def test_sklearn_query():
sklearn_dataset = sklearn.datasets.load_iris()
sklearn_df = pd.DataFrame(data=sklearn_dataset.data,
columns=sklearn_dataset.feature_names)
iris = Table("dbo", "iris", [
Float("sepal length (cm)", 4, 8),
Float("sepal width (cm)", 2, 5),
Float("petal length (cm)", 1, 7),
Float("petal width (cm)", 0, 3)
], 150)
schema = CollectionMetadata([iris], "csv")
reader = PandasReader(sklearn_df, schema)
rowset = execute_private_query(
schema, reader, 0.3, 'SELECT AVG("petal width (cm)") FROM dbo.iris')
df = pd.DataFrame(rowset[1:], columns=rowset[0])
assert df is not None
assert len(df) == 1
def test_sklearn_query():
sklearn_dataset = sklearn.datasets.load_iris()
sklearn_df = pd.DataFrame(data=sklearn_dataset.data,
columns=sklearn_dataset.feature_names)
iris = Table("dbo", "iris", [
Float("sepal length (cm)", 4, 8),
Float("sepal width (cm)", 2, 5),
Float("petal length (cm)", 1, 7),
Float("petal width (cm)", 0, 3)
], 150)
schema = CollectionMetadata([iris], "csv")
reader = PandasReader(sklearn_df, schema)
# Calling both times for back compat check
for params in ([reader, schema], [schema, reader]):
df = execute_private_query(
*params, 0.3, 'SELECT AVG("petal width (cm)") FROM dbo.iris')
assert df is not None
assert len(df) == 1
iris_dataset_path = os.path.join(root_url, "service", "datasets", "iris.csv")
if not os.path.exists(iris_dataset_path):
sklearn_dataset = sklearn.datasets.load_iris()
sklearn_df = pd.DataFrame(data=sklearn_dataset.data,
columns=sklearn_dataset.feature_names)
sklearn_df.to_csv(iris_dataset_path)
iris_schema_path = os.path.join(root_url, "service", "datasets", "iris.yaml")
if not os.path.exists(iris_schema_path):
iris = Table("iris", "iris", [
Float("sepal length (cm)", 4, 8),
Float("sepal width (cm)", 2, 5),
Float("petal length (cm)", 1, 7),
Float("petal width (cm)", 0, 3)
], 150)
schema = CollectionMetadata([iris], "csv")
schema.to_file(iris_schema_path, "iris")
def find_ngrams(input_list, n):
return input_list if n == 1 else list(
zip(*[input_list[i:] for i in range(n)]))
def _download_file(url, local_file):
try:
from urllib import urlretrieve
except ImportError:
from urllib.request import urlretrieve
urlretrieve(url, local_file)