def __repr__(self) -> str:
global ANONYMIZED
if not ANONYMIZED:
return super().__repr__()
"""
Return a string representation for a particular DataFrame.
"""
buf = StringIO("")
if self._info_repr():
self.info(buf=buf)
return buf.getvalue()
max_rows = get_option("display.max_rows")
min_rows = get_option("display.min_rows")
max_cols = get_option("display.max_columns")
max_colwidth = get_option("display.max_colwidth")
show_dimensions = get_option("display.show_dimensions")
if get_option("display.expand_frame_repr"):
width, _ = console.get_console_size()
else:
width = None
formatters = [(Anon(x).get_value if x in self.anonymized else normal)
for x in self.columns]
self.to_string(
buf=buf,
max_rows=max_rows,
min_rows=min_rows,
max_cols=max_cols,
line_width=width,
max_colwidth=max_colwidth,
show_dimensions=show_dimensions,
formatters=formatters,
)
return buf.getvalue()
def _repr_dataframe(df):
num_rows = pandas.get_option("display.max_rows") or 10
num_cols = pandas.get_option("display.max_columns") or 20
if pandas.get_option("display.max_columns") is None and pandas.get_option(
"display.expand_frame_repr"):
width, _ = console.get_console_size()
col_counter = 0
i = 0
while col_counter < width:
col_counter += len(str(df.columns[i])) + 1
i += 1
num_cols = i
i = len(df.columns) - 1
col_counter = 0
while col_counter < width:
col_counter += len(str(df.columns[i])) + 1
i -= 1
num_cols += len(df.columns) - i
result = repr(_repr_frame(df, df.columns, num_rows, num_cols))
if len(df) > num_rows or len(df.columns) > num_cols:
return (result.rsplit("\n\n", 1)[0] +
f"\n\n[{len(df)} rows x {len(df.columns)} columns]")
else:
return result
def _display(self, max_rows=10, max_width=None, max_colwidth=50):
summary = ["<regionmask.{}>".format(type(self).__name__)]
if max_rows is None:
max_rows = len(self)
if max_width is None:
max_width, _ = console.get_console_size()
summary += _display_metadata(self.name, self.source, max_width=max_width)
summary.append("")
summary += _display_regions_gp(self, max_rows, max_width, max_colwidth)
summary.append("")
summary.append("[{:d} regions]".format(len(self)))
return "\n".join(summary)
def format_object_summary(
obj,
formatter: Callable,
is_justify: bool = True,
name: Optional[str] = None,
indent_for_name: bool = True,
line_break_each_value: bool = False,
) -> str:
"""
Return the formatted obj as a unicode string
Parameters
----------
obj : object
must be iterable and support __getitem__
formatter : callable
string formatter for an element
is_justify : boolean
should justify the display
name : name, optional
defaults to the class name of the obj
indent_for_name : bool, default True
Whether subsequent lines should be be indented to
align with the name.
line_break_each_value : bool, default False
If True, inserts a line break for each value of ``obj``.
If False, only break lines when the a line of values gets wider
than the display width.
.. versionadded:: 0.25.0
Returns
-------
summary string
"""
from pandas.io.formats.console import get_console_size
from pandas.io.formats.format import _get_adjustment
display_width, _ = get_console_size()
if display_width is None:
display_width = get_option("display.width") or 80
if name is None:
name = type(obj).__name__
if indent_for_name:
name_len = len(name)
space1 = f'\n{(" " * (name_len + 1))}'
space2 = f'\n{(" " * (name_len + 2))}'
else:
space1 = "\n"
space2 = "\n " # space for the opening '['
n = len(obj)
if line_break_each_value:
# If we want to vertically align on each value of obj, we need to
# separate values by a line break and indent the values
sep = ",\n " + " " * len(name)
else:
sep = ","
max_seq_items = get_option("display.max_seq_items") or n
# are we a truncated display
is_truncated = n > max_seq_items
# adj can optionally handle unicode eastern asian width
adj = _get_adjustment()
def _extend_line(s: str, line: str, value: str, display_width: int,
next_line_prefix: str) -> Tuple[str, str]:
if adj.len(line.rstrip()) + adj.len(value.rstrip()) >= display_width:
s += line.rstrip()
line = next_line_prefix
line += value
return s, line
def best_len(values: List[str]) -> int:
if values:
return max(adj.len(x) for x in values)
else:
return 0
close = ", "
if n == 0:
summary = f"[]{close}"
elif n == 1 and not line_break_each_value:
first = formatter(obj[0])
summary = f"[{first}]{close}"
elif n == 2 and not line_break_each_value:
first = formatter(obj[0])
last = formatter(obj[-1])
summary = f"[{first}, {last}]{close}"
else:
if n > max_seq_items:
n = min(max_seq_items // 2, 10)
head = [formatter(x) for x in obj[:n]]
tail = [formatter(x) for x in obj[-n:]]
else:
head = []
tail = [formatter(x) for x in obj]
# adjust all values to max length if needed
if is_justify:
if line_break_each_value:
# Justify each string in the values of head and tail, so the
# strings will right align when head and tail are stacked
# vertically.
head, tail = _justify(head, tail)
elif is_truncated or not (len(", ".join(head)) < display_width and
len(", ".join(tail)) < display_width):
# Each string in head and tail should align with each other
max_length = max(best_len(head), best_len(tail))
head = [x.rjust(max_length) for x in head]
tail = [x.rjust(max_length) for x in tail]
# If we are not truncated and we are only a single
# line, then don't justify
if line_break_each_value:
# Now head and tail are of type List[Tuple[str]]. Below we
# convert them into List[str], so there will be one string per
# value. Also truncate items horizontally if wider than
# max_space
max_space = display_width - len(space2)
value = tail[0]
for max_items in reversed(range(1, len(value) + 1)):
pprinted_seq = _pprint_seq(value, max_seq_items=max_items)
if len(pprinted_seq) < max_space:
break
head = [_pprint_seq(x, max_seq_items=max_items) for x in head]
tail = [_pprint_seq(x, max_seq_items=max_items) for x in tail]
summary = ""
line = space2
for max_items in range(len(head)):
word = head[max_items] + sep + " "
summary, line = _extend_line(summary, line, word, display_width,
space2)
if is_truncated:
# remove trailing space of last line
summary += line.rstrip() + space2 + "..."
line = space2
for max_items in range(len(tail) - 1):
word = tail[max_items] + sep + " "
summary, line = _extend_line(summary, line, word, display_width,
space2)
# last value: no sep added + 1 space of width used for trailing ','
summary, line = _extend_line(summary, line, tail[-1],
display_width - 2, space2)
summary += line
# right now close is either '' or ', '
# Now we want to include the ']', but not the maybe space.
close = "]" + close.rstrip(" ")
summary += close
if len(summary) > (display_width) or line_break_each_value:
summary += space1
else: # one row
summary += " "
# remove initial space
summary = "[" + summary[len(space2):]
return summary
def format_object_summary(obj,
formatter,
is_justify=True,
name=None,
indent_for_name=True):
"""
Return the formatted obj as a unicode string
Parameters
----------
obj : object
must be iterable and support __getitem__
formatter : callable
string formatter for an element
is_justify : boolean
should justify the display
name : name, optional
defaults to the class name of the obj
indent_for_name : bool, default True
Whether subsequent lines should be be indented to
align with the name.
Returns
-------
summary string
"""
from pandas.io.formats.console import get_console_size
from pandas.io.formats.format import _get_adjustment
display_width, _ = get_console_size()
if display_width is None:
display_width = get_option('display.width') or 80
if name is None:
name = obj.__class__.__name__
if indent_for_name:
name_len = len(name)
space1 = "\n%s" % (' ' * (name_len + 1))
space2 = "\n%s" % (' ' * (name_len + 2))
else:
space1 = "\n"
space2 = "\n " # space for the opening '['
n = len(obj)
sep = ','
max_seq_items = get_option('display.max_seq_items') or n
# are we a truncated display
is_truncated = n > max_seq_items
# adj can optionally handle unicode eastern asian width
adj = _get_adjustment()
def _extend_line(s, line, value, display_width, next_line_prefix):
if (adj.len(line.rstrip()) + adj.len(value.rstrip()) >= display_width):
s += line.rstrip()
line = next_line_prefix
line += value
return s, line
def best_len(values):
if values:
return max(adj.len(x) for x in values)
else:
return 0
close = u', '
if n == 0:
summary = u'[]{}'.format(close)
elif n == 1:
first = formatter(obj[0])
summary = u'[{}]{}'.format(first, close)
elif n == 2:
first = formatter(obj[0])
last = formatter(obj[-1])
summary = u'[{}, {}]{}'.format(first, last, close)
else:
if n > max_seq_items:
n = min(max_seq_items // 2, 10)
head = [formatter(x) for x in obj[:n]]
tail = [formatter(x) for x in obj[-n:]]
else:
head = []
tail = [formatter(x) for x in obj]
# adjust all values to max length if needed
if is_justify:
# however, if we are not truncated and we are only a single
# line, then don't justify
if (is_truncated
or not (len(', '.join(head)) < display_width
and len(', '.join(tail)) < display_width)):
max_len = max(best_len(head), best_len(tail))
head = [x.rjust(max_len) for x in head]
tail = [x.rjust(max_len) for x in tail]
summary = ""
line = space2
for i in range(len(head)):
word = head[i] + sep + ' '
summary, line = _extend_line(summary, line, word, display_width,
space2)
if is_truncated:
# remove trailing space of last line
summary += line.rstrip() + space2 + '...'
line = space2
for i in range(len(tail) - 1):
word = tail[i] + sep + ' '
summary, line = _extend_line(summary, line, word, display_width,
space2)
# last value: no sep added + 1 space of width used for trailing ','
summary, line = _extend_line(summary, line, tail[-1],
display_width - 2, space2)
summary += line
# right now close is either '' or ', '
# Now we want to include the ']', but not the maybe space.
close = ']' + close.rstrip(' ')
summary += close
if len(summary) > (display_width):
summary += space1
else: # one row
summary += ' '
# remove initial space
summary = '[' + summary[len(space2):]
return summary
def format_object_summary(obj, formatter, is_justify=True, name=None):
"""
Return the formatted obj as a unicode string
Parameters
----------
obj : object
must be iterable and support __getitem__
formatter : callable
string formatter for an element
is_justify : boolean
should justify the display
name : name, optiona
defaults to the class name of the obj
Returns
-------
summary string
"""
from pandas.io.formats.console import get_console_size
from pandas.io.formats.format import _get_adjustment
display_width, _ = get_console_size()
if display_width is None:
display_width = get_option('display.width') or 80
if name is None:
name = obj.__class__.__name__
space1 = "\n%s" % (' ' * (len(name) + 1))
space2 = "\n%s" % (' ' * (len(name) + 2))
n = len(obj)
sep = ','
max_seq_items = get_option('display.max_seq_items') or n
# are we a truncated display
is_truncated = n > max_seq_items
# adj can optionally handle unicode eastern asian width
adj = _get_adjustment()
def _extend_line(s, line, value, display_width, next_line_prefix):
if (adj.len(line.rstrip()) + adj.len(value.rstrip()) >=
display_width):
s += line.rstrip()
line = next_line_prefix
line += value
return s, line
def best_len(values):
if values:
return max(adj.len(x) for x in values)
else:
return 0
if n == 0:
summary = '[], '
elif n == 1:
first = formatter(obj[0])
summary = '[%s], ' % first
elif n == 2:
first = formatter(obj[0])
last = formatter(obj[-1])
summary = '[%s, %s], ' % (first, last)
else:
if n > max_seq_items:
n = min(max_seq_items // 2, 10)
head = [formatter(x) for x in obj[:n]]
tail = [formatter(x) for x in obj[-n:]]
else:
head = []
tail = [formatter(x) for x in obj]
# adjust all values to max length if needed
if is_justify:
# however, if we are not truncated and we are only a single
# line, then don't justify
if (is_truncated or
not (len(', '.join(head)) < display_width and
len(', '.join(tail)) < display_width)):
max_len = max(best_len(head), best_len(tail))
head = [x.rjust(max_len) for x in head]
tail = [x.rjust(max_len) for x in tail]
summary = ""
line = space2
for i in range(len(head)):
word = head[i] + sep + ' '
summary, line = _extend_line(summary, line, word,
display_width, space2)
if is_truncated:
# remove trailing space of last line
summary += line.rstrip() + space2 + '...'
line = space2
for i in range(len(tail) - 1):
word = tail[i] + sep + ' '
summary, line = _extend_line(summary, line, word,
display_width, space2)
# last value: no sep added + 1 space of width used for trailing ','
summary, line = _extend_line(summary, line, tail[-1],
display_width - 2, space2)
summary += line
summary += '],'
if len(summary) > (display_width):
summary += space1
else: # one row
summary += ' '
# remove initial space
summary = '[' + summary[len(space2):]
return summary
