How to use swifter - 10 common examples
To help you get started, we’ve selected a few swifter examples, based on popular ways it is used in public projects.
Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.
jmcarpenter2 / swifter / swifter / swifter_tests.py View on Github 
def test_set_dask_threshold(self):
LOG.info("test_set_dask_threshold")
expected = 1000
for swifter_df in [
pd.DataFrame().swifter,
pd.Series().swifter,
pd.DataFrame(
{"x": np.arange(0, 10)}, index=pd.date_range("2019-01-1", "2020-01-1", periods=10)
).swifter.rolling("1d"),
pd.DataFrame(
{"x": np.arange(0, 10)}, index=pd.date_range("2019-01-1", "2020-01-1", periods=10)
).swifter.resample("3T"),
]:
before = swifter_df._dask_threshold
swifter_df.set_dask_threshold(expected)
actual = swifter_df._dask_threshold
self.assertEqual(actual, expected)
self.assertNotEqual(before, actual)def test_disable_progress_bar(self):
LOG.info("test_disable_progress_bar")
expected = False
for swifter_df in [
pd.DataFrame().swifter,
pd.Series().swifter,
pd.DataFrame(
{"x": np.arange(0, 10)}, index=pd.date_range("2019-01-1", "2020-01-1", periods=10)
).swifter.rolling("1d"),
pd.DataFrame(
{"x": np.arange(0, 10)}, index=pd.date_range("2019-01-1", "2020-01-1", periods=10)
).swifter.resample("3T"),
]:
before = swifter_df._progress_bar
swifter_df.progress_bar(expected)
actual = swifter_df._progress_bar
self.assertEqual(actual, expected)
self.assertNotEqual(before, actual)def test_set_dask_scheduler(self):
LOG.info("test_set_dask_scheduler")
expected = "my-scheduler"
for swifter_df in [
pd.DataFrame().swifter,
pd.Series().swifter,
pd.DataFrame(
{"x": np.arange(0, 10)}, index=pd.date_range("2019-01-1", "2020-01-1", periods=10)
).swifter.rolling("1d"),
pd.DataFrame(
{"x": np.arange(0, 10)}, index=pd.date_range("2019-01-1", "2020-01-1", periods=10)
).swifter.resample("3T"),
]:
before = swifter_df._scheduler
swifter_df.set_dask_scheduler(expected)
actual = swifter_df._scheduler
self.assertEqual(actual, expected)
self.assertNotEqual(before, actual)def test_set_npartitions(self):
LOG.info("test_set_npartitions")
for swifter_df, set_npartitions, expected in zip(
[
pd.DataFrame().swifter,
pd.Series().swifter,
pd.DataFrame(
{"x": np.arange(0, 10)}, index=pd.date_range("2019-01-1", "2020-01-1", periods=10)
).swifter.rolling("1d"),
pd.DataFrame(
{"x": np.arange(0, 10)}, index=pd.date_range("2019-01-1", "2020-01-1", periods=10)
).swifter.resample("3T"),
],
[None, 1000, 1001, 1002],
[cpu_count() * 2, 1000, 1001, 1002],
):
before = swifter_df._npartitions
swifter_df.set_npartitions(set_npartitions)
actual = swifter_df._npartitions
self.assertEqual(actual, expected)
if set_npartitions is not None:
self.assertNotEqual(before, actual)def test_set_dask_threshold(self):
LOG.info("test_set_dask_threshold")
expected = 1000
for swifter_df in [
pd.DataFrame().swifter,
pd.Series().swifter,
pd.DataFrame(
{"x": np.arange(0, 10)}, index=pd.date_range("2019-01-1", "2020-01-1", periods=10)
).swifter.rolling("1d"),
pd.DataFrame(
{"x": np.arange(0, 10)}, index=pd.date_range("2019-01-1", "2020-01-1", periods=10)
).swifter.resample("3T"),
]:
before = swifter_df._dask_threshold
swifter_df.set_dask_threshold(expected)
actual = swifter_df._dask_threshold
self.assertEqual(actual, expected)
self.assertNotEqual(before, actual)def test_set_npartitions(self):
LOG.info("test_set_npartitions")
for swifter_df, set_npartitions, expected in zip(
[
pd.DataFrame().swifter,
pd.Series().swifter,
pd.DataFrame(
{"x": np.arange(0, 10)}, index=pd.date_range("2019-01-1", "2020-01-1", periods=10)
).swifter.rolling("1d"),
pd.DataFrame(
{"x": np.arange(0, 10)}, index=pd.date_range("2019-01-1", "2020-01-1", periods=10)
).swifter.resample("3T"),
],
[None, 1000, 1001, 1002],
[cpu_count() * 2, 1000, 1001, 1002],
):
before = swifter_df._npartitions
swifter_df.set_npartitions(set_npartitions)
actual = swifter_df._npartitions
self.assertEqual(actual, expected)
if set_npartitions is not None:
self.assertNotEqual(before, actual)def test_disable_progress_bar(self):
LOG.info("test_disable_progress_bar")
expected = False
for swifter_df in [
pd.DataFrame().swifter,
pd.Series().swifter,
pd.DataFrame(
{"x": np.arange(0, 10)}, index=pd.date_range("2019-01-1", "2020-01-1", periods=10)
).swifter.rolling("1d"),
pd.DataFrame(
{"x": np.arange(0, 10)}, index=pd.date_range("2019-01-1", "2020-01-1", periods=10)
).swifter.resample("3T"),
]:
before = swifter_df._progress_bar
swifter_df.progress_bar(expected)
actual = swifter_df._progress_bar
self.assertEqual(actual, expected)
self.assertNotEqual(before, actual)def test_set_dask_scheduler(self):
LOG.info("test_set_dask_scheduler")
expected = "my-scheduler"
for swifter_df in [
pd.DataFrame().swifter,
pd.Series().swifter,
pd.DataFrame(
{"x": np.arange(0, 10)}, index=pd.date_range("2019-01-1", "2020-01-1", periods=10)
).swifter.rolling("1d"),
pd.DataFrame(
{"x": np.arange(0, 10)}, index=pd.date_range("2019-01-1", "2020-01-1", periods=10)
).swifter.resample("3T"),
]:
before = swifter_df._scheduler
swifter_df.set_dask_scheduler(expected)
actual = swifter_df._scheduler
self.assertEqual(actual, expected)
self.assertNotEqual(before, actual)def setUp(self):
LOG.info(f"Version {swifter.__version__}")
self.addTypeEqualityFunc(pd.Series, self.assertSeriesEqual)
self.addTypeEqualityFunc(pd.DataFrame, self.assertDataFrameEqual)
self.ncores = cpu_count()def setUp(self):
LOG.info(f"Version {swifter.__version__}")
self.addTypeEqualityFunc(pd.Series, self.assertSeriesEqual)
self.addTypeEqualityFunc(pd.DataFrame, self.assertDataFrameEqual)
self.ncores = cpu_count()swifter
A package which efficiently applies any function to a pandas dataframe or series in the fastest available manner
