def test_group_runs(root, schema, encoding, **unused):
with tempdir(cleanup_on_error=CLEANUP_ON_ERROR):
with loom.preql.get_server(root, encoding, debug=True) as preql:
test_columns = json_load(schema).keys()[:10]
for column in test_columns:
groupings_csv = 'group.{}.csv'.format(column)
preql.group(column, result_out=groupings_csv)
print open(groupings_csv).read()
def test_group_runs(root, schema, encoding, **unused):
with tempdir(cleanup_on_error=CLEANUP_ON_ERROR):
with loom.preql.get_server(root, encoding, debug=True) as preql:
test_columns = json_load(schema).keys()[:10]
for column in test_columns:
groupings_csv = 'group.{}.csv'.format(column)
preql.group(column, result_out=groupings_csv)
print open(groupings_csv).read()
def test_group_pandas(root, rows_csv, rows, **unused):
row_count = sum(1 for _ in protobuf_stream_load(rows))
with loom.preql.get_server(root, debug=True) as preql:
feature_names = preql.feature_names
for feature in feature_names[:10]:
result_string = preql.group(feature)
result_df = pandas.read_csv(StringIO(result_string), index_col=0)
print 'result_df ='
print result_df
assert_equal(result_df.ndim, 2)
assert_equal(result_df.shape[0], row_count)
assert_equal(result_df.shape[1], 2)
def test_group_pandas(root, rows_csv, rows, **unused):
row_count = sum(1 for _ in protobuf_stream_load(rows))
with loom.preql.get_server(root, debug=True) as preql:
feature_names = preql.feature_names
for feature in feature_names[:10]:
result_string = preql.group(feature)
result_df = pandas.read_csv(StringIO(result_string), index_col=0)
print 'result_df ='
print result_df
assert_equal(result_df.ndim, 2)
assert_equal(result_df.shape[0], row_count)
assert_equal(result_df.shape[1], 2)
