Skip to content

ENH: show percentiles in timestamp describe (#30164) #30209

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
Jan 20, 2020
Merged

ENH: show percentiles in timestamp describe (#30164) #30209

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
2f57671
ENH: show percentiles in timestamp describe (#30164)
david-cortes Jan 18, 2020
0082f81
use internal series methods for datetime describe (#30209)
david-cortes Jan 20, 2020
57a77db
more tests for datetimes describe
david-cortes Jan 20, 2020
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
11 changes: 11 additions & 0 deletions doc/source/whatsnew/v1.1.0.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,6 +21,17 @@ Other enhancements
-
-

.. ---------------------------------------------------------------------------

.. _whatsnew_110.api.other:

Other API changes
^^^^^^^^^^^^^^^^^

- :meth:`Series.describe` will now show distribution percentiles for ``datetime`` dtypes, statistics ``first`` and ``last``
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

can you move to api changes section.

will now be ``min`` and ``max`` to match with numeric dtypes in :meth:`DataFrame.describe` (:issue:`30164`)
-
-

.. ---------------------------------------------------------------------------

Expand Down
34 changes: 14 additions & 20 deletions pandas/core/generic.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9626,26 +9626,8 @@ def describe_categorical_1d(data):
dtype = None
if result[1] > 0:
top, freq = objcounts.index[0], objcounts.iloc[0]

if is_datetime64_any_dtype(data):
tz = data.dt.tz
asint = data.dropna().values.view("i8")
top = Timestamp(top)
if top.tzinfo is not None and tz is not None:
# Don't tz_localize(None) if key is already tz-aware
top = top.tz_convert(tz)
else:
top = top.tz_localize(tz)
names += ["top", "freq", "first", "last"]
result += [
top,
freq,
Timestamp(asint.min(), tz=tz),
Timestamp(asint.max(), tz=tz),
]
else:
names += ["top", "freq"]
result += [top, freq]
names += ["top", "freq"]
result += [top, freq]

# If the DataFrame is empty, set 'top' and 'freq' to None
# to maintain output shape consistency
Expand All @@ -9656,11 +9638,23 @@ def describe_categorical_1d(data):

return pd.Series(result, index=names, name=data.name, dtype=dtype)

def describe_timestamp_1d(data):
# GH-30164
stat_index = ["count", "mean", "min"] + formatted_percentiles + ["max"]
d = (
[data.count(), data.mean(), data.min()]
+ data.quantile(percentiles).tolist()
+ [data.max()]
)
return pd.Series(d, index=stat_index, name=data.name)

def describe_1d(data):
if is_bool_dtype(data):
return describe_categorical_1d(data)
elif is_numeric_dtype(data):
return describe_numeric_1d(data)
elif is_datetime64_any_dtype(data):
return describe_timestamp_1d(data)
elif is_timedelta64_dtype(data):
return describe_numeric_1d(data)
else:
Expand Down
45 changes: 6 additions & 39 deletions pandas/tests/frame/methods/test_describe.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -253,52 +253,19 @@ def test_describe_tz_values(self, tz_naive_fixture):

expected = DataFrame(
{
"s1": [
5,
np.nan,
np.nan,
np.nan,
np.nan,
np.nan,
2,
1.581139,
0,
1,
2,
3,
4,
],
"s1": [5, 2, 0, 1, 2, 3, 4, 1.581139],
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

do we have sufficient tests for timedeltas?

can you create a test for Period (which likely don't work), if you'd just xfail it (alt if you'd create an issue)

"s2": [
5,
5,
s2.value_counts().index[0],
1,
Timestamp(2018, 1, 3).tz_localize(tz),
start.tz_localize(tz),
s2[1],
s2[2],
s2[3],
end.tz_localize(tz),
np.nan,
np.nan,
np.nan,
np.nan,
np.nan,
np.nan,
np.nan,
],
},
index=[
"count",
"unique",
"top",
"freq",
"first",
"last",
"mean",
"std",
"min",
"25%",
"50%",
"75%",
"max",
],
index=["count", "mean", "min", "25%", "50%", "75%", "max", "std"],
)
result = df.describe(include="all")
tm.assert_frame_equal(result, expected)
Expand Down
41 changes: 36 additions & 5 deletions pandas/tests/series/methods/test_describe.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
import numpy as np

from pandas import Series, Timestamp, date_range
from pandas import Period, Series, Timedelta, Timestamp, date_range
import pandas._testing as tm


Expand Down Expand Up @@ -29,6 +29,36 @@ def test_describe(self):
)
tm.assert_series_equal(result, expected)

s = Series(
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

ok for now, in a followon we want to parameterize these.

[
Timedelta("1 days"),
Timedelta("2 days"),
Timedelta("3 days"),
Timedelta("4 days"),
Timedelta("5 days"),
],
name="timedelta_data",
)
result = s.describe()
expected = Series(
[5, s[2], s.std(), s[0], s[1], s[2], s[3], s[4]],
name="timedelta_data",
index=["count", "mean", "std", "min", "25%", "50%", "75%", "max"],
)
tm.assert_series_equal(result, expected)

s = Series(
[Period("2020-01", "M"), Period("2020-01", "M"), Period("2019-12", "M")],
name="period_data",
)
result = s.describe()
expected = Series(
[3, 2, s[0], 2],
name="period_data",
index=["count", "unique", "top", "freq"],
)
tm.assert_series_equal(result, expected)

def test_describe_empty_object(self):
# https://github.com/pandas-dev/pandas/issues/27183
s = Series([None, None], dtype=object)
Expand Down Expand Up @@ -57,13 +87,14 @@ def test_describe_with_tz(self, tz_naive_fixture):
expected = Series(
[
5,
5,
s.value_counts().index[0],
1,
Timestamp(2018, 1, 3).tz_localize(tz),
start.tz_localize(tz),
s[1],
s[2],
s[3],
end.tz_localize(tz),
],
name=name,
index=["count", "unique", "top", "freq", "first", "last"],
index=["count", "mean", "min", "25%", "50%", "75%", "max"],
)
tm.assert_series_equal(result, expected)