def test_empty_stripes(self):
r = []
s = self.schema1
result = repr(
ATable(r,
s,
offset=0,
format_settings=Formatting(wrap='stripes', width=80)))
result = '\n'.join([line.rstrip() for line in result.splitlines()])
expected = '''[0]--------------------------
i32 =
floaties =
long_column_name_ugh_and_ugh=
long_value =
s ='''
self.assertEqual(expected, result)
result = repr(
ATable(r,
s,
offset=0,
format_settings=Formatting(wrap='stripes',
width=80,
with_types=True)))
result = '\n'.join([line.rstrip() for line in result.splitlines()])
expected = '''[0]------------------------------
i32:int =
floaties:float =
long_column_name_ugh_and_ugh:str=
long_value:str =
s:str ='''
self.assertEqual(expected, result)
def test_neg_inspect_settings(self):
try:
ATable(1, [], 0, format_settings='jump')
except TypeError:
pass
else:
self.fail("Expected TypeError")
def test_inspection(self):
result = repr(
ATable(self.rows1,
self.schema1,
offset=0,
format_settings=Formatting(wrap=2, truncate=40, width=80)))
result = '\n'.join([line.rstrip() for line in result.splitlines()])
expected = '''[#] i32 floaties long_column_name_ugh_and_ugh
=====================================================
[0] 1 3.14159265358 a
[1] 2 8.014512183 b
[#] long_value s
==================================================
[0] The sun was shining on the sea, one
Shini...
[1] I'm going down. Down, down, down, do... two
[#] i32 floaties long_column_name_ugh_and_ugh
================================================
[2] 32 1.0 c
[#] long_value s
=========================================================
[2] AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA thirty-two'''
self.assertEqual(expected, result)
def test_line_numbers(self):
r = [[x, 'b%s' % x, None] for x in xrange(10)]
s = self.abc_schema
result = repr(
ATable(r,
s,
offset=92,
format_settings=Formatting(wrap=5, width=80)))
result = '\n'.join([line.rstrip() for line in result.splitlines()])
expected = '''[##] a b c
=================
[92] 0 b0 None
[93] 1 b1 None
[94] 2 b2 None
[95] 3 b3 None
[96] 4 b4 None
[###] a b c
==================
[97] 5 b5 None
[98] 6 b6 None
[99] 7 b7 None
[100] 8 b8 None
[101] 9 b9 None'''
self.assertEqual(expected, result)
def test_empty(self):
r = []
s = self.abc_schema
result = repr(
ATable(r,
s,
offset=0,
format_settings=Formatting(wrap=5, width=80)))
expected = '''[##] a b c
============='''
self.assertEqual(expected, result)
result = repr(
ATable(r,
s,
offset=0,
format_settings=Formatting(wrap=5,
width=80,
with_types=True)))
expected = '''[##] a:int b:unicode c:unicode
================================='''
self.assertEqual(expected, result)
def test_wrap_long_str_1(self):
r = [[
'12345678901234567890123456789012345678901234567890123456789012345678901234567890'
]]
s = [('s', str)]
settings = Formatting(wrap=5)
result = repr(ATable(r, s, offset=0, format_settings=settings))
result = '\n'.join([line.rstrip() for line in result.splitlines()])
expected = '''[#] s
================================================================================
[0] 12345678901234567890123456789012345678901234567890123456789012345678901234567890'''
self.assertEqual(expected, result)
def test_inspect_nones(self):
schema = [('s', str), ('v', float)]
rows = [['super', 1.0095], [None, None]]
result = repr(
ATable(rows,
schema,
offset=0,
format_settings=Formatting(wrap=2, round=2, truncate=4)))
result = '\n'.join([line.rstrip() for line in result.splitlines()])
self.assertEqual(
"""[#] s v
===============
[0] s... 1.01
[1] None None""", result)
def test_simple_stripes(self):
result = repr(
ATable(self.two_abc_rows,
self.abc_schema,
offset=0,
format_settings=Formatting(wrap='stripes', margin=10)))
expected = '''[0]
a=1
b=sixteen_16_abced
c=long
[1]
a=2
b=tiny
c=really really really really long'''
self.assertEqual(expected, result)
def get_inspect(self,
n=10,
offset=0,
columns=None,
wrap=inspect_settings._unspecified,
truncate=inspect_settings._unspecified,
round=inspect_settings._unspecified,
width=inspect_settings._unspecified,
margin=inspect_settings._unspecified,
with_types=inspect_settings._unspecified):
"""Returns an ATable object representing the table inspect --see frame.inspect()"""
from sparktk.frame.ops.take import take_rich
format_settings = inspect_settings.copy(wrap, truncate, round, width,
margin, with_types)
result = take_rich(self, n, offset, columns)
return ATable(result.data,
result.schema,
offset=offset,
format_settings=format_settings)
def r(value, num_digits):
return ATable.get_rounder(float, num_digits)(value)
def r(value, num_digits):
return ATable.get_rounder(float, num_digits)(value)
def inspect(self,
n=10,
offset=0,
columns=None,
wrap=inspect_settings._unspecified,
truncate=inspect_settings._unspecified,
round=inspect_settings._unspecified,
width=inspect_settings._unspecified,
margin=inspect_settings._unspecified,
with_types=inspect_settings._unspecified):
"""
Pretty-print of the frame data
Essentially returns a string, but technically returns a RowInspection object which renders a string.
The RowInspection object naturally converts to a str when needed, like when printed or when displayed
by python REPL (i.e. using the object's __repr__). If running in a script and want the inspect output
to be printed, then it must be explicitly printed, then `print frame.inspect()`
Parameters
----------
:param n: (Optional[int]) The number of rows to print
:param offset: (Optional[int]) The number of rows to skip before printing.
:param columns: (Optional[List[str]]) Filter columns to be included. By default, all columns are included.
:param wrap: (Optional[int or 'stripes']) If set to 'stripes' then inspect prints rows in stripes; if set to an
integer N, rows will be printed in clumps of N columns, where the columns are wrapped.
:param truncate: (Optional[int]) If set to integer N, all strings will be truncated to length N, including all
tagged ellipses.
:param round: (Optional[int]) If set to integer N, all floating point numbers will be rounded and truncated to
N digits.
:param width: (Optional[int]) If set to integer N, the print out will try to honor a max line width of N.
:param margin: (Optional[int]) Applies to 'stripes' mode only. If set to integer N, the margin for printing names
in a stripe will be limited to N characters.
:param with_types: (Optinoal[bool]) If set to True, header will include the data_type of each column.
:return: (RowsInspection) An object which naturally converts to a pretty-print string.
Examples
--------
To look at the first 4 rows of data in a frame:
<skip>
>>> frame.inspect(4)
[#] animal name age weight
==================================
[0] human George 8 542.5
[1] human Ursula 6 495.0
[2] ape Ape 41 400.0
[3] elephant Shep 5 8630.0
</skip>
# For other examples, see :ref:`example_frame.inspect`.
Note: if the frame data contains unicode characters, this method may raise a Unicode exception when
running in an interactive REPL or otherwise which triggers the standard python repr(). To get around
this problem, explicitly print the unicode of the returned object:
<skip>
>>> print unicode(frame.inspect())
</skip>
**Global Settings**
If not specified, the arguments that control formatting receive default values from
'sparktk.inspect_settings'. Make changes there to affect all calls to inspect.
>>> import sparktk
>>> sparktk.inspect_settings
wrap 20
truncate None
round None
width 80
margin None
with_types False
>>> sparktk.inspect_settings.width = 120 # changes inspect to use 120 width globally
>>> sparktk.inspect_settings.truncate = 16 # changes inspect to always truncate strings to 16 chars
>>> sparktk.inspect_settings
wrap 20
truncate 16
round None
width 120
margin None
with_types False
>>> sparktk.inspect_settings.width = None # return value back to default
>>> sparktk.inspect_settings
wrap 20
truncate 16
round None
width 80
margin None
with_types False
>>> sparktk.inspect_settings.reset() # set everything back to default
>>> sparktk.inspect_settings
wrap 20
truncate None
round None
width 80
margin None
with_types False
"""
from sparktk.frame.ops.take import take_rich
format_settings = inspect_settings.copy(wrap, truncate, round, width,
margin, with_types)
result = take_rich(self, n, offset, columns)
return ATable(result.data,
result.schema,
offset=offset,
format_settings=format_settings)