Skip to content

Excelfancy #2370

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

Merged
merged 11 commits into from
Nov 29, 2012
Merged

Excelfancy #2370

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
b1e916e
excel format
Nov 21, 2012
bce9118
excel format
Nov 21, 2012
b178066
excel format
Nov 21, 2012
afde3f2
adding na_repl, cols argument to excel formatter
Nov 22, 2012
d354267
adding float_format to ExcelFormatter
Nov 22, 2012
c99dc49
Merge branch 'master' into excelfancy
Nov 27, 2012
f13d093
excelformatter handles multiindex, aliases
Nov 28, 2012
9ae35f8
hadling all attributes
Nov 28, 2012
5138bdc
reader bug fix (colnames was None.1,....), datetime hadling, period
Nov 28, 2012
c1708b2
adding styling test
Nov 28, 2012
389da90
adding argument has index_labels to excel reader to handle index_lab…
Nov 29, 2012
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
215 changes: 215 additions & 0 deletions pandas/core/format.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,6 +17,9 @@

import numpy as np

import itertools


docstring_to_string = """
Parameters
----------
Expand Down Expand Up @@ -400,6 +403,7 @@ def _get_column_name_list(self):
names.append('' if columns.name is None else columns.name)
return names


class HTMLFormatter(object):

indent_delta = 2
Expand Down Expand Up @@ -674,6 +678,217 @@ def grouper(x):

return result


#from collections import namedtuple
# ExcelCell = namedtuple("ExcelCell",
# 'row, col, val, style, mergestart, mergeend')

class ExcelCell:
__fields__ = ('row', 'col', 'val', 'style', 'mergestart', 'mergeend')
__slots__ = __fields__

def __init__(self, row, col, val,
style=None, mergestart=None, mergeend=None):
self.row = row
self.col = col
self.val = val
self.style = style
self.mergestart = mergestart
self.mergeend = mergeend


header_style = {"font": {"bold": True},
"borders": {"top": "thin",
"right": "thin",
"bottom": "thin",
"left": "thin"},
"alignment": {"horizontal": "center"}}


class ExcelFormatter(object):
"""
Class for formatting a DataFrame to a list of ExcelCells,

Parameters
----------
df : dataframe
na_rep: na representation
float_format : string, default None
Format string for floating point numbers
cols : sequence, optional
Columns to write
header : boolean or list of string, default True
Write out column names. If a list of string is given it is
assumed to be aliases for the column names
index : boolean, default True
output row names (index)
index_label : string or sequence, default None
Column label for index column(s) if desired. If None is given, and
`header` and `index` are True, then the index names are used. A
sequence should be given if the DataFrame uses MultiIndex.
"""

def __init__(self,
df,
na_rep='',
float_format=None,
cols=None,
header=True,
index=True,
index_label=None
):
self.df = df
self.rowcounter = 0
self.na_rep = na_rep
self.columns = cols
if cols is None:
self.columns = df.columns
self.float_format = float_format
self.index = index
self.index_label = index_label
self.header = header

def _format_value(self, val):
if lib.checknull(val):
val = self.na_rep
if self.float_format is not None and com.is_float(val):
val = float(self.float_format % val)
return val

def _format_header_mi(self):
levels = self.columns.format(sparsify=True, adjoin=False,
names=False)
level_lenghts = _get_level_lengths(levels)
coloffset = 0
if isinstance(self.df.index, MultiIndex):
coloffset = len(self.df.index[0]) - 1

for lnum, (records, values) in enumerate(zip(level_lenghts,
levels)):
name = self.columns.names[lnum]
yield ExcelCell(lnum, coloffset, name, header_style)
for i in records:
if records[i] > 1:
yield ExcelCell(lnum,coloffset + i + 1, values[i],
header_style, lnum, coloffset + i + records[i])
else:
yield ExcelCell(lnum, coloffset + i + 1, values[i], header_style)

self.rowcounter = lnum

def _format_header_regular(self):
has_aliases = isinstance(self.header, (tuple, list, np.ndarray))
if has_aliases or self.header:
coloffset = 0
if self.index:
coloffset = 1
if isinstance(self.df.index, MultiIndex):
coloffset = len(self.df.index[0])

colnames = self.columns
if has_aliases:
if len(self.header) != len(self.columns):
raise ValueError(('Writing %d cols but got %d aliases'
% (len(self.columns), len(self.header))))
else:
colnames = self.header

for colindex, colname in enumerate(colnames):
yield ExcelCell(self.rowcounter, colindex + coloffset, colname,
header_style)

def _format_header(self):
if isinstance(self.columns, MultiIndex):
gen = self._format_header_mi()
else:
gen = self._format_header_regular()

gen2 = ()
if self.df.index.names:
row = [x if x is not None else ''
for x in self.df.index.names] + [''] * len(self.columns)
if reduce(lambda x, y: x and y, map(lambda x: x != '', row)):
gen2 = (ExcelCell(self.rowcounter, colindex, val, header_style)
for colindex, val in enumerate(row))
self.rowcounter += 1
return itertools.chain(gen, gen2)

def _format_body(self):

if isinstance(self.df.index, MultiIndex):
return self._format_hierarchical_rows()
else:
return self._format_regular_rows()

def _format_regular_rows(self):
self.rowcounter += 1

coloffset = 0
#output index and index_label?
if self.index:
#chek aliases
#if list only take first as this is not a MultiIndex
if self.index_label and isinstance(self.index_label,
(list, tuple, np.ndarray)):
index_label = self.index_label[0]
#if string good to go
elif self.index_label and isinstance(self.index_label, str):
index_label = self.index_label
else:
index_label = self.df.index.names[0]

if index_label:
yield ExcelCell(self.rowcounter, 0,
index_label, header_style)
self.rowcounter += 1

#write index_values
index_values = self.df.index
coloffset = 1
for idx, idxval in enumerate(index_values):
yield ExcelCell(self.rowcounter + idx, 0, idxval, header_style)

for colidx, colname in enumerate(self.columns):
series = self.df[colname]
for i, val in enumerate(series):
yield ExcelCell(self.rowcounter + i, colidx + coloffset, val)

def _format_hierarchical_rows(self):
self.rowcounter += 1

gcolidx = 0
#output index and index_label?
if self.index:
index_labels = self.df.index.names
#check for aliases
if self.index_label and isinstance(self.index_label,
(list, tuple, np.ndarray)):
index_labels = self.index_label

#if index labels are not empty go ahead and dump
if filter(lambda x: x is not None, index_labels):
for cidx, name in enumerate(index_labels):
yield ExcelCell(self.rowcounter, cidx,
name, header_style)
self.rowcounter += 1

for indexcolvals in zip(*self.df.index):
for idx, indexcolval in enumerate(indexcolvals):
yield ExcelCell(self.rowcounter + idx, gcolidx,
indexcolval, header_style)
gcolidx += 1

for colidx, colname in enumerate(self.columns):
series = self.df[colname]
for i, val in enumerate(series):
yield ExcelCell(self.rowcounter + i, gcolidx + colidx, val)

def get_formatted_cells(self):
for cell in itertools.chain(self._format_header(),
self._format_body()):
cell.val = self._format_value(cell.val)
yield cell

#----------------------------------------------------------------------
# Array formatters

Expand Down
25 changes: 17 additions & 8 deletions pandas/core/frame.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1221,7 +1221,7 @@ def to_panel(self):

to_wide = deprecate('to_wide', to_panel)

def _helper_csvexcel(self, writer, na_rep=None, cols=None,
def _helper_csv(self, writer, na_rep=None, cols=None,
header=True, index=True,
index_label=None, float_format=None):
if cols is None:
Expand Down Expand Up @@ -1356,7 +1356,7 @@ def to_csv(self, path_or_buf, sep=",", na_rep='', float_format=None,
else:
csvout = csv.writer(f, lineterminator='\n', delimiter=sep,
quoting=quoting)
self._helper_csvexcel(csvout, na_rep=na_rep,
self._helper_csv(csvout, na_rep=na_rep,
float_format=float_format, cols=cols,
header=header, index=index,
index_label=index_label)
Expand All @@ -1367,7 +1367,7 @@ def to_csv(self, path_or_buf, sep=",", na_rep='', float_format=None,

def to_excel(self, excel_writer, sheet_name='sheet1', na_rep='',
float_format=None, cols=None, header=True, index=True,
index_label=None):
index_label=None, startrow=0, startcol=0):
"""
Write DataFrame to a excel sheet

Expand All @@ -1392,6 +1392,9 @@ def to_excel(self, excel_writer, sheet_name='sheet1', na_rep='',
Column label for index column(s) if desired. If None is given, and
`header` and `index` are True, then the index names are used. A
sequence should be given if the DataFrame uses MultiIndex.
startow : upper left cell row to dump data frame
startcol : upper left cell column to dump data frame


Notes
-----
Expand All @@ -1408,11 +1411,17 @@ def to_excel(self, excel_writer, sheet_name='sheet1', na_rep='',
if isinstance(excel_writer, basestring):
excel_writer = ExcelWriter(excel_writer)
need_save = True
excel_writer.cur_sheet = sheet_name
self._helper_csvexcel(excel_writer, na_rep=na_rep,
float_format=float_format, cols=cols,
header=header, index=index,
index_label=index_label)

formatter = fmt.ExcelFormatter(self,
na_rep=na_rep,
cols=cols,
header=header,
float_format=float_format,
index=index,
index_label=index_label)
formatted_cells = formatter.get_formatted_cells()
excel_writer.write_cells(formatted_cells, sheet_name,
startrow=startrow, startcol=startcol)
if need_save:
excel_writer.save()

Expand Down
Loading