def test_metadata():
all_datasets = Dataset.list_datasets()
local_datasets = Dataset.list_local_datasets()
for name in all_datasets:
dataobj = getattr(data, name.replace("-", "_"))
if name in local_datasets:
# Local datasets should all have a description defined
assert len(dataobj.description) > 0
assert len(dataobj.filepath) > 0
else:
with pytest.raises(ValueError) as err:
dataobj.filepath
assert str(
err.value) == "filepath is only valid for local datasets"
# Descriptions should either be defined, or be None
assert dataobj.description is None or len(dataobj.description) > 0
# References should either be a list, or be None
assert dataobj.references is None or type(dataobj.references) is list
def _download_datasets():
"""Utility to download datasets into package source"""
def filepath(*args):
return abspath(join(dirname(__file__), '..', 'vega_datasets', *args))
dataset_listing = {}
for name in DATASETS_TO_DOWNLOAD:
data = Dataset(name)
url = data.url
filename = filepath('data', data.filename)
print("retrieving data {0} -> {1}".format(url, filename))
urlretrieve(url, filename)
dataset_listing[name] = 'data/{0}'.format(data.filename)
with open(filepath('local_datasets.json'), 'w') as f:
json.dump(dataset_listing, f, indent=2)
def _download_datasets():
"""Utility to download datasets into package source"""
def filepath(*args):
return abspath(join(dirname(__file__), "..", "vega_datasets", *args))
dataset_listing = {}
for name in DATASETS_TO_DOWNLOAD:
data = Dataset(name)
url = data.url
filename = filepath("_data", data.filename)
print("retrieving data {0} -> {1}".format(url, filename))
urlretrieve(url, filename)
dataset_listing[name] = "_data/{0}".format(data.filename)
with open(filepath("local_datasets.json"), "w") as f:
json.dump(dataset_listing, f, indent=2, sort_keys=True)
def test_local_data_dirlist():
assert set(dir(local_data)) == {
name.replace("-", "_")
for name in Dataset.list_local_datasets()
}
import pandas as pd
from pandas.testing import assert_frame_equal
import pytest
from vega_datasets import data, local_data
from vega_datasets.core import Dataset
@pytest.mark.parametrize("name", Dataset.list_local_datasets())
def test_load_local_dataset(name):
loader = getattr(data, name.replace("-", "_"))
local_loader = getattr(local_data, name.replace("-", "_"))
df1 = data(name)
df2 = loader() # equivalent to data.dataset_name()
df3 = local_data(name)
df4 = local_loader() # equivalent to local_data.dataset_name()
assert_frame_equal(df1, df2)
assert_frame_equal(df1, df3)
assert_frame_equal(df1, df4)
raw1 = loader.raw()
raw2 = local_loader.raw()
raw3 = data(name, return_raw=True)
raw4 = local_data(name, return_raw=True)
assert raw1 == raw2 == raw3 == raw4
assert type(raw1) is type(raw2) is type(raw3) is type(raw4) is bytes
def test_iris_column_names():
iris = data.iris()
def __init__(self, name):
Dataset.__init__(self, name)
self.url = 'https://raw.githubusercontent.com/korakot/thailand-hex-map/master/data/thailand-topo.json'
def test_undefined_infodict():
with pytest.raises(ValueError) as err:
Dataset._infodict("blahblahblah")
assert str(err.value).startswith("No such dataset blahblahblah exists")
import pytest
from vega_datasets import data, local_data
from vega_datasets.core import Dataset
def test_undefined_dataset():
with pytest.raises(AttributeError) as err:
data("blahblahblah")
assert str(err.value) == "No dataset named 'blahblahblah'"
with pytest.raises(AttributeError) as err:
local_data("blahblahblah")
assert str(err.value) == "No dataset named 'blahblahblah'"
def test_undefined_infodict():
with pytest.raises(ValueError) as err:
Dataset._infodict("blahblahblah")
assert str(err.value).startswith("No such dataset blahblahblah exists")
@pytest.mark.parametrize(
"name",
(set(Dataset.list_datasets()) - set(Dataset.list_local_datasets())))
def test_local_dataset_error(name):
with pytest.raises(ValueError) as err:
local_data(name)
assert str(err.value).startswith("'{0}' dataset is not available locally"
"".format(name.replace("-", "_")))
def test_undefined_infodict():
with pytest.raises(ValueError) as err:
info = Dataset._infodict('blahblahblah')
assert str(err.value).startswith('No such dataset blahblahblah exists')