Skip to content

ENH: pd.DataFrame.info() to show line numbers GH17304 #17332

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

Closed
wants to merge 3 commits into from
Closed

ENH: pd.DataFrame.info() to show line numbers GH17304 #17332

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
ba8f01c
ENH: pd.DataFrame.info() to show line numbers GH17304
pratapvardhan Aug 25, 2017
ff70d33
df.info column summary line numbers with header separator
Jul 9, 2018
7c13220
TST: df.info(null_counts=False) header as Dtype
Jul 10, 2018
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
29 changes: 29 additions & 0 deletions doc/source/whatsnew/v0.24.0.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -66,6 +66,35 @@ Current Behavior:

result

.. _whatsnew_0240.enhancements.output_formatting:

Output Formatting Enhancements
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

- :func:`DataFrame.info` now shows line numbers for the columns summary (:issue:`17304`)

.. ipython:: python

df = pd.DataFrame({
'int_col': [1, 2, 3, 4, 5],
'text_col': ['alpha', 'beta', 'gamma', 'delta', 'epsilon'],
'float_col': [0.0, 0.25, 0.5, 0.75, 1.0]})
df.info()

Previous Behavior:

.. code-block:: python

In [1]: df.info()
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 5 entries, 0 to 4
Data columns (total 3 columns):
int_col 5 non-null int64
text_col 5 non-null object
float_col 5 non-null float64
dtypes: float64(1), int64(1), object(1)
memory usage: 200.0+ bytes

.. _whatsnew_0240.enhancements.other:

Other Enhancements
Expand Down
72 changes: 46 additions & 26 deletions pandas/core/frame.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2121,9 +2121,11 @@ def info(self, verbose=None, buf=None, max_cols=None, memory_usage=None,
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 5 entries, 0 to 4
Data columns (total 3 columns):
int_col 5 non-null int64
text_col 5 non-null object
float_col 5 non-null float64
#. Column Non-Null Count & Dtype
--- ------ ----------------------
0 int_col 5 non-null int64
1 text_col 5 non-null object
2 float_col 5 non-null float64
dtypes: float64(1), int64(1), object(1)
memory usage: 200.0+ bytes

Expand Down Expand Up @@ -2161,19 +2163,23 @@ def info(self, verbose=None, buf=None, max_cols=None, memory_usage=None,
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1000000 entries, 0 to 999999
Data columns (total 3 columns):
column_1 1000000 non-null object
column_2 1000000 non-null object
column_3 1000000 non-null object
#. Column Non-Null Count & Dtype
--- ------ ----------------------
0 column_1 1000000 non-null object
1 column_2 1000000 non-null object
2 column_3 1000000 non-null object
dtypes: object(3)
memory usage: 22.9+ MB

>>> df.info(memory_usage='deep')
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1000000 entries, 0 to 999999
Data columns (total 3 columns):
column_1 1000000 non-null object
column_2 1000000 non-null object
column_3 1000000 non-null object
#. Column Non-Null Count & Dtype
--- ------ ----------------------
0 column_1 1000000 non-null object
1 column_2 1000000 non-null object
2 column_3 1000000 non-null object
dtypes: object(3)
memory usage: 188.8 MB
"""
Expand All @@ -2192,48 +2198,62 @@ def info(self, verbose=None, buf=None, max_cols=None, memory_usage=None,
return

cols = self.columns
cols_count = len(cols)

# hack
if max_cols is None:
max_cols = get_option('display.max_info_columns',
len(self.columns) + 1)
max_cols = get_option('display.max_info_columns', cols_count + 1)

max_rows = get_option('display.max_info_rows', len(self) + 1)

if null_counts is None:
show_counts = ((len(self.columns) <= max_cols) and
show_counts = ((cols_count <= max_cols) and
(len(self) < max_rows))
else:
show_counts = null_counts
exceeds_info_cols = len(self.columns) > max_cols
exceeds_info_cols = cols_count > max_cols

def _verbose_repr():
lines.append('Data columns (total %d columns):' %
len(self.columns))
space = max(len(pprint_thing(k)) for k in self.columns) + 4
lines.append('Data columns (total '
'{count} columns):'.format(count=cols_count))
space = max(len(pprint_thing(k)) for k in cols)
len_column = len(pprint_thing('Column'))
space = max(space, len_column) + 4
space_num = len(pprint_thing(cols_count))
len_id = len(pprint_thing(' #.'))
space_num = max(space_num, len_id) + 2
counts = None

tmpl = "{count}{dtype}"
header = _put_str(' #.', space_num) + _put_str('Column', space)
if show_counts:
counts = self.count()
if len(cols) != len(counts): # pragma: no cover
raise AssertionError(
'Columns must equal counts '
'({cols:d} != {counts:d})'.format(
cols=len(cols), counts=len(counts)))
tmpl = "{count} non-null {dtype}"

'({cols_count} != {count})'.format(
cols_count=cols_count, count=len(counts)))
col_header = 'Non-Null Count & Dtype'
tmpl = '{count} non-null {dtype}'
else:
col_header = 'Dtype'
tmpl = '{count}{dtype}'
header += col_header

lines.append(header)
lines.append(_put_str('-' * len_id, space_num) +
_put_str('-' * len_column, space) +
'-' * len(pprint_thing(col_header)))
dtypes = self.dtypes
for i, col in enumerate(self.columns):
for i, col in enumerate(cols):
dtype = dtypes.iloc[i]
col = pprint_thing(col)

count = ""
line_no = _put_str(' {num}'.format(num=i), space_num)
count = ''
if show_counts:
count = counts.iloc[i]

lines.append(_put_str(col, space) + tmpl.format(count=count,
dtype=dtype))
lines.append(line_no + _put_str(col, space) +
tmpl.format(count=count, dtype=dtype))

def _non_verbose_repr():
lines.append(self.columns._summary(name='Columns'))
Expand Down
36 changes: 28 additions & 8 deletions pandas/tests/frame/test_repr_info.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -217,13 +217,33 @@ def test_info_memory(self):
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 2 entries, 0 to 1
Data columns (total 1 columns):
a 2 non-null int64
#. Column Non-Null Count & Dtype
--- ------ ----------------------
0 a 2 non-null int64
dtypes: int64(1)
memory usage: {} bytes
""".format(bytes))

assert result == expected

def test_info_without_null_counts(self):
df = pd.DataFrame({'a': [1, 2]})
buf = StringIO()
df.info(buf=buf, null_counts=False)
buf.seek(0)
lines = buf.readlines()
result = ''.join(lines[:-1])
expected = textwrap.dedent('''\
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 2 entries, 0 to 1
Data columns (total 1 columns):
#. Column Dtype
--- ------ -----
0 a int64
dtypes: int64(1)
''')
assert result == expected

def test_info_wide(self):
from pandas import set_option, reset_option
io = StringIO()
Expand Down Expand Up @@ -259,8 +279,8 @@ def test_info_duplicate_columns_shows_correct_dtypes(self):
frame.info(buf=io)
io.seek(0)
lines = io.readlines()
assert 'a 1 non-null int64\n' == lines[3]
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 add a an explict test for this, one that specifically checks the formatting (a bit duplicative of this one), but like it separate

assert 'a 1 non-null float64\n' == lines[4]
assert ' 0 a 1 non-null int64\n' == lines[5]
assert ' 1 a 1 non-null float64\n' == lines[6]

def test_info_shows_column_dtypes(self):
dtypes = ['int64', 'float64', 'datetime64[ns]', 'timedelta64[ns]',
Expand All @@ -274,29 +294,29 @@ def test_info_shows_column_dtypes(self):
df.info(buf=buf)
res = buf.getvalue()
for i, dtype in enumerate(dtypes):
name = '%d %d non-null %s' % (i, n, dtype)
name = '%s %d non-null %s' % (i, n, dtype)

assert name in res

def test_info_max_cols(self):
df = DataFrame(np.random.randn(10, 5))
for len_, verbose in [(5, None), (5, False), (10, True)]:
for len_, verbose in [(5, None), (5, False), (12, True)]:
# For verbose always ^ setting ^ summarize ^ full output
with option_context('max_info_columns', 4):
buf = StringIO()
df.info(buf=buf, verbose=verbose)
res = buf.getvalue()
assert len(res.strip().split('\n')) == len_

for len_, verbose in [(10, None), (5, False), (10, True)]:

for len_, verbose in [(12, None), (5, False), (12, True)]:
# max_cols no exceeded
with option_context('max_info_columns', 5):
buf = StringIO()
df.info(buf=buf, verbose=verbose)
res = buf.getvalue()
assert len(res.strip().split('\n')) == len_

for len_, max_cols in [(10, 5), (5, 4)]:
for len_, max_cols in [(12, 5), (5, 4)]:
# setting truncates
with option_context('max_info_columns', 4):
buf = StringIO()
Expand Down