class Test_pivot_2(unittest.TestCase):
def setUp(self):
D={
'SUBJECT':[1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100],
'AGE':'old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young'.split(','),
'CONDITION':'counting,counting,counting,counting,counting,counting,counting,counting,counting,counting,rhyming,rhyming,rhyming,rhyming,rhyming,rhyming,rhyming,rhyming,rhyming,rhyming,adjective,adjective,adjective,adjective,adjective,adjective,adjective,adjective,adjective,adjective,imagery,imagery,imagery,imagery,imagery,imagery,imagery,imagery,imagery,imagery,intention,intention,intention,intention,intention,intention,intention,intention,intention,intention,counting,counting,counting,counting,counting,counting,counting,counting,counting,counting,rhyming,rhyming,rhyming,rhyming,rhyming,rhyming,rhyming,rhyming,rhyming,rhyming,adjective,adjective,adjective,adjective,adjective,adjective,adjective,adjective,adjective,adjective,imagery,imagery,imagery,imagery,imagery,imagery,imagery,imagery,imagery,imagery,intention,intention,intention,intention,intention,intention,intention,intention,intention,intention'.split(','),
'WORDS':[9,8,6,8,10,4,6,5,7,7,7,9,6,6,6,11,6,3,8,7,11,13,8,6,14,11,13,13,10,11,12,11,16,11,9,23,12,10,19,11,10,19,14,5,10,11,14,15,11,11,8,6,4,6,7,6,5,7,9,7,10,7,8,10,4,7,10,6,7,7,14,11,18,14,13,22,17,16,12,11,20,16,16,15,18,16,20,22,14,19,21,19,17,15,22,16,22,22,18,21],
}
self.df=DataFrame()
self.df.read_tbl('data/words~ageXcondition.csv')
def test12(self):
R="""\
avg(WORDS)
CONDITION AGE Value
==========================
adjective old 11
adjective young 14.800
counting old 7
counting young 6.500
imagery old 13.400
imagery young 17.600
intention old 12
intention young 19.300
rhyming old 6.900
rhyming young 7.600
==========================
Total 11.610 """
D = self.df.pivot('WORDS', rows=['CONDITION','AGE'])
list(D)
# verify the values in the table
self.failUnlessEqual(str(D),R)
def test13(self):
R="""\
avg(WORDS)
CONDITION=adjective, CONDITION=adjective, CONDITION=counting, CONDITION=counting, CONDITION=imagery, CONDITION=imagery, CONDITION=intention, CONDITION=intention, CONDITION=rhyming, CONDITION=rhyming, Total
AGE=old AGE=young AGE=old AGE=young AGE=old AGE=young AGE=old AGE=young AGE=old AGE=young
==================================================================================================================================================================================================================================
11 14.800 7 6.500 13.400 17.600 12 19.300 6.900 7.600 11.610 """
D = self.df.pivot('WORDS', cols=['CONDITION','AGE'])
# verify the values in the table
self.failUnlessEqual(str(D),R)
def long2wide(in_fname,
id,
dvs,
between=[],
within=[],
covariates=[],
out_fname=None,
nested=True):
# load in_fname into a PyvtTbl object
print(('reading "%s"...' % in_fname))
cls = DataFrame()
cls.read_tbl(in_fname)
# loop through DVs and append within columns
d = [sorted(set(cls[id]))]
header = [id] + covariates + between
for col in covariates + between:
z = cls.pivot(col, cols=[id], aggregate='arbitrary')
d.extend(list(z))
# start controls whether nested factors are examined
if nested: start = 1
else: start = len(within)
for i, dv in enumerate(dvs):
print(('\ncollaborating %s' % dv))
for j in _xrange(start, len(within) + 1):
for factors in _xunique_combinations(within, j):
print((' pivoting', factors, '...'))
z = cls.pivot(dv, rows=factors, cols=[id], aggregate='avg')
d.extend(list(z))
# process headers
for names in z.rnames:
h = '_'.join(('%s.%s' % (f, str(c)) for (f, c) in names))
header.append('%s__%s' % (dv, h))
# Now we can write the data
if out_fname == None:
out_fname = 'wide_data.csv'
with open(out_fname, 'wb') as f:
wtr = csv.writer(f)
wtr.writerow([n.upper() for n in header])
wtr.writerows(list(zip(*d))) # transpose and write
def test2(self):
df=DataFrame()
df.read_tbl('data/error~subjectXtimeofdayXcourseXmodel_MISSING.csv')
pt = df.pivot('ERROR', ['MODEL','TIMEOFDAY'],['COURSE'],where=['SUBJECT != 1'])
self.assertEqual(repr(eval(repr(pt))), repr(pt))
def test4(self):
"""method='full', aggregate=count, invalid row"""
R = """\
count(id)
member Name=name1, Name=name1, Name=name2, Name=name2, Total
Year=2010 Year=2011 Year=2010 Year=2011
======================================================================
N 0 1 -- 0 1
Y 1 0 -- 1 2
======================================================================
Total 1 1 -- 1 3 """
df = DataFrame()
df.insert({'id': 0, 'Name': 'name1', 'Year': 2010, 'member': 'Y'})
df.insert({'id': 1, 'Name': 'name1', 'Year': 2011, 'member': 'N'})
df.insert({'id': 2, 'Name': 'name2', 'Year': 2011, 'member': 'Y'})
my_pivot = df.pivot('id',
rows=['member'],
cols=['Name', 'Year'],
aggregate='count',
method='full')
self.assertEqual(R, str(my_pivot))
def test3(self):
"""method='full', aggregate=count, invalid row"""
R = """\
count(id)
Name Year member=N member=Y Total
==========================================
name1 2010 0 1 1
name1 2011 1 0 1
name2 2010 -- -- --
name2 2011 0 1 1
==========================================
Total 1 2 3 """
df = DataFrame()
df.insert({'id': 0, 'Name': 'name1', 'Year': 2010, 'member': 'Y'})
df.insert({'id': 1, 'Name': 'name1', 'Year': 2011, 'member': 'N'})
df.insert({'id': 2, 'Name': 'name2', 'Year': 2011, 'member': 'Y'})
my_pivot = df.pivot('id',
rows=['Name', 'Year'],
cols=['member'],
aggregate='count',
method='full')
self.assertEqual(R, str(my_pivot))
def test0(self):
df = DataFrame()
df.read_tbl('data/error~subjectXtimeofdayXcourseXmodel_MISSING.csv')
pt = df.pivot('ERROR', ['TIMEOFDAY'], ['COURSE'])
self.assertAlmostEqual(3.22222222222, pt[1, 0], 5)
def test4(self):
"""method='full', aggregate=tolist, invalid col"""
R = """\
tolist(id)
member Name=name1, Name=name1, Name=name2, Name=name2,
Year=2010 Year=2011 Year=2010 Year=2011
==================================================================
N [None, None] [1.0, 1.0] [None, None] [None, None]
Y [0.0, 0.0] [None, None] [None, None] [2.0, 2.0] """
df = DataFrame()
df.insert({'id':0,'Name':'name1','Year':2010,'member':'Y','rep':1})
df.insert({'id':1,'Name':'name1','Year':2011,'member':'N','rep':1})
df.insert({'id':2,'Name':'name2','Year':2011,'member':'Y','rep':1})
df.insert({'id':0,'Name':'name1','Year':2010,'member':'Y','rep':2})
df.insert({'id':1,'Name':'name1','Year':2011,'member':'N','rep':2})
df.insert({'id':2,'Name':'name2','Year':2011,'member':'Y','rep':2})
my_pivot = df.pivot('id',rows = ['member'], cols = ['Name','Year'],
aggregate='tolist', method='full')
## print(my_pivot)
self.assertEqual(R,str(my_pivot))
def test3(self):
"""method='full', aggregate=tolist, invalid row"""
R = """\
tolist(id)
Name Year member=N member=Y
==========================================
name1 2010 [None, None] [0.0, 0.0]
name1 2011 [1.0, 1.0] [None, None]
name2 2010 [None, None] [None, None]
name2 2011 [None, None] [2.0, 2.0] """
df = DataFrame()
df.insert({'id':0,'Name':'name1','Year':2010,'member':'Y','rep':1})
df.insert({'id':1,'Name':'name1','Year':2011,'member':'N','rep':1})
df.insert({'id':2,'Name':'name2','Year':2011,'member':'Y','rep':1})
df.insert({'id':0,'Name':'name1','Year':2010,'member':'Y','rep':2})
df.insert({'id':1,'Name':'name1','Year':2011,'member':'N','rep':2})
df.insert({'id':2,'Name':'name2','Year':2011,'member':'Y','rep':2})
my_pivot = df.pivot('id',rows = ['Name','Year'], cols = ['member'],
aggregate='tolist', method='full')
## print(my_pivot)
self.assertEqual(R,str(my_pivot))
def test0(self):
df=DataFrame()
df.read_tbl('data/error~subjectXtimeofdayXcourseXmodel_MISSING.csv')
pt = df.pivot('ERROR', ['TIMEOFDAY'],['COURSE'])
self.assertAlmostEqual(3.22222222222,pt[1,0],5)
def test1(self):
df = DataFrame()
df.read_tbl('data/error~subjectXtimeofdayXcourseXmodel_MISSING.csv')
pt = df.pivot('ERROR', ['TIMEOFDAY', 'MODEL'], ['COURSE'])
self.assertEqual(repr(eval(repr(pt))), repr(pt))
def export_csv_pivot(request, entidad=1, ano=str(date.today().year)):
consumos = Consumo.objects.filter(entidad__pk=entidad, ano=ano)
from collections import namedtuple
LineaDetalle = namedtuple('LineaDetalle',[u'Año', "Mes", 'Local_o_Vehiculo', "Consumo", "Valor"])
df = DataFrame()
for c in consumos:
if c.content_type.id == 16:
denominacion = Local.objects.get(pk=c.object_id).denominacion
else:
denominacion = Vehiculo.objects.get(pk=c.object_id).denominacion
df.insert(LineaDetalle(c.ano, c.mes, denominacion.encode("utf-8"), c.medida.denominacion.encode("utf-8"), c.valor)._asdict())
pt = df.pivot("Valor", ['Local_o_Vehiculo','Consumo'], ['Mes'])
# get the response object, this can be used as a stream.
response = HttpResponse(mimetype='text/csv')
# force download.
response['Content-Disposition'] = 'attachment;filename=export.csv'
response.write(pt)
return response
def long2wide(in_fname, id, dvs, between=[], within=[],
covariates=[], out_fname=None, nested=True):
# load in_fname into a PyvtTbl object
print('reading "%s"...'%in_fname)
cls = DataFrame()
cls.read_tbl(in_fname)
# loop through DVs and append within columns
d = [sorted(set(cls[id]))]
header = [id] + covariates + between
for col in covariates+between:
z = cls.pivot(col, cols=[id], aggregate='arbitrary')
d.extend(list(z))
# start controls whether nested factors are examined
if nested : start = 1
else : start = len(within)
for i, dv in enumerate(dvs):
print('\ncollaborating %s'%dv)
for j in _xrange(start, len(within)+1):
for factors in _xunique_combinations(within, j):
print(' pivoting', factors, '...')
z = cls.pivot(dv, rows=factors, cols=[id],
aggregate='avg')
d.extend(list(z))
# process headers
for names in z.rnames:
h = '_'.join(('%s.%s'%(f, str(c)) for (f,c) in names))
header.append('%s__%s'%(dv, h))
# Now we can write the data
if out_fname == None:
out_fname = 'wide_data.csv'
with open(out_fname,'wb') as f:
wtr = csv.writer(f)
wtr.writerow([n.upper() for n in header])
wtr.writerows(zip(*d)) # transpose and write
def test2(self):
R =[7.16666666667, 6.5, 4.0, 3.22222222222, 2.88888888889, 1.55555555556]
df=DataFrame()
df.read_tbl('data/error~subjectXtimeofdayXcourseXmodel_MISSING.csv')
pt = df.pivot('ERROR', cols=['TIMEOFDAY','COURSE'])
pt_flat = pt.flatten()
for r,d in zip(R,pt_flat):
self.assertAlmostEqual(r,d)
def test2(self):
R =[7.16666666667, 6.5, 4.0,
3.22222222222, 2.88888888889, 1.55555555556]
df=DataFrame()
df.read_tbl('data/error~subjectXtimeofdayXcourseXmodel_MISSING.csv')
pt = df.pivot('ERROR', ['TIMEOFDAY','COURSE'])
for r,L in zip(R,pt.flat):
self.assertEqual('%.5f'%r, '%.5f'%L)
def test2(self):
R = """\
GROUP=AA, GROUP=AA, GROUP=AB, GROUP=AB, GROUP=LAB, GROUP=LAB,
AGE=old AGE=young AGE=old AGE=young AGE=old AGE=young
=======================================================================
22.188 9.813 29.188 10.041 34.141 11.875 """
df = DataFrame()
df.read_tbl('data/suppression~subjectXgroupXageXcycleXphase.csv')
pt = df.pivot('SUPPRESSION', cols=['GROUP', 'AGE'])
df2 = pt.to_dataframe()
self.assertEqual(str(df2), R)
def test5(self):
R = """\
avg(ERROR)
TIMEOFDAY COURSE=C1
=====================
T1 7.167
T2 3.222 """
df = DataFrame()
df.read_tbl('data/error~subjectXtimeofdayXcourseXmodel_MISSING.csv')
pt = df.pivot('ERROR', ['TIMEOFDAY'], ['COURSE'])
self.assertEqual(R, str(pt[:, 0]))
def test7(self):
R ="""\
avg(ERROR)
TIMEOFDAY COURSE=C1 COURSE=C2
=================================
T1 7.167 6.500 """
df=DataFrame()
df.read_tbl('data/error~subjectXtimeofdayXcourseXmodel_MISSING.csv')
pt = df.pivot('ERROR', ['TIMEOFDAY'],['COURSE'])
self.assertEqual(R, str(pt[0,:2]))
def test2(self):
R = """\
GROUP=AA, GROUP=AA, GROUP=AB, GROUP=AB, GROUP=LAB, GROUP=LAB,
AGE=old AGE=young AGE=old AGE=young AGE=old AGE=young
=======================================================================
22.188 9.813 29.188 10.041 34.141 11.875 """
df = DataFrame()
df.read_tbl('data/suppression~subjectXgroupXageXcycleXphase.csv')
pt = df.pivot('SUPPRESSION',
cols=['GROUP', 'AGE'])
df2 = pt.to_dataframe()
self.assertEqual(str(df2),R)
def test2(self):
R = [
7.16666666667, 6.5, 4.0, 3.22222222222, 2.88888888889,
1.55555555556
]
df = DataFrame()
df.read_tbl('data/error~subjectXtimeofdayXcourseXmodel_MISSING.csv')
pt = df.pivot('ERROR', ['TIMEOFDAY', 'COURSE'])
for r, L in zip(R, pt.flat):
self.assertEqual('%.5f' % r, '%.5f' % L)
def test3(self):
R = np.array(
[[7.16666667, 6.5, 4., 3.22222222, 2.88888889, 1.55555556]])
df = DataFrame()
df.read_tbl('data/error~subjectXtimeofdayXcourseXmodel_MISSING.csv')
pt = df.pivot('ERROR', cols=['TIMEOFDAY', 'COURSE'])
self.assertEqual(str(R.shape), str(pt.shape))
for r, L in zip(R.flatten(), pt.flatten()):
self.assertAlmostEqual(r, L)
def test4(self):
R = """\
avg(ERROR)
TIMEOFDAY COURSE=C1 COURSE=C2 COURSE=C3
=============================================
T2 3.222 2.889 1.556 """
df = DataFrame()
df.read_tbl('data/error~subjectXtimeofdayXcourseXmodel_MISSING.csv')
pt = df.pivot('ERROR', ['TIMEOFDAY'], ['COURSE'])
self.assertEqual(R, str(pt[-1:]))
def test0(self):
R = """\
TIME CONDITION=A CONDITION=B
=================================
day 1.864 1.933
night 1.622 1.731 """
df = DataFrame()
df.read_tbl('data/example.csv')
df['LOG10_X']=[math.log10(x) for x in df['X']]
pt = df.pivot('LOG10_X', ['TIME'], ['CONDITION'])
df2 = pt.to_dataframe()
self.assertEqual(str(df2),R)
def test0(self):
R = """\
TIME CONDITION=A CONDITION=B
=================================
day 1.864 1.933
night 1.622 1.731 """
df = DataFrame()
df.read_tbl('data/example.csv')
df['LOG10_X'] = [math.log10(x) for x in df['X']]
pt = df.pivot('LOG10_X', ['TIME'], ['CONDITION'])
df2 = pt.to_dataframe()
self.assertEqual(str(df2), R)
def test1(self):
R = """\
N/A(ERROR)
TIMEOFDAY COURSE=C1 COURSE=C2 COURSE=C3 Total
======================================================
T1 51.361 42.250 16 31.574
T2 10.383 8.346 2.420 6.531
======================================================
Total 23.040 18.778 7.716 15.178 """
df = DataFrame()
df.read_tbl('data/error~subjectXtimeofdayXcourseXmodel_MISSING.csv')
sums = df.pivot('ERROR', ['TIMEOFDAY'], ['COURSE'], aggregate='sum')
counts = df.pivot('ERROR', ['TIMEOFDAY'], ['COURSE'],
aggregate='count')
aves = df.pivot('ERROR', ['TIMEOFDAY'], ['COURSE'], aggregate='avg')
calc_aves = sums / counts.astype(np.float64)
## print('\n'.join(str(aves).split('\n')[1:]))
## print('\n'.join(str(calc_aves).split('\n')[1:]))
self.assertEqual('\n'.join(str(aves).split('\n')[1:]),
'\n'.join(str(calc_aves).split('\n')[1:]))
def test1(self):
R ="""\
N/A(ERROR)
TIMEOFDAY COURSE=C1 COURSE=C2 COURSE=C3 Total
======================================================
T1 51.361 42.250 16 31.574
T2 10.383 8.346 2.420 6.531
======================================================
Total 23.040 18.778 7.716 15.178 """
df=DataFrame()
df.read_tbl('data/error~subjectXtimeofdayXcourseXmodel_MISSING.csv')
sums = df.pivot('ERROR', ['TIMEOFDAY'],['COURSE'],aggregate='sum')
counts = df.pivot('ERROR', ['TIMEOFDAY'],['COURSE'],aggregate='count')
aves = df.pivot('ERROR', ['TIMEOFDAY'],['COURSE'],aggregate='avg')
calc_aves = sums/counts.astype(np.float64)
## print('\n'.join(str(aves).split('\n')[1:]))
## print('\n'.join(str(calc_aves).split('\n')[1:]))
self.assertEqual('\n'.join(str(aves).split('\n')[1:]),
'\n'.join(str(calc_aves).split('\n')[1:]))
def test1(self):
R = """\
avg(ERROR)
TIMEOFDAY=T1, TIMEOFDAY=T1, TIMEOFDAY=T1, TIMEOFDAY=T2, TIMEOFDAY=T2, TIMEOFDAY=T2, Total
COURSE=C1 COURSE=C2 COURSE=C3 COURSE=C1 COURSE=C2 COURSE=C3
=====================================================================================================
7.167 6.500 4 3.222 2.889 1.556 3.896 """
df = DataFrame()
df.read_tbl('data/error~subjectXtimeofdayXcourseXmodel_MISSING.csv')
pt = df.pivot('ERROR', rows=['TIMEOFDAY', 'COURSE'])
pt2 = pt.transpose()
self.assertEqual(str(pt2), R)
def test4(self):
R ="""\
avg(ERROR)
TIMEOFDAY COURSE=C1 COURSE=C2 COURSE=C3
=============================================
T2 3.222 2.889 1.556 """
df=DataFrame()
df.read_tbl('data/error~subjectXtimeofdayXcourseXmodel_MISSING.csv')
pt = df.pivot('ERROR', ['TIMEOFDAY'],['COURSE'])
self.assertEqual(R, str(pt[-1:]))
def test0(self):
# __add__ constant
R = """\
N/A(ERROR)
TIMEOFDAY COURSE=C1 COURSE=C2 COURSE=C3 Total
======================================================
T1 12.167 11.500 9 10.619
T2 8.222 7.889 6.556 7.556
======================================================
Total 9.800 9.333 7.778 8.896 """
df = DataFrame()
df.read_tbl('data/error~subjectXtimeofdayXcourseXmodel_MISSING.csv')
pt = df.pivot('ERROR', ['TIMEOFDAY'], ['COURSE'])
self.assertAlmostEqual(np.sum(pt), 25.3333333333, 5)
def test2(self):
# __add__ ndarray
R = """\
N/A(ERROR)
TIMEOFDAY COURSE=C1 COURSE=C2 COURSE=C3
=============================================
T1 12.167 11.500 9
T2 8.222 7.889 6.556 """
df = DataFrame()
df.read_tbl('data/error~subjectXtimeofdayXcourseXmodel_MISSING.csv')
pt = df.pivot('ERROR', ['TIMEOFDAY'], ['COURSE'])
pt2 = pt + np.array([[5, 5, 5], [5, 5, 5]])
self.assertEqual(str(pt2), R)
def test1(self):
R ="""\
avg(ERROR)
TIMEOFDAY=T1, TIMEOFDAY=T1, TIMEOFDAY=T1, TIMEOFDAY=T2, TIMEOFDAY=T2, TIMEOFDAY=T2, Total
COURSE=C1 COURSE=C2 COURSE=C3 COURSE=C1 COURSE=C2 COURSE=C3
=====================================================================================================
7.167 6.500 4 3.222 2.889 1.556 3.896 """
df=DataFrame()
df.read_tbl('data/error~subjectXtimeofdayXcourseXmodel_MISSING.csv')
pt = df.pivot('ERROR', rows=['TIMEOFDAY','COURSE'])
pt2 = pt.transpose()
self.assertEqual(str(pt2),R)
def test2(self):
# __add__ ndarray
R ="""\
N/A(ERROR)
TIMEOFDAY COURSE=C1 COURSE=C2 COURSE=C3
=============================================
T1 12.167 11.500 9
T2 8.222 7.889 6.556 """
df=DataFrame()
df.read_tbl('data/error~subjectXtimeofdayXcourseXmodel_MISSING.csv')
pt = df.pivot('ERROR', ['TIMEOFDAY'],['COURSE'])
pt2=pt+np.array([[5,5,5], [5,5,5]])
self.assertEqual(str(pt2),R)
def test0(self):
# __add__ constant
R ="""\
N/A(ERROR)
TIMEOFDAY COURSE=C1 COURSE=C2 COURSE=C3 Total
======================================================
T1 12.167 11.500 9 10.619
T2 8.222 7.889 6.556 7.556
======================================================
Total 9.800 9.333 7.778 8.896 """
df=DataFrame()
df.read_tbl('data/error~subjectXtimeofdayXcourseXmodel_MISSING.csv')
pt = df.pivot('ERROR', ['TIMEOFDAY'],['COURSE'])
self.assertAlmostEqual(np.sum(pt),25.3333333333, 5)
def test3(self):
R =[7.16666666667, 6.5, 4.0,
3.22222222222, 2.88888888889, 1.55555555556]
Rinds = [(0,0),(0,1),(0,2),(0,3),(0,4),(0,5)]
df=DataFrame()
df.read_tbl('data/error~subjectXtimeofdayXcourseXmodel_MISSING.csv')
pt = df.pivot('ERROR', cols=['TIMEOFDAY','COURSE'])
i=0
for inds,L in pt.ndenumerate():
self.assertEqual('%.5f'%L, '%.5f'%R[i])
self.assertEqual(str(inds), str(Rinds[i]))
i+=1
def test3(self):
R = """\
GROUP AGE Value
======================
AA old 22.188
AA young 9.813
AB old 29.188
AB young 10.041
LAB old 34.141
LAB young 11.875 """
df = DataFrame()
df.read_tbl('data/suppression~subjectXgroupXageXcycleXphase.csv')
pt = df.pivot('SUPPRESSION', rows=['GROUP', 'AGE'])
df2 = pt.to_dataframe()
self.assertEqual(str(df2), R)
def test3(self):
R = """\
GROUP AGE Value
======================
AA old 22.188
AA young 9.813
AB old 29.188
AB young 10.041
LAB old 34.141
LAB young 11.875 """
df = DataFrame()
df.read_tbl('data/suppression~subjectXgroupXageXcycleXphase.csv')
pt = df.pivot('SUPPRESSION',
rows=['GROUP', 'AGE'])
df2 = pt.to_dataframe()
self.assertEqual(str(df2),R)
def test3(self):
R =np.array([[7.16666667,
6.5,
4.,
3.22222222,
2.88888889,
1.55555556]])
df=DataFrame()
df.read_tbl('data/error~subjectXtimeofdayXcourseXmodel_MISSING.csv')
pt = df.pivot('ERROR', cols=['TIMEOFDAY','COURSE'])
self.assertEqual(str(R.shape),str(pt.shape))
for r,L in zip(R.flatten(),pt.flatten()):
self.assertAlmostEqual(r,L)
def test0(self):
R = """\
avg(ERROR)
COURSE TIMEOFDAY=T1 TIMEOFDAY=T2 Total
============================================
C1 7.167 3.222 4.800
C2 6.500 2.889 4.333
C3 4 1.556 2.778
============================================
Total 5.619 2.556 3.896 """
df = DataFrame()
df.read_tbl('data/error~subjectXtimeofdayXcourseXmodel_MISSING.csv')
pt = df.pivot('ERROR', ['TIMEOFDAY'], ['COURSE'])
pt2 = pt.transpose()
self.assertEqual(str(pt2), R)
def test0(self):
R = """\
avg(ERROR)
TIMEOFDAY COURSE=C1 COURSE=C2 COURSE=C3 Total
=====================================================
T1 7.167 6.500 4 5.619
T2 0 2.889 1.556 2.556
=====================================================
Total 4.800 4.333 2.778 3.896 """
df = DataFrame()
df.read_tbl("data/error~subjectXtimeofdayXcourseXmodel_MISSING.csv")
pt = df.pivot("ERROR", ["TIMEOFDAY"], ["COURSE"])
pt[1, 0] = 0.0
self.assertEqual(R, str(pt))
def test2(self):
# __mul__ ndarray
R = """\
N/A(ERROR)
TIMEOFDAY COURSE=C1 COURSE=C2 COURSE=C3
=============================================
T1 35.833 32.500 20
T2 16.111 14.444 7.778 """
df = DataFrame()
df.read_tbl('data/error~subjectXtimeofdayXcourseXmodel_MISSING.csv')
pt = df.pivot('ERROR', ['TIMEOFDAY'], ['COURSE'])
pt2 = pt * np.array([[5, 5, 5], [5, 5, 5]])
## print(pt2)
self.assertEqual(str(pt2), R)
def test2(self):
# __mul__ ndarray
R ="""\
N/A(ERROR)
TIMEOFDAY COURSE=C1 COURSE=C2 COURSE=C3
=============================================
T1 35.833 32.500 20
T2 16.111 14.444 7.778 """
df=DataFrame()
df.read_tbl('data/error~subjectXtimeofdayXcourseXmodel_MISSING.csv')
pt = df.pivot('ERROR', ['TIMEOFDAY'],['COURSE'])
pt2=pt*np.array([[5,5,5], [5,5,5]])
## print(pt2)
self.assertEqual(str(pt2),R)
def test0(self):
R = """\
avg(ERROR)
TIMEOFDAY COURSE=C1 COURSE=C2 COURSE=C3 Total
=====================================================
T1 7.167 6.500 4 5.619
T2 0 2.889 1.556 2.556
=====================================================
Total 4.800 4.333 2.778 3.896 """
df = DataFrame()
df.read_tbl('data/error~subjectXtimeofdayXcourseXmodel_MISSING.csv')
pt = df.pivot('ERROR', ['TIMEOFDAY'], ['COURSE'])
pt[1, 0] = 0.
self.assertEqual(R, str(pt))
def test1(self):
# __add__ PyvtTbl
R = """\
N/A(ERROR)
TIMEOFDAY COURSE=C1 COURSE=C2 COURSE=C3 Total
======================================================
T1 14.333 13 8 11.238
T2 6.444 5.778 3.111 5.111
======================================================
Total 9.600 8.667 5.556 7.792 """
df = DataFrame()
df.read_tbl('data/error~subjectXtimeofdayXcourseXmodel_MISSING.csv')
pt = df.pivot('ERROR', ['TIMEOFDAY'], ['COURSE'])
pt2 = pt + pt
self.assertEqual(str(pt2), R)
def test1(self):
R =["""\
avg(ERROR)
TIMEOFDAY COURSE=C1 COURSE=C2 COURSE=C3
=============================================
T1 7.167 6.500 4 """,
"""\
avg(ERROR)
TIMEOFDAY COURSE=C1 COURSE=C2 COURSE=C3
=============================================
T2 3.222 2.889 1.556 """]
df=DataFrame()
df.read_tbl('data/error~subjectXtimeofdayXcourseXmodel_MISSING.csv')
pt = df.pivot('ERROR', ['TIMEOFDAY'],['COURSE'])
for r,L in zip(R, pt):
self.assertAlmostEqual(r, str(L))
def test3(self):
R = [
7.16666666667, 6.5, 4.0, 3.22222222222, 2.88888888889,
1.55555555556
]
Rinds = [(0, 0), (0, 1), (0, 2), (0, 3), (0, 4), (0, 5)]
df = DataFrame()
df.read_tbl('data/error~subjectXtimeofdayXcourseXmodel_MISSING.csv')
pt = df.pivot('ERROR', cols=['TIMEOFDAY', 'COURSE'])
i = 0
for inds, L in pt.ndenumerate():
self.assertEqual('%.5f' % L, '%.5f' % R[i])
self.assertEqual(str(inds), str(Rinds[i]))
i += 1
def test1(self):
# __add__ PyvtTbl
R ="""\
N/A(ERROR)
TIMEOFDAY COURSE=C1 COURSE=C2 COURSE=C3 Total
======================================================
T1 14.333 13 8 11.238
T2 6.444 5.778 3.111 5.111
======================================================
Total 9.600 8.667 5.556 7.792 """
df=DataFrame()
df.read_tbl('data/error~subjectXtimeofdayXcourseXmodel_MISSING.csv')
pt = df.pivot('ERROR', ['TIMEOFDAY'],['COURSE'])
pt2=pt+pt
self.assertEqual(str(pt2),R)
def test0(self):
R ="""\
avg(ERROR)
COURSE TIMEOFDAY=T1 TIMEOFDAY=T2 Total
============================================
C1 7.167 3.222 4.800
C2 6.500 2.889 4.333
C3 4 1.556 2.778
============================================
Total 5.619 2.556 3.896 """
df=DataFrame()
df.read_tbl('data/error~subjectXtimeofdayXcourseXmodel_MISSING.csv')
pt = df.pivot('ERROR', ['TIMEOFDAY'],['COURSE'])
pt2 = pt.transpose()
self.assertEqual(str(pt2),R)
def test0(self):
# __mul__ constant
R = """\
N/A(ERROR)
TIMEOFDAY COURSE=C1 COURSE=C2 COURSE=C3 Total
======================================================
T1 35.833 32.500 20 28.095
T2 16.111 14.444 7.778 12.778
======================================================
Total 24 21.667 13.889 19.479 """
df = DataFrame()
df.read_tbl('data/error~subjectXtimeofdayXcourseXmodel_MISSING.csv')
pt = df.pivot('ERROR', ['TIMEOFDAY'], ['COURSE'])
pt2 = pt * 5
## print(pt2)
self.assertEqual(str(pt2), R)
def test2(self):
R = """\
avg(ERROR)
TIMEOFDAY COURSE=C1 COURSE=C2 COURSE=C3 Total
=====================================================
T1 -- -- -- 5.619
T2 3.222 2.889 1.556 2.556
=====================================================
Total 4.800 4.333 2.778 3.896 """
df = DataFrame()
df.read_tbl("data/error~subjectXtimeofdayXcourseXmodel_MISSING.csv")
pt = df.pivot("ERROR", ["TIMEOFDAY"], ["COURSE"])
pt[0, :] = [0, 0, 0]
pt.mask[0, :] = [True, True, True]
self.assertEqual(R, str(pt))
def test1(self):
R = [
"""\
avg(ERROR)
TIMEOFDAY COURSE=C1 COURSE=C2 COURSE=C3
=============================================
T1 7.167 6.500 4 """, """\
avg(ERROR)
TIMEOFDAY COURSE=C1 COURSE=C2 COURSE=C3
=============================================
T2 3.222 2.889 1.556 """
]
df = DataFrame()
df.read_tbl('data/error~subjectXtimeofdayXcourseXmodel_MISSING.csv')
pt = df.pivot('ERROR', ['TIMEOFDAY'], ['COURSE'])
for r, L in zip(R, pt):
self.assertAlmostEqual(r, str(L))
def test2(self):
R = """\
avg(ERROR)
TIMEOFDAY COURSE=C1 COURSE=C2 COURSE=C3 Total
=====================================================
T1 -- -- -- 5.619
T2 3.222 2.889 1.556 2.556
=====================================================
Total 4.800 4.333 2.778 3.896 """
df = DataFrame()
df.read_tbl('data/error~subjectXtimeofdayXcourseXmodel_MISSING.csv')
pt = df.pivot('ERROR', ['TIMEOFDAY'], ['COURSE'])
pt[0, :] = [0, 0, 0]
pt.mask[0, :] = [True, True, True]
self.assertEqual(R, str(pt))
def test4(self):
R =["""\
avg(ERROR)
TIMEOFDAY COURSE=C1 COURSE=C2 COURSE=C3
=================================================================================================================================================================
T1 [10.0, 8.0, 6.0, 8.0, 7.0, 4.0, None, None, None] [9.0, 10.0, 6.0, 4.0, 7.0, 3.0, None, None, None] [7.0, 6.0, 3.0, 4.0, 5.0, 2.0, 3.0, 4.0, 2.0] """,
"""\
avg(ERROR)
TIMEOFDAY COURSE=C1 COURSE=C2 COURSE=C3
=========================================================================================================================================================
T2 [5.0, 4.0, 3.0, 4.0, 3.0, 3.0, 4.0, 1.0, 2.0] [4.0, 3.0, 3.0, 4.0, 2.0, 2.0, 3.0, 3.0, 2.0] [2.0, 2.0, 1.0, 2.0, 3.0, 2.0, 1.0, 0.0, 1.0] """]
df=DataFrame()
df.read_tbl('data/error~subjectXtimeofdayXcourseXmodel_MISSING.csv')
pt = df.pivot('ERROR', ['TIMEOFDAY'],['COURSE'],aggregate='tolist')
for r,L in zip(R,pt):
self.assertEqual(r, str(L))
def test0(self):
# __mul__ constant
R ="""\
N/A(ERROR)
TIMEOFDAY COURSE=C1 COURSE=C2 COURSE=C3 Total
======================================================
T1 35.833 32.500 20 28.095
T2 16.111 14.444 7.778 12.778
======================================================
Total 24 21.667 13.889 19.479 """
df=DataFrame()
df.read_tbl('data/error~subjectXtimeofdayXcourseXmodel_MISSING.csv')
pt = df.pivot('ERROR', ['TIMEOFDAY'],['COURSE'])
pt2=pt*5
## print(pt2)
self.assertEqual(str(pt2),R)
def test2(self):
R ="""\
avg(ERROR)
TIMEOFDAY COURSE Value
==========================
T1 C1 7.167
T1 C2 6.500
T1 C3 4
T2 C1 3.222
T2 C2 2.889
T2 C3 1.556
==========================
Total 3.896 """
df=DataFrame()
df.read_tbl('data/error~subjectXtimeofdayXcourseXmodel_MISSING.csv')
pt = df.pivot('ERROR', cols=['TIMEOFDAY','COURSE'])
pt2 = pt.transpose()
self.assertEqual(str(pt2),R)
def test2(self):
R = """\
avg(ERROR)
TIMEOFDAY COURSE Value
==========================
T1 C1 7.167
T1 C2 6.500
T1 C3 4
T2 C1 3.222
T2 C2 2.889
T2 C3 1.556
==========================
Total 3.896 """
df = DataFrame()
df.read_tbl('data/error~subjectXtimeofdayXcourseXmodel_MISSING.csv')
pt = df.pivot('ERROR', cols=['TIMEOFDAY', 'COURSE'])
pt2 = pt.transpose()
self.assertEqual(str(pt2), R)
def test4(self):
R = [
"""\
avg(ERROR)
TIMEOFDAY COURSE=C1 COURSE=C2 COURSE=C3
=================================================================================================================================================================
T1 [10.0, 8.0, 6.0, 8.0, 7.0, 4.0, None, None, None] [9.0, 10.0, 6.0, 4.0, 7.0, 3.0, None, None, None] [7.0, 6.0, 3.0, 4.0, 5.0, 2.0, 3.0, 4.0, 2.0] """,
"""\
avg(ERROR)
TIMEOFDAY COURSE=C1 COURSE=C2 COURSE=C3
=========================================================================================================================================================
T2 [5.0, 4.0, 3.0, 4.0, 3.0, 3.0, 4.0, 1.0, 2.0] [4.0, 3.0, 3.0, 4.0, 2.0, 2.0, 3.0, 3.0, 2.0] [2.0, 2.0, 1.0, 2.0, 3.0, 2.0, 1.0, 0.0, 1.0] """
]
df = DataFrame()
df.read_tbl('data/error~subjectXtimeofdayXcourseXmodel_MISSING.csv')
pt = df.pivot('ERROR', ['TIMEOFDAY'], ['COURSE'], aggregate='tolist')
for r, L in zip(R, pt):
self.assertEqual(r, str(L))
def test1(self):
R = """\
CYCLE PHASE GROUP=AA, GROUP=AA, GROUP=AB, GROUP=AB, GROUP=LAB, GROUP=LAB,
AGE=old AGE=young AGE=old AGE=young AGE=old AGE=young
=======================================================================================
1 I 17.750 8.675 12.625 5.525 21.625 7.825
1 II 20.875 8.300 22.750 8.675 36.250 13.750
2 I 22.375 10.225 23.500 8.825 21.375 9.900
2 II 28.125 10.250 41.125 13.100 46.875 14.375
3 I 23.125 10.500 20.000 9.125 23.750 9.500
3 II 20.750 9.525 46.125 14.475 50.375 15.575
4 I 20.250 9.925 15.625 7.750 26.375 9.650
4 II 24.250 11.100 51.750 12.850 46.500 14.425 """
df = DataFrame()
df.read_tbl('data/suppression~subjectXgroupXageXcycleXphase.csv')
pt = df.pivot('SUPPRESSION',
rows=['CYCLE', 'PHASE'],
cols=['GROUP', 'AGE'])
df2 = pt.to_dataframe()
self.assertEqual(str(df2), R)
def test1(self):
R = """\
CYCLE PHASE GROUP=AA, GROUP=AA, GROUP=AB, GROUP=AB, GROUP=LAB, GROUP=LAB,
AGE=old AGE=young AGE=old AGE=young AGE=old AGE=young
=======================================================================================
1 I 17.750 8.675 12.625 5.525 21.625 7.825
1 II 20.875 8.300 22.750 8.675 36.250 13.750
2 I 22.375 10.225 23.500 8.825 21.375 9.900
2 II 28.125 10.250 41.125 13.100 46.875 14.375
3 I 23.125 10.500 20.000 9.125 23.750 9.500
3 II 20.750 9.525 46.125 14.475 50.375 15.575
4 I 20.250 9.925 15.625 7.750 26.375 9.650
4 II 24.250 11.100 51.750 12.850 46.500 14.425 """
df = DataFrame()
df.read_tbl('data/suppression~subjectXgroupXageXcycleXphase.csv')
pt = df.pivot('SUPPRESSION',
rows=['CYCLE', 'PHASE'],
cols=['GROUP', 'AGE'])
df2 = pt.to_dataframe()
self.assertEqual(str(df2),R)
def test5(self):
R = [
"""\
avg(ERROR)
COURSE TIMEOFDAY=T1 TIMEOFDAY=T2
====================================
C1 7.167 3.222 """, """\
avg(ERROR)
COURSE TIMEOFDAY=T1 TIMEOFDAY=T2
====================================
C2 6.500 2.889 """, """\
avg(ERROR)
COURSE TIMEOFDAY=T1 TIMEOFDAY=T2
====================================
C3 4 1.556 """
]
df = DataFrame()
df.read_tbl('data/error~subjectXtimeofdayXcourseXmodel_MISSING.csv')
pt = df.pivot('ERROR', ['TIMEOFDAY'], ['COURSE'])
for r, L in zip(R, pt.transpose()):
self.assertAlmostEqual(r, str(L))
class Test_pivot_1(unittest.TestCase):
def setUp(self):
D = {
'SUBJECT': [
1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18,
19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34,
35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50,
51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66,
67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82,
83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98,
99, 100
],
'AGE':
'old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young'
.split(','),
'CONDITION':
'counting,counting,counting,counting,counting,counting,counting,counting,counting,counting,rhyming,rhyming,rhyming,rhyming,rhyming,rhyming,rhyming,rhyming,rhyming,rhyming,adjective,adjective,adjective,adjective,adjective,adjective,adjective,adjective,adjective,adjective,imagery,imagery,imagery,imagery,imagery,imagery,imagery,imagery,imagery,imagery,intention,intention,intention,intention,intention,intention,intention,intention,intention,intention,counting,counting,counting,counting,counting,counting,counting,counting,counting,counting,rhyming,rhyming,rhyming,rhyming,rhyming,rhyming,rhyming,rhyming,rhyming,rhyming,adjective,adjective,adjective,adjective,adjective,adjective,adjective,adjective,adjective,adjective,imagery,imagery,imagery,imagery,imagery,imagery,imagery,imagery,imagery,imagery,intention,intention,intention,intention,intention,intention,intention,intention,intention,intention'
.split(','),
'WORDS': [
9, 8, 6, 8, 10, 4, 6, 5, 7, 7, 7, 9, 6, 6, 6, 11, 6, 3, 8, 7,
11, 13, 8, 6, 14, 11, 13, 13, 10, 11, 12, 11, 16, 11, 9, 23,
12, 10, 19, 11, 10, 19, 14, 5, 10, 11, 14, 15, 11, 11, 8, 6, 4,
6, 7, 6, 5, 7, 9, 7, 10, 7, 8, 10, 4, 7, 10, 6, 7, 7, 14, 11,
18, 14, 13, 22, 17, 16, 12, 11, 20, 16, 16, 15, 18, 16, 20, 22,
14, 19, 21, 19, 17, 15, 22, 16, 22, 22, 18, 21
],
}
self.df = DataFrame()
self.df.read_tbl('data/words~ageXcondition.csv')
def test0(self):
R = """\
avg(WORDS)
AGE CONDITION=adjective CONDITION=counting CONDITION=imagery CONDITION=intention CONDITION=rhyming Total
=======================================================================================================================
old 11 7 13.400 12 6.900 10.060
young 14.800 6.500 17.600 19.300 7.600 13.160
=======================================================================================================================
Total 12.900 6.750 15.500 15.650 7.250 11.610 """
D = self.df.pivot('WORDS', rows=['AGE'], cols=['CONDITION'])
## print(repr(D))
# verify the values in the table
self.failUnlessEqual(str(D), R)
def test2(self):
R = """\
avg(WORDS)
CONDITION=adjective CONDITION=counting CONDITION=imagery CONDITION=intention CONDITION=rhyming Total
===============================================================================================================
12.900 6.750 15.500 15.650 7.250 11.610 """
D = self.df.pivot('WORDS', cols=['CONDITION'])
# verify the values in the table
self.failUnlessEqual(str(D), R)
def test3(self):
R = """\
avg(WORDS)
CONDITION Value
==================
adjective 12.900
counting 6.750
imagery 15.500
intention 15.650
rhyming 7.250
==================
Total 11.610 """
D = self.df.pivot('WORDS', rows=['CONDITION'])
# verify the values in the table
self.failUnlessEqual(str(D), R)
def test4(self):
R = """\
stdev(WORDS)
Value
=====
5.191 """
# No rows or cols
D = self.df.pivot('WORDS', aggregate='stdev')
# verify the values in the table
self.failUnlessEqual(str(D), R)
def test6(self):
# tolist handles text data differently then integer
# or float data. We need to test this case as well
R = """\
tolist(ABC)
AGE CONDITION=adjective CONDITION=counting CONDITION=imagery CONDITION=intention CONDITION=rhyming
================================================================================================================================================================================================================================================================================================================================
old [u'L', u'N', u'I', u'G', u'O', u'L', u'N', u'N', u'K', u'L'] [u'J', u'I', u'G', u'I', u'K', u'E', u'G', u'F', u'H', u'H'] [u'M', u'L', u'Q', u'L', u'J', u'X', u'M', u'K', u'T', u'L'] [u'K', u'T', u'O', u'F', u'K', u'L', u'O', u'P', u'L', u'L'] [u'H', u'J', u'G', u'G', u'G', u'L', u'G', u'D', u'I', u'H']
young [u'O', u'L', u'S', u'O', u'N', u'W', u'R', u'Q', u'M', u'L'] [u'I', u'G', u'E', u'G', u'H', u'G', u'F', u'H', u'J', u'H'] [u'U', u'Q', u'Q', u'P', u'S', u'Q', u'U', u'W', u'O', u'T'] [u'V', u'T', u'R', u'P', u'W', u'Q', u'W', u'W', u'S', u'V'] [u'K', u'H', u'I', u'K', u'E', u'H', u'K', u'G', u'H', u'H'] """
# caesar cipher
num2abc = dict(zip(list(range(26)), 'ABCDEFGHIJKLMNOPQRSTUVWXYZ'))
self.df['ABC'] = [num2abc[v % 26] for v in self.df['WORDS']]
D = self.df.pivot('ABC',
rows=['AGE'],
cols=['CONDITION'],
aggregate='tolist')
# verify the values in the table
self.failUnlessEqual(str(D), R)
def test7(self):
# test group_concat
R = """\
group_concat(WORDS)
AGE CONDITION=adjective CONDITION=counting CONDITION=imagery CONDITION=intention CONDITION=rhyming
=====================================================================================================================================================
old 11,13,8,6,14,11,13,13,10,11 9,8,6,8,10,4,6,5,7,7 12,11,16,11,9,23,12,10,19,11 10,19,14,5,10,11,14,15,11,11 7,9,6,6,6,11,6,3,8,7
young 14,11,18,14,13,22,17,16,12,11 8,6,4,6,7,6,5,7,9,7 20,16,16,15,18,16,20,22,14,19 21,19,17,15,22,16,22,22,18,21 10,7,8,10,4,7,10,6,7,7 """
D = self.df.pivot('WORDS',
rows=['AGE'],
cols=['CONDITION'],
aggregate='group_concat')
# verify the values in the table
self.failUnlessEqual(str(D), R)
def test8(self):
# tolist handles text data differently then integer
# or float data. We need to test this case as well
R = """\
tolist(ABC)
CONDITION=adjective CONDITION=counting CONDITION=imagery CONDITION=intention CONDITION=rhyming
====================================================================================================================================================================================================================================================================================================================================================================================================================================================================================================================================================================================================================================
[u'L', u'N', u'I', u'G', u'O', u'L', u'N', u'N', u'K', u'L', u'O', u'L', u'S', u'O', u'N', u'W', u'R', u'Q', u'M', u'L'] [u'J', u'I', u'G', u'I', u'K', u'E', u'G', u'F', u'H', u'H', u'I', u'G', u'E', u'G', u'H', u'G', u'F', u'H', u'J', u'H'] [u'M', u'L', u'Q', u'L', u'J', u'X', u'M', u'K', u'T', u'L', u'U', u'Q', u'Q', u'P', u'S', u'Q', u'U', u'W', u'O', u'T'] [u'K', u'T', u'O', u'F', u'K', u'L', u'O', u'P', u'L', u'L', u'V', u'T', u'R', u'P', u'W', u'Q', u'W', u'W', u'S', u'V'] [u'H', u'J', u'G', u'G', u'G', u'L', u'G', u'D', u'I', u'H', u'K', u'H', u'I', u'K', u'E', u'H', u'K', u'G', u'H', u'H'] """
# caesar cipher
num2abc = dict(zip(list(range(26)), 'ABCDEFGHIJKLMNOPQRSTUVWXYZ'))
self.df['ABC'] = [num2abc[v % 26] for v in self.df['WORDS']]
D = self.df.pivot('ABC', cols=['CONDITION'], aggregate='tolist')
# verify the values in the table
self.failUnlessEqual(str(D), R)
def test9(self):
# tolist handles text data differently then integer
# or float data. We need to test this case as well
R = """\
tolist(ABC)
CONDITION Value
====================================================================================================================================
adjective [u'L', u'N', u'I', u'G', u'O', u'L', u'N', u'N', u'K', u'L', u'O', u'L', u'S', u'O', u'N', u'W', u'R', u'Q', u'M', u'L']
counting [u'J', u'I', u'G', u'I', u'K', u'E', u'G', u'F', u'H', u'H', u'I', u'G', u'E', u'G', u'H', u'G', u'F', u'H', u'J', u'H']
imagery [u'M', u'L', u'Q', u'L', u'J', u'X', u'M', u'K', u'T', u'L', u'U', u'Q', u'Q', u'P', u'S', u'Q', u'U', u'W', u'O', u'T']
intention [u'K', u'T', u'O', u'F', u'K', u'L', u'O', u'P', u'L', u'L', u'V', u'T', u'R', u'P', u'W', u'Q', u'W', u'W', u'S', u'V']
rhyming [u'H', u'J', u'G', u'G', u'G', u'L', u'G', u'D', u'I', u'H', u'K', u'H', u'I', u'K', u'E', u'H', u'K', u'G', u'H', u'H'] """
# caesar cipher
num2abc = dict(zip(list(range(26)), 'ABCDEFGHIJKLMNOPQRSTUVWXYZ'))
self.df['ABC'] = [num2abc[v % 26] for v in self.df['WORDS']]
D = self.df.pivot('ABC', rows=['CONDITION'], aggregate='tolist')
# verify the values in the table
self.failUnlessEqual(str(D), R)
def test10(self):
# test group_concat
R = """\
group_concat(WORDS)
AGE=old AGE=young
======================================================================================================================================================================================================================================================================
9,8,6,8,10,4,6,5,7,7,7,9,6,6,6,11,6,3,8,7,11,13,8,6,14,11,13,13,10,11,12,11,16,11,9,23,12,10,19,11,10,19,14,5,10,11,14,15,11,11 8,6,4,6,7,6,5,7,9,7,10,7,8,10,4,7,10,6,7,7,14,11,18,14,13,22,17,16,12,11,20,16,16,15,18,16,20,22,14,19,21,19,17,15,22,16,22,22,18,21 """
D = self.df.pivot('WORDS', cols=['AGE'], aggregate='group_concat')
# verify the values in the table
self.failUnlessEqual(str(D), R)
def test11(self):
# test group_concat
R = """\
group_concat(WORDS)
AGE Value
============================================================================================================================================
old 9,8,6,8,10,4,6,5,7,7,7,9,6,6,6,11,6,3,8,7,11,13,8,6,14,11,13,13,10,11,12,11,16,11,9,23,12,10,19,11,10,19,14,5,10,11,14,15,11,11
young 8,6,4,6,7,6,5,7,9,7,10,7,8,10,4,7,10,6,7,7,14,11,18,14,13,22,17,16,12,11,20,16,16,15,18,16,20,22,14,19,21,19,17,15,22,16,22,22,18,21 """
D = self.df.pivot('WORDS', rows=['AGE'], aggregate='group_concat')
# verify the values in the table
self.failUnlessEqual(str(D), R)
