Skip to content

ENH: #3335 Pivot table support for setting name of margins column. #10296

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

Closed
wants to merge 1 commit into from
Closed

ENH: #3335 Pivot table support for setting name of margins column. #10296

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
71 changes: 52 additions & 19 deletions pandas/tools/pivot.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,20 +1,22 @@
# pylint: disable=E1103

import warnings

from pandas import Series, DataFrame
from pandas.core.index import MultiIndex, Index
from pandas.core.groupby import Grouper
from pandas.tools.merge import concat
from pandas.tools.util import cartesian_product
from pandas.compat import range, lrange, zip
from pandas.util.decorators import deprecate_kwarg
from pandas import compat
import pandas.core.common as com
import numpy as np

DEFAULT_MARGIN_COLUMN_NAME = 'All'


def pivot_table(data, values=None, index=None, columns=None, aggfunc='mean',
fill_value=None, margins=False, dropna=True):
fill_value=None, margins=False, dropna=True,
margins_column=DEFAULT_MARGIN_COLUMN_NAME):
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

no need to have another variable for this, just set it here in the constructor.

how about call this margins_name

"""
Create a spreadsheet-style pivot table as a DataFrame. The levels in the
pivot table will be stored in MultiIndex objects (hierarchical indexes) on
Expand All @@ -40,6 +42,9 @@ def pivot_table(data, values=None, index=None, columns=None, aggfunc='mean',
Add all row / columns (e.g. for subtotal / grand totals)
dropna : boolean, default True
Do not include columns whose entries are all NaN
margins_column : string, default 'All'
Name of the row / column that will contain the totals
when margins is True.

Examples
--------
Expand Down Expand Up @@ -127,7 +132,7 @@ def pivot_table(data, values=None, index=None, columns=None, aggfunc='mean',
m = MultiIndex.from_arrays(cartesian_product(table.columns.levels))
table = table.reindex_axis(m, axis=1)
except AttributeError:
pass # it's a single level or a series
pass # it's a single level or a series

if isinstance(table, DataFrame):
if isinstance(table.columns, MultiIndex):
Expand All @@ -140,7 +145,8 @@ def pivot_table(data, values=None, index=None, columns=None, aggfunc='mean',

if margins:
table = _add_margins(table, data, values, rows=index,
cols=columns, aggfunc=aggfunc)
cols=columns, aggfunc=aggfunc,
margins_column=margins_column)

# discard the top level
if values_passed and not values_multi:
Expand All @@ -155,28 +161,50 @@ def pivot_table(data, values=None, index=None, columns=None, aggfunc='mean',
DataFrame.pivot_table = pivot_table


def _add_margins(table, data, values, rows, cols, aggfunc):
def _add_margins(table, data, values, rows, cols, aggfunc,
margins_column=DEFAULT_MARGIN_COLUMN_NAME):
exception_message = 'Must choose different value for margins_column'
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

maybe conflicting name for margins

for level in table.index.names:
if margins_column in table.index.get_level_values(level):
raise ValueError(exception_message)
# could be passed a Series object with no 'columns'
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

you can move this a bit lower (e.g. past 176)

if hasattr(table, 'columns'):
for level in table.columns.names[1:]:
if margins_column in table.columns.get_level_values(level):
raise ValueError(exception_message)

grand_margin = _compute_grand_margin(data, values, aggfunc)
grand_margin = _compute_grand_margin(data, values, aggfunc, margins_column)

if not values and isinstance(table, Series):
# If there are no values and the table is a series, then there is only
# one column in the data. Compute grand margin and return it.
row_key = ('All',) + ('',) * (len(rows) - 1) if len(rows) > 1 else 'All'
return table.append(Series({row_key: grand_margin['All']}))

if len(rows) > 1:
row_key = (margins_column,) + ('',) * (len(rows) - 1)
else:
row_key = margins_column

return table.append(Series({row_key: grand_margin[margins_column]}))

if values:
marginal_result_set = _generate_marginal_results(table, data, values, rows, cols, aggfunc, grand_margin)
marginal_result_set = _generate_marginal_results(table, data, values,
rows, cols, aggfunc,
grand_margin,
margins_column)
if not isinstance(marginal_result_set, tuple):
return marginal_result_set
result, margin_keys, row_margin = marginal_result_set
else:
marginal_result_set = _generate_marginal_results_without_values(table, data, rows, cols, aggfunc)
marginal_result_set = _generate_marginal_results_without_values(
table, data, rows, cols, aggfunc, margins_column)
if not isinstance(marginal_result_set, tuple):
return marginal_result_set
result, margin_keys, row_margin = marginal_result_set

key = ('All',) + ('',) * (len(rows) - 1) if len(rows) > 1 else 'All'
if len(rows) > 1:
key = (margins_column,) + ('',) * (len(rows) - 1)
else:
key = margins_column

row_margin = row_margin.reindex(result.columns)
# populate grand margin
Expand All @@ -195,7 +223,8 @@ def _add_margins(table, data, values, rows, cols, aggfunc):
return result


def _compute_grand_margin(data, values, aggfunc):
def _compute_grand_margin(data, values, aggfunc,
margins_column=DEFAULT_MARGIN_COLUMN_NAME):

if values:
grand_margin = {}
Expand All @@ -214,17 +243,19 @@ def _compute_grand_margin(data, values, aggfunc):
pass
return grand_margin
else:
return {'All': aggfunc(data.index)}
return {margins_column: aggfunc(data.index)}


def _generate_marginal_results(table, data, values, rows, cols, aggfunc, grand_margin):
def _generate_marginal_results(table, data, values, rows, cols, aggfunc,
grand_margin,
margins_column=DEFAULT_MARGIN_COLUMN_NAME):
if len(cols) > 0:
# need to "interleave" the margins
table_pieces = []
margin_keys = []

def _all_key(key):
return (key, 'All') + ('',) * (len(cols) - 1)
return (key, margins_column) + ('',) * (len(cols) - 1)

if len(rows) > 0:
margin = data[rows + values].groupby(rows).agg(aggfunc)
Expand Down Expand Up @@ -269,15 +300,17 @@ def _all_key(key):
return result, margin_keys, row_margin


def _generate_marginal_results_without_values(table, data, rows, cols, aggfunc):
def _generate_marginal_results_without_values(
table, data, rows, cols, aggfunc,
margins_column=DEFAULT_MARGIN_COLUMN_NAME):
if len(cols) > 0:
# need to "interleave" the margins
margin_keys = []

def _all_key():
if len(cols) == 1:
return 'All'
return ('All', ) + ('', ) * (len(cols) - 1)
return margins_column
return (margins_column, ) + ('', ) * (len(cols) - 1)

if len(rows) > 0:
margin = data[rows].groupby(rows).apply(aggfunc)
Expand Down
151 changes: 97 additions & 54 deletions pandas/tools/tests/test_pivot.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,7 @@
from pandas import DataFrame, Series, Index, MultiIndex, Grouper
from pandas.tools.merge import concat
from pandas.tools.pivot import pivot_table, crosstab
from pandas.tools.pivot import DEFAULT_MARGIN_COLUMN_NAME
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

you know its defaulted to All, so just use that directly.

from pandas.compat import range, u, product
import pandas.util.testing as tm

Expand Down Expand Up @@ -224,82 +225,106 @@ def test_pivot_with_tz(self):
tm.assert_frame_equal(pv, expected)

def test_margins(self):
def _check_output(res, col, index=['A', 'B'], columns=['C']):
cmarg = res['All'][:-1]
exp = self.data.groupby(index)[col].mean()
tm.assert_series_equal(cmarg, exp, check_names=False)
self.assertEqual(cmarg.name, 'All')

res = res.sortlevel()
rmarg = res.xs(('All', ''))[:-1]
exp = self.data.groupby(columns)[col].mean()
tm.assert_series_equal(rmarg, exp, check_names=False)
self.assertEqual(rmarg.name, ('All', ''))

gmarg = res['All']['All', '']
exp = self.data[col].mean()
self.assertEqual(gmarg, exp)
def _check_output(result, values_col, index=['A', 'B'],
columns=['C'],
margins_col=DEFAULT_MARGIN_COLUMN_NAME):
col_margins = result.ix[:-1, margins_col]
expected_col_margins = self.data.groupby(index)[values_col].mean()
tm.assert_series_equal(col_margins, expected_col_margins,
check_names=False)
self.assertEqual(col_margins.name, margins_col)

result = result.sortlevel()
index_margins = result.ix[(margins_col, '')].iloc[:-1]
expected_ix_margins = self.data.groupby(columns)[values_col].mean()
tm.assert_series_equal(index_margins, expected_ix_margins,
check_names=False)
self.assertEqual(index_margins.name, (margins_col, ''))

grand_total_margins = result.loc[(margins_col, ''), margins_col]
expected_total_margins = self.data[values_col].mean()
self.assertEqual(grand_total_margins, expected_total_margins)

# column specified
table = self.data.pivot_table('D', index=['A', 'B'], columns='C',
margins=True, aggfunc=np.mean)
_check_output(table, 'D')
result = self.data.pivot_table(values='D', index=['A', 'B'],
columns='C',
margins=True, aggfunc=np.mean)
_check_output(result, 'D')

# Set a different margins_column (not 'All')
result = self.data.pivot_table(values='D', index=['A', 'B'],
columns='C',
margins=True, aggfunc=np.mean,
margins_column='Totals')
_check_output(result, 'D', margins_col='Totals')

# no column specified
table = self.data.pivot_table(index=['A', 'B'], columns='C',
margins=True, aggfunc=np.mean)
for valcol in table.columns.levels[0]:
_check_output(table[valcol], valcol)
for value_col in table.columns.levels[0]:
_check_output(table[value_col], value_col)

# no col

# to help with a buglet
self.data.columns = [k * 2 for k in self.data.columns]
table = self.data.pivot_table(index=['AA', 'BB'], margins=True,
aggfunc=np.mean)
for valcol in table.columns:
gmarg = table[valcol]['All', '']
self.assertEqual(gmarg, self.data[valcol].mean())

# this is OK
table = self.data.pivot_table(index=['AA', 'BB'], margins=True,
aggfunc='mean')
for value_col in table.columns:
totals = table.loc[(DEFAULT_MARGIN_COLUMN_NAME, ''), value_col]
self.assertEqual(totals, self.data[value_col].mean())

# no rows
rtable = self.data.pivot_table(columns=['AA', 'BB'], margins=True,
aggfunc=np.mean)
tm.assert_isinstance(rtable, Series)

table = self.data.pivot_table(index=['AA', 'BB'], margins=True,
aggfunc='mean')
for item in ['DD', 'EE', 'FF']:
gmarg = table[item]['All', '']
self.assertEqual(gmarg, self.data[item].mean())
totals = table.loc[(DEFAULT_MARGIN_COLUMN_NAME, ''), item]
self.assertEqual(totals, self.data[item].mean())

# issue number #8349: pivot_table with margins and dictionary aggfunc
data = [
{'JOB': 'Worker', 'NAME': 'Bob', 'YEAR': 2013,
'MONTH': 12, 'DAYS': 3, 'SALARY': 17},
{'JOB': 'Employ', 'NAME':
'Mary', 'YEAR': 2013, 'MONTH': 12, 'DAYS': 5, 'SALARY': 23},
{'JOB': 'Worker', 'NAME': 'Bob', 'YEAR': 2014,
'MONTH': 1, 'DAYS': 10, 'SALARY': 100},
{'JOB': 'Worker', 'NAME': 'Bob', 'YEAR': 2014,
'MONTH': 1, 'DAYS': 11, 'SALARY': 110},
{'JOB': 'Employ', 'NAME': 'Mary', 'YEAR': 2014,
'MONTH': 1, 'DAYS': 15, 'SALARY': 200},
{'JOB': 'Worker', 'NAME': 'Bob', 'YEAR': 2014,
'MONTH': 2, 'DAYS': 8, 'SALARY': 80},
{'JOB': 'Employ', 'NAME': 'Mary', 'YEAR': 2014,
'MONTH': 2, 'DAYS': 5, 'SALARY': 190},
]

df=DataFrame([ {'JOB':'Worker','NAME':'Bob' ,'YEAR':2013,'MONTH':12,'DAYS': 3,'SALARY': 17},
{'JOB':'Employ','NAME':'Mary','YEAR':2013,'MONTH':12,'DAYS': 5,'SALARY': 23},
{'JOB':'Worker','NAME':'Bob' ,'YEAR':2014,'MONTH': 1,'DAYS':10,'SALARY':100},
{'JOB':'Worker','NAME':'Bob' ,'YEAR':2014,'MONTH': 1,'DAYS':11,'SALARY':110},
{'JOB':'Employ','NAME':'Mary','YEAR':2014,'MONTH': 1,'DAYS':15,'SALARY':200},
{'JOB':'Worker','NAME':'Bob' ,'YEAR':2014,'MONTH': 2,'DAYS': 8,'SALARY': 80},
{'JOB':'Employ','NAME':'Mary','YEAR':2014,'MONTH': 2,'DAYS': 5,'SALARY':190} ])

df=df.set_index(['JOB','NAME','YEAR','MONTH'],drop=False,append=False)

rs=df.pivot_table( index=['JOB','NAME'],
columns=['YEAR','MONTH'],
values=['DAYS','SALARY'],
aggfunc={'DAYS':'mean','SALARY':'sum'},
margins=True)
df = DataFrame(data)

ex=df.pivot_table(index=['JOB','NAME'],columns=['YEAR','MONTH'],values=['DAYS'],aggfunc='mean',margins=True)
df = df.set_index(['JOB', 'NAME', 'YEAR', 'MONTH'], drop=False,
append=False)

tm.assert_frame_equal(rs['DAYS'], ex['DAYS'])
result = df.pivot_table(index=['JOB', 'NAME'],
columns=['YEAR', 'MONTH'],
values=['DAYS', 'SALARY'],
aggfunc={'DAYS': 'mean', 'SALARY': 'sum'},
margins=True)

ex=df.pivot_table(index=['JOB','NAME'],columns=['YEAR','MONTH'],values=['SALARY'],aggfunc='sum',margins=True)
expected = df.pivot_table(index=['JOB', 'NAME'],
columns=['YEAR', 'MONTH'], values=['DAYS'],
aggfunc='mean', margins=True)

tm.assert_frame_equal(rs['SALARY'], ex['SALARY'])
tm.assert_frame_equal(result['DAYS'], expected['DAYS'])

expected = df.pivot_table(index=['JOB', 'NAME'],
columns=['YEAR', 'MONTH'], values=['SALARY'],
aggfunc='sum', margins=True)

tm.assert_frame_equal(result['SALARY'], expected['SALARY'])

def test_pivot_integer_columns(self):
# caused by upstream bug in unstack
Expand Down Expand Up @@ -402,6 +427,24 @@ def test_margins_no_values_two_row_two_cols(self):
result = self.data[['A', 'B', 'C', 'D']].pivot_table(index=['A', 'B'], columns=['C', 'D'], aggfunc=len, margins=True)
self.assertEqual(result.All.tolist(), [3.0, 1.0, 4.0, 3.0, 11.0])

def test_pivot_table_with_margins_set_margin_column(self):
for margin_column in ['foo', 'one']:
with self.assertRaises(ValueError):
# multi-index index
pivot_table(self.data, values='D', index=['A', 'B'],
columns=['C'], margins=True,
margins_column=margin_column)
with self.assertRaises(ValueError):
# multi-index column
pivot_table(self.data, values='D', index=['C'],
columns=['A', 'B'], margins=True,
margins_column=margin_column)
with self.assertRaises(ValueError):
# non-multi-index index/column
pivot_table(self.data, values='D', index=['A'],
columns=['B'], margins=True,
margins_column=margin_column)

def test_pivot_timegrouper(self):
df = DataFrame({
'Branch' : 'A A A A A A A B'.split(),
Expand Down Expand Up @@ -678,17 +721,17 @@ def test_crosstab_margins(self):
self.assertEqual(result.index.names, ('a',))
self.assertEqual(result.columns.names, ['b', 'c'])

all_cols = result['All', '']
all_cols = result[DEFAULT_MARGIN_COLUMN_NAME, '']
exp_cols = df.groupby(['a']).size().astype('i8')
exp_cols = exp_cols.append(Series([len(df)], index=['All']))
exp_cols.name = ('All', '')
exp_cols = exp_cols.append(Series([len(df)], index=[DEFAULT_MARGIN_COLUMN_NAME]))
exp_cols.name = (DEFAULT_MARGIN_COLUMN_NAME, '')

tm.assert_series_equal(all_cols, exp_cols)

all_rows = result.ix['All']
all_rows = result.ix[DEFAULT_MARGIN_COLUMN_NAME]
exp_rows = df.groupby(['b', 'c']).size().astype('i8')
exp_rows = exp_rows.append(Series([len(df)], index=[('All', '')]))
exp_rows.name = 'All'
exp_rows = exp_rows.append(Series([len(df)], index=[(DEFAULT_MARGIN_COLUMN_NAME, '')]))
exp_rows.name = DEFAULT_MARGIN_COLUMN_NAME

exp_rows = exp_rows.reindex(all_rows.index)
exp_rows = exp_rows.fillna(0).astype(np.int64)
Expand Down