Skip to content

BUG: cleanup on describe #7129

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 1 commit into from
May 14, 2014
Merged

BUG: cleanup on describe #7129

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
22 changes: 9 additions & 13 deletions pandas/core/generic.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3573,22 +3573,18 @@ def describe_numeric_1d(series, percentiles):
[series.max()])

def describe_categorical_1d(data):
if data.dtype == object:
names = ['count', 'unique']
objcounts = data.value_counts()
result = [data.count(), len(objcounts)]
if result[1] > 0:
names = ['count', 'unique']
objcounts = data.value_counts()
result = [data.count(), len(objcounts)]
if result[1] > 0:
top, freq = objcounts.index[0], objcounts.iloc[0]

if data.dtype == object:
names += ['top', 'freq']
top, freq = objcounts.index[0], objcounts.iloc[0]
result += [top, freq]

elif issubclass(data.dtype.type, np.datetime64):
names = ['count', 'unique']
asint = data.dropna().values.view('i8')
objcounts = compat.Counter(asint)
result = [data.count(), len(objcounts)]
if result[1] > 0:
top, freq = objcounts.most_common(1)[0]
elif issubclass(data.dtype.type, np.datetime64):
asint = data.dropna().values.view('i8')
names += ['first', 'last', 'top', 'freq']
result += [lib.Timestamp(asint.min()),
lib.Timestamp(asint.max()),
Expand Down
15 changes: 8 additions & 7 deletions pandas/tests/test_generic.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -988,30 +988,31 @@ def test_describe_objects(self):
assert_frame_equal(result, expected)

df = DataFrame({"C1": pd.date_range('2010-01-01', periods=4, freq='D')})
df.loc[4] = pd.Timestamp('2010-01-04')
result = df.describe()
expected = DataFrame({"C1": [4, 4, pd.Timestamp('2010-01-01'),
expected = DataFrame({"C1": [5, 4, pd.Timestamp('2010-01-01'),
pd.Timestamp('2010-01-04'),
pd.Timestamp('2010-01-01'), 1]},
pd.Timestamp('2010-01-04'), 2]},
index=['count', 'unique', 'first', 'last', 'top',
'freq'])
assert_frame_equal(result, expected)

# mix time and str
df['C2'] = ['a', 'a', 'b', 'c']
df['C2'] = ['a', 'a', 'b', 'c', 'a']
result = df.describe()
# when mix of dateimte / obj the index gets reordered.
expected['C2'] = [4, 3, np.nan, np.nan, 'a', 2]
expected['C2'] = [5, 3, np.nan, np.nan, 'a', 3]
assert_frame_equal(result, expected)

# just str
expected = DataFrame({'C2': [4, 3, 'a', 2]},
expected = DataFrame({'C2': [5, 3, 'a', 4]},
index=['count', 'unique', 'top', 'freq'])
result = df[['C2']].describe()

# mix of time, str, numeric
df['C3'] = [2, 4, 6, 8]
df['C3'] = [2, 4, 6, 8, 2]
result = df.describe()
expected = DataFrame({"C3": [4., 5., 2.5819889, 2., 3.5, 5., 6.5, 8.]},
expected = DataFrame({"C3": [5., 4.4, 2.607681, 2., 2., 4., 6., 8.]},
index=['count', 'mean', 'std', 'min', '25%',
'50%', '75%', 'max'])
assert_frame_equal(result, expected)
Expand Down