def test_wide_repr_multiindex_cols(self):
with option_context('mode.sim_interactive', True):
col = lambda l, k: [tm.rands(k) for _ in xrange(l)]
midx = pandas.MultiIndex.from_arrays(
[np.array(col(10, 5)),
np.array(col(10, 5))])
mcols = pandas.MultiIndex.from_arrays(
[np.array(col(20, 3)),
np.array(col(20, 3))])
df = DataFrame([col(20, 25) for _ in range(10)],
index=midx,
columns=mcols)
df.index.names = ['Level 0', 'Level 1']
set_option('display.expand_frame_repr', False)
rep_str = repr(df)
set_option('display.expand_frame_repr', True)
wide_repr = repr(df)
self.assert_(rep_str != wide_repr)
with option_context('display.line_width', 120):
wider_repr = repr(df)
self.assert_(len(wider_repr) < len(wide_repr))
self.assert_(len(wide_repr.splitlines()) == 14 * 10 - 1)
reset_option('display.expand_frame_repr')
def test_wide_repr_wide_long_columns(self):
set_option('test.interactive', True)
df = DataFrame({'a': ['a'*30, 'b'*30], 'b': ['c'*70, 'd'*80]})
result = repr(df)
self.assertTrue('ccccc' in result)
self.assertTrue('ddddd' in result)
set_option('test.interactive', False)
def barf(self, num_rows=5, max_col=None):
"""
Keep on running into issues where in notebook, I want to just show everything.
"""
from IPython.core.display import HTML
import pandas.core.config as config
config.set_option("display.max_columns", 1000)
h = HTML(self.to_html())
config.reset_option("display.max_columns")
return h
def barf(self, num_rows=5, max_col=None):
"""
Keep on running into issues where in notebook, I want to just show everything.
"""
from IPython.core.display import HTML
import pandas.core.config as config
config.set_option("display.max_columns", 1000)
h = HTML(self.to_html())
config.reset_option("display.max_columns")
return h
def test_option_mpl_style(self):
set_option('display.mpl_style', 'default')
set_option('display.mpl_style', None)
set_option('display.mpl_style', False)
with tm.assertRaises(ValueError):
set_option('display.mpl_style', 'default2')
def test_option_mpl_style(self):
set_option("display.mpl_style", "default")
set_option("display.mpl_style", None)
set_option("display.mpl_style", False)
with tm.assertRaises(ValueError):
set_option("display.mpl_style", "default2")
def test_option_mpl_style(self):
set_option('display.mpl_style', 'default')
set_option('display.mpl_style', None)
set_option('display.mpl_style', False)
with tm.assertRaises(ValueError):
set_option('display.mpl_style', 'default2')
def test_wide_repr_unicode(self):
with option_context('mode.sim_interactive', True):
col = lambda l, k: [tm.randu(k) for _ in xrange(l)]
df = DataFrame([col(20, 25) for _ in range(10)])
set_option('display.expand_frame_repr', False)
rep_str = repr(df)
set_option('display.expand_frame_repr', True)
wide_repr = repr(df)
self.assert_(rep_str != wide_repr)
with option_context('display.line_width', 120):
wider_repr = repr(df)
self.assert_(len(wider_repr) < len(wide_repr))
reset_option('display.expand_frame_repr')
def test_option_mpl_style(self):
set_option("display.mpl_style", "default")
set_option("display.mpl_style", None)
set_option("display.mpl_style", False)
try:
set_option("display.mpl_style", "default2")
except ValueError:
pass
def test_option_mpl_style(self):
set_option('display.mpl_style', 'default')
set_option('display.mpl_style', None)
set_option('display.mpl_style', False)
try:
set_option('display.mpl_style', 'default2')
except ValueError:
pass
def test_option_mpl_style(self):
set_option('display.mpl_style', 'default')
set_option('display.mpl_style', None)
set_option('display.mpl_style', False)
try:
set_option('display.mpl_style', 'default2')
except ValueError:
pass
def test_wide_repr(self):
with option_context("mode.sim_interactive", True):
col = lambda l, k: [tm.rands(k) for _ in xrange(l)]
df = DataFrame([col(20, 25) for _ in range(10)])
set_option("print.expand_frame_repr", False)
rep_str = repr(df)
set_option("print.expand_frame_repr", True)
wide_repr = repr(df)
self.assert_(rep_str != wide_repr)
with option_context("print.line_width", 120):
wider_repr = repr(df)
self.assert_(len(wider_repr) < len(wide_repr))
reset_option("print.expand_frame_repr")
def test_wide_repr_unicode(self):
with option_context('mode.sim_interactive', True):
col = lambda l, k: [tm.randu(k) for _ in xrange(l)]
df = DataFrame([col(20, 25) for _ in range(10)])
set_option('display.expand_frame_repr', False)
rep_str = repr(df)
set_option('display.expand_frame_repr', True)
wide_repr = repr(df)
self.assert_(rep_str != wide_repr)
with option_context('display.line_width', 120):
wider_repr = repr(df)
self.assert_(len(wider_repr) < len(wide_repr))
reset_option('display.expand_frame_repr')
def set_eng_float_format(precision=None, accuracy=3, use_eng_prefix=False):
"""
Alter default behavior on how float is formatted in DataFrame.
Format float in engineering format. By accuracy, we mean the number of
decimal digits after the floating point.
See also EngFormatter.
"""
if precision is not None: # pragma: no cover
import warnings
warnings.warn("'precision' parameter in set_eng_float_format is "
"being renamed to 'accuracy'", FutureWarning)
accuracy = precision
set_option("print.float_format", EngFormatter(accuracy, use_eng_prefix))
set_option("print.column_space", max(12, accuracy + 9))
def set_eng_float_format(precision=None, accuracy=3, use_eng_prefix=False):
"""
Alter default behavior on how float is formatted in DataFrame.
Format float in engineering format. By accuracy, we mean the number of
decimal digits after the floating point.
See also EngFormatter.
"""
if precision is not None: # pragma: no cover
import warnings
warnings.warn(
"'precision' parameter in set_eng_float_format is "
"being renamed to 'accuracy'", FutureWarning)
accuracy = precision
set_option("display.float_format", EngFormatter(accuracy, use_eng_prefix))
set_option("display.column_space", max(12, accuracy + 9))
def test_wide_repr_multiindex_cols(self):
with option_context("mode.sim_interactive", True):
col = lambda l, k: [tm.rands(k) for _ in xrange(l)]
midx = pandas.MultiIndex.from_arrays([np.array(col(10, 5)), np.array(col(10, 5))])
mcols = pandas.MultiIndex.from_arrays([np.array(col(20, 3)), np.array(col(20, 3))])
df = DataFrame([col(20, 25) for _ in range(10)], index=midx, columns=mcols)
df.index.names = ["Level 0", "Level 1"]
set_option("display.expand_frame_repr", False)
rep_str = repr(df)
set_option("display.expand_frame_repr", True)
wide_repr = repr(df)
self.assert_(rep_str != wide_repr)
with option_context("display.line_width", 120):
wider_repr = repr(df)
self.assert_(len(wider_repr) < len(wide_repr))
self.assert_(len(wide_repr.splitlines()) == 14 * 10 - 1)
reset_option("display.expand_frame_repr")
def test_wide_repr_named(self):
with option_context('mode.sim_interactive', True):
col = lambda l, k: [tm.rands(k) for _ in xrange(l)]
df = DataFrame([col(20, 25) for _ in range(10)])
df.index.name = 'DataFrame Index'
set_option('display.expand_frame_repr', False)
rep_str = repr(df)
set_option('display.expand_frame_repr', True)
wide_repr = repr(df)
self.assert_(rep_str != wide_repr)
with option_context('display.line_width', 120):
wider_repr = repr(df)
self.assert_(len(wider_repr) < len(wide_repr))
for line in wide_repr.splitlines()[1::13]:
self.assert_('DataFrame Index' in line)
reset_option('display.expand_frame_repr')
def test_wide_repr_multiindex(self):
with option_context("mode.sim_interactive", True):
col = lambda l, k: [tm.rands(k) for _ in xrange(l)]
midx = pandas.MultiIndex.from_arrays([np.array(col(10, 5)), np.array(col(10, 5))])
df = DataFrame([col(20, 25) for _ in range(10)], index=midx)
df.index.names = ["Level 0", "Level 1"]
set_option("print.expand_frame_repr", False)
rep_str = repr(df)
set_option("print.expand_frame_repr", True)
wide_repr = repr(df)
self.assert_(rep_str != wide_repr)
with option_context("print.line_width", 120):
wider_repr = repr(df)
self.assert_(len(wider_repr) < len(wide_repr))
for line in wide_repr.splitlines()[1::13]:
self.assert_("Level 0 Level 1" in line)
reset_option("print.expand_frame_repr")
def test_wide_repr_named(self):
with option_context('mode.sim_interactive', True):
col = lambda l, k: [tm.rands(k) for _ in xrange(l)]
df = DataFrame([col(20, 25) for _ in range(10)])
df.index.name = 'DataFrame Index'
set_option('display.expand_frame_repr', False)
rep_str = repr(df)
set_option('display.expand_frame_repr', True)
wide_repr = repr(df)
self.assert_(rep_str != wide_repr)
with option_context('display.line_width', 120):
wider_repr = repr(df)
self.assert_(len(wider_repr) < len(wide_repr))
for line in wide_repr.splitlines()[1::13]:
self.assert_('DataFrame Index' in line)
reset_option('display.expand_frame_repr')
def test_option_mpl_style(self):
# just a sanity check
try:
import matplotlib
except:
raise nose.SkipTest
set_option('display.mpl_style', 'default')
set_option('display.mpl_style', None)
set_option('display.mpl_style', False)
try:
set_option('display.mpl_style', 'default2')
except ValueError:
pass
def test_option_mpl_style(self):
# just a sanity check
try:
import matplotlib
except:
raise nose.SkipTest
set_option('display.mpl_style', 'default')
set_option('display.mpl_style', None)
set_option('display.mpl_style', False)
try:
set_option('display.mpl_style', 'default2')
except ValueError:
pass
def test_register_writer(self):
# some awkward mocking to test out dispatch and such actually works
called_save = []
called_write_cells = []
class DummyClass(ExcelWriter):
called_save = False
called_write_cells = False
supported_extensions = ['test', 'xlsx', 'xls']
engine = 'dummy'
def save(self):
called_save.append(True)
def write_cells(self, *args, **kwargs):
called_write_cells.append(True)
def check_called(func):
func()
self.assert_(len(called_save) >= 1)
self.assert_(len(called_write_cells) >= 1)
del called_save[:]
del called_write_cells[:]
register_writer(DummyClass)
writer = ExcelWriter('something.test')
tm.assert_isinstance(writer, DummyClass)
df = tm.makeCustomDataframe(1, 1)
panel = tm.makePanel()
func = lambda: df.to_excel('something.test')
check_called(func)
check_called(lambda: panel.to_excel('something.test'))
from pandas import set_option, get_option
val = get_option('io.excel.xlsx.writer')
set_option('io.excel.xlsx.writer', 'dummy')
check_called(lambda: df.to_excel('something.xlsx'))
check_called(lambda: df.to_excel('something.xls', engine='dummy'))
set_option('io.excel.xlsx.writer', val)
def test_register_writer(self):
# some awkward mocking to test out dispatch and such actually works
called_save = []
called_write_cells = []
class DummyClass(ExcelWriter):
called_save = False
called_write_cells = False
supported_extensions = ['test', 'xlsx', 'xls']
engine = 'dummy'
def save(self):
called_save.append(True)
def write_cells(self, *args, **kwargs):
called_write_cells.append(True)
def check_called(func):
func()
self.assert_(len(called_save) >= 1)
self.assert_(len(called_write_cells) >= 1)
del called_save[:]
del called_write_cells[:]
register_writer(DummyClass)
writer = ExcelWriter('something.test')
tm.assert_isinstance(writer, DummyClass)
df = tm.makeCustomDataframe(1, 1)
panel = tm.makePanel()
func = lambda: df.to_excel('something.test')
check_called(func)
check_called(lambda: panel.to_excel('something.test'))
from pandas import set_option, get_option
val = get_option('io.excel.xlsx.writer')
set_option('io.excel.xlsx.writer', 'dummy')
check_called(lambda: df.to_excel('something.xlsx'))
check_called(lambda: df.to_excel('something.xls', engine='dummy'))
set_option('io.excel.xlsx.writer', val)
def test_repr_truncation(self):
max_len = 20
set_option("print_config.max_colwidth", max_len)
df = DataFrame(
{"A": np.random.randn(10), "B": [tm.rands(np.random.randint(max_len - 1, max_len + 1)) for i in range(10)]}
)
r = repr(df)
r = r[r.find("\n") + 1 :]
for line, value in zip(r.split("\n"), df["B"]):
if fmt._strlen(value) + 1 > max_len:
self.assert_("..." in line)
else:
self.assert_("..." not in line)
set_option("print_config.max_colwidth", 999999)
self.assert_("..." not in repr(df))
set_option("print_config.max_colwidth", max_len + 2)
self.assert_("..." not in repr(df))
def test_repr_truncation(self):
max_len = 20
set_option("print_config.max_colwidth", max_len)
df = DataFrame({'A': np.random.randn(10),
'B': [tm.rands(np.random.randint(max_len - 1,
max_len + 1)) for i in range(10)]})
r = repr(df)
r = r[r.find('\n') + 1:]
for line, value in zip(r.split('\n'), df['B']):
if fmt._strlen(value) + 1 > max_len:
self.assert_('...' in line)
else:
self.assert_('...' not in line)
set_option("print_config.max_colwidth", 999999)
self.assert_('...' not in repr(df))
set_option("print_config.max_colwidth", max_len + 2)
self.assert_('...' not in repr(df))
def test_repr_truncation(self):
max_len = 20
set_option("print.max_colwidth", max_len)
df = DataFrame({'A': np.random.randn(10),
'B': [tm.rands(np.random.randint(max_len - 1,
max_len + 1)) for i in range(10)]})
r = repr(df)
r = r[r.find('\n') + 1:]
_strlen = fmt._strlen_func()
for line, value in zip(r.split('\n'), df['B']):
if _strlen(value) + 1 > max_len:
self.assert_('...' in line)
else:
self.assert_('...' not in line)
set_option("print.max_colwidth", 999999)
self.assert_('...' not in repr(df))
set_option("print.max_colwidth", max_len + 2)
self.assert_('...' not in repr(df))
def test_wide_repr_unicode(self):
set_option('test.interactive', True)
col = lambda l, k: [tm.randu(k) for _ in xrange(l)]
df = DataFrame([col(20, 25) for _ in range(10)])
set_option('print.expand_frame_repr', False)
rep_str = repr(df)
set_option('print.expand_frame_repr', True)
wide_repr = repr(df)
self.assert_(rep_str != wide_repr)
set_option('print.line_width', 120)
wider_repr = repr(df)
self.assert_(len(wider_repr) < len(wide_repr))
reset_option('print.expand_frame_repr')
set_option('test.interactive', False)
set_option('print.line_width', 80)
def __init__(self):
set_option('display.max_rows', None)
def set_printoptions(precision=None,
column_space=None,
max_rows=None,
max_columns=None,
colheader_justify=None,
max_colwidth=None,
notebook_repr_html=None,
date_dayfirst=None,
date_yearfirst=None,
pprint_nest_depth=None,
multi_sparse=None,
encoding=None):
"""
Alter default behavior of DataFrame.toString
precision : int
Floating point output precision (number of significant digits). This is
only a suggestion
column_space : int
Default space for DataFrame columns, defaults to 12
max_rows : int
max_columns : int
max_rows and max_columns are used in __repr__() methods to decide if
to_string() or info() is used to render an object to a string.
Either one, or both can be set to 0 (experimental). Pandas will figure
out how big the terminal is and will not display more rows or/and
columns that can fit on it.
colheader_justify
notebook_repr_html : boolean
When True (default), IPython notebook will use html representation for
pandas objects (if it is available).
date_dayfirst : boolean
When True, prints and parses dates with the day first, eg 20/01/2005
date_yearfirst : boolean
When True, prints and parses dates with the year first, eg 2005/01/20
pprint_nest_depth : int
Defaults to 3.
Controls the number of nested levels to process when pretty-printing
nested sequences.
multi_sparse : boolean
Default True, "sparsify" MultiIndex display (don't display repeated
elements in outer levels within groups)
"""
if precision is not None:
set_option("print_config.precision", precision)
if column_space is not None:
set_option("print_config.column_space", column_space)
if max_rows is not None:
set_option("print_config.max_rows", max_rows)
if max_colwidth is not None:
set_option("print_config.max_colwidth", max_colwidth)
if max_columns is not None:
set_option("print_config.max_columns", max_columns)
if colheader_justify is not None:
set_option("print_config.colheader_justify", colheader_justify)
if notebook_repr_html is not None:
set_option("print_config.notebook_repr_html", notebook_repr_html)
if date_dayfirst is not None:
set_option("print_config.date_dayfirst", date_dayfirst)
if date_yearfirst is not None:
set_option("print_config.date_yearfirst", date_yearfirst)
if pprint_nest_depth is not None:
set_option("print_config.pprint_nest_depth", pprint_nest_depth)
if multi_sparse is not None:
set_option("print_config.multi_sparse", multi_sparse)
if encoding is not None:
set_option("print_config.encoding", encoding)
def tearDown(self):
set_option(self.option_name, self.prev_engine)
def setUp(self):
self.check_skip()
super(ExcelWriterBase, self).setUp()
self.option_name = 'io.excel.%s.writer' % self.ext.strip('.')
self.prev_engine = get_option(self.option_name)
set_option(self.option_name, self.engine_name)
def setUp(self):
self.check_skip()
super(ExcelWriterBase, self).setUp()
self.option_name = 'io.excel.%s.writer' % self.ext.strip('.')
self.prev_engine = get_option(self.option_name)
set_option(self.option_name, self.engine_name)
def set_printoptions(precision=None, column_space=None, max_rows=None,
max_columns=None, colheader_justify=None,
max_colwidth=None, notebook_repr_html=None,
date_dayfirst=None, date_yearfirst=None,
pprint_nest_depth=None,multi_sparse=None, encoding=None):
"""
Alter default behavior of DataFrame.toString
precision : int
Floating point output precision (number of significant digits). This is
only a suggestion
column_space : int
Default space for DataFrame columns, defaults to 12
max_rows : int
max_columns : int
max_rows and max_columns are used in __repr__() methods to decide if
to_string() or info() is used to render an object to a string.
Either one, or both can be set to 0 (experimental). Pandas will figure
out how big the terminal is and will not display more rows or/and
columns that can fit on it.
colheader_justify
notebook_repr_html : boolean
When True (default), IPython notebook will use html representation for
pandas objects (if it is available).
date_dayfirst : boolean
When True, prints and parses dates with the day first, eg 20/01/2005
date_yearfirst : boolean
When True, prints and parses dates with the year first, eg 2005/01/20
pprint_nest_depth : int
Defaults to 3.
Controls the number of nested levels to process when pretty-printing
nested sequences.
multi_sparse : boolean
Default True, "sparsify" MultiIndex display (don't display repeated
elements in outer levels within groups)
"""
import warnings
warnings.warn("set_printoptions is deprecated, use set_option instead",
FutureWarning)
if precision is not None:
set_option("print.precision", precision)
if column_space is not None:
set_option("print.column_space", column_space)
if max_rows is not None:
set_option("print.max_rows", max_rows)
if max_colwidth is not None:
set_option("print.max_colwidth", max_colwidth)
if max_columns is not None:
set_option("print.max_columns", max_columns)
if colheader_justify is not None:
set_option("print.colheader_justify", colheader_justify)
if notebook_repr_html is not None:
set_option("print.notebook_repr_html", notebook_repr_html)
if date_dayfirst is not None:
set_option("print.date_dayfirst", date_dayfirst)
if date_yearfirst is not None:
set_option("print.date_yearfirst", date_yearfirst)
if pprint_nest_depth is not None:
set_option("print.pprint_nest_depth", pprint_nest_depth)
if multi_sparse is not None:
set_option("print.multi_sparse", multi_sparse)
if encoding is not None:
set_option("print.encoding", encoding)
def tearDown(self):
set_option(self.option_name, self.prev_engine)
def test_wide_repr_multiindex_cols(self):
set_option('test.interactive', True)
col = lambda l, k: [tm.rands(k) for _ in xrange(l)]
midx = pandas.MultiIndex.from_arrays([np.array(col(10, 5)),
np.array(col(10, 5))])
mcols = pandas.MultiIndex.from_arrays([np.array(col(20, 3)),
np.array(col(20, 3))])
df = DataFrame([col(20, 25) for _ in range(10)],
index=midx, columns=mcols)
df.index.names = ['Level 0', 'Level 1']
set_option('print.expand_frame_repr', False)
rep_str = repr(df)
set_option('print.expand_frame_repr', True)
wide_repr = repr(df)
self.assert_(rep_str != wide_repr)
set_option('print.line_width', 120)
wider_repr = repr(df)
self.assert_(len(wider_repr) < len(wide_repr))
self.assert_(len(wide_repr.splitlines()) == 14 * 10 - 1)
reset_option('print.expand_frame_repr')
set_option('test.interactive', False)
set_option('print.line_width', 80)
