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 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 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)
# exit()
#
# cs = Pipeline(SelectKB)
# print(cs)
# exit()
#
# s = cs.sample()
# print(s)
# exit()
expr = Workflow(
OnlyApply(File("abalone3.arff"), Binarize()),
Partition(),
Map(
Wrap(
select(SelectBest),
ApplyUsing(select(DT, RF, NB)),
OnlyApply(Metric(functions=['length'])),
OnlyUse(Metric(functions=['accuracy', 'error'])),
# AfterUse(Metric(function=['diversity']))
), ),
Report('HISTORY ... S: {history}'),
Summ(function='mean_std'),
Report('mean and std ... S: $S'),
OnlyApply(Copy(from_field="S", to_field="B")),
OnlyApply(Report('copy S to B ... B: $B')),
OnlyUse(
MConcat(input_field1="B",
input_field2="S",
output_field="S",
direction='vertical')),
cache = partial(Cache, storage_alias='default_sqlite')
# cache = partial(Cache, storage_alias='mysql')
# cache = partial(Cache, storage_alias='default_dump')
# cache = partial(Cache, storage_alias='amnesia')
# expr = Pipeline(File(arq), cache(ApplyUsing(NB())))
# p = expr
# p.apply()
expr = Workflow(
OnlyApply(File(arq), cache(Binarize())),
cache(
Partition(),
Map(
Wrap(
select(SelectBest), # slow??
cache(ApplyUsing(select(DT, NB, hold(RF, n_estimators=40)))),
OnlyApply(Metric(functions=['length'])),
OnlyUse(Metric(functions=['accuracy', 'error'])),
# AfterUse(Metric(function=['diversity']))
),
),
# Report('HISTORY ... S: {history}'),
Summ(function='mean_std'),
),
Report('mean and std ... S: $S'),
OnlyApply(Copy(from_field="S", to_field="B")),
OnlyApply(Report('copy S to B ... B: $B')),
# OnlyUse(Report('>>>>>> B: {B.shape}')),
# Report('>>>>>> S: {S.shape}'),
print('ok!')
except DuplicateEntryException:
print('Duplicate! Ignored.')
numpy.random.seed(50)
# import sklearn
# print('The scikit-learn version is {}.'.format(sklearn.__version__))
print('expr .................')
expr = Workflow(
OnlyApply(File('iris.arff')),
Cache(
evaluator(
Wrap(
shuffle(Std, MinMax),
# shuffle(Std, select(UnderS, OverS), MinMax),
ApplyUsing(select(DT, NB)),
),
Metric(functions=['accuracy']))))
# {history.last.config['function']}
print(expr)
print('sample .................')
pipe = full(rnd(expr, n=10), field='S').sample()
pipe.enable_pretty_printing()
print(f'Pipe:\n{pipe}')
print(f'Wrapped:\n{pipe.unwrap}')
pipe = Chain(File('abalone3.arff'), Binarize(), Split(), pipe.unwrap, Metric(),
Report())
print('apply .................')
model = pipe.apply()