'Bike', 'Transit', ''])
assert numpy.array_equal(q['chosen'].values,
[6052., 810., 196., 72., 434., 7564.])
assert numpy.array_equal(
q['available'].values,
numpy.array([6376.0, 7564.0, 4179.0, 7564.0, 4199.0, ''],
dtype=object))
assert numpy.array_equal(q['chosen but not available'].values,
[942.0, 0.0, 0.0, 0.0, 0.0, 942.0])
def test_latent_class(swissmetro_raw_df):
dfs = larch.DataFrames(swissmetro_raw_df, alt_codes=[1, 2, 3])
m1 = larch.Model(dataservice=dfs)
m1.availability_co_vars = {
1: "TRAIN_AV_SP",
2: "SM_AV",
3: "CAR_AV_SP",
}
m1.choice_co_code = 'CHOICE'
m1.utility_co[1] = P("ASC_TRAIN") + X("TRAIN_CO*(GA==0)") * P("B_COST")
m1.utility_co[2] = X("SM_CO*(GA==0)") * P("B_COST")
m1.utility_co[3] = P("ASC_CAR") + X("CAR_CO") * P("B_COST")
m2 = larch.Model(dataservice=dfs)
m2.availability_co_vars = {
1: "TRAIN_AV_SP",
2: "SM_AV",
3: "CAR_AV_SP",
}
m2.choice_co_code = 'CHOICE'
m2.utility_co[1] = P("ASC_TRAIN") + X("TRAIN_TT") * P("B_TIME") + X(
"TRAIN_CO*(GA==0)") * P("B_COST")
m2.utility_co[
2] = X("SM_TT") * P("B_TIME") + X("SM_CO*(GA==0)") * P("B_COST")
m2.utility_co[3] = P(
"ASC_CAR") + X("CAR_TT") * P("B_TIME") + X("CAR_CO") * P("B_COST")
km = larch.Model()
km.utility_co[2] = P.W_OTHER
from larch.model.latentclass import LatentClassModel
m = LatentClassModel(km, {1: m1, 2: m2})
m.load_data()
m.set_value(P.ASC_CAR, 0.125 / 2)
m.set_value(P.ASC_TRAIN, -0.398 / 2)
m.set_value(P.B_COST, -.0126 / 2)
m.set_value(P.B_TIME, -0.028 / 2)
m.set_value(P.W_OTHER, 1.095 / 2)
check1 = m.check_d_loglike()
assert dict(check1.data.analytic) == approx({
'ASC_CAR': -81.69736186616234,
'ASC_TRAIN': -613.131371089499,
'B_COST': -6697.31706964777,
'B_TIME': -40104.940072046316,
'W_OTHER': 245.43145056623683,
})
assert check1.data.similarity.min() > 4
m.set_value(P.ASC_CAR, 0.125)
m.set_value(P.ASC_TRAIN, -0.398)
m.set_value(P.B_COST, -.0126)
m.set_value(P.B_TIME, -0.028)
m.set_value(P.W_OTHER, 1.095)
assert m.loglike() == approx(-5208.502259337974)
check2 = m.check_d_loglike()
assert dict(check2.data.analytic) == approx({
'ASC_CAR': 0.6243716033364302,
'ASC_TRAIN': 0.9297965389102578,
'B_COST': -154.03997923797007,
'B_TIME': 76.19297915128493,
'W_OTHER': -0.7936963902343083,
})
assert check2.data.similarity.min(
) > 2 # similarity is a bit lower very close to the optimum
def test_simple_model_group():
df = pd.read_csv(example_file("MTCwork.csv.gz"))
df.set_index(['casenum', 'altnum'], inplace=True)
d = larch.DataFrames(df, ch='chose', crack=True)
d.set_alternative_names({
1: 'DA',
2: 'SR2',
3: 'SR3+',
4: 'Transit',
5: 'Bike',
6: 'Walk',
})
m0 = larch.Model(dataservice=d)
m0.utility_co[2] = P("ASC_SR2") + P("hhinc#2") * X("hhinc")
m0.utility_co[3] = P("ASC_SR3P") + P("hhinc#3") * X("hhinc")
m0.utility_co[4] = P("ASC_TRAN") + P("hhinc#4") * X("hhinc")
m0.utility_co[5] = P("ASC_BIKE") + P("hhinc#5") * X("hhinc")
m0.utility_co[6] = P("ASC_WALK") + P("hhinc#6") * X("hhinc")
m0.utility_ca = (
(P("tottime_m") * X("tottime") + P("totcost_m") * X("totcost")) *
X("femdum == 0") +
(P("tottime_f") * X("tottime") + P("totcost_f") * X("totcost")) *
X("femdum == 1"))
m1 = larch.Model(dataservice=d.selector_co("femdum == 0"))
m1.utility_co[2] = P("ASC_SR2") + P("hhinc#2") * X("hhinc")
m1.utility_co[3] = P("ASC_SR3P") + P("hhinc#3") * X("hhinc")
m1.utility_co[4] = P("ASC_TRAN") + P("hhinc#4") * X("hhinc")
m1.utility_co[5] = P("ASC_BIKE") + P("hhinc#5") * X("hhinc")
m1.utility_co[6] = P("ASC_WALK") + P("hhinc#6") * X("hhinc")
m1.utility_ca = P("tottime_m") * X("tottime") + P("totcost_m") * X(
"totcost")
m2 = larch.Model(dataservice=d.selector_co("femdum == 1"))
m2.utility_co[2] = P("ASC_SR2") + P("hhinc#2") * X("hhinc")
m2.utility_co[3] = P("ASC_SR3P") + P("hhinc#3") * X("hhinc")
m2.utility_co[4] = P("ASC_TRAN") + P("hhinc#4") * X("hhinc")
m2.utility_co[5] = P("ASC_BIKE") + P("hhinc#5") * X("hhinc")
m2.utility_co[6] = P("ASC_WALK") + P("hhinc#6") * X("hhinc")
m2.utility_ca = P("tottime_f") * X("tottime") + P("totcost_f") * X(
"totcost")
m0.load_data()
assert m0.loglike2().ll == approx(-7309.600971749625)
m1.load_data()
assert m1.loglike2().ll == approx(-4068.8091617468717)
m2.load_data()
assert m2.loglike2().ll == approx(-3240.7918100027578)
from larch.model.model_group import ModelGroup
mg = ModelGroup([m1, m2])
assert mg.loglike2().ll == approx(-7309.600971749625)
assert mg.loglike() == approx(-7309.600971749625)
pd.testing.assert_series_equal(mg.loglike2().dll.sort_index(),
m0.loglike2().dll.sort_index())
m0.simple_step_bhhh()
mg.set_values(**m0.pf.value)
pd.testing.assert_series_equal(mg.loglike2().dll.sort_index(),
m0.loglike2().dll.sort_index())
assert mg.loglike2().ll == approx(-4926.4822036792275)
assert mg.check_d_loglike().data.similarity.min() > 4
result = mg.maximize_loglike(method='slsqp')
assert result.loglike == approx(-3620.697668335103)
mg2 = ModelGroup([])
mg2.append(m1)
mg2.append(m2)
assert mg2.loglike() == approx(-3620.697667552756)
mg3 = ModelGroup([])
mg3.append(m1)
mg3.append(m2)
mg3.doctor()
assert mg3.loglike() == approx(-3620.697667552756)
skims.get_rc_dataframe(
df["HOMETAZi"], df["DTAZi"],
)
)
# For clarity, we can define numbers as names for modes
DA = 1
SR = 2
Walk = 3
Bike = 4
Transit = 5
dfs = larch.DataFrames(
co=df,
alt_codes=[DA,SR,Walk,Bike,Transit],
alt_names=['DA','SR','Walk','Bike','Transit'],
ch_name='TOURMODE',
)
# Model Definition
m = larch.Model(dataservice=dfs)
m.title = "Exampville Work Tour Mode Choice v1"
from larch import P, X
P('NamedParameter')
X.NamedDataValue
P('Named Parameter')
X("log(INCOME)")
P.InVehTime * X.AUTO_TIME + P.Cost * X.AUTO_COST
m.utility_co[DA] = (