def test_update_form(app_fixture, model_fixtures):
test_client = app_fixture.test_client()
response = json_call(test_client.get, '/forms/beta-feedback')
assert response.status_code == 200
form = response.json
form['description'] = 'Form used to get feedback on beta.phila.gov'
response = json_call(test_client.put, '/forms/beta-feedback', form)
assert response.status_code == 200
assert dict_contains(
response.json, {
'name': 'beta-feedback',
'title': 'Beta Feedback Form',
'description': 'Form used to get feedback on beta.phila.gov',
'action': 'webhook',
'forms': [],
'schema': None,
'action_config': {
'url': 'https://example.com/webhook'
},
'max_submissions_per_minute': 5,
'created_at': iso_regex,
'updated_at': iso_regex
})
def test_create_form(app_fixture, model_fixtures):
test_client = app_fixture.test_client()
response = json_call(
test_client.post, '/forms', {
'name': 'my-form',
'title': 'My Form',
'action': 'webhook',
'action_config': {
'url': 'https://foo.com/webhook'
}
})
assert response.status_code == 201
assert dict_contains(
response.json, {
'name': 'my-form',
'title': 'My Form',
'description': None,
'action': 'webhook',
'forms': [],
'schema': None,
'action_config': {
'url': 'https://foo.com/webhook'
},
'max_submissions_per_minute': 5,
'created_at': iso_regex,
'updated_at': iso_regex
})
def loss_variance(cls, result, config=None):
if config['dataset_name'] not in _dataset_cache:
_dataset_cache[config['dataset_name']] = json_call(
config['dataset_name'])
dataset = _dataset_cache[config['dataset_name']]
n_valid = dataset.descr['n_valid']
p = cls.loss(result, config)
if p is None:
return None
return p * (1.0 - p) / (n_valid - 1)
def loss_variance(cls, result, config=None):
if config['dataset_name'] not in _dataset_cache:
_dataset_cache[config['dataset_name']] = json_call(
config['dataset_name'])
dataset = _dataset_cache[config['dataset_name']]
n_valid = dataset.descr['n_valid']
p = cls.loss(result, config)
if p is None:
return None
return p * (1.0 - p) / (n_valid - 1)
def test_submit_form(app_fixture, model_fixtures, monkeypatch):
mock_google_response = MockGoogleResponse()
def mock_google_recaptcha(data):
return mock_google_response
monkeypatch.setattr(resources, 'google_recaptcha', mock_google_recaptcha)
test_client = app_fixture.test_client()
response = json_call(test_client.post, '/forms/beta-feedback/submissions', {
'recaptcha': 'somerandomslug',
'what_happened': 'I have a suggestion or idea.',
'tell_us_more': 'Have more pictures of puppies.'
})
assert response.status_code == 204
response = json_call(test_client.get, '/submissions?form_name=beta-feedback')
assert response.status_code == 200
assert response.json['count'] == 1
assert response.json['page'] == 1
assert response.json['total_pages'] == 1
assert len(response.json['data']) == 1
assert dict_contains(response.json['data'][0], {
'id': 1,
'form': 'beta-feedback', ## TODO: form vs form_name ?
'status': 'submitted',
'data': {
'tell_us_more': 'Have more pictures of puppies.',
'what_happened': 'I have a suggestion or idea.'
},
'referrer': None,
'user_agent': 'werkzeug/0.12.2',
'ip': '127.0.0.1',
'worker_id': None,
'locked_at': None,
'retry_delay': 300,
'timeout': 600,
'attempts': 0,
'max_attempts': 1,
'created_at': iso_regex,
'updated_at': iso_regex
})
def test_list_forms(app_fixture, model_fixtures):
test_client = app_fixture.test_client()
response = json_call(test_client.get, '/forms')
assert response.status_code == 200
assert response.json['count'] == 2
assert response.json['page'] == 1
assert response.json['total_pages'] == 1
assert len(response.json['data']) == 2
assert dict_contains(
response.json['data'][0], {
'name': 'beta-feedback',
'title': 'Beta Feedback Form',
'description': None,
'action': 'webhook',
'forms': [],
'schema': None,
'action_config': {
'url': 'https://example.com/webhook'
},
'max_submissions_per_minute': 5,
'created_at': iso_regex,
'updated_at': iso_regex
})
assert dict_contains(
response.json['data'][1], {
'name': 'parks-contact-us',
'title': 'Parks and Recreation Contact Us Form',
'description':
'Primary ontact us form for the Parks and Recreation Department',
'action': 'store_only',
'forms': [],
'schema': None,
'action_config': None,
'max_submissions_per_minute': 5,
'created_at': iso_regex,
'updated_at': iso_regex
})
def preprocess_data(config, ctrl):
dataset = json_call(config['dataset_name'])
train, valid, test = classification_train_valid_test(dataset)
X_train, y_train = numpy.asarray(train[0]), numpy.asarray(train[1])
X_valid, y_valid = numpy.asarray(valid[0]), numpy.asarray(valid[1])
X_test, y_test = numpy.asarray(test[0]), numpy.asarray(test[1])
if config['preprocessing']['kind'] == 'pca':
# compute pca of input (TODO: retrieve only pca_whitened input)
raise NotImplementedError('rewrite since cut and paste')
(eigvals,eigvecs), centered_trainset = pylearn_pca.pca_from_examples(
X=dataset['inputs'][:dataset['n_train']],
max_energy_fraction=config['pca_energy'])
eigmean = dataset['inputs'][0] - centered_trainset[0]
whitened_inputs = pylearn_pca.pca_whiten((eigvals,eigvecs),
dataset['inputs']-eigmean)
ctrl.info('PCA kept %i of %i components'%(whitened_inputs.shape[1],
dataset['n_inputs']))
elif config['preprocessing']['kind'] == 'zca':
(eigvals,eigvecs), centered_trainset = pylearn_pca.pca_from_examples(
X=X_train,
max_energy_fraction=config['preprocessing']['energy'])
eigmean = X_train[0] - centered_trainset[0]
def whiten(X):
X = pylearn_pca.pca_whiten((eigvals,eigvecs),
X - eigmean)
X = pylearn_pca.pca_whiten_inverse((eigvals, eigvecs),
X) + eigmean
X = X.astype('float32')
X_min = X.min()
X_max = X.max()
ctrl.info('ZCA min:%f max:%f' % (X_min, X_max))
if X_min < 0 or X_max > 1.0:
ctrl.info('ZCA clamping return value to (0, 1) interval')
X = numpy.clip(X, 0, 1, out=X)
return X
X_train, X_valid, X_test = [whiten(X)
for X in [X_train, X_valid, X_test]]
elif config['preprocessing']['kind'] == 'normalize':
raise NotImplementedError('rewrite since cut and paste')
n_train=dataset['n_train']
whitened_inputs = dataset['inputs']
whitened_inputs = whitened_inputs - whitened_inputs[:n_train].mean(axis=0)
whitened_inputs /= whitened_inputs[:n_train].std(axis=0)+1e-7
elif config['preprocessing']['kind'] == 'raw':
pass
else:
raise ValueError(
'unrecognized preprocessing',
config['preprocessing']['kind'])
for Xy in 'X', 'y':
for suffix in 'train', 'valid', 'test':
varname = '%s_%s'%(Xy, suffix)
var = locals()[varname]
ctrl.info('%s shape=%s max=%f min=%f' % (
varname,
var.shape,
var.max(),
var.min()))
s_X_train = theano.shared(X_train)
s_y_train = theano.shared(y_train)
s_X_valid = theano.shared(X_valid)
s_y_valid = theano.shared(y_valid)
s_X_test = theano.shared(X_test)
s_y_test = theano.shared(y_test)
return (dataset,
(s_X_train, s_y_train),
(s_X_valid, s_y_valid),
(s_X_test, s_y_test))
def preprocess_data(config, ctrl):
dataset = json_call(config['dataset_name'])
train, valid, test = classification_train_valid_test(dataset)
X_train, y_train = numpy.asarray(train[0]), numpy.asarray(train[1])
X_valid, y_valid = numpy.asarray(valid[0]), numpy.asarray(valid[1])
X_test, y_test = numpy.asarray(test[0]), numpy.asarray(test[1])
if config['preprocessing']['kind'] == 'pca':
# compute pca of input (TODO: retrieve only pca_whitened input)
raise NotImplementedError('rewrite since cut and paste')
(eigvals, eigvecs), centered_trainset = pylearn_pca.pca_from_examples(
X=dataset['inputs'][:dataset['n_train']],
max_energy_fraction=config['pca_energy'])
eigmean = dataset['inputs'][0] - centered_trainset[0]
whitened_inputs = pylearn_pca.pca_whiten((eigvals, eigvecs),
dataset['inputs'] - eigmean)
ctrl.info('PCA kept %i of %i components' %
(whitened_inputs.shape[1], dataset['n_inputs']))
elif config['preprocessing']['kind'] == 'zca':
(eigvals, eigvecs), centered_trainset = pylearn_pca.pca_from_examples(
X=X_train, max_energy_fraction=config['preprocessing']['energy'])
eigmean = X_train[0] - centered_trainset[0]
def whiten(X):
X = pylearn_pca.pca_whiten((eigvals, eigvecs), X - eigmean)
X = pylearn_pca.pca_whiten_inverse((eigvals, eigvecs), X) + eigmean
X = X.astype('float32')
X_min = X.min()
X_max = X.max()
ctrl.info('ZCA min:%f max:%f' % (X_min, X_max))
if X_min < 0 or X_max > 1.0:
ctrl.info('ZCA clamping return value to (0, 1) interval')
X = numpy.clip(X, 0, 1, out=X)
return X
X_train, X_valid, X_test = [
whiten(X) for X in [X_train, X_valid, X_test]
]
elif config['preprocessing']['kind'] == 'normalize':
raise NotImplementedError('rewrite since cut and paste')
n_train = dataset['n_train']
whitened_inputs = dataset['inputs']
whitened_inputs = whitened_inputs - whitened_inputs[:n_train].mean(
axis=0)
whitened_inputs /= whitened_inputs[:n_train].std(axis=0) + 1e-7
elif config['preprocessing']['kind'] == 'raw':
pass
else:
raise ValueError('unrecognized preprocessing',
config['preprocessing']['kind'])
for Xy in 'X', 'y':
for suffix in 'train', 'valid', 'test':
varname = '%s_%s' % (Xy, suffix)
var = locals()[varname]
ctrl.info('%s shape=%s max=%f min=%f' %
(varname, var.shape, var.max(), var.min()))
s_X_train = theano.shared(X_train)
s_y_train = theano.shared(y_train)
s_X_valid = theano.shared(X_valid)
s_y_valid = theano.shared(y_valid)
s_X_test = theano.shared(X_test)
s_y_test = theano.shared(y_test)
return (dataset, (s_X_train, s_y_train), (s_X_valid, s_y_valid),
(s_X_test, s_y_test))
