def test_message_with_time(source, message, is_long, time, time_str):
out = _message_with_time(source, message, time)
if is_long:
assert len(out) > 70
else:
assert len(out) == 70
assert out.startswith('[' + source + '] ')
out = out[len(source) + 3:]
assert out.endswith(time_str)
out = out[:-len(time_str)]
assert out.endswith(', total=')
out = out[:-len(', total=')]
assert out.endswith(message)
out = out[:-len(message)]
assert out.endswith(' ')
out = out[:-1]
if is_long:
assert not out
else:
assert list(set(out)) == ['.']
out = out[:-len(', total=')]
assert out.endswith(message)
out = out[:-len(message)]
assert out.endswith(' ')
out = out[:-1]
if is_long:
assert not out
else:
assert list(set(out)) == ['.']
@pytest.mark.parametrize(
['message', 'expected'],
[
('hello', _message_with_time('ABC', 'hello', 0.1) + '\n'),
('', _message_with_time('ABC', '', 0.1) + '\n'),
(None, ''),
])
def test_print_elapsed_time(message, expected, capsys, monkeypatch):
monkeypatch.setattr(timeit, 'default_timer', lambda: 0)
with _print_elapsed_time('ABC', message):
monkeypatch.setattr(timeit, 'default_timer', lambda: 0.1)
assert capsys.readouterr().out == expected
@pytest.mark.parametrize("value, result", [(float("nan"), True),
(np.nan, True),
(np.float("nan"), True),
(np.float32("nan"), True),
(np.float64("nan"), True),
out = out[:-len(', total=')]
assert out.endswith(message)
out = out[:-len(message)]
assert out.endswith(' ')
out = out[:-1]
if is_long:
assert not out
else:
assert list(set(out)) == ['.']
@pytest.mark.parametrize(
['message', 'expected'],
[
('hello', _message_with_time('ABC', 'hello', 0.1) + '\n'),
('', _message_with_time('ABC', '', 0.1) + '\n'),
(None, ''),
])
def test_print_elapsed_time(message, expected, capsys, monkeypatch):
monkeypatch.setattr(timeit, 'default_timer', lambda: 0)
with _print_elapsed_time('ABC', message):
monkeypatch.setattr(timeit, 'default_timer', lambda: 0.1)
assert capsys.readouterr().out == expected
@pytest.mark.parametrize("value, result", [(float("nan"), True),
(np.nan, True),
(np.float("nan"), True),
(np.float32("nan"), True),
(np.float64("nan"), True),
out = out[:-len(", total=")]
assert out.endswith(message)
out = out[:-len(message)]
assert out.endswith(" ")
out = out[:-1]
if is_long:
assert not out
else:
assert list(set(out)) == ["."]
@pytest.mark.parametrize(
["message", "expected"],
[
("hello", _message_with_time("ABC", "hello", 0.1) + "\n"),
("", _message_with_time("ABC", "", 0.1) + "\n"),
(None, ""),
],
)
def test_print_elapsed_time(message, expected, capsys, monkeypatch):
monkeypatch.setattr(timeit, "default_timer", lambda: 0)
with _print_elapsed_time("ABC", message):
monkeypatch.setattr(timeit, "default_timer", lambda: 0.1)
assert capsys.readouterr().out == expected
@pytest.mark.parametrize(
"value, result",
[
(float("nan"), True),
def _fit_and_score(estimator,
X,
y,
scorer,
train,
test,
verbose,
parameters,
fit_params,
return_train_score=False,
return_parameters=False,
return_n_test_samples=False,
return_times=True,
return_estimator=False,
error_score=np.nan):
if verbose > 1:
if parameters is None:
msg = ''
else:
msg = '%s' % (', '.join('%s=%s' % (k, v)
for k, v in parameters.items()))
print("[CV] %s %s" % (msg, (64 - len(msg)) * '.'))
# Adjust length of sample weights
fit_params = fit_params if fit_params is not None else {}
fit_params = _check_fit_params(X, fit_params, train)
train_scores = {}
if parameters is not None:
# clone after setting parameters in case any parameters
# are estimators (like pipeline steps)
# because pipeline doesn't clone steps in fit
cloned_parameters = {}
for k, v in parameters.items():
cloned_parameters[k] = clone(v, safe=False)
estimator = estimator.set_params(**cloned_parameters)
start_time = time.perf_counter()
X_train, y_train = _safe_split(estimator, X, y, train)
X_test, y_test = _safe_split(estimator, X, y, test, train)
try:
if y_train is None:
estimator.fit(X_train, **fit_params)
else:
estimator.fit(X_train, y_train, **fit_params)
except Exception as e:
# Note fit time as time until error
fit_time = time.perf_counter() - start_time
score_time = 0.0
if error_score == 'raise':
raise
elif isinstance(error_score, numbers.Number):
if isinstance(scorer, dict):
test_scores = {name: error_score for name in scorer}
if return_train_score:
train_scores = test_scores.copy()
else:
test_scores = error_score
if return_train_score:
train_scores = error_score
warnings.warn(
"Estimator fit failed. The score on this train-test"
" partition for these parameters will be set to %f. "
"Details: \n%s" %
(error_score, format_exception_only(type(e), e)[0]),
FitFailedWarning)
else:
raise ValueError("error_score must be the string 'raise' or a"
" numeric value. (Hint: if using 'raise', please"
" make sure that it has been spelled correctly.)")
else:
fit_time = time.perf_counter() - start_time
test_scores = _score(estimator, X_test, y_test, scorer)
score_time = time.perf_counter() - start_time - fit_time
if return_train_score:
train_scores = _score(estimator, X_train, y_train, scorer)
if verbose > 2:
if isinstance(test_scores, dict):
for scorer_name in sorted(test_scores):
msg += ", %s=" % scorer_name
if return_train_score:
msg += "(train=%.3f," % train_scores[scorer_name]
msg += " test=%.3f)" % test_scores[scorer_name]
else:
msg += "%.3f" % test_scores[scorer_name]
else:
msg += ", score="
msg += ("%.3f" % test_scores if not return_train_score else
"(train=%.3f, test=%.3f)" % (train_scores, test_scores))
total_time = score_time + fit_time
if verbose > 1:
print(_message_with_time('CV', msg, total_time))
ret = [train_scores, test_scores] if return_train_score else [test_scores]
p = pickle.dumps(estimator)
mem = sys.getsizeof(p) #in bytes
#TODO переделать без костылей
#for numpy
if (isinstance(X_test, np.ndarray)):
inf_example = X_test[0].reshape(1, -1)
#for DataFrame
if (isinstance(X_test, pd.DataFrame)):
inf_example = X_test.iloc[0].to_numpy().reshape(1, -1)
#Reshape your data either using array.reshape(-1, 1)
#if your data has a single feature or array.reshape(1, -1) if it contains
#a single sample.
inference_time_start = time.perf_counter()
s = estimator.predict(inf_example)
inference_time_end = time.perf_counter()
inference_time = inference_time_end - inference_time_start
if return_n_test_samples:
ret.append(_num_samples(X_test))
if return_times:
ret.extend([fit_time, score_time, inference_time, mem, total_time])
if return_parameters:
ret.append(parameters)
if return_estimator:
ret.append(estimator)
return ret
