Skip to content

feat: update plot sample to 1000 rows #458

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 7 commits into from
Mar 21, 2024
Merged

feat: update plot sample to 1000 rows #458

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
a79e61a
feat: update plot sample to 1000 rows
tswast Mar 18, 2024
f42ee25
update test to use larger data for sampling
tswast Mar 19, 2024
ef3553b
Merge remote-tracking branch 'origin/main' into tswast-patch-1
tswast Mar 19, 2024
1d3bc4b
Merge remote-tracking branch 'origin/main' into tswast-patch-1
tswast Mar 20, 2024
e75774e
add constants for default values
tswast Mar 20, 2024
b0f7dd5
typo
tswast Mar 20, 2024
bbbb583
Merge remote-tracking branch 'origin/main' into tswast-patch-1
tswast Mar 21, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 7 additions & 2 deletions bigframes/operations/_matplotlib/core.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,6 +17,9 @@

import matplotlib.pyplot as plt

DEFAULT_SAMPLING_N = 1000
DEFAULT_SAMPLING_STATE = 0


class MPLPlot(abc.ABC):
@abc.abstractmethod
Expand Down Expand Up @@ -45,8 +48,10 @@ def generate(self) -> None:

def _compute_plot_data(self, data):
# TODO: Cache the sampling data in the PlotAccessor.
sampling_n = self.kwargs.pop("sampling_n", 100)
sampling_random_state = self.kwargs.pop("sampling_random_state", 0)
sampling_n = self.kwargs.pop("sampling_n", DEFAULT_SAMPLING_N)
sampling_random_state = self.kwargs.pop(
"sampling_random_state", DEFAULT_SAMPLING_STATE
)
return data.sample(
n=sampling_n,
random_state=sampling_random_state,
Expand Down
8 changes: 4 additions & 4 deletions tests/system/small/operations/test_plotting.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,6 +17,7 @@
import pandas._testing as tm
import pytest

import bigframes.operations._matplotlib.core as bf_mpl
import bigframes.pandas as bpd


Expand Down Expand Up @@ -209,19 +210,18 @@ def test_scatter(scalars_dfs):


def test_sampling_plot_args_n():
df = bpd.DataFrame(np.arange(1000), columns=["one"])
df = bpd.DataFrame(np.arange(bf_mpl.DEFAULT_SAMPLING_N * 10), columns=["one"])
ax = df.plot.line()
assert len(ax.lines) == 1
# Default sampling_n is 100
assert len(ax.lines[0].get_data()[1]) == 100
assert len(ax.lines[0].get_data()[1]) == bf_mpl.DEFAULT_SAMPLING_N

ax = df.plot.line(sampling_n=2)
assert len(ax.lines) == 1
assert len(ax.lines[0].get_data()[1]) == 2


def test_sampling_plot_args_random_state():
df = bpd.DataFrame(np.arange(1000), columns=["one"])
df = bpd.DataFrame(np.arange(bf_mpl.DEFAULT_SAMPLING_N * 10), columns=["one"])
ax_0 = df.plot.line()
ax_1 = df.plot.line()
ax_2 = df.plot.line(sampling_random_state=100)
Expand Down