def test_generational_generation():
from EvoDAG.population import Generational
from EvoDAG import EvoDAG
function_set = [x for x in EvoDAG()._function_set if x.regression]
gp = EvoDAG(population_class='Generational',
classifier=False,
function_set=function_set,
popsize=10)
gp.X = X
y = cl.copy()
y[y != 1] = -1
gp.y = y
gp.create_population()
assert isinstance(gp.population, Generational)
p = []
for i in range(gp.popsize - 1):
a = gp.random_offspring()
p.append(a)
gp.replace(a)
assert len(gp.population._inner) == (gp.popsize - 1)
a = gp.random_offspring()
p.append(a)
gp.replace(a)
assert len(gp.population._inner) == 0
for a, b in zip(gp.population.population, p):
assert a == b
def test_model_graphviz():
from EvoDAG import RootGP
from EvoDAG.node import Function
import tempfile
y = cl.copy()
mask = y == 0
y[mask] = 1
y[~mask] = -1
gp = RootGP(generations=3,
tournament_size=2,
early_stopping_rounds=-1,
classifier=False,
pr_variable=1,
seed=0,
popsize=10).fit(X, y)
m = gp.model()
print(m._hist)
print(m._hist[-1].position, m._hist[-1]._variable)
with tempfile.TemporaryFile('w+') as io:
m.graphviz(io)
io.seek(0)
l = io.readlines()
cnt = len(m._hist)
for k in m._hist:
if isinstance(k, Function):
v = k._variable
if isinstance(v, list):
cnt += len(v)
else:
cnt += 1
print("".join(l))
print(cnt, len(l))
assert 2 + cnt == len(l)
def test_g_precision():
from EvoDAG import EvoDAG
y = cl.copy()
gp = EvoDAG(generations=np.inf,
tournament_size=2,
early_stopping_rounds=200,
time_limit=0.9,
fitness_function='g_precision',
multiple_outputs=True,
seed=0,
popsize=1000)
gp.y = y
gp.X = X
gp.create_population()
# off = gp.random_offspring()
off = gp.population.bsf
hy = SparseArray.argmax(off.hy)
index = np.array(gp._mask_ts.index)
y = np.array(gp._y_klass.full_array())[index]
hy = np.array(hy.full_array())[index]
nclasses = gp._bagging_fitness.nclasses
precision = np.array([(y[hy == k] == k).mean() for k in range(nclasses)])
score = np.prod(precision) - 1
assert gp._fitness_function == 'g_precision'
gp._bagging_fitness.set_fitness(off)
assert_almost_equals(score, off.fitness)
index = np.array(gp._mask_ts.full_array()) == 0
y = np.array(gp._y_klass.full_array())[index]
hy = SparseArray.argmax(off.hy)
hy = np.array(hy.full_array())[index]
precision = np.array([(y[hy == k] == k).mean() for k in range(nclasses)])
score = np.prod(precision) - 1
if np.isfinite(score) and np.isfinite(off.fitness_vs):
assert_almost_equals(score, off.fitness_vs)
def test_model_hist():
from EvoDAG import EvoDAG
from EvoDAG.base import Model
y = cl.copy()
gp = EvoDAG(generations=np.inf,
multiple_outputs=True,
tournament_size=2,
early_stopping_rounds=-1,
seed=1,
popsize=30).fit(X[:-10], y[:-10], test_set=X[-10:])
hist = gp.population.hist
trace = gp.trace(gp.population.estopping)
a = hist[trace[-1]].variable
if not isinstance(a, list):
a = [a]
m = Model(trace, hist)
b = m._hist[-1].variable
if not isinstance(b, list):
b = [b]
print([(x, x.height) for x in m._hist])
print((m._map, a, b))
for v1, v2 in zip(a, b):
if v1 not in m._map:
assert v1 == v2
else:
assert m._map[v1] == v2
def test_a_precision():
from EvoDAG.cython_utils import Score
from EvoDAG import EvoDAG
y = cl.copy()
gp = EvoDAG(generations=np.inf,
tournament_size=2,
early_stopping_rounds=100,
time_limit=0.9,
multiple_outputs=True,
seed=0,
popsize=500)
gp.y = y
gp.X = X
gp.create_population()
# off = gp.random_offspring()
off = gp.population.bsf
hy = SparseArray.argmax(off.hy)
index = np.array(gp._mask_ts.index)
y = np.array(gp._y_klass.full_array())[index]
hy = np.array(hy.full_array())[index]
nclasses = gp._bagging_fitness.nclasses
precision = np.array([(y[hy == k] == k).mean() for k in range(nclasses)])
f1 = Score(nclasses)
mf1, mf1_v = f1.a_precision(gp._y_klass, SparseArray.argmax(off.hy),
gp._mask_ts.index)
assert_almost_equals(np.mean(precision), mf1)
gp._fitness_function = 'a_precision'
gp._bagging_fitness.set_fitness(off)
assert_almost_equals(mf1 - 1, off.fitness)
index = np.array(gp._mask_ts.full_array()) == 0
y = np.array(gp._y_klass.full_array())[index]
hy = SparseArray.argmax(off.hy)
hy = np.array(hy.full_array())[index]
precision = np.array([(y[hy == k] == k).mean() for k in range(nclasses)])
assert_almost_equals(np.mean(precision) - 1, off.fitness_vs)
def test_ensemble_model():
from EvoDAG import RootGP
from EvoDAG.model import Ensemble
y = cl.copy()
mask = y == 0
y[mask] = 1
y[~mask] = -1
gps = [
RootGP(generations=np.inf,
tournament_size=2,
early_stopping_rounds=-1,
classifier=False,
seed=seed,
popsize=10).fit(X[:-10], y[:-10], test_set=X)
for seed in range(3)
]
ens = Ensemble([gp.model() for gp in gps])
res = [gp.decision_function() for gp in gps]
res = np.median([x.full_array() for x in res], axis=0)
res = SparseArray.fromlist(res)
print(res)
# res = Add.cumsum(res) * (1 / 3.)
r2 = ens.decision_function(None)
print(res.full_array()[:10], r2.full_array()[:10])
print(res.SSE(r2))
assert res.SSE(r2) == 0
def test_random_generations():
from EvoDAG import EvoDAG
from EvoDAG.population import SteadyState
class P(SteadyState):
def random_selection(self, negative=False):
raise RuntimeError('!')
y = cl.copy()
y[y != 1] = -1
for pop in ['SteadyState', 'Generational', P]:
gp = EvoDAG(population_class=pop,
classifier=False,
all_inputs=True,
random_generations=1,
early_stopping_rounds=1,
popsize=2)
gp.X = X
gp.y = y
gp.create_population()
print(gp.population._random_generations)
assert gp.population._random_generations == 1
if pop == P:
try:
ind = gp.random_offspring()
gp.replace(ind)
assert False
except RuntimeError:
pass
else:
for i in range(3):
gp.replace(gp.random_offspring())
assert gp.population.generation == 2
def test_random_generations():
from EvoDAG import EvoDAG
from EvoDAG.population import SteadyState
class P(SteadyState):
def random_selection(self, negative=False):
raise RuntimeError('!')
y = cl.copy()
y[y != 1] = -1
for pop in ['SteadyState', 'Generational', P]:
gp = EvoDAG(population_class=pop,
all_inputs=True, random_generations=1,
early_stopping_rounds=1, popsize=2)
gp.X = X
gp.y = y
gp.create_population()
print(gp.population._random_generations)
assert gp.population._random_generations == 1
if pop == P:
try:
ind = gp.random_offspring()
gp.replace(ind)
assert False
except RuntimeError:
pass
else:
for i in range(3):
gp.replace(gp.random_offspring())
assert gp.population.generation == 2
def test_multiple_variables():
import numpy as np
from EvoDAG.population import Inputs
from EvoDAG.cython_utils import SelectNumbers
from EvoDAG import EvoDAG
from SparseArray import SparseArray
y = cl.copy()
gp = EvoDAG(classifier=True,
multiple_outputs=True,
popsize=5,
share_inputs=True)
gp.X = X
gp.X[-1]._eval_tr = SparseArray.fromlist(
[0 for x in range(gp.X[-1].hy.size())])
gp.nclasses(y)
gp.y = y
inputs = Inputs(gp, SelectNumbers([x for x in range(len(gp.X))]))
inputs._func = [inputs._func[-1]]
inputs._nfunc = 1
v = inputs.input()
assert v is not None
mask = np.array(gp._mask[0].full_array(), dtype=np.bool)
D = np.array([x.hy.full_array() for x in gp.X]).T
b = np.array(gp._ytr[0].full_array())
coef = np.linalg.lstsq(D[mask], b[mask])[0]
for a, b in zip(coef, v.weight[0]):
assert_almost_equals(a, b)
def test_inputs_func_argument_regression():
from EvoDAG import EvoDAG
class Error:
nargs = 2
min_nargs = 2
classification = True
regression = True
def __init__(self, *args, **kwargs):
raise RuntimeError('aqui')
y = cl.copy()
y[y == 0] = -1
y[y > -1] = 1
gp = EvoDAG(classifier=False,
multiple_outputs=False,
pr_variable=0,
input_functions=[Error],
popsize=5,
share_inputs=True)
gp.X = X
gp.nclasses(y)
gp.y = y
try:
gp.create_population()
assert False
except RuntimeError:
pass
def test_multiple_outputs_error_rate_ts():
from EvoDAG import EvoDAG
from EvoDAG.node import Add, Min, Max
y = cl.copy()
gp = EvoDAG(generations=np.inf,
tournament_size=2,
function_set=[Add, Min, Max],
early_stopping_rounds=100,
time_limit=0.9,
multiple_outputs=True,
fitness_function='ER',
seed=0,
popsize=100)
gp.X = X[:-1]
gp.nclasses(y[:-1])
gp.y = y[:-1]
gp.create_population()
a = gp.random_offspring()
hys = SparseArray.argmax(a.hy)
hy = np.array(hys.full_array())
# print(((hys - gp._y_klass).sign().fabs() * gp._mask_ts).sum())
mask = np.array(gp._mask_ts.full_array()).astype(np.bool)
# print((y[:-1][mask] != hy[mask]).mean())
print(-a.fitness, (y[:-1][mask] != hy[mask]).mean())
assert_almost_equals(-a.fitness, (y[:-1][mask] != hy[mask]).mean())
def test_model_graphviz():
from EvoDAG import RootGP
from EvoDAG.node import Function
import tempfile
y = cl.copy()
mask = y == 0
y[mask] = 1
y[~mask] = -1
gp = RootGP(generations=3,
tournament_size=2,
early_stopping_rounds=-1,
seed=0,
popsize=10).fit(X, y)
m = gp.model()
print(m._hist)
print(m._hist[-1].position, m._hist[-1]._variable)
with tempfile.TemporaryFile('w+') as io:
m.graphviz(io)
io.seek(0)
l = io.readlines()
cnt = len(m._hist)
for k in m._hist:
if isinstance(k, Function):
v = k._variable
if isinstance(v, list):
cnt += len(v)
else:
cnt += 1
print("".join(l))
print(cnt, len(l))
assert 2 + cnt == len(l)
def test_popsize_nvar():
from EvoDAG import EvoDAG
y = cl.copy()
gp = EvoDAG.init(popsize='nvar', time_limit=5)
print(X.shape)
gp.fit(X, y)
default_nargs()
assert gp.population._popsize == (X.shape[1] + len(gp._input_functions))
def test_share_inputs():
from EvoDAG import EvoDAG
y = cl.copy()
gp = EvoDAG(classifier=True,
multiple_outputs=True,
popsize=5,
share_inputs=True)
gp.fit(X, y)
assert gp._share_inputs
def create_problem_node2(nargs=4, seed=0):
from EvoDAG import RootGP
gp = RootGP(generations=1, popsize=nargs, multiple_outputs=True, seed=seed)
gp.X = X
gp.Xtest = X
y = cl.copy()
gp.nclasses(y)
gp.y = y
return gp, [gp.X[x] for x in range(nargs)]
def create_problem_node(nargs=4):
from EvoDAG import RootGP
gp = RootGP(generations=1, popsize=4)
gp.X = X
gp.Xtest = X
y = cl.copy()
mask = y == 0
y[mask] = 1
y[~mask] = -1
gp.y = y
return gp, [gp.X[x] for x in range(nargs)]
def test_random_selection():
from EvoDAG import RootGP
y = cl.copy()
mask = y == 0
y[mask] = 1
y[~mask] = -1
RootGP(generations=np.inf,
tournament_size=1,
early_stopping_rounds=-1,
seed=0,
popsize=10).fit(X[:-10], y[:-10], test_set=X[-10:])
def create_problem_node(nargs=4, seed=0):
from EvoDAG import RootGP
gp = RootGP(generations=1, popsize=nargs, classifier=False, seed=seed)
gp.X = X
gp.Xtest = X
y = cl.copy()
mask = y == 0
y[mask] = 1
y[~mask] = -1
gp.y = y
return gp, [gp.X[x] for x in range(nargs)]
def test_random_selection():
from EvoDAG import RootGP
y = cl.copy()
mask = y == 0
y[mask] = 1
y[~mask] = -1
RootGP(generations=np.inf,
tournament_size=1,
early_stopping_rounds=-1,
classifier=False,
seed=0,
popsize=10).fit(X[:-10], y[:-10], test_set=X[-10:])
def test_macro_F1():
from EvoDAG.cython_utils import Score
from EvoDAG import EvoDAG
y = cl.copy()
gp = EvoDAG(generations=np.inf,
tournament_size=2,
early_stopping_rounds=100,
time_limit=0.9,
multiple_outputs=True,
seed=2,
popsize=1000)
gp.y = y
gp.X = X
gp.create_population()
off = gp.random_offspring()
hy = SparseArray.argmax(off.hy)
index = np.array(gp._mask_ts.index)
y = np.array(gp._y_klass.full_array())[index]
hy = np.array(hy.full_array())[index]
nclasses = gp._bagging_fitness.nclasses
precision = np.array([(y[hy == k] == k).mean() for k in range(nclasses)])
recall = np.array([(hy[y == k] == k).mean() for k in range(nclasses)])
print(precision, recall)
f1 = Score(nclasses)
mf1, mf1_v = f1.a_F1(gp._y_klass, SparseArray.argmax(off.hy),
gp._mask_ts.index)
for x, y in zip(precision, f1.precision):
if not np.isfinite(x):
continue
assert_almost_equals(x, y)
for x, y in zip(recall, f1.recall):
if not np.isfinite(x):
continue
assert_almost_equals(x, y)
_ = (2 * precision * recall) / (precision + recall)
m = ~np.isfinite(_)
_[m] = 0
assert_almost_equals(np.mean(_), mf1)
print(f1.precision, f1.recall, mf1, mf1_v)
gp._fitness_function = 'macro-F1'
gp._bagging_fitness.set_fitness(off)
assert_almost_equals(off.fitness, mf1 - 1)
assert_almost_equals(off.fitness_vs, mf1_v - 1)
index = np.array(gp._mask_ts.full_array()) == 0
y = np.array(gp._y_klass.full_array())[index]
hy = SparseArray.argmax(off.hy)
hy = np.array(hy.full_array())[index]
precision = np.array([(y[hy == k] == k).mean() for k in range(nclasses)])
recall = np.array([(hy[y == k] == k).mean() for k in range(nclasses)])
_ = (2 * precision * recall) / (precision + recall)
m = ~np.isfinite(_)
_[m] = 0
assert_almost_equals(np.mean(_) - 1, off.fitness_vs)
def test_input_functions():
from EvoDAG import EvoDAG
y = cl.copy()
gp = EvoDAG.init(
input_functions=["NaiveBayes", "NaiveBayesMN", "Centroid"],
Centroid=2,
time_limit=5)
input_functions = [x for x in gp._input_functions]
gp.fit(X, y)
default_nargs()
for a, b in zip(input_functions, gp.population.hist[:3]):
print(b, a)
assert isinstance(b, a)
def test_min_class():
from EvoDAG import EvoDAG
y = cl.copy()
gp = EvoDAG(generations=np.inf,
tournament_size=2,
early_stopping_rounds=100,
time_limit=0.9,
multiple_outputs=True,
seed=0,
popsize=100)
gp.y = y[:-1]
gp.X = X[:-1]
assert gp._bagging_fitness.min_class == 2
def test_SteadyState_generation():
from EvoDAG import EvoDAG
y = cl.copy()
y[y != 1] = -1
gp = EvoDAG(population_class='SteadyState',
all_inputs=True,
early_stopping_rounds=1,
popsize=2)
gp.X = X
gp.y = y
gp.create_population()
for i in range(3):
gp.replace(gp.random_offspring())
assert gp.population.generation == 2
def test_transform_to_mo():
from EvoDAG import EvoDAG
y = cl.copy()
gp = EvoDAG(generations=np.inf,
tournament_size=2,
early_stopping_rounds=100,
time_limit=0.9,
multiple_outputs=True,
seed=0,
popsize=10000)
gp.nclasses(y)
k = np.unique(y)
y = gp._bagging_fitness.transform_to_mo(y)
assert k.shape[0] == y.shape[1]
def create_problem_node2(nargs=4, seed=0):
from EvoDAG import RootGP
from test_root import X, cl
import numpy as np
gp = RootGP(generations=1, popsize=nargs, multiple_outputs=True, seed=seed)
X1 = np.concatenate((X, np.atleast_2d(np.zeros(X.shape[0])).T), axis=1)
for i in range(10, 20):
X1[i, -1] = 1
gp.X = X1
gp.Xtest = X1
y = cl.copy()
gp.nclasses(y)
gp.y = y
return gp, [gp.X[x] for x in range(nargs)]
def test_multiple_outputs2():
from EvoDAG import EvoDAG
from EvoDAG.model import Model
y = cl.copy()
gp = EvoDAG(generations=np.inf,
tournament_size=2,
early_stopping_rounds=100,
time_limit=0.9,
multiple_outputs=True,
seed=0,
popsize=10000).fit(X, y, test_set=X)
m = gp.model()
assert isinstance(m, Model)
assert len(gp.y) == 3
def test_SteadyState_generation():
from EvoDAG import EvoDAG
y = cl.copy()
y[y != 1] = -1
gp = EvoDAG(population_class='SteadyState',
all_inputs=True,
classifier=False,
early_stopping_rounds=1,
popsize=2)
gp.X = X
gp.y = y
gp.create_population()
for i in range(3):
gp.replace(gp.random_offspring())
assert gp.population.generation == 2
def test_multiple_outputs_decision_function():
from EvoDAG import EvoDAG
y = cl.copy()
gp = EvoDAG(generations=np.inf,
tournament_size=2,
multiple_outputs=True,
early_stopping_rounds=-1,
seed=0,
popsize=10).fit(X[:-10], y[:-10], test_set=X[-10:])
m = gp.model()
assert m.multiple_outputs
hy = m.decision_function(X)
assert len(hy) == 3
for i in hy:
assert i.isfinite()
def test_multiple_outputs():
from EvoDAG import EvoDAG
y = cl.copy()
gp = EvoDAG(generations=np.inf,
tournament_size=2,
early_stopping_rounds=100,
time_limit=0.9,
multiple_outputs=True,
seed=0,
popsize=10000)
gp.X = X
gp.nclasses(y)
gp.y = y
gp.create_population()
assert len(gp.y) == 3
def test_HGeneration_pr_variable():
import json
from EvoDAG.utils import RandomParameterSearch
from EvoDAG import EvoDAG
get_remote_data()
params = json.loads(open('evodag.params').read())
params['population_class'] = 'HGenerational'
params['pr_variable'] = 1.0
kw = RandomParameterSearch.process_params(params)
y = cl.copy()
try:
EvoDAG(**kw).fit(X, y)
except AssertionError:
return
assert False
def test_multiple_outputs_predict():
from EvoDAG import EvoDAG
y = cl.copy()
gp = EvoDAG(generations=np.inf,
tournament_size=2,
multiple_outputs=True,
early_stopping_rounds=-1,
seed=0,
popsize=10).fit(X[:-10], y[:-10], test_set=X[-10:])
m = gp.model()
assert m.multiple_outputs
hy = m.predict(X)
u = np.unique(y)
for i in np.unique(hy):
assert i in u
def test_mask():
from EvoDAG import EvoDAG
y = cl.copy()
gp = EvoDAG(generations=np.inf,
tournament_size=2,
early_stopping_rounds=100,
time_limit=0.9,
multiple_outputs=True,
seed=0,
popsize=100)
gp.y = y
gp.X = X
gp.create_population()
ts = np.array(gp._mask_ts.full_array()) == 0
vs = np.array(gp._mask_vs.full_array()) == 1
assert np.all(ts == vs)
def test_all_inputs2():
from EvoDAG import EvoDAG
y = cl.copy()
y[y != 1] = -1
gp = EvoDAG(population_class='Generational',
all_inputs=True,
popsize=3)
gp.X = X
gp.y = y
gp.create_population()
print(len(gp.population.population), len(gp.X))
assert len(gp.population.population) == len(gp.X)
for i in range(gp.popsize):
a = gp.random_offspring()
gp.replace(a)
assert len(gp.population.population) == gp.popsize
def test_all_inputs():
from EvoDAG import EvoDAG
y = cl.copy()
y[y != 1] = -1
for pc in ['Generational', 'SteadyState']:
gp = EvoDAG(population_class=pc,
all_inputs=True,
popsize=10)
gp.X = X
gp.y = y
gp.create_population()
assert len(gp.population.population) < 10
for i in range(gp.population.popsize,
gp.population._popsize):
a = gp.random_offspring()
gp.replace(a)
assert len(gp.population.population) == 10
def test_pickle_model():
from EvoDAG import RootGP
import pickle
y = cl.copy()
mask = y == 0
y[mask] = 1
y[~mask] = -1
gp = RootGP(generations=np.inf,
tournament_size=2,
early_stopping_rounds=-1,
seed=0,
popsize=10).fit(X[:-10], y[:-10], test_set=X[-10:])
m = gp.model()
hy = gp.decision_function(X=X[-10:])
m1 = pickle.loads(pickle.dumps(m))
hy1 = m1.decision_function(X=X[-10:])
assert hy.SSE(hy1) == 0
def test_all_inputs():
from EvoDAG import EvoDAG
y = cl.copy()
y[y != 1] = -1
for pc in ['Generational', 'SteadyState']:
gp = EvoDAG(population_class=pc,
all_inputs=True,
classifier=False,
popsize=10)
gp.X = X
gp.y = y
gp.create_population()
assert len(gp.population.population) < 10
for i in range(gp.population.popsize, gp.population._popsize):
a = gp.random_offspring()
gp.replace(a)
assert len(gp.population.population) == 10
def test_inputs_func_argument():
from EvoDAG import EvoDAG
class Error:
nargs = 2
min_nargs = 2
classification = True
regression = True
def __init__(self, *args, **kwargs):
raise RuntimeError('aqui')
y = cl.copy()
gp = EvoDAG(classifier=True,
multiple_outputs=True,
pr_variable=0,
input_functions=[Error],
popsize=5,
share_inputs=True)
gp.X = X
gp.nclasses(y)
gp.y = y
try:
gp.create_population()
assert False
except RuntimeError:
pass
gp = EvoDAG(
classifier=True,
multiple_outputs=True,
pr_variable=0,
input_functions=['NaiveBayes', 'NaiveBayesMN', 'MultipleVariables'],
popsize=5,
share_inputs=True).fit(X, y)
assert gp
try:
EvoDAG(classifier=True,
multiple_outputs=True,
pr_variable=0,
input_functions=[
'NaiveBayesXX', 'NaiveBayesMN', 'MultipleVariables'
],
popsize=5,
share_inputs=True).fit(X, y)
except AttributeError:
pass
def test_model_nvar():
from EvoDAG import EvoDAG
y = cl.copy()
gp = EvoDAG(classifier=True,
multiple_outputs=True,
popsize=5,
share_inputs=True)
gp.fit(X, y)
assert gp._share_inputs
m = gp.model()
print(X.shape)
assert m.nvar == X.shape[1]
try:
m.predict(X[:, :3])
assert False
except RuntimeError:
pass
def test_model_hist():
from EvoDAG import RootGP
from EvoDAG.base import Model
y = cl.copy()
mask = y == 0
y[mask] = 1
y[~mask] = -1
gp = RootGP(generations=np.inf,
tournament_size=2,
early_stopping_rounds=-1,
seed=1,
popsize=10).fit(X[:-10], y[:-10], test_set=X[-10:])
hist = gp.population.hist
trace = gp.trace(gp.population.estopping)
a = hist[trace[-1]].variable
m = Model(trace, hist)
print((m._map, a, m._hist[-1].variable))
for v1, v2 in zip(a, m._hist[-1].variable):
assert m._map[v1] == v2
def test_all_init_popsize():
from EvoDAG import EvoDAG
y = cl.copy()
y[y != 1] = -1
gp = EvoDAG(population_class='Generational',
all_inputs=True,
early_stopping_rounds=1,
popsize=2)
gp.X = X
gp.y = y
gp.create_population()
assert gp.init_popsize == len(gp.X)
gp = EvoDAG(population_class='Generational',
# all_inputs=True,
early_stopping_rounds=1,
popsize=2)
gp.X = X
gp.y = y
gp.create_population()
assert gp.init_popsize == gp.popsize
def test_ensemble():
from EvoDAG import RootGP
from EvoDAG.model import Ensemble
from EvoDAG.node import Add
y = cl.copy()
gps = [RootGP(generations=np.inf,
tournament_size=2,
early_stopping_rounds=-1,
seed=seed,
popsize=10).fit(X[:-10],
y[:-10],
test_set=X)
for seed in range(2, 5)]
ens = Ensemble([gp.model() for gp in gps])
res = [gp.decision_function() for gp in gps]
res = [Add.cumsum([x[j] for x in res]) for j in range(3)]
res = [x / 3. for x in res]
r2 = ens.decision_function(None)
for a, b in zip(res, r2):
assert a.SSE(b) == 0
r2 = ens.predict(None)
def test_clean():
from EvoDAG import EvoDAG
y = cl.copy()
y[y != 1] = -1
for pc in ['Generational', 'SteadyState']:
gp = EvoDAG(population_class=pc,
popsize=5)
gp.X = X
gp.y = y
gp.create_population()
for i in range(10):
v = gp.random_offspring()
gp.replace(v)
pop = gp.population.population
esi = gp.population.estopping
for i in gp.population._hist:
print(i == esi, i in pop, i, '-'*10, i.fitness)
if i == esi:
assert i.hy is not None
elif i in pop:
assert i.hy is not None
assert gp.population.estopping.hy is not None
def test_ensemble_model():
from EvoDAG import RootGP
from EvoDAG.model import Ensemble
from EvoDAG.node import Add
y = cl.copy()
mask = y == 0
y[mask] = 1
y[~mask] = -1
gps = [RootGP(generations=np.inf,
tournament_size=2,
early_stopping_rounds=-1,
seed=seed,
popsize=10).fit(X[:-10],
y[:-10],
test_set=X)
for seed in range(3)]
ens = Ensemble([gp.model() for gp in gps])
res = [gp.decision_function() for gp in gps]
res = Add.cumsum(res) / 3
r2 = ens.decision_function(None)
assert res.SSE(r2) == 0
a = SparseArray.fromlist(ens.predict(None))
assert r2.sign().SSE(a) == 0
def test_generational_generation():
from EvoDAG.population import Generational
from EvoDAG import EvoDAG
gp = EvoDAG(population_class='Generational',
popsize=10)
gp.X = X
y = cl.copy()
y[y != 1] = -1
gp.y = y
gp.create_population()
assert isinstance(gp.population, Generational)
p = []
for i in range(gp.popsize-1):
a = gp.random_offspring()
p.append(a)
gp.replace(a)
assert len(gp.population._inner) == (gp.popsize - 1)
a = gp.random_offspring()
p.append(a)
gp.replace(a)
assert len(gp.population._inner) == 0
for a, b in zip(gp.population.population, p):
assert a == b
