Skip to content
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

Jump to bottom

Include missing data count in pd.DataFrame.describe() #26102

Closed
wants to merge 4 commits into from
Closed

Include missing data count in pd.DataFrame.describe() #26102

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
1627cd3
Include missing data count in pd.DataFrame.describe
alexander-ponomaroff Apr 15, 2019
f40bad3
Changed missing to size
alexander-ponomaroff Apr 27, 2019
cc13046
Merge
alexander-ponomaroff Apr 27, 2019
5398274
Documentation fix
alexander-ponomaroff Apr 27, 2019
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
3 changes: 1 addition & 2 deletions doc/source/whatsnew/v0.25.0.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -412,8 +412,7 @@ Other

- Improved :class:`Timestamp` type checking in various datetime functions to prevent exceptions when using a subclassed `datetime` (:issue:`25851`)
- Bug in :class:`Series` and :class:`DataFrame` repr where ``np.datetime64('NaT')`` and ``np.timedelta64('NaT')`` with ``dtype=object`` would be represented as ``NaN`` (:issue:`25445`)
-
-
- Added enhancement to :func:`pd.DataFrame.describe` to include missing data count as one of the summary statistics (:issue:`21689`)


.. _whatsnew_0.250.contributors:
Expand Down
5 changes: 3 additions & 2 deletions pandas/core/generic.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9802,9 +9802,10 @@ def describe(self, percentiles=None, include=None, exclude=None):

def describe_numeric_1d(series):
stat_index = (['count', 'mean', 'std', 'min'] +
formatted_percentiles + ['max'])
formatted_percentiles + ['max', 'missing'])
d = ([series.count(), series.mean(), series.std(), series.min()] +
Copy link
Contributor

Choose a reason for hiding this comment

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

should be the first arg

series.quantile(percentiles).tolist() + [series.max()])
series.quantile(percentiles).tolist() + [series.max(),
series.isna().sum()])
return pd.Series(d, index=stat_index, name=series.name)

def describe_categorical_1d(data):
Expand Down
65 changes: 40 additions & 25 deletions pandas/tests/frame/test_analytics.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -505,6 +505,19 @@ def test_corrwith_kendall(self):
# ---------------------------------------------------------------------
# Describe

def test_missing_describe(self):
df = pd.DataFrame(data={'col1': [1, np.nan],
'col2': [3, 4]})
result = df.describe()

expected = pd.DataFrame({'col1': [1, 1, np.nan, 1, 1, 1, 1, 1, 1],
'col2': [2, 3.5, 0.707107, 3, 3.25, 3.5,
3.75, 4, 0]},
index=['count', 'mean', 'std', 'min', '25%',
'50%', '75%', 'max', 'missing'])

tm.assert_frame_equal(result, expected)

def test_bool_describe_in_mixed_frame(self):
df = DataFrame({
'string_data': ['a', 'b', 'c', 'd', 'e'],
Expand All @@ -516,9 +529,9 @@ def test_bool_describe_in_mixed_frame(self):
# Boolean and string data are not.
result = df.describe()
expected = DataFrame({'int_data': [5, 30, df.int_data.std(),
10, 20, 30, 40, 50]},
10, 20, 30, 40, 50, 0]},
index=['count', 'mean', 'std', 'min', '25%',
'50%', '75%', 'max'])
'50%', '75%', 'max', 'missing'])
tm.assert_frame_equal(result, expected)

# Top value is a boolean value that is False
Expand Down Expand Up @@ -546,9 +559,9 @@ def test_describe_bool_frame(self):
})
result = df.describe()
expected = DataFrame({'int_data': [5, 2, df.int_data.std(), 0, 1,
2, 3, 4]},
2, 3, 4, 0]},
index=['count', 'mean', 'std', 'min', '25%',
'50%', '75%', 'max'])
'50%', '75%', 'max', 'missing'])
tm.assert_frame_equal(result, expected)

df = pd.DataFrame({
Expand Down Expand Up @@ -605,11 +618,11 @@ def test_describe_categorical_columns(self):
categories=['int1', 'int2', 'obj'],
ordered=True, name='XXX')
expected = DataFrame({'int1': [5, 30, df.int1.std(),
10, 20, 30, 40, 50],
10, 20, 30, 40, 50, 0],
'int2': [5, 30, df.int2.std(),
10, 20, 30, 40, 50]},
10, 20, 30, 40, 50, 0]},
index=['count', 'mean', 'std', 'min', '25%',
'50%', '75%', 'max'],
'50%', '75%', 'max', 'missing'],
columns=exp_columns)
tm.assert_frame_equal(result, expected)
tm.assert_categorical_equal(result.columns.values,
Expand All @@ -627,11 +640,11 @@ def test_describe_datetime_columns(self):
exp_columns = pd.DatetimeIndex(['2011-01-01', '2011-02-01'],
freq='MS', tz='US/Eastern', name='XXX')
expected = DataFrame({0: [5, 30, df.iloc[:, 0].std(),
10, 20, 30, 40, 50],
10, 20, 30, 40, 50, 0],
1: [5, 30, df.iloc[:, 1].std(),
10, 20, 30, 40, 50]},
10, 20, 30, 40, 50, 0]},
index=['count', 'mean', 'std', 'min', '25%',
'50%', '75%', 'max'])
'50%', '75%', 'max', 'missing'])
expected.columns = exp_columns
tm.assert_frame_equal(result, expected)
assert result.columns.freq == 'MS'
Expand All @@ -649,29 +662,30 @@ def test_describe_timedelta_values(self):
pd.Timedelta('2 days'),
pd.Timedelta('3 days'),
pd.Timedelta('4 days'),
pd.Timedelta('5 days')],
pd.Timedelta('5 days'), 0],
't2': [5, pd.Timedelta('3 hours'),
df.iloc[:, 1].std(),
pd.Timedelta('1 hours'),
pd.Timedelta('2 hours'),
pd.Timedelta('3 hours'),
pd.Timedelta('4 hours'),
pd.Timedelta('5 hours')]},
pd.Timedelta('5 hours'), 0]},
index=['count', 'mean', 'std', 'min', '25%',
'50%', '75%', 'max'])
'50%', '75%', 'max', 'missing'])

result = df.describe()
tm.assert_frame_equal(result, expected)

exp_repr = (" t1 t2\n"
"count 5 5\n"
"mean 3 days 00:00:00 0 days 03:00:00\n"
"std 1 days 13:56:50.394919 0 days 01:34:52.099788\n"
"min 1 days 00:00:00 0 days 01:00:00\n"
"25% 2 days 00:00:00 0 days 02:00:00\n"
"50% 3 days 00:00:00 0 days 03:00:00\n"
"75% 4 days 00:00:00 0 days 04:00:00\n"
"max 5 days 00:00:00 0 days 05:00:00")
exp_repr = (" t1 t2\n"
"count 5 5\n"
"mean 3 days 00:00:00 0 days 03:00:00\n"
"std 1 days 13:56:50.394919 0 days 01:34:52.099788\n"
"min 1 days 00:00:00 0 days 01:00:00\n"
"25% 2 days 00:00:00 0 days 02:00:00\n"
"50% 3 days 00:00:00 0 days 03:00:00\n"
"75% 4 days 00:00:00 0 days 04:00:00\n"
"max 5 days 00:00:00 0 days 05:00:00\n"
"missing 0 0")
assert repr(result) == exp_repr

def test_describe_tz_values(self, tz_naive_fixture):
Expand All @@ -684,14 +698,15 @@ def test_describe_tz_values(self, tz_naive_fixture):
df = pd.DataFrame({'s1': s1, 's2': s2})

expected = DataFrame({'s1': [5, np.nan, np.nan, np.nan, np.nan, np.nan,
2, 1.581139, 0, 1, 2, 3, 4],
2, 1.581139, 0, 1, 2, 3, 4, 0],
's2': [5, 5, s2.value_counts().index[0], 1,
start.tz_localize(tz),
end.tz_localize(tz), np.nan, np.nan,
np.nan, np.nan, np.nan, np.nan, 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']
'75%', 'max', 'missing']
)
result = df.describe(include='all')
tm.assert_frame_equal(result, expected)
Expand Down