forked from pydata/xarray
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge remote-tracking branch 'upstream/main' into groupby-aggs-using-…
…numpy-groupies * upstream/main: Add groupby & resample benchmarks (pydata#5922) Fix plot.line crash for data of shape (1, N) in _title_for_slice on format_item (pydata#5948) Disable unit test comments (pydata#5946) Publish test results from workflow_run only (pydata#5947)
Showing
6 changed files
with
93 additions
and
37 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,39 +1,98 @@ | ||
import numpy as np | ||
import pandas as pd | ||
|
||
import xarray as xr | ||
|
||
from . import parameterized, requires_dask | ||
from . import _skip_slow, parameterized, requires_dask | ||
|
||
|
||
class GroupBy: | ||
def setup(self, *args, **kwargs): | ||
self.ds = xr.Dataset( | ||
self.n = 100 | ||
self.ds1d = xr.Dataset( | ||
{ | ||
"a": xr.DataArray(np.r_[np.arange(500.0), np.arange(500.0)]), | ||
"b": xr.DataArray(np.arange(1000.0)), | ||
"a": xr.DataArray(np.r_[np.repeat(1, self.n), np.repeat(2, self.n)]), | ||
"b": xr.DataArray(np.arange(2 * self.n)), | ||
} | ||
) | ||
self.ds2d = self.ds1d.expand_dims(z=10) | ||
|
||
@parameterized(["method"], [("sum", "mean")]) | ||
def time_agg(self, method): | ||
return getattr(self.ds.groupby("a"), method)() | ||
@parameterized(["ndim"], [(1, 2)]) | ||
def time_init(self, ndim): | ||
getattr(self, f"ds{ndim}d").groupby("b") | ||
|
||
@parameterized(["method", "ndim"], [("sum", "mean"), (1, 2)]) | ||
def time_agg_small_num_groups(self, method, ndim): | ||
ds = getattr(self, f"ds{ndim}d") | ||
getattr(ds.groupby("a"), method)() | ||
|
||
@parameterized(["method", "ndim"], [("sum", "mean"), (1, 2)]) | ||
def time_agg_large_num_groups(self, method, ndim): | ||
ds = getattr(self, f"ds{ndim}d") | ||
getattr(ds.groupby("b"), method)() | ||
|
||
|
||
class GroupByDask(GroupBy): | ||
def setup(self, *args, **kwargs): | ||
requires_dask() | ||
super().setup(**kwargs) | ||
self.ds = self.ds.chunk({"dim_0": 50}) | ||
self.ds1d = self.ds1d.sel(dim_0=slice(None, None, 2)).chunk({"dim_0": 50}) | ||
self.ds2d = self.ds2d.sel(dim_0=slice(None, None, 2)).chunk( | ||
{"dim_0": 50, "z": 5} | ||
) | ||
|
||
|
||
class GroupByDataFrame(GroupBy): | ||
class GroupByPandasDataFrame(GroupBy): | ||
"""Run groupby tests using pandas DataFrame.""" | ||
|
||
def setup(self, *args, **kwargs): | ||
# Skip testing in CI as it won't ever change in a commit: | ||
_skip_slow() | ||
|
||
super().setup(**kwargs) | ||
self.ds = self.ds.to_dataframe() | ||
self.ds1d = self.ds1d.to_dataframe() | ||
|
||
|
||
class GroupByDaskDataFrame(GroupBy): | ||
"""Run groupby tests using dask DataFrame.""" | ||
|
||
def setup(self, *args, **kwargs): | ||
# Skip testing in CI as it won't ever change in a commit: | ||
_skip_slow() | ||
|
||
requires_dask() | ||
super().setup(**kwargs) | ||
self.ds1d = self.ds1d.chunk({"dim_0": 50}).to_dataframe() | ||
|
||
|
||
class Resample: | ||
def setup(self, *args, **kwargs): | ||
self.ds1d = xr.Dataset( | ||
{ | ||
"b": ("time", np.arange(365.0 * 24)), | ||
}, | ||
coords={"time": pd.date_range("2001-01-01", freq="H", periods=365 * 24)}, | ||
) | ||
self.ds2d = self.ds1d.expand_dims(z=10) | ||
|
||
@parameterized(["ndim"], [(1, 2)]) | ||
def time_init(self, ndim): | ||
getattr(self, f"ds{ndim}d").resample(time="D") | ||
|
||
@parameterized(["method", "ndim"], [("sum", "mean"), (1, 2)]) | ||
def time_agg_small_num_groups(self, method, ndim): | ||
ds = getattr(self, f"ds{ndim}d") | ||
getattr(ds.resample(time="3M"), method)() | ||
|
||
@parameterized(["method", "ndim"], [("sum", "mean"), (1, 2)]) | ||
def time_agg_large_num_groups(self, method, ndim): | ||
ds = getattr(self, f"ds{ndim}d") | ||
getattr(ds.resample(time="48H"), method)() | ||
|
||
|
||
class ResampleDask(Resample): | ||
def setup(self, *args, **kwargs): | ||
requires_dask() | ||
super().setup(**kwargs) | ||
self.ds = self.ds.chunk({"dim_0": 50}).to_dataframe() | ||
self.ds1d = self.ds1d.chunk({"time": 50}) | ||
self.ds2d = self.ds2d.chunk({"time": 50, "z": 4}) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters