def test_cross_validation_score(self):
rows = 100
folds = 10
X = np.random.random((rows, 10))
y = np.random.randint(0, 2, (rows))
p = Pipeline()
np_in_X = p.add(NumpyRead(X))
np_in_y = p.add(NumpyRead(y))
cv_score = p.add(
CrossValidationScore(wrap(SVC), 'score', {}, folds,
random_state=0))
np_in_X['output'] > cv_score['X_train']
np_in_y['output'] > cv_score['y_train']
score_out = p.add(CSVWrite(self._tmp_files('out.csv')))
cv_score['score'] > score_out['input']
self.run_pipeline(p)
result = self._tmp_files.csv_read('out.csv')['f0']
ctrl_kf = SKKFold(rows, folds, random_state=0)
ctrl = np.mean(cross_val_score(SVC(), X, y, cv=ctrl_kf))
self.assertTrue(np.allclose(ctrl, result))
def test_feature_importance(self):
#50% 20% 100% predictability
X = np.array([[1, 0, 1], [1, 0, 0], [1, 0, 1], [0, 0, 1], [0, 0, 0],
[0, 0, 1], [1, 0, 1], [0, 0, 1]])
y = np.array([1, 0, 1, 1, 0, 1, 1, 1])
p = Pipeline()
X_in = p.add(NumpyRead(X))
y_in = p.add(NumpyRead(y))
est = p.add(
wrap_and_make_instance('sklearn.ensemble.RandomForestClassifier',
random_state=0))
est(X_train=X_in, y_train=y_in)
out = p.add(NumpyWrite())
out(est['feature_importances'])
p.run()
result = out.get_stage().result['col_name']
ctrl = np.array(['f2', 'f0', 'f1'])
self.assertTrue(np.array_equal(ctrl, result))
def test_merge(self):
a1 = np.array([(0, 'Lisa', 2), (1, 'Bill', 1), (2, 'Fred', 2),
(3, 'Samantha', 2), (4, 'Augustine', 1),
(5, 'William', 0)],
dtype=[('id', int), ('name', 'S64'), ('dept_id', int)])
a2 = np.array([(0, 'accts receivable'), (1, 'accts payable'),
(2, 'shipping')],
dtype=[('id', int), ('name', 'S64')])
kwargs = {}
p = Pipeline()
a1_in = p.add(NumpyRead(a1))
a2_in = p.add(NumpyRead(a2))
merge = p.add(Merge('dept_id', 'id', **kwargs))
out = p.add(NumpyWrite())
out(merge(a1_in, a2_in))
self.run_pipeline(p)
result = out.get_stage().result
ctrl = obj_to_str(
pd.DataFrame(a1).merge(pd.DataFrame(a2),
left_on='dept_id',
right_on='id').to_records(index=False))
assert (np.array_equal(result, ctrl))
def test_grid_search(self):
"""
Simulates behavior of example in:
http://scikit-learn.org/stable/modules/generated/sklearn.grid_search.GridSearchCV.html#sklearn.grid_search.GridSearchCV
"""
folds = 2
parameters = {
'kernel': (
'rbf',
'linear'),
'C': [
1,
10,
100],
'random_state': [0]}
iris = datasets.load_iris()
iris_data = iris.data
iris_target = iris.target
p = Pipeline()
node_data = p.add(NumpyRead(iris_data))
node_target = p.add(NumpyRead(iris_target))
node_split = p.add(SplitTrainTest(2, random_state=1))
node_search = p.add(GridSearch(
wrap(SVC),
parameters,
'score',
cv_stage_kwargs={'n_folds': folds}))
node_params_out = p.add(CSVWrite(self._tmp_files.get('out.csv')))
node_data['output'] > node_split['input0']
node_target['output'] > node_split['input1']
node_split['train0'] > node_search['X_train']
node_split['train1'] > node_search['y_train']
node_split['test0'] > node_search['X_test']
node_split['test1'] > node_search['y_test']
node_search['params_out'] > node_params_out['input']
self.run_pipeline(p)
result = self._tmp_files.csv_read('out.csv')
ctrl_X_train, _, ctrl_y_train, _ = train_test_split(
iris_data, iris_target, random_state=1)
ctrl_cv = SKKFold(ctrl_y_train.size, folds)
ctrl_search = grid_search.GridSearchCV(SVC(), parameters, cv=ctrl_cv)
ctrl_search.fit(ctrl_X_train, ctrl_y_train)
control = ctrl_search.best_params_
# TODO a number of configurations tie here, and sklearn picks a different
# best configuration than upsg does (although they have the same score)
# ideally, we want to find some parameters where there is a clear
# winner
control = {'C': 10, 'kernel': 'linear', 'random_state': 0}
self.assertEqual(np_sa_to_dict(np.array([result])), control)
def test_multiclassify(self):
samples = 150
features = 3
folds = 2
X = np.random.random((samples, features))
y = np.random.randint(0, 2, (samples))
p = Pipeline()
np_in_X = p.add(NumpyRead(X))
np_in_y = p.add(NumpyRead(y))
split_train_test = p.add(SplitTrainTest(2))
np_in_X['output'] > split_train_test['input0']
np_in_y['output'] > split_train_test['input1']
multi = p.add(
Multiclassify('score', self._tmp_files('report.html'), None,
folds))
split_train_test['train0'] > multi['X_train']
split_train_test['test0'] > multi['X_test']
split_train_test['train1'] > multi['y_train']
split_train_test['test1'] > multi['y_test']
self.run_pipeline(p)
self.assertTrue(os.path.isfile(self._tmp_files('report.html')))
def test_hstack(self):
a = np.array([(0.0, 0.1), (1.0, 1.1), (2.0, 2.1)],
dtype=[('f0', float), ('f1', float)])
b = np.array([(0.2, 0.3), (1.2, 1.3), (2.2, 2.3)],
dtype=[('f2', float), ('f3', float)])
ctrl = np.array([(0.0, 0.1, 0.2, 0.3), (1.0, 1.1, 1.2, 1.3),
(2.0, 2.1, 2.2, 2.3)],
dtype=[('f0', float), ('f1', float), ('f2', float),
('f3', float)])
p = Pipeline()
np_in_a = p.add(NumpyRead(a))
np_in_b = p.add(NumpyRead(b))
hstack = p.add(HStack(2))
hstack(np_in_a, np_in_b)
out = p.add(NumpyWrite())
out(hstack)
p.run()
self.assertTrue(np.array_equal(ctrl, out.get_stage().result))
def test_moving_params(self):
digits = datasets.load_digits()
digits_data = digits.data
digits_target = digits.target
p = Pipeline()
node_data = p.add(NumpyRead(digits_data))
node_target = p.add(NumpyRead(digits_target))
node_split = p.add(SplitTrainTest(2, random_state=0))
# parameters from
# http://scikit-learn.org/stable/auto_examples/plot_classifier_comparison.html
node_clf1 = p.add(
wrap_and_make_instance(RandomForestClassifier,
max_depth=5,
n_estimators=10,
max_features=1,
random_state=0))
node_clf2 = p.add(
wrap_and_make_instance(RandomForestClassifier,
max_depth=12,
n_estimators=100,
max_features=1000))
node_params_out_1 = p.add(
CSVWrite(self._tmp_files.get('out_params_1.csv')))
node_params_out_2 = p.add(
CSVWrite(self._tmp_files.get('out_params_2.csv')))
node_pred_out_1 = p.add(CSVWrite(
self._tmp_files.get('out_pred_1.csv')))
node_pred_out_2 = p.add(CSVWrite(
self._tmp_files.get('out_pred_2.csv')))
node_data['output'] > node_split['input0']
node_target['output'] > node_split['input1']
node_split['train0'] > node_clf1['X_train']
node_split['train1'] > node_clf1['y_train']
node_split['test0'] > node_clf1['X_test']
node_split['train0'] > node_clf2['X_train']
node_split['train1'] > node_clf2['y_train']
node_split['test0'] > node_clf2['X_test']
node_clf1['params_out'] > node_clf2['params_in']
node_clf1['params_out'] > node_params_out_1['input']
node_clf2['params_out'] > node_params_out_2['input']
node_clf1['y_pred'] > node_pred_out_1['input']
node_clf2['y_pred'] > node_pred_out_2['input']
self.run_pipeline(p)
params_1 = self._tmp_files.csv_read('out_params_1.csv')
params_2 = self._tmp_files.csv_read('out_params_2.csv')
self.assertTrue(np.array_equal(params_1, params_2))
y_pred_1 = self._tmp_files.csv_read('out_pred_1.csv')
y_pred_2 = self._tmp_files.csv_read('out_pred_2.csv')
self.assertTrue(np.array_equal(y_pred_1, y_pred_2))
def test_lambda(self):
# Test output key generation
l1 = LambdaStage(lambda x, y: 0)
self.assertEqual(l1.input_keys, ['x', 'y'])
self.assertEqual(l1.output_keys, [
'output0',
])
l2 = LambdaStage(lambda: 0, n_outputs=3)
self.assertEqual(l2.input_keys, [])
self.assertEqual(l2.output_keys,
['output{}'.format(i) for i in xrange(3)])
# Test running in pipeline
in_data = np_nd_to_sa(np.random.random((100, 10)))
scale = np_nd_to_sa(np.array(3))
out_keys = ['augmented', 'log_col', 'sqrt_col', 'scale_col']
def log1_sqrt2_scale3(A, scale):
names = A.dtype.names
log_col = np.log(A[names[0]])
sqrt_col = np.sqrt(A[names[1]])
scale_col = A[names[2]] * scale[0][0]
return (append_fields(A, ['log1', 'sqrt2', 'scale3'],
(log_col, sqrt_col, scale_col)), log_col,
sqrt_col, scale_col)
p = Pipeline()
np_in = p.add(NumpyRead(in_data))
scale_in = p.add(NumpyRead(scale))
lambda_stage = p.add(LambdaStage(log1_sqrt2_scale3, out_keys))
np_in['output'] > lambda_stage['A']
scale_in['output'] > lambda_stage['scale']
csv_out_stages = []
for key in out_keys:
stage = p.add(CSVWrite(self._tmp_files('out_{}.csv'.format(key))))
csv_out_stages.append(stage)
lambda_stage[key] > stage['input']
self.run_pipeline(p)
controls = log1_sqrt2_scale3(in_data, scale)
for i, key in enumerate(out_keys):
control = controls[i]
if is_sa(control):
control = np_sa_to_nd(control)[0]
result = self._tmp_files.csv_read('out_{}.csv'.format(key),
as_nd=True)
self.assertTrue(np.allclose(control, result))
def test_multimetric(self):
samples = 150
features = 3
metrics = (VisualMetricSpec(
'sklearn.metrics.precision_recall_curve', # metric
'recall', # output key corresponding to x-axis
'precision', # output key corresponding to y-axis
'Precision/Recall Curve', # graph title
'recall', # x-label
'precision',), # y-label
VisualMetricSpec(
'sklearn.metrics.roc_curve',
None,
('tpr', 'fpr'),
'ROC Curve',
'Results tagged positive',
'Rate',
('FPR', 'TPR')),
NumericMetricSpec(
'sklearn.metrics.roc_auc_score',
'auc',
'ROC AUC Score'))
X = np.random.random((samples, features))
y = np.random.randint(0, 2, (samples))
p = Pipeline()
np_in_X = p.add(NumpyRead(X))
np_in_y = p.add(NumpyRead(y))
split_train_test = p.add(SplitTrainTest(2))
np_in_X['output'] > split_train_test['input0']
np_in_y['output'] > split_train_test['input1']
clf = p.add(wrap_and_make_instance(SVC, kernel='linear'))
split_train_test['train0'] > clf['X_train']
split_train_test['test0'] > clf['X_test']
split_train_test['train1'] > clf['y_train']
split_train_test['test1'] > clf['y_test']
node_proba_cat_1 = p.add(SplitY(-1))
clf['pred_proba'] > node_proba_cat_1['input']
multi = p.add(Multimetric(
metrics, 'SVC',
self._tmp_files('report.html')))
node_proba_cat_1['y'] > multi['pred_proba']
split_train_test['test1'] > multi['y_true']
clf['params_out'] > multi['params']
self.run_pipeline(p)
self.assertTrue(os.path.isfile(self._tmp_files('report.html')))
def test_numpy_write(self):
in_data = np.random.rand(10, 10)
p = Pipeline()
np_in = p.add(NumpyRead(in_data))
np_out = p.add(NumpyWrite())
np_in['output'] > np_out['input']
self.run_pipeline(p)
self.assertTrue(
np.allclose(in_data,
np_sa_to_nd(np_out.get_stage().result)[0]))
def test_generate_feature(self):
in_array = np.array([(0.0, 0.1, 0.2, 0.3), (1.0, 1.1, 1.2, 1.3),
(2.0, 2.1, 2.2, 2.3)],
dtype=[('f0', float), ('f1', float), ('f2', float),
('f3', float)])
ctrl = np.array([(10.4, ), (12.4, ), (14.4, )], dtype=[('f0', float)])
cols = ['f1', 'f3']
f = lambda tab: tab['f1'] + tab['f3'] + 10
p = Pipeline()
np_in = p.add(NumpyRead(in_array))
gen_feat = p.add(GenerateFeature(f, cols))
gen_feat(np_in)
out = p.add(NumpyWrite())
out(gen_feat)
p.run()
self.assertTrue(np.array_equal(ctrl, out.get_stage().result))
ctrl = np.array([(1, 10.1), (11, 11.1), (21, 12.1)],
dtype=[('times10', float), ('add10', float)])
cols = ['f1']
f = lambda tab: np.array(zip(tab['f1'] * 10, tab['f1'] + 10))
out_col_names = ['times10', 'add10']
p = Pipeline()
np_in = p.add(NumpyRead(in_array))
gen_feat = p.add(GenerateFeature(f, cols, out_col_names))
gen_feat(np_in)
out = p.add(NumpyWrite())
out(gen_feat)
p.run()
self.assertTrue(np.array_equal(ctrl, out.get_stage().result))
def test_cross_validation_score(self):
rows = 100
folds = 10
X = np.random.random((rows, 10))
y = np.random.randint(0, 2, (rows))
trials = ((SKKFold,
{'random_state': 0, 'n_folds': folds},
{'n': rows, 'n_folds': folds, 'random_state': 0}),
(StratifiedKFold,
{'random_state': 0, 'n_folds': folds},
{'y': y, 'n_folds': folds, 'random_state': 0}))
for PartIter, res_kwargs, ctrl_kwargs in trials:
p = Pipeline()
np_in_X = p.add(NumpyRead(X))
np_in_y = p.add(NumpyRead(y))
cv_score = p.add(CrossValidationScore(
wrap(SVC),
{},
'score',
wrap(PartIter),
res_kwargs))
np_in_X['output'] > cv_score['X_train']
np_in_y['output'] > cv_score['y_train']
score_out = p.add(CSVWrite(self._tmp_files('out.csv')))
cv_score['score'] > score_out['input']
self.run_pipeline(p)
result = self._tmp_files.csv_read('out.csv')['f0']
ctrl_kf = PartIter(**ctrl_kwargs)
ctrl = np.mean(cross_val_score(SVC(), X, y, cv=ctrl_kf))
self.assertTrue(np.allclose(ctrl, result))
def test_plot_roc(self):
# based on
# http://scikit-learn.org/stable/auto_examples/plot_roc_crossval.html
from sklearn.svm import SVC
from sklearn.metrics import roc_curve
from sklearn import datasets
iris = datasets.load_iris()
iris_data = iris.data[iris.target != 2]
iris_target = iris.target[iris.target != 2]
p = Pipeline()
node_data = p.add(NumpyRead(iris_data))
node_target = p.add(NumpyRead(iris_target))
node_split = p.add(SplitTrainTest(2, random_state=0))
node_clf = p.add(wrap_and_make_instance(SVC, random_state=0))
node_select = p.add(SplitY(1))
node_roc = p.add(wrap_and_make_instance(roc_curve))
node_plot = p.add(
Plot(self._tmp_files('result.png'),
'co-',
title='ROC Curve',
xlabel='FPR',
ylabel='TPR'))
node_data['output'] > node_split['input0']
node_target['output'] > node_split['input1']
node_split['train0'] > node_clf['X_train']
node_split['train1'] > node_clf['y_train']
node_split['test0'] > node_clf['X_test']
node_clf['pred_proba'] > node_select['input']
node_select['y'] > node_roc['y_score']
node_split['test1'] > node_roc['y_true']
node_roc['fpr'] > node_plot['x']
node_roc['tpr'] > node_plot['y']
self.run_pipeline(p)
self.assertTrue(os.path.isfile(self._tmp_files('result.png')))
def test_kfold(self):
folds = 3
rows = 6
X = np.random.randint(0, 1000, (rows, 3))
y = np.random.randint(0, 1000, (rows, 1))
p = Pipeline()
np_in_X = p.add(NumpyRead(X))
np_in_y = p.add(NumpyRead(y))
kfold = p.add(KFold(2, folds, random_state=0))
np_in_X['output'] > kfold['input0']
np_in_y['output'] > kfold['input1']
ctrl_kf = SKKFold(rows, n_folds=folds, random_state=0)
out_files = []
expected_folds = []
arrays = (X, y)
for fold_i, train_test_inds in enumerate(ctrl_kf):
for array_i, array in enumerate(arrays):
for select_i, selection in enumerate(('train', 'test')):
out_key = '{}{}_{}'.format(selection, array_i, fold_i)
out_file = out_key + '.csv'
out_files.append(out_file)
stage = p.add(CSVWrite(self._tmp_files(out_file)))
kfold[out_key] > stage['input']
slice_inds = train_test_inds[select_i]
expected_folds.append(
np_nd_to_sa(arrays[array_i][slice_inds]))
self.run_pipeline(p)
for out_file, expected_fold in zip(out_files, expected_folds):
self.assertTrue(
np.array_equal(self._tmp_files.csv_read(out_file),
expected_fold))
def test_apply_to_selected_cols(self):
rows = 100
cols = 10
random_data = np.random.rand(rows, cols)
# enough nans so that there /has/ to be a Nan in 1 of our 3 selected cols
nans = 701
with_nans = np.copy(random_data)
for r, c in zip(np.random.randint(0, rows, nans),
np.random.randint(0, cols, nans)):
with_nans[r, c] = np.NaN
trials = ((wrap('sklearn.preprocessing.StandardScaler'), (), 'X_train',
'X_new', np_nd_to_sa(random_data)),
(FillNA, (0, ), 'input', 'output', np_nd_to_sa(with_nans)))
sel_cols = ('f2', 'f3', 'f4')
trials = trials[1:]
for trans_cls, args, in_key, out_key, in_data in trials:
p = Pipeline()
node_in = p.add(NumpyRead(in_data))
node_selected = p.add(
ApplyToSelectedCols(sel_cols, trans_cls, *args))
node_in['output'] > node_selected[in_key]
node_out = p.add(NumpyWrite())
node_selected[out_key] > node_out['input']
node_ctrl_split = p.add(SplitColumns(sel_cols))
node_in['output'] > node_ctrl_split['input']
node_ctrl_trans = p.add(trans_cls(*args))
node_ctrl_split['output'] > node_ctrl_trans[in_key]
node_ctrl_out = p.add(NumpyWrite())
node_ctrl_trans[out_key] > node_ctrl_out['input']
self.run_pipeline(p)
result = node_out.get_stage().result
ctrl = node_ctrl_out.get_stage().result
for col in in_data.dtype.names:
if col in sel_cols:
self.assertTrue(np.allclose(result[col], ctrl[col]))
else:
self.assertTrue(
np.allclose(np.nan_to_num(result[col]),
np.nan_to_num(in_data[col])))
def test_identity(self):
trials = [(('input0', 'input1'), ('output0', 'output1'), {
'input0': 'output0',
'input1': 'output1'
}, True),
(('input0', 'input1', 'input2'), ('input0_out', 'input1_out',
'input2_out'),
('input0', 'input1', 'input2'), True),
(('input0', 'input1'), ('output0', 'output1'), {
'output0': 'input0',
'output1': 'input1'
}, False),
(('output0_in', 'output1_in', 'output2_in'),
('output0', 'output1', 'output2'), ('output0', 'output1',
'output2'), False)]
for input_keys, output_keys, arg, specify_input in trials:
in_data_arrays = []
out_nodes = []
p = Pipeline()
if specify_input:
node_id = p.add(Identity(arg))
else:
node_id = p.add(Identity(output_keys=arg))
for input_key, output_key, in zip(input_keys, output_keys):
in_data = np_nd_to_sa(np.random.random((100, 10)))
node_in = p.add(NumpyRead(in_data))
node_in['output'] > node_id[input_key]
node_out = p.add(NumpyWrite())
node_id[output_key] > node_out['input']
in_data_arrays.append(in_data)
out_nodes.append(node_out)
self.run_pipeline(p)
for in_data, out_node in zip(in_data_arrays, out_nodes):
self.assertTrue(
np.array_equal(in_data,
out_node.get_stage().result))
def test_query_dates(self):
p = Pipeline()
dates = np.array([(np.datetime64('2012-01-01')),
(np.datetime64('2013-04-05')),
(np.datetime64('2014-03-11')),
(np.datetime64('2015-01-01'))],
dtype=[('dt', 'M8[D]')])
inds = np.array([(i, ) for i in xrange(dates.size)],
dtype=[('f0', int)])
np_in = p.add(NumpyRead(dates))
q2_node = p.add(Query("dt <= DT('2014-01-01')"))
np_in['output'] > q2_node['input']
np_out = p.add(NumpyWrite())
q2_node['output'] > np_out['input']
np_complement = p.add(NumpyWrite())
q2_node['complement'] > np_complement['input']
np_out_inds = p.add(NumpyWrite())
q2_node['output_inds'] > np_out_inds['input']
np_complement_inds = p.add(NumpyWrite())
q2_node['complement_inds'] > np_complement_inds['input']
self.run_pipeline(p)
self.assertTrue(np.array_equal(np_out.get_stage().result, dates[:2]))
self.assertTrue(
np.array_equal(np_complement.get_stage().result, dates[2:]))
self.assertTrue(
np.array_equal(np_out_inds.get_stage().result, inds[:2]))
self.assertTrue(
np.array_equal(np_complement_inds.get_stage().result, inds[2:]))
def test_split_by_inds(self):
in_data = np.array([(0, 0), (1, 1), (2, 0), (3, 1)],
dtype=[('id', int), ('include', int)])
p = Pipeline()
np_in = p.add(NumpyRead(in_data))
query = p.add(Query('include != 0'))
query(np_in)
split_inds = p.add(SplitByInds())
split_inds(np_in, query['output_inds'])
out = p.add(NumpyWrite())
out(split_inds)
self.run_pipeline(p)
ctrl = np.array([(1, 1), (3, 1)],
dtype=[('id', int), ('include', int)])
self.assertTrue(np.array_equal(ctrl, out.get_stage().result))
def test_tutorial(self):
"""
Verifies we can do what sklearn does here:
http://scikit-learn.org/stable/tutorial/basic/tutorial.html
"""
digits = datasets.load_digits()
digits_data = digits.data
# for now, we need a column vector rather than an array
digits_target = digits.target
p = Pipeline()
# load data from a numpy dataset
stage_data = NumpyRead(digits_data)
stage_target = NumpyRead(digits_target)
# train/test split
stage_split_data = SplitTrainTest(2, test_size=1, random_state=0)
# build a classifier
stage_clf = wrap_and_make_instance(SVC, gamma=0.001, C=100.)
# output to a csv
stage_csv = CSVWrite(self._tmp_files('out.csv'))
node_data, node_target, node_split, node_clf, node_csv = map(
p.add,
[stage_data, stage_target, stage_split_data, stage_clf, stage_csv])
# connect the pipeline stages together
node_data['output'] > node_split['input0']
node_target['output'] > node_split['input1']
node_split['train0'] > node_clf['X_train']
node_split['train1'] > node_clf['y_train']
node_split['test0'] > node_clf['X_test']
node_clf['y_pred'] > node_csv['input']
self.run_pipeline(p)
result = self._tmp_files.csv_read('out.csv', True)
# making sure we get the same result as sklearn
clf = SVC(gamma=0.001, C=100.)
# The tutorial just splits using array slicing, but we need to make
# sure that both UPSG and sklearn are splitting the same way, so we
# do something more sophisticated
train_X, test_X, train_y, test_y = train_test_split(digits_data,
digits_target,
test_size=1,
random_state=0)
clf.fit(train_X, np.ravel(train_y))
control = clf.predict(test_X)[0]
self.assertAlmostEqual(result, control)
# model persistance
s = pickle.dumps(stage_clf)
stage_clf2 = pickle.loads(s)
self.assertEqual(stage_clf.get_params(), stage_clf2.get_params())
def __metric_pipeline(self, metric, params={}, in_data=None):
X_in, y_in = self.__process_in_data(in_data)
metric_stage = wrap_and_make_instance(metric, **params)
in_keys = metric_stage.input_keys
out_keys = metric_stage.output_keys
p = Pipeline()
node_X_in = p.add(NumpyRead(X_in))
node_y_in = p.add(NumpyRead(y_in))
node_split = p.add(SplitTrainTest(2, random_state=0))
node_X_in['output'] > node_split['input0']
node_y_in['output'] > node_split['input1']
ctrl_X_train, ctrl_X_test, ctrl_y_train, ctrl_y_test = (
train_test_split(X_in, y_in, random_state=0))
node_clf = p.add(wrap_and_make_instance(SVC, random_state=0))
node_split['train0'] > node_clf['X_train']
node_split['train1'] > node_clf['y_train']
node_split['test0'] > node_clf['X_test']
ctrl_clf = SVC(random_state=0, probability=True)
ctrl_clf.fit(ctrl_X_train, ctrl_y_train)
node_proba_1 = p.add(SplitY(1))
node_clf['pred_proba'] > node_proba_1['input']
ctrl_y_score = ctrl_clf.predict_proba(ctrl_X_test)[:, 1]
node_metric = p.add(metric_stage)
ctrl_metric_args = {}
if 'y_true' in in_keys:
node_split['test1'] > node_metric['y_true']
ctrl_metric_args['y_true'] = ctrl_y_test
if 'y_score' in in_keys:
node_proba_1['y'] > node_metric['y_score']
ctrl_metric_args['y_score'] = ctrl_y_score
if 'probas_pred' in in_keys:
node_proba_1['y'] > node_metric['probas_pred']
ctrl_metric_args['probas_pred'] = ctrl_y_score
out_nodes = [
p.add(CSVWrite(self._tmp_files('out_{}.csv'.format(out_key))))
for out_key in out_keys
]
[
node_metric[out_key] > out_nodes[i]['input']
for i, out_key in enumerate(out_keys)
]
self.run_pipeline(p)
ctrl_returns = metric(**ctrl_metric_args)
if len(out_keys) == 1:
ctrl_returns = (ctrl_returns, )
for i, out_key in enumerate(out_keys):
control = ctrl_returns[i]
result = self._tmp_files.csv_read('out_{}.csv'.format(out_key),
as_nd=True)
self.assertTrue(result.shape == control.shape
and np.allclose(result, control))
def __simple_pipeline(self,
sk_cls,
sk_method_name,
upsg_out_key,
init_kwargs={},
in_data=None):
X_in, y_in = self.__process_in_data(in_data)
ctrl_sk_inst = sk_cls(**init_kwargs)
est_params = ctrl_sk_inst.get_params()
try:
random_state = est_params['random_state']
if random_state is None:
# This has to be fixed. Set a state and try again
init_kwargs['random_state'] = 0
ctrl_sk_inst = sk_cls(**init_kwargs)
except KeyError:
pass
p = Pipeline()
sk_stage = p.add(wrap_and_make_instance(sk_cls, **init_kwargs))
X_in_stage = p.add(NumpyRead(X_in))
y_in_stage = p.add(NumpyRead(y_in))
if sk_method_name == 'predict':
train_test = p.add(SplitTrainTest(2, random_state=0))
X_in_stage['output'] > train_test['input0']
y_in_stage['output'] > train_test['input1']
input_keys = sk_stage.get_stage().input_keys
if 'X_train' in input_keys:
train_test['train0'] > sk_stage['X_train']
if 'X_test' in input_keys:
train_test['test0'] > sk_stage['X_test']
if 'y_train' in input_keys:
train_test['train1'] > sk_stage['y_train']
else:
X_in_stage['output'] > sk_stage['X_train']
y_in_stage['output'] > sk_stage['y_train']
csv_out = p.add(CSVWrite(self._tmp_files.get('out.csv')))
sk_stage[upsg_out_key] > csv_out['input']
self.run_pipeline(p)
if sk_method_name == 'predict':
ctrl_X_train, ctrl_X_test, ctrl_y_train, ctrl_y_test = (
train_test_split(X_in, y_in, random_state=0))
ctrl_sk_inst.fit(ctrl_X_train, ctrl_y_train)
control = ctrl_sk_inst.predict(ctrl_X_test)
else:
control = ctrl_sk_inst.fit_transform(X_in, y_in)
result = self._tmp_files.csv_read('out.csv', as_nd=True)
if result.ndim != control.ndim and result.ndim == 1:
result = result.reshape(result.size, 1)
self.assertTrue(result.shape == control.shape
and np.allclose(result, control))
def test_wrap_cross_validation(self):
X = np.array([(0, 2001, 12.31), (1, 1999, 14.32), (2, 1999, 120.76),
(3, 2002, 32.12), (4, 2004, 98.64), (5, 2005, 32.21),
(6, 2002, 100.23), (7, 2006, 123.40), (8, 2000, 72.21)],
dtype=[('id', int), ('year', int), ('fine', float)])
y = np.array([(0, ), (1, ), (0, ), (1, ), (0, ), (1, ), (0, ), (1, ),
(0, )],
dtype=[('category', int)])
ctrl_inds = [([1, 2, 8], [0, 3, 6]), ([0, 3, 6], [4]), ([4], [5, 7])]
p = Pipeline()
node_X_in = p.add(NumpyRead(X))
node_y_in = p.add(NumpyRead(y))
node_just_time = p.add(SplitColumns(['year']))
node_just_time(node_X_in)
training_windows = by_window_ranges(1999, 2000, 2004, 2)
testing_windows = by_window_ranges(2001, 2002, 2006, 2)
mode = ByWindowMode.SLIDING
node_cv = p.add(
wrap_and_make_instance(
'upsg.transform.partition_iterators.ByWindow',
n_arrays=2,
training_windows=training_windows,
testing_windows=testing_windows,
mode=ByWindowMode.SLIDING))
node_cv(input0=node_X_in, input1=node_y_in, y=node_just_time)
self.assertEqual(len(node_cv.output_keys), 2 * 2 * len(ctrl_inds))
out_nodes = []
for i in xrange(len(ctrl_inds)):
train_node_X = p.add(NumpyWrite())
train_node_X(node_cv['train0_{}'.format(i)])
train_node_y = p.add(NumpyWrite())
train_node_y(node_cv['train1_{}'.format(i)])
test_node_X = p.add(NumpyWrite())
test_node_X(node_cv['test0_{}'.format(i)])
test_node_y = p.add(NumpyWrite())
test_node_y(node_cv['test1_{}'.format(i)])
out_nodes.append(
(train_node_X, train_node_y, test_node_X, test_node_y))
p.run()
for i, (train_node_X, train_node_y, test_node_X, test_node_y) in \
enumerate(out_nodes):
self.assertTrue(
np.array_equal(train_node_X.get_stage().result,
X[ctrl_inds[i][0]]))
self.assertTrue(
np.array_equal(train_node_y.get_stage().result,
y[ctrl_inds[i][0]]))
self.assertTrue(
np.array_equal(test_node_X.get_stage().result,
X[ctrl_inds[i][1]]))
self.assertTrue(
np.array_equal(test_node_y.get_stage().result,
y[ctrl_inds[i][1]]))