def _get_level_lengths(index):
"""
Given an index, find the level lenght for each element.
Result is a dictionary of (level, inital_position): span
"""
sentinel = com.sentinel_factory()
levels = index.format(sparsify=sentinel, adjoin=False, names=False)
if index.nlevels == 1:
return {(0, i): 1 for i, value in enumerate(levels)}
lengths = {}
for i, lvl in enumerate(levels):
for j, row in enumerate(lvl):
if not get_option('display.multi_sparse'):
lengths[(i, j)] = 1
elif row != sentinel:
last_label = j
lengths[(i, last_label)] = 1
else:
lengths[(i, last_label)] += 1
return lengths
def _get_level_lengths(index):
"""
Given an index, find the level lenght for each element.
Result is a dictionary of (level, inital_position): span
"""
sentinel = com.sentinel_factory()
levels = index.format(sparsify=sentinel, adjoin=False, names=False)
if index.nlevels == 1:
return {(0, i): 1 for i, value in enumerate(levels)}
lengths = {}
for i, lvl in enumerate(levels):
for j, row in enumerate(lvl):
if not get_option('display.multi_sparse'):
lengths[(i, j)] = 1
elif row != sentinel:
last_label = j
lengths[(i, last_label)] = 1
else:
lengths[(i, last_label)] += 1
return lengths
def _get_level_lengths(index, hidden_elements=None):
"""
Given an index, find the level length for each element.
Optional argument is a list of index positions which
should not be visible.
Result is a dictionary of (level, inital_position): span
"""
sentinel = com.sentinel_factory()
levels = index.format(sparsify=sentinel, adjoin=False, names=False)
if hidden_elements is None:
hidden_elements = []
lengths = {}
if index.nlevels == 1:
for i, value in enumerate(levels):
if (i not in hidden_elements):
lengths[(0, i)] = 1
return lengths
for i, lvl in enumerate(levels):
for j, row in enumerate(lvl):
if not get_option('display.multi_sparse'):
lengths[(i, j)] = 1
elif (row != sentinel) and (j not in hidden_elements):
last_label = j
lengths[(i, last_label)] = 1
elif (row != sentinel):
# even if its hidden, keep track of it in case
# length >1 and later elements are visible
last_label = j
lengths[(i, last_label)] = 0
elif (j not in hidden_elements):
lengths[(i, last_label)] += 1
non_zero_lengths = {
element: length
for element, length in lengths.items() if length >= 1
}
return non_zero_lengths
def _get_level_lengths(index, hidden_elements=None):
"""
Given an index, find the level length for each element.
Optional argument is a list of index positions which
should not be visible.
Result is a dictionary of (level, inital_position): span
"""
sentinel = com.sentinel_factory()
levels = index.format(sparsify=sentinel, adjoin=False, names=False)
if hidden_elements is None:
hidden_elements = []
lengths = {}
if index.nlevels == 1:
for i, value in enumerate(levels):
if(i not in hidden_elements):
lengths[(0, i)] = 1
return lengths
for i, lvl in enumerate(levels):
for j, row in enumerate(lvl):
if not get_option('display.multi_sparse'):
lengths[(i, j)] = 1
elif (row != sentinel) and (j not in hidden_elements):
last_label = j
lengths[(i, last_label)] = 1
elif (row != sentinel):
# even if its hidden, keep track of it in case
# length >1 and later elements are visible
last_label = j
lengths[(i, last_label)] = 0
elif(j not in hidden_elements):
lengths[(i, last_label)] += 1
non_zero_lengths = {}
for element, length in lengths.items():
if(length >= 1):
non_zero_lengths[element] = length
return non_zero_lengths
def _write_hierarchical_rows(self, fmt_values, indent):
template = 'rowspan="{span}" valign="top"'
truncate_h = self.fmt.truncate_h
truncate_v = self.fmt.truncate_v
frame = self.fmt.tr_frame
nrows = len(frame)
row_levels = self.frame.index.nlevels
idx_values = frame.index.format(sparsify=False,
adjoin=False,
names=False)
idx_values = lzip(*idx_values)
if self.fmt.sparsify:
# GH3547
sentinel = com.sentinel_factory()
levels = frame.index.format(sparsify=sentinel,
adjoin=False,
names=False)
level_lengths = get_level_lengths(levels, sentinel)
inner_lvl = len(level_lengths) - 1
if truncate_v:
# Insert ... row and adjust idx_values and
# level_lengths to take this into account.
ins_row = self.fmt.tr_row_num
inserted = False
for lnum, records in enumerate(level_lengths):
rec_new = {}
for tag, span in list(records.items()):
if tag >= ins_row:
rec_new[tag + 1] = span
elif tag + span > ins_row:
rec_new[tag] = span + 1
# GH 14882 - Make sure insertion done once
if not inserted:
dot_row = list(idx_values[ins_row - 1])
dot_row[-1] = u('...')
idx_values.insert(ins_row, tuple(dot_row))
inserted = True
else:
dot_row = list(idx_values[ins_row])
dot_row[inner_lvl - lnum] = u('...')
idx_values[ins_row] = tuple(dot_row)
else:
rec_new[tag] = span
# If ins_row lies between tags, all cols idx cols
# receive ...
if tag + span == ins_row:
rec_new[ins_row] = 1
if lnum == 0:
idx_values.insert(
ins_row,
tuple([u('...')] * len(level_lengths)))
# GH 14882 - Place ... in correct level
elif inserted:
dot_row = list(idx_values[ins_row])
dot_row[inner_lvl - lnum] = u('...')
idx_values[ins_row] = tuple(dot_row)
level_lengths[lnum] = rec_new
level_lengths[inner_lvl][ins_row] = 1
for ix_col in range(len(fmt_values)):
fmt_values[ix_col].insert(ins_row, '...')
nrows += 1
for i in range(nrows):
row = []
tags = {}
sparse_offset = 0
j = 0
for records, v in zip(level_lengths, idx_values[i]):
if i in records:
if records[i] > 1:
tags[j] = template.format(span=records[i])
else:
sparse_offset += 1
continue
j += 1
row.append(v)
row.extend(fmt_values[j][i] for j in range(self.ncols))
if truncate_h:
row.insert(
row_levels - sparse_offset + self.fmt.tr_col_num,
'...')
self.write_tr(row,
indent,
self.indent_delta,
tags=tags,
nindex_levels=len(levels) - sparse_offset)
else:
for i in range(len(frame)):
idx_values = list(
zip(*frame.index.format(
sparsify=False, adjoin=False, names=False)))
row = []
row.extend(idx_values[i])
row.extend(fmt_values[j][i] for j in range(self.ncols))
if truncate_h:
row.insert(row_levels + self.fmt.tr_col_num, '...')
self.write_tr(row,
indent,
self.indent_delta,
tags=None,
nindex_levels=frame.index.nlevels)
def _write_header(self, indent):
truncate_h = self.fmt.truncate_h
row_levels = self.frame.index.nlevels
if not self.fmt.header:
# write nothing
return indent
self.write('<thead>', indent)
indent += self.indent_delta
if isinstance(self.columns, ABCMultiIndex):
template = 'colspan="{span:d}" halign="left"'
if self.fmt.sparsify:
# GH3547
sentinel = com.sentinel_factory()
else:
sentinel = None
levels = self.columns.format(sparsify=sentinel,
adjoin=False,
names=False)
level_lengths = get_level_lengths(levels, sentinel)
inner_lvl = len(level_lengths) - 1
for lnum, (records,
values) in enumerate(zip(level_lengths, levels)):
if truncate_h:
# modify the header lines
ins_col = self.fmt.tr_col_num
if self.fmt.sparsify:
recs_new = {}
# Increment tags after ... col.
for tag, span in list(records.items()):
if tag >= ins_col:
recs_new[tag + 1] = span
elif tag + span > ins_col:
recs_new[tag] = span + 1
if lnum == inner_lvl:
values = (values[:ins_col] + (u('...'), ) +
values[ins_col:])
else:
# sparse col headers do not receive a ...
values = (values[:ins_col] +
(values[ins_col - 1], ) +
values[ins_col:])
else:
recs_new[tag] = span
# if ins_col lies between tags, all col headers
# get ...
if tag + span == ins_col:
recs_new[ins_col] = 1
values = (values[:ins_col] + (u('...'), ) +
values[ins_col:])
records = recs_new
inner_lvl = len(level_lengths) - 1
if lnum == inner_lvl:
records[ins_col] = 1
else:
recs_new = {}
for tag, span in list(records.items()):
if tag >= ins_col:
recs_new[tag + 1] = span
else:
recs_new[tag] = span
recs_new[ins_col] = 1
records = recs_new
values = (values[:ins_col] + [u('...')] +
values[ins_col:])
name = self.columns.names[lnum]
row = [''] * (row_levels - 1) + [
'' if name is None else pprint_thing(name)
]
if row == [""] and self.fmt.index is False:
row = []
tags = {}
j = len(row)
for i, v in enumerate(values):
if i in records:
if records[i] > 1:
tags[j] = template.format(span=records[i])
else:
continue
j += 1
row.append(v)
self.write_tr(row,
indent,
self.indent_delta,
tags=tags,
header=True)
else:
if self.fmt.index:
row = [''] * (self.frame.index.nlevels - 1)
row.append(self.columns.name or '')
else:
row = []
row.extend(self.columns)
align = self.fmt.justify
if truncate_h:
if not self.fmt.index:
row_levels = 0
ins_col = row_levels + self.fmt.tr_col_num
row.insert(ins_col, '...')
self.write_tr(row,
indent,
self.indent_delta,
header=True,
align=align)
if all((self.fmt.has_index_names, self.fmt.index,
self.fmt.show_index_names)):
row = (
[x if x is not None else '' for x in self.frame.index.names] +
[''] * (self.ncols + (1 if truncate_h else 0)))
self.write_tr(row, indent, self.indent_delta, header=True)
indent -= self.indent_delta
self.write('</thead>', indent)
return indent
def _write_hierarchical_rows(self, fmt_values, indent):
template = 'rowspan="{span}" valign="top"'
truncate_h = self.fmt.truncate_h
truncate_v = self.fmt.truncate_v
frame = self.fmt.tr_frame
ncols = len(frame.columns)
nrows = len(frame)
row_levels = self.frame.index.nlevels
idx_values = frame.index.format(sparsify=False, adjoin=False,
names=False)
idx_values = lzip(*idx_values)
if self.fmt.sparsify:
# GH3547
sentinel = com.sentinel_factory()
levels = frame.index.format(sparsify=sentinel, adjoin=False,
names=False)
level_lengths = get_level_lengths(levels, sentinel)
inner_lvl = len(level_lengths) - 1
if truncate_v:
# Insert ... row and adjust idx_values and
# level_lengths to take this into account.
ins_row = self.fmt.tr_row_num
inserted = False
for lnum, records in enumerate(level_lengths):
rec_new = {}
for tag, span in list(records.items()):
if tag >= ins_row:
rec_new[tag + 1] = span
elif tag + span > ins_row:
rec_new[tag] = span + 1
# GH 14882 - Make sure insertion done once
if not inserted:
dot_row = list(idx_values[ins_row - 1])
dot_row[-1] = u('...')
idx_values.insert(ins_row, tuple(dot_row))
inserted = True
else:
dot_row = list(idx_values[ins_row])
dot_row[inner_lvl - lnum] = u('...')
idx_values[ins_row] = tuple(dot_row)
else:
rec_new[tag] = span
# If ins_row lies between tags, all cols idx cols
# receive ...
if tag + span == ins_row:
rec_new[ins_row] = 1
if lnum == 0:
idx_values.insert(ins_row, tuple(
[u('...')] * len(level_lengths)))
# GH 14882 - Place ... in correct level
elif inserted:
dot_row = list(idx_values[ins_row])
dot_row[inner_lvl - lnum] = u('...')
idx_values[ins_row] = tuple(dot_row)
level_lengths[lnum] = rec_new
level_lengths[inner_lvl][ins_row] = 1
for ix_col in range(len(fmt_values)):
fmt_values[ix_col].insert(ins_row, '...')
nrows += 1
for i in range(nrows):
row = []
tags = {}
sparse_offset = 0
j = 0
for records, v in zip(level_lengths, idx_values[i]):
if i in records:
if records[i] > 1:
tags[j] = template.format(span=records[i])
else:
sparse_offset += 1
continue
j += 1
row.append(v)
row.extend(fmt_values[j][i] for j in range(ncols))
if truncate_h:
row.insert(row_levels - sparse_offset +
self.fmt.tr_col_num, '...')
self.write_tr(row, indent, self.indent_delta, tags=tags,
nindex_levels=len(levels) - sparse_offset)
else:
for i in range(len(frame)):
idx_values = list(zip(*frame.index.format(
sparsify=False, adjoin=False, names=False)))
row = []
row.extend(idx_values[i])
row.extend(fmt_values[j][i] for j in range(ncols))
if truncate_h:
row.insert(row_levels + self.fmt.tr_col_num, '...')
self.write_tr(row, indent, self.indent_delta, tags=None,
nindex_levels=frame.index.nlevels)
def _write_header(self, indent):
truncate_h = self.fmt.truncate_h
row_levels = self.frame.index.nlevels
if not self.fmt.header:
# write nothing
return indent
def _column_header():
if self.fmt.index:
row = [''] * (self.frame.index.nlevels - 1)
else:
row = []
if isinstance(self.columns, ABCMultiIndex):
if self.fmt.has_column_names and self.fmt.index:
row.append(single_column_table(self.columns.names))
else:
row.append('')
style = "text-align: {just};".format(just=self.fmt.justify)
row.extend([single_column_table(c, self.fmt.justify, style)
for c in self.columns])
else:
if self.fmt.index:
row.append(self.columns.name or '')
row.extend(self.columns)
return row
self.write('<thead>', indent)
indent += self.indent_delta
if isinstance(self.columns, ABCMultiIndex):
template = 'colspan="{span:d}" halign="left"'
if self.fmt.sparsify:
# GH3547
sentinel = com.sentinel_factory()
else:
sentinel = None
levels = self.columns.format(sparsify=sentinel, adjoin=False,
names=False)
level_lengths = get_level_lengths(levels, sentinel)
inner_lvl = len(level_lengths) - 1
for lnum, (records, values) in enumerate(zip(level_lengths,
levels)):
if truncate_h:
# modify the header lines
ins_col = self.fmt.tr_col_num
if self.fmt.sparsify:
recs_new = {}
# Increment tags after ... col.
for tag, span in list(records.items()):
if tag >= ins_col:
recs_new[tag + 1] = span
elif tag + span > ins_col:
recs_new[tag] = span + 1
if lnum == inner_lvl:
values = (values[:ins_col] + (u('...'),) +
values[ins_col:])
else:
# sparse col headers do not receive a ...
values = (values[:ins_col] +
(values[ins_col - 1], ) +
values[ins_col:])
else:
recs_new[tag] = span
# if ins_col lies between tags, all col headers
# get ...
if tag + span == ins_col:
recs_new[ins_col] = 1
values = (values[:ins_col] + (u('...'),) +
values[ins_col:])
records = recs_new
inner_lvl = len(level_lengths) - 1
if lnum == inner_lvl:
records[ins_col] = 1
else:
recs_new = {}
for tag, span in list(records.items()):
if tag >= ins_col:
recs_new[tag + 1] = span
else:
recs_new[tag] = span
recs_new[ins_col] = 1
records = recs_new
values = (values[:ins_col] + [u('...')] +
values[ins_col:])
name = self.columns.names[lnum]
row = [''] * (row_levels - 1) + ['' if name is None else
pprint_thing(name)]
if row == [""] and self.fmt.index is False:
row = []
tags = {}
j = len(row)
for i, v in enumerate(values):
if i in records:
if records[i] > 1:
tags[j] = template.format(span=records[i])
else:
continue
j += 1
row.append(v)
self.write_tr(row, indent, self.indent_delta, tags=tags,
header=True)
else:
col_row = _column_header()
align = self.fmt.justify
if truncate_h:
ins_col = row_levels + self.fmt.tr_col_num
col_row.insert(ins_col, '...')
self.write_tr(col_row, indent, self.indent_delta, header=True,
align=align)
if all((self.fmt.has_index_names,
self.fmt.index,
self.fmt.show_index_names)):
row = ([x if x is not None else ''
for x in self.frame.index.names] +
[''] * min(len(self.columns), self.max_cols))
if truncate_h:
ins_col = row_levels + self.fmt.tr_col_num
row.insert(ins_col, '')
self.write_tr(row, indent, self.indent_delta, header=True)
indent -= self.indent_delta
self.write('</thead>', indent)
return indent
def _write_col_header(self, indent):
truncate_h = self.fmt.truncate_h
if isinstance(self.columns, ABCMultiIndex):
template = 'colspan="{span:d}" halign="left"'
if self.fmt.sparsify:
# GH3547
sentinel = com.sentinel_factory()
else:
sentinel = False
levels = self.columns.format(sparsify=sentinel,
adjoin=False,
names=False)
level_lengths = get_level_lengths(levels, sentinel)
inner_lvl = len(level_lengths) - 1
for lnum, (records,
values) in enumerate(zip(level_lengths, levels)):
if truncate_h:
# modify the header lines
ins_col = self.fmt.tr_col_num
if self.fmt.sparsify:
recs_new = {}
# Increment tags after ... col.
for tag, span in list(records.items()):
if tag >= ins_col:
recs_new[tag + 1] = span
elif tag + span > ins_col:
recs_new[tag] = span + 1
if lnum == inner_lvl:
values = (values[:ins_col] + (u('...'), ) +
values[ins_col:])
else:
# sparse col headers do not receive a ...
values = (values[:ins_col] +
(values[ins_col - 1], ) +
values[ins_col:])
else:
recs_new[tag] = span
# if ins_col lies between tags, all col headers
# get ...
if tag + span == ins_col:
recs_new[ins_col] = 1
values = (values[:ins_col] + (u('...'), ) +
values[ins_col:])
records = recs_new
inner_lvl = len(level_lengths) - 1
if lnum == inner_lvl:
records[ins_col] = 1
else:
recs_new = {}
for tag, span in list(records.items()):
if tag >= ins_col:
recs_new[tag + 1] = span
else:
recs_new[tag] = span
recs_new[ins_col] = 1
records = recs_new
values = (values[:ins_col] + [u('...')] +
values[ins_col:])
# see gh-22579
# Column Offset Bug with to_html(index=False) with
# MultiIndex Columns and Index.
# Initially fill row with blank cells before column names.
# TODO: Refactor to remove code duplication with code
# block below for standard columns index.
row = [''] * (self.row_levels - 1)
if self.fmt.index or self.show_col_idx_names:
# see gh-22747
# If to_html(index_names=False) do not show columns
# index names.
# TODO: Refactor to use _get_column_name_list from
# DataFrameFormatter class and create a
# _get_formatted_column_labels function for code
# parity with DataFrameFormatter class.
if self.fmt.show_index_names:
name = self.columns.names[lnum]
row.append(pprint_thing(name or ''))
else:
row.append('')
tags = {}
j = len(row)
for i, v in enumerate(values):
if i in records:
if records[i] > 1:
tags[j] = template.format(span=records[i])
else:
continue
j += 1
row.append(v)
self.write_tr(row,
indent,
self.indent_delta,
tags=tags,
header=True)
else:
# see gh-22579
# Column misalignment also occurs for
# a standard index when the columns index is named.
# Initially fill row with blank cells before column names.
# TODO: Refactor to remove code duplication with code block
# above for columns MultiIndex.
row = [''] * (self.row_levels - 1)
if self.fmt.index or self.show_col_idx_names:
# see gh-22747
# If to_html(index_names=False) do not show columns
# index names.
# TODO: Refactor to use _get_column_name_list from
# DataFrameFormatter class.
if self.fmt.show_index_names:
row.append(self.columns.name or '')
else:
row.append('')
row.extend(self.columns)
align = self.fmt.justify
if truncate_h:
ins_col = self.row_levels + self.fmt.tr_col_num
row.insert(ins_col, '...')
self.write_tr(row,
indent,
self.indent_delta,
header=True,
align=align)
def _write_col_header(self, indent):
truncate_h = self.fmt.truncate_h
if isinstance(self.columns, ABCMultiIndex):
template = 'colspan="{span:d}" halign="left"'
if self.fmt.sparsify:
# GH3547
sentinel = com.sentinel_factory()
else:
sentinel = False
levels = self.columns.format(sparsify=sentinel, adjoin=False,
names=False)
level_lengths = get_level_lengths(levels, sentinel)
inner_lvl = len(level_lengths) - 1
for lnum, (records, values) in enumerate(zip(level_lengths,
levels)):
if truncate_h:
# modify the header lines
ins_col = self.fmt.tr_col_num
if self.fmt.sparsify:
recs_new = {}
# Increment tags after ... col.
for tag, span in list(records.items()):
if tag >= ins_col:
recs_new[tag + 1] = span
elif tag + span > ins_col:
recs_new[tag] = span + 1
if lnum == inner_lvl:
values = (values[:ins_col] + (u('...'),) +
values[ins_col:])
else:
# sparse col headers do not receive a ...
values = (values[:ins_col] +
(values[ins_col - 1], ) +
values[ins_col:])
else:
recs_new[tag] = span
# if ins_col lies between tags, all col headers
# get ...
if tag + span == ins_col:
recs_new[ins_col] = 1
values = (values[:ins_col] + (u('...'),) +
values[ins_col:])
records = recs_new
inner_lvl = len(level_lengths) - 1
if lnum == inner_lvl:
records[ins_col] = 1
else:
recs_new = {}
for tag, span in list(records.items()):
if tag >= ins_col:
recs_new[tag + 1] = span
else:
recs_new[tag] = span
recs_new[ins_col] = 1
records = recs_new
values = (values[:ins_col] + [u('...')] +
values[ins_col:])
# see gh-22579
# Column Offset Bug with to_html(index=False) with
# MultiIndex Columns and Index.
# Initially fill row with blank cells before column names.
# TODO: Refactor to remove code duplication with code
# block below for standard columns index.
row = [''] * (self.row_levels - 1)
if self.fmt.index or self.show_col_idx_names:
# see gh-22747
# If to_html(index_names=False) do not show columns
# index names.
# TODO: Refactor to use _get_column_name_list from
# DataFrameFormatter class and create a
# _get_formatted_column_labels function for code
# parity with DataFrameFormatter class.
if self.fmt.show_index_names:
name = self.columns.names[lnum]
row.append(pprint_thing(name or ''))
else:
row.append('')
tags = {}
j = len(row)
for i, v in enumerate(values):
if i in records:
if records[i] > 1:
tags[j] = template.format(span=records[i])
else:
continue
j += 1
row.append(v)
self.write_tr(row, indent, self.indent_delta, tags=tags,
header=True)
else:
# see gh-22579
# Column misalignment also occurs for
# a standard index when the columns index is named.
# Initially fill row with blank cells before column names.
# TODO: Refactor to remove code duplication with code block
# above for columns MultiIndex.
row = [''] * (self.row_levels - 1)
if self.fmt.index or self.show_col_idx_names:
# see gh-22747
# If to_html(index_names=False) do not show columns
# index names.
# TODO: Refactor to use _get_column_name_list from
# DataFrameFormatter class.
if self.fmt.show_index_names:
row.append(self.columns.name or '')
else:
row.append('')
row.extend(self.columns)
align = self.fmt.justify
if truncate_h:
ins_col = self.row_levels + self.fmt.tr_col_num
row.insert(ins_col, '...')
self.write_tr(row, indent, self.indent_delta, header=True,
align=align)
