def test_cache(arq="iris.arff"):
pipe = Workflow(Cache(File(arq), storage_alias="default_sqlite"),
Report("{history}"))
train, test = pipe.dual_transform()
print("Train..............\n", train.history ^ "name")
print("Test..........\n", test.history ^ "name")
def test_with_summ_reduce(arq="iris.arff"):
pipe = Workflow(
File(arq),
Partition(),
Map(PCA(), SVMC(), Metric()),
Map(Report("<---------------------- etapa")),
Summ(),
Reduce(),
Report("mean ... S: $S"),
)
train, test = pipe.dual_transform()
print("Train..............\n", train.history ^ "longname")
print("Test..........\n", test.history ^ "longname")
def test_partition(arq="iris.arff"):
pipe = Workflow(
File(arq),
Partition(),
Map(PCA(), SVMC(), Metric(enhance=False)),
Summ(function="mean", enhance=False),
Reduce(),
Report("mean ... S: $S", enhance=False),
Report("$X"),
Report("$y"),
)
train, test = pipe.dual_transform()
print("Train..............\n", train)
print("Test..........\n", test)
def printing_test(arq="iris.arff"):
print(Chain(Map(select(File(arq)))))
exp = Workflow(
File(arq),
Partition(),
Map(PCA(), SVMC(), Metric(enhance=False)),
Map(Report("<---------------------- fold"), enhance=False),
Summ(function="mean", enhance=False),
Reduce(),
Report("mean ... S: $S", enhance=False),
)
print(exp)
print(select(DT(), SVMC()))
sel = select(DT(), SVMC())
print(sel)
print(Map(DT()))
exp = ChainCS(
File(arq),
Partition(),
Map(PCA(), select(SVMC(), DT(criterion="gini")),
Metric(enhance=False)),
Report("teste"),
Map(Report("<---------------------- fold")),
)
print(exp)
def test_check_architecture(arq="iris.arff"):
pipe = Workflow(
File(arq),
Partition(partitions=2),
Map(PCA(), SVMC(), Metric(enhance=False)),
Summ(field="Y", function="mean", enhance=False),
)
# tenho file na frente
train_01 = pipe.enhancer.transform(sd.NoData)
test_01 = pipe.model(sd.NoData).transform(sd.NoData)
train_02, test_02 = pipe.dual_transform(sd.NoData, sd.NoData)
# Collection uuid depends on data, which depends on consumption.
for t, *_ in train_01, train_02, test_01, test_02:
# print(111111111, t.y)
pass
assert train_01.uuid == train_02.uuid
assert test_01.uuid == test_02.uuid
def ger_workflow(seed=0, arq="iris.arff"):
np.random.seed(seed)
workflow = Workflow(File(arq),
Partition(),
Map(PCA(), select(SVMC(), DT(criterion="gini")),
Metric(enhance=False)),
Summ(function="mean", enhance=False),
Reduce(),
Report("Mean S: $S", enhance=False),
seed=seed)
return workflow
def test_sequence_of_classifiers(arq="abalone.arff"):
pipe = Workflow(
File(arq),
Binarize(),
Report('1 {X.shape} {history^name}'),
PCA(n=5),
SVMC(),
Metric(),
Report('2 {X.shape} {history^name}'),
DT(),
Metric(),
Report('3 {X.shape} {history^name}'),
)
print('Enh')
train = pipe.enhancer.transform(sd.NoData)
print('Mod')
test = pipe.model(sd.NoData).transform(
sd.NoData) # TODO: pq report não aparece no test?
print()
print("[test_sequence_of_classifiers] Train.........\n",
train.history ^ "longname")
print("[test_sequence_of_classifiers] Test..........\n",
test.history ^ "longname")
def random_search(arq="iris.arff"):
np.random.seed(0)
exp = Workflow(
File(arq),
Partition(),
Map(PCA(), select(SVMC(), DT(criterion="gini")), Metric()),
# Map(Report("<---------------------- fold"), enhance=False),
Summ(function="mean"),
Reduce(),
Report("Mean S: $S"),
)
expr = sample(exp, n=10)
result = optimize(expr, n=5)
result.disable_pretty_printing()
print(result)
def test_check_architecture2(arq="iris.arff"):
pipe = Workflow(
File(arq),
Partition(),
Map(PCA(), SVMC(), Metric(enhance=False)),
Summ(field="Y", function="mean", enhance=False),
Report("mean ... S: $S", enhance=False),
)
# tenho file na frente
train_ = pipe.enhancer.transform(sd.NoData)
test_ = pipe.model(sd.NoData).transform(sd.NoData)
test_ = pipe.model(sd.NoData).transform((sd.NoData, sd.NoData))
train_, test_ = pipe.dual_transform(sd.NoData, sd.NoData)
train_, test_ = pipe.dual_transform(sd.NoData, (sd.NoData, sd.NoData))
def test_pca(arq="iris.arff"):
cs = File(arq).cs
pipe = Workflow(File(arq), Split(), PCA(), SVMC(), Metric())
train, test = pipe.dual_transform()
print("Train..............\n", train.history ^ "name")
print("Test..........\n", test.history ^ "name")
def test_metric(arq="iris.arff"):
pipe = Workflow(File(arq), Split(), SVMC(), Metric(enhance=False))
train, test = pipe.dual_transform()
print("Train..............\n", train)
print("Test..........\n", test)
def test_split(arq="iris.arff"):
pipe = Workflow(File(arq), Split(), SVMC())
train, test = pipe.dual_transform()
print("Train..............\n", str(train))
print("Test..........\n", str(test))
def test_svmc(arq="iris.arff"):
cs = File(arq).cs
pipe = Workflow(File(arq), SVMC())
train, test = pipe.dual_transform()
print("Train..............\n", train)
print("Test..........\n", test)