superset/tests/dataframe_test.py
Rob DiCiuccio 6537d5ed8c Replace pandas.DataFrame with PyArrow.Table for nullable int typing (#8733)
* Use PyArrow Table for query result serialization

* Cleanup dev comments

* Additional cleanup

* WIP: tests

* Remove explicit dtype logic from db_engine_specs

* Remove obsolete  column property

* SupersetTable column types

* Port SupersetDataFrame methods to SupersetTable

* Add test for nullable boolean columns

* Support datetime values with timezone offsets

* Black formatting

* Pylint

* More linting/formatting

* Resolve issue with timezones not appearing in results

* Types

* Enable running of tests in tests/db_engine_specs

* Resolve application context errors

* Refactor and add tests for pyodbc.Row conversion

* Appease isort, regardless of isort:skip

* Re-enable RESULTS_BACKEND_USE_MSGPACK default based on benchmarks

* Dataframe typing and nits

* Renames to reduce ambiguity
2020-01-03 11:55:39 -05:00

52 lines
1.9 KiB
Python

# Licensed to the Apache Software Foundation (ASF) under one
# or more contributor license agreements. See the NOTICE file
# distributed with this work for additional information
# regarding copyright ownership. The ASF licenses this file
# to you under the Apache License, Version 2.0 (the
# "License"); you may not use this file except in compliance
# with the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing,
# software distributed under the License is distributed on an
# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
# KIND, either express or implied. See the License for the
# specific language governing permissions and limitations
# under the License.
import numpy as np
import pandas as pd
from superset.dataframe import df_to_records
from superset.db_engine_specs import BaseEngineSpec
from superset.result_set import SupersetResultSet
from .base_tests import SupersetTestCase
class SupersetDataFrameTestCase(SupersetTestCase):
def test_df_to_records(self):
data = [("a1", "b1", "c1"), ("a2", "b2", "c2")]
cursor_descr = (("a", "string"), ("b", "string"), ("c", "string"))
results = SupersetResultSet(data, cursor_descr, BaseEngineSpec)
df = results.to_pandas_df()
self.assertEqual(
df_to_records(df),
[{"a": "a1", "b": "b1", "c": "c1"}, {"a": "a2", "b": "b2", "c": "c2"}],
)
def test_js_max_int(self):
data = [(1, 1239162456494753670, "c1"), (2, 100, "c2")]
cursor_descr = (("a", "int"), ("b", "int"), ("c", "string"))
results = SupersetResultSet(data, cursor_descr, BaseEngineSpec)
df = results.to_pandas_df()
self.assertEqual(
df_to_records(df),
[
{"a": 1, "b": "1239162456494753670", "c": "c1"},
{"a": 2, "b": 100, "c": "c2"},
],
)