Skip to content

fix: plot.scatter s parameter cannot accept float-like column #563

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 3 commits into from
Apr 3, 2024
Merged

fix: plot.scatter s parameter cannot accept float-like column #563

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
12da4a2
fix: plot.scatter s parameter cannot accept float-like column
chelsea-lin Apr 2, 2024
4e78ca1
fixing lint
chelsea-lin Apr 2, 2024
a0091c6
addressing comments
chelsea-lin Apr 3, 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
19 changes: 12 additions & 7 deletions bigframes/operations/_matplotlib/core.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,7 +14,6 @@

import abc
import typing
import uuid

import pandas as pd

Expand Down Expand Up @@ -115,6 +114,18 @@ def _compute_plot_data(self):
if self._is_column_name(c, sample) and sample[c].dtype == dtypes.STRING_DTYPE:
sample[c] = sample[c].astype("object")

# To avoid Matplotlib's automatic conversion of `Float64` or `Int64` columns
# to `object` types (which breaks float-like behavior), this code proactively
# converts the column to a compatible format.
s = self.kwargs.get("s", None)
if pd.core.dtypes.common.is_integer(s):
s = self.data.columns[s]
if self._is_column_name(s, sample):
if sample[s].dtype == dtypes.INT_DTYPE:
sample[s] = sample[s].astype("int64")
elif sample[s].dtype == dtypes.FLOAT_DTYPE:
sample[s] = sample[s].astype("float64")

return sample

def _is_sequence_arg(self, arg):
Expand All @@ -130,9 +141,3 @@ def _is_column_name(self, arg, data):
and pd.core.dtypes.common.is_hashable(arg)
and arg in data.columns
)

def _generate_new_column_name(self, data):
col_name = None
while col_name is None or col_name in data.columns:
col_name = f"plot_temp_{str(uuid.uuid4())[:8]}"
return col_name
26 changes: 26 additions & 0 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 @@ -240,6 +240,32 @@ def test_scatter_args_c(c):
)


@pytest.mark.parametrize(
("s"),
[
pytest.param([10, 34, 50], id="int"),
pytest.param([1.0, 3.4, 5.0], id="float"),
pytest.param(
[True, True, False], id="bool", marks=pytest.mark.xfail(raises=ValueError)
),
],
)
def test_scatter_args_s(s):
data = {
"a": [1, 2, 3],
"b": [1, 2, 3],
}
data["s"] = s
df = bpd.DataFrame(data)
pd_df = pd.DataFrame(data)

ax = df.plot.scatter(x="a", y="b", s="s")
pd_ax = pd_df.plot.scatter(x="a", y="b", s="s")
tm.assert_numpy_array_equal(
ax.collections[0].get_sizes(), pd_ax.collections[0].get_sizes()
)


@pytest.mark.parametrize(
("arg_name"),
[
Expand Down