def test_build_schema(self):
illegal_col_regex = re.compile(r'\W|[A-Z]')
for dataset_name in self.TEST_DATASETS:
dataset = Dataset.create(self.test_dataset_ids[dataset_name])
Dataset.build_schema(dataset,
self.test_data[dataset_name].dtypes)
# get dataset with new schema
dataset = Dataset.find_one(self.test_dataset_ids[dataset_name])
for key in [CREATED_AT, SCHEMA, UPDATED_AT]:
self.assertTrue(key in dataset.keys())
df_columns = self.test_data[dataset_name].columns.tolist()
seen_columns = []
for column_name, column_attributes in dataset[SCHEMA].items():
# check column_name is unique
self.assertFalse(column_name in seen_columns)
seen_columns.append(column_name)
# check column name is only legal chars
self.assertFalse(illegal_col_regex.search(column_name))
# check has require attributes
self.assertTrue(SIMPLETYPE in column_attributes)
self.assertTrue(OLAP_TYPE in column_attributes)
self.assertTrue(LABEL in column_attributes)
# check label is an original column
self.assertTrue(column_attributes[LABEL] in df_columns)
df_columns.remove(column_attributes[LABEL])
# ensure all columns in df_columns have store columns
self.assertTrue(len(df_columns) == 0)
def get(self):
Dataset.deleteAll()
Dumpfile.deleteAll()
for dataset in yaml.load(open("predefined_datasets.yaml", 'r')):
Dataset(name=dataset['name'], voidURI=dataset['voidURI']).put()
return webapp2.redirect('/datasets')
def import_dataset(_file, dataset):
"""
For reading a URL and saving the corresponding dataset.
"""
dframe = read_csv(_file)
Dataset.build_schema(dataset, dframe.dtypes)
Observation.save(dframe, dataset)
def setUp(self):
TestBase.setUp(self)
self.dataset = Dataset.save(self.test_dataset_ids['good_eats.csv'])
Dataset.build_schema(self.dataset,
self.test_data['good_eats.csv'].dtypes)
self.formula = 'rating'
self.name = 'test'
def test_update(self):
for dataset_name in self.TEST_DATASETS:
dataset = Dataset.create(self.test_dataset_ids[dataset_name])
self.assertFalse('field' in dataset)
Dataset.update(dataset, {'field': {'key': 'value'}})
dataset = Dataset.find_one(self.test_dataset_ids[dataset_name])
self.assertTrue('field' in dataset)
self.assertEqual(dataset['field'], {'key': 'value'})
def test_find(self):
for dataset_name in self.TEST_DATASETS:
record = Dataset.save(self.test_dataset_ids[dataset_name])
cursor = Dataset.find(self.test_dataset_ids[dataset_name])
rows = [x for x in cursor]
self.assertTrue(isinstance(cursor, Cursor))
self.assertEqual(record, rows[0])
self.assertEqual(record, Dataset.find_one(
self.test_dataset_ids[dataset_name]))
def test_POST_remove_summary(self):
Datasets().GET(self.dataset_id, mode=MODE_SUMMARY)
dataset = Dataset.find_one(self.dataset_id)
self.assertTrue(isinstance(dataset[STATS], dict))
self.assertTrue(isinstance(dataset[STATS][ALL], dict))
self._post_formula()
# [STATS][ALL] should be removed
dataset = Dataset.find_one(self.dataset_id)
self.assertEqual(dataset[STATS].get(ALL), None)
def test_delete(self):
for dataset_name in self.TEST_DATASETS:
record = Dataset.save(self.test_dataset_ids[dataset_name])
records = [x for x in \
Dataset.find(self.test_dataset_ids[dataset_name])]
self.assertNotEqual(records, [])
Dataset.delete(self.test_dataset_ids[dataset_name])
records = [x for x in
Dataset.find(self.test_dataset_ids[dataset_name])]
self.assertEqual(records, [])
def DELETE(self, dataset_id):
"""
Delete observations (i.e. the dataset) with hash *dataset_id* from mongo
"""
dataset = Dataset.find_one(dataset_id)
result = None
if dataset:
Dataset.delete(dataset_id)
Observation.delete(dataset)
result = {SUCCESS: 'deleted dataset: %s' % dataset_id}
return dump_or_error(result, 'id not found')
def update(cls, dframe, dataset):
"""
Update *dataset* by overwriting all observations with the given
*dframe*.
"""
previous_dtypes = cls.find(dataset, as_df=True).dtypes.to_dict()
new_dtypes = dframe.dtypes.to_dict().items()
cols_to_add = dict([(name, dtype) for name, dtype in
new_dtypes if name not in previous_dtypes])
Dataset.update_schema(dataset, cols_to_add)
cls.delete(dataset)
cls.save(dframe, dataset)
return cls.find(dataset, as_df=True)
def combined_dataset(cls, ids, window_length):
dataset = Dataset.empty()
for id in ids:
session = cls.from_api(id)
windows = list(session.window_gen(window_length=window_length))
dataset = dataset + session.dataset(windows)
return dataset
def get(self, datasetID):
dataset = Dataset.get_by_id(long(datasetID))
crawl = Crawl(dataset=dataset, status='QUEUED')
crawl.put()
''' Queue the crawl immediately '''
crawl.queue(5)
return webapp2.redirect('/datasets/' + datasetID)
def __init__(self, exchange, period_start: datetime, period_end=None, interval=60, *args, **kwargs):
self.exchange = exchange
self.interval = interval
self.period_start = period_start
self.period_end = period_end
self.start = datetime.now()
self.dataset = Dataset().create(
data={'exchange': '/api/exchanges/'+self.exchange.name.lower(), 'periodStart': self.period_start, 'periodEnd': self.period_end,
'candleSize': 60,
'currency': '/api/currencies/'+self.exchange.currency.lower(), 'asset': '/api/currencies/'+self.exchange.asset.lower()})
def get(self, datasetID):
dataset = Dataset.get_by_id(long(datasetID))
for crawl in Crawl.all().filter('dataset =', dataset).run():
crawl.delete()
for dump in Dumpfile.all().filter('dataset =', dataset).run():
dump.delete()
dataset.delete()
logging.info('Deleted dataset ' + datasetID)
return webapp2.redirect('/datasets')
def dataset(self, windows, remove_seconds=0):
if len(windows) == 0:
return Dataset.empty()
n_samples = len(windows)
n_channels = len(self.ch_names)
window_length = np.shape(windows)[1]
X = np.empty([n_samples, n_channels, window_length])
y = np.empty([n_samples], dtype=np.int8)
for i, window in enumerate(windows):
X[i] = window[:, 0:n_channels].T
y[i] = int(max(window[:, -1]))
if remove_seconds > 0:
change_points = []
action_labels = []
for i in range(1, len(y), 1):
if y[i] != y[i - 1]:
change_points.append(i)
action_labels.append(np.max(y[i - 1:i + 1]))
remove_distance = (250 * remove_seconds) / window_length
keep_indices = []
for i in range(len(y)):
label = y[i]
if label == 0:
viable = True
for point in change_points:
if np.abs(i - point) <= remove_distance:
viable = False
if viable:
keep_indices.append(i)
else:
keep_indices.append(i)
X = X[keep_indices]
y = y[keep_indices]
return Dataset(X, y, self.person_id, self.id)
def start_dataset_creating():
start = datetime.datetime.now()
dataset_name = 'dataset_' + str(time.time()).replace('.', '')
dataset_dir = os.path.join(current_app.config['DATASET_DIR'], dataset_name)
os.makedirs(dataset_dir, exist_ok=True)
dataset = Dataset(name=dataset_name,
path=dataset_dir,
dt_start=start,
status=DatasetStatus.start,
type=DatasetType.top_one)
db.session.add(dataset)
db.session.commit()
collector = DatasetCollector(dataset_model=dataset)
try:
# TODO: добавить параметры датасета
collector.create_doctor_item_base_matrix()
collector.create_datasets_for_catboost(min_appts=10)
except Exception as e:
traceback.print_exc()
dataset.status = DatasetStatus.fail
dataset.error = str(e)
else:
dataset.status = DatasetStatus.end
finally:
dataset.dt_end = datetime.datetime.now()
db.session.add(dataset)
db.session.commit()
return redirect(url_for('dataset.main'))
def setUp(self):
TestBase.setUp(self)
self.dataset = Dataset.save(self.test_dataset_ids['good_eats.csv'])
dframe = self.test_data['good_eats.csv']
Dataset.build_schema(self.dataset, dframe.dtypes)
Observation.save(dframe, self.dataset)
self.calculations = [
'rating',
'gps',
'amount + gps_alt',
'amount - gps_alt',
'amount + 5',
'amount - gps_alt + 2.5',
'amount * gps_alt',
'amount / gps_alt',
'amount * gps_alt / 2.5',
'amount + gps_alt * gps_precision',
'(amount + gps_alt) * gps_precision',
'amount = 2',
'10 < amount',
'10 < amount + gps_alt',
'not amount = 2',
'not(amount = 2)',
'amount = 2 and 10 < amount',
'amount = 2 or 10 < amount',
'not not amount = 2 or 10 < amount',
'not amount = 2 or 10 < amount',
'(not amount = 2) or 10 < amount',
'not(amount = 2 or 10 < amount)',
'amount ^ 3',
'(amount + gps_alt) ^ 2 + 100',
'-amount',
'-amount < gps_alt - 100',
'rating in ["delectible"]',
'risk_factor in ["low_risk"]',
'amount in ["9.0", "2.0", "20.0"]',
'(risk_factor in ["low_risk"]) and (amount in ["9.0", "20.0"])',
]
self.places = 5
def parse_datasets(res):
soup = BeautifulSoup(res.text, 'html.parser')
views = soup.findAll('div', {'class': 'views-row'})
datasets = []
for view in views:
div = view.find('div', {'class': 'views-field-body'})
if div != -1:
el = div.find('a')
datasetid = el['href'].replace("/download/content/", "")
name = el.text
datasets.append(Dataset(datasetid, name))
return datasets
def create_dataset_from_csv(csv_file):
"""
Create a dataset from the uploaded .csv file.
"""
dataset_id = uuid.uuid4().hex
dataset = Dataset.create(dataset_id)
# need to write out to a named tempfile in order
# to get a handle in order for pandas read_csv
with tempfile.NamedTemporaryFile() as tmpfile:
tmpfile.write(read_uploaded_file(csv_file))
import_dataset(tmpfile.name, dataset)
return {ID: dataset_id}
def GET(self, dataset_id, mode=False, query='{}', select=None,
group=ALL):
"""
Return data set for hash *dataset_id*.
Execute query *query* in mongo if passed.
If summary is passed return summary statistics for data set.
If group is passed group the summary, if summary is false group is
ignored.
"""
dataset = Dataset.find_one(dataset_id)
result = None
try:
if dataset:
if mode == MODE_INFO:
result = Dataset.schema(dataset)
elif mode == MODE_SUMMARY:
result = summarize(dataset, query, select, group)
else:
return mongo_to_json(Observation.find(dataset, query,
select))
except JSONError, e:
result = {ERROR: e.__str__()}
def full_dataset_gen(cls, window_length, count=1, sessions=None):
if sessions is None:
Print.info("Fetching sessions")
sessions = Session.fetch_all(only_real=True,
include_timeframes=True)
for _ in range(count):
dataset = Dataset.empty()
for session in sessions:
windows = list(session.window_gen(window_length=window_length))
dataset = dataset + session.dataset(windows=windows)
yield dataset
def sample(self, n):
"""Sample a batch size n of experience"""
if len(self.memory) < n:
raise IndexError('Size of memory ({}) is less than requested sample ({})'.format(len(self), n))
else:
scores = [x[1] for x in self.memory]
sample = np.random.choice(len(self), size=n, replace=False, p=scores / np.sum(scores))
sample = [self.memory[i] for i in sample]
smiles = [x[0] for x in sample]
scores = [x[1] for x in sample]
prior_likelihood = [x[2] for x in sample]
tokenized = [self.voc.tokenize(smile) for smile in smiles]
encoded = [self.voc.encode(tokenized_i) for tokenized_i in tokenized]
encoded = Dataset.collate_fn(encoded)
return encoded, np.array(scores), np.array(prior_likelihood)
def summarize(dataset, query, select, group):
"""
Return a summary for the rows/values filtered by *query* and *select*
and grouped by *group* or the overall summary if no group is specified.
"""
# narrow list of observations via query/select
dframe = Observation.find(dataset, query, select, as_df=True)
# do not allow group by numeric types
# TODO check schema for valid groupby columns once included
_type = dframe.dtypes.get(group)
if group != ALL and (_type is None or _type.type != np.object_):
return {ERROR: "group: '%s' is not categorical." % group}
# check cached stats for group and update as necessary
stats = dataset.get(STATS, {})
if not stats.get(group):
stats = {ALL: summarize_df(dframe)} if group == ALL \
else summarize_with_groups(dframe, stats, group)
Dataset.update(dataset, {STATS: stats})
stats_to_return = stats.get(group)
return dict_from_mongo(stats_to_return if group == ALL else {group:
stats_to_return})
def _test_summary_no_group(self, results):
result_keys = results.keys()
print result_keys
print self.test_data[self._file_name].columns.tolist()
self.assertEqual(len(result_keys), self.NUM_COLS)
columns = [col for col in
self.test_data[self._file_name].columns.tolist()
if not col in MONGO_RESERVED_KEYS]
dataset = Dataset.find_one(self.dataset_id)
labels_to_slugs = build_labels_to_slugs(dataset)
for col in columns:
slug = labels_to_slugs[col]
self.assertTrue(slug in result_keys,
'col (slug): %s in: %s' % (slug, result_keys))
self.assertTrue(SUMMARY in results[slug].keys())
def generate_yaml_from_netCDF(nc_path, product_name, product_description,
no_data):
# Extract data from netCDF file
dataset = xarray.load_dataset(nc_path)
measurements = []
dims = [i for i in dataset.sizes.mapping.mapping]
for var in dataset:
ds_var = dataset[var].variable
if "units" in ds_var.attrs.keys():
measurements.append(
Measurement(
var,
ds_var.dtype.name,
ds_var.attrs["units"],
no_data,
Path(nc_path).name,
))
# Classes generation
dataset = Dataset(
product_name,
dataset.longitude.data,
dataset.latitude.data,
measurements,
)
product = Product(
product_name,
product_description,
measurements=measurements,
storage_driver="NetCDF CF",
storage_dimension_order=dims,
)
# YAML configuration
yaml.emitter.Emitter.process_tag = lambda self, *args, **kw: None
CWD = os.path.dirname(__file__)
# Product generation
with open(os.path.join(CWD, "./tests/product_generated.yaml"), "w") as f:
yaml.dump(product, f, sort_keys=False)
# Dataset generation
data = yaml.dump(dataset, sort_keys=False)
data = data.replace("'%", "")
data = data.replace("%'", "")
with open(os.path.join(CWD, "./tests/dataset_generated.yaml"), "w") as f:
f.write(data)
def get(self, datasetID):
startIn = self.request.get('start').split(':')
if len(startIn) == 2:
logging.info('Queuing harvest in ' + startIn[0] + ' hours ' + startIn[1] + ' minutes')
seconds = int(startIn[0]) * 3600 + int(startIn[1]) * 60
dataset = Dataset.get_by_id(long(datasetID))
''' TODO store 'interval' param in dataset object (if any) '''
crawl = Crawl(dataset=dataset, status='QUEUED')
crawl.put()
crawl.queue(seconds)
return webapp2.redirect('/datasets/' + datasetID)
else:
''' TODO decent error handling '''
logging.info('Invalid crawl time: ' + self.request.get('start'))
return webapp2.redirect('/datasets/' + datasetID + '?error=true')
def initiate_from_file(self, fname, scoring_function, Prior):
"""Adds experience from a file with SMILES
Needs a scoring function and an RNN to score the sequences"""
with open(fname, 'r') as f:
smiles = []
for line in f:
smile = line.split()[0]
if Chem.MolFromSmiles(smile):
smile = Chem.MolToSmiles(Chem.MolFromSmiles(smile), isomericSmiles=False)
smiles.append(smile)
scores = scoring_function(smiles)
tokenized = [self.voc.tokenize(smile) for smile in smiles]
encoded = [self.voc.encode(tokenized_i) for tokenized_i in tokenized]
encoded = Dataset.collate_fn(encoded)
prior_likelihood, _ = Prior.likelihood(encoded.long())
prior_likelihood = prior_likelihood.data.cpu().numpy()
new_experience = zip(smiles, scores, prior_likelihood)
self.add_experience(new_experience)
def create_dataset_from_url(url, allow_local_file=False):
"""
Load a URL, read from a CSV, create a dataset and return the unique ID.
"""
_file = None
try:
_file = open_data_file(url, allow_local_file)
except (IOError, urllib2.HTTPError):
# error reading file/url, return
pass
if not _file:
# could not get a file handle
return {ERROR: 'could not get a filehandle for: %s' % url}
dataset_id = uuid.uuid4().hex
dataset = Dataset.create(dataset_id)
import_dataset(_file, dataset)
return {ID: dataset_id}
def __init__(self, exchange: Exchange, timeout=60, *args, **kwargs):
super().__init__(exchange, timeout, *args, **kwargs)
self.buy_price = 0
self.sell_price = 0
self.stop_loss = 0
self.market_delta = 0
self.advised = False
self.waiting_order = False
self.fulfilled_orders = []
self.last_price = 0
# create a dataset for the session
self.dataset = Dataset().create(
data={
'exchange': self.exchange.name.lower(),
'periodStart': datetime.now(),
'candleSize': 60,
'currency': self.exchange.currency,
'asset': self.exchange.asset
})
def __init__(self,
exchange: Exchange,
period_start: datetime,
period_end=None,
interval=60):
self.launchedAt = datetime.now()
# Try to find dataset
dataset = Dataset().get({
"exchange": exchange.name.lower(),
"currency": exchange.currency.lower(),
"asset": exchange.asset.lower(),
"periodStart": period_start,
"periodEnd": period_end,
"candleSize": interval
})
if dataset and len(dataset) > 0:
print(dataset)
print(dataset[0])
print("Dataset found: " + dataset[0]['uuid'])
price = Price()
for prices in price.query('get', {"dataset": dataset[0]['uuid']}):
for price in prices:
print(price)
newPrice = Price()
newPrice.populate(price)
exchange.strategy.set_price(newPrice)
exchange.strategy.run()
else:
print("Dataset not found, external API call to " + exchange.name)
for price in exchange.historical_symbol_ticker_candle(
period_start, period_end, interval):
exchange.strategy.set_price(price)
exchange.strategy.run()
execution_time = datetime.now() - self.launchedAt
print('Execution time: ' + str(execution_time.total_seconds()) +
' seconds')
sys.exit(0)
config = yaml.safe_load(f) # load logger lc = config['environment']['log_config'] logging.config.fileConfig(lc) logs = logging.getLogger() # load device config cuda = config['environment']['cuda'] os.environ["CUDA_VISIBLE_DEVICES"] = "0" # load dataloader it = config['test']['image_root'] bs = 1 iz = None data = Dataset(it, iz, cuda) loader = DataLoader(data, bs, cuda) # load color transform network net_col = col.Generator(2) net_col = nn.DataParallel(net_col) net_col = net_col.cuda() if cuda else net_col # load temporal constraint network net_tem = tem.Generator(64) net_tem = nn.DataParallel(net_tem) net_tem = net_tem.cuda() if cuda else net_tem # load pretrained models # col_gen.load_state_dict(torch.load(test['load_pretrain_model'][0], map_location='cpu')) # tem_gen.load_state_dict(torch.load(test['load_pretrain_model'][1], map_location='cpu'))
elif mode == 'live':
exchange.start_symbol_ticker_socket(exchange.get_symbol())
elif mode == 'backtest':
period_start = config('PERIOD_START')
period_end = config('PERIOD_END')
print("Backtest period from {} to {} with {} seconds candlesticks.".format(
period_start, period_end, interval))
# Try to find dataset
dataset = Dataset().query(
'get', {
"exchange": '/api/exchanges/' + exchange.name.lower(),
"currency": '/api/currencies/' + currency.lower(),
"asset": '/api/currencies/' + asset.lower(),
"period_start": period_start,
"period_end": period_end,
"candleSize": interval
})
if dataset and len(dataset) > 0:
print(dataset[0])
price = Price()
for price in price.query('get', {"dataset": dataset[0]['uuid']}):
newPrice = Price()
newPrice.populate(price)
exchange.strategy.set_price(newPrice)
exchange.strategy.run()
else:
print("Dataset not found, external API call to " + exchange.name)
def get(self):
datasets = Dataset.all()
self.render_response('datasets/datasets_listall.html', **{'datasets':datasets})
def post(self):
dataset = Dataset(name=self.request.get('name'),
voidURI=self.request.get('voidURI'))
dataset.put()
return webapp2.redirect('/datasets')
except ParseError, err:
# do not save record, return error
return {ERROR: err}
record = {
DATASET_ID: dataset[DATASET_ID],
cls.FORMULA: formula,
cls.NAME: name,
}
cls.collection.insert(record)
# invalidate summary ALL since we have a new column
stats = dataset.get(STATS)
if stats:
del stats[ALL]
del dataset[STATS]
Dataset.update(dataset, {STATS: stats})
# call remote calculate and pass calculation id
calculate_column.delay(dataset, dframe, formula, name)
return mongo_remove_reserved_keys(record)
@classmethod
def find(cls, dataset):
"""
Return the calculations for given *dataset*.
"""
return [mongo_remove_reserved_keys(record) for record in cls.collection.find({
DATASET_ID: dataset[DATASET_ID],
})]
def test_save(self):
for dataset_name in self.TEST_DATASETS:
record = Dataset.save(self.test_dataset_ids[dataset_name])
self.assertTrue(isinstance(record, dict))
self.assertTrue('_id' in record.keys())
def get(self, datasetID):
dataset = Dataset.get_by_id(long(datasetID))
self.response.write(json.dumps(dataset.toJSON()))
def get(self, datasetID):
dataset = Dataset.get_by_id(long(datasetID))
self.render_response('datasets/datasets_show.html', **{'dataset':dataset})
def test_create(self):
for dataset_name in self.TEST_DATASETS:
dataset = Dataset.create(self.test_dataset_ids[dataset_name])
self.assertTrue(isinstance(dataset, dict))
from models.dataset import Dataset # Creating a dataset of dimension 2 in input and 3 in output dset = Dataset(2, 3) # Adding datapoints dset.add_xy([0.0, 1.0], [ 1.0, 2.0, 0.0]) dset.add_xy([1.0, 0.0], [ 0.0, 0.0, 2.0]) dset.add_xy([2.0,-1.0], [-1.0,-2.0, 4.0]) # Nearest neighbors queries on input, requesting 2 neighbors dset.nn_x([0.2, 0.5], 2) # Nearest neighbors queries on output, requesting 1 neighbors dist, index = dset.nn_y([1.0, 1.0, 1.0], 1) # Retrieving the nearest output of [1.0, 1.0, 1.0] print dset.get_y(index[0]) # Retrieving the nearest datapoint print dset.get_xy(index[0])
def _test_calculator(self, delay=True):
dframe = Observation.find(self.dataset, as_df=True)
columns = dframe.columns.tolist()
start_num_cols = len(columns)
added_num_cols = 0
column_labels_to_slugs = build_labels_to_slugs(self.dataset)
label_list, slugified_key_list = [list(ary) for ary in
zip(*column_labels_to_slugs.items())]
for idx, formula in enumerate(self.calculations):
name = 'test-%s' % idx
if delay:
task = calculate_column.delay(self.dataset, dframe,
formula, name)
# test that task has completed
self.assertTrue(task.ready())
self.assertTrue(task.successful())
else:
task = calculate_column(self.dataset, dframe,
formula, name)
column_labels_to_slugs = build_labels_to_slugs(self.dataset)
unslug_name = name
name = column_labels_to_slugs[unslug_name]
# test that updated dataframe persisted
dframe = Observation.find(self.dataset, as_df=True)
self.assertTrue(name in dframe.columns)
# test new number of columns
added_num_cols += 1
self.assertEqual(start_num_cols + added_num_cols,
len(dframe.columns.tolist()))
# test that the schema is up to date
dataset = Dataset.find_one(self.dataset[DATASET_ID])
self.assertTrue(SCHEMA in dataset.keys())
self.assertTrue(isinstance(dataset[SCHEMA], dict))
schema = dataset[SCHEMA]
# test slugified column names
slugified_key_list.append(name)
self.assertEqual(sorted(schema.keys()), sorted(slugified_key_list))
# test column labels
label_list.append(unslug_name)
labels = [schema[col][LABEL] for col in schema.keys()]
self.assertEqual(sorted(labels), sorted(label_list))
# test result of calculation
formula = column_labels_to_slugs[formula]
for idx, row in dframe.iterrows():
try:
result = np.float64(row[name])
stored = np.float64(row[formula])
# np.nan != np.nan, continue if we have two nan values
if np.isnan(result) and np.isnan(stored):
continue
msg = self._equal_msg(result, stored, formula)
self.assertAlmostEqual(result, stored, self.places, msg)
except ValueError:
msg = self._equal_msg(row[name], row[formula], formula)
self.assertEqual(row[name], row[formula], msg)
def setUp(self):
TestBase.setUp(self)
self.dataset = Dataset.save(self.test_dataset_ids['good_eats.csv'])
Dataset.build_schema(self.dataset,
self.test_data['good_eats.csv'].dtypes)