Python DataFrame.pivot方法代码示例

# 需要导入模块: from pyvttbl import DataFrame [as 别名]
# 或者: from pyvttbl.DataFrame import pivot [as 别名]
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)

# 需要导入模块: from pyvttbl import DataFrame [as 别名]
# 或者: from pyvttbl.DataFrame import pivot [as 别名]
    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))

# 需要导入模块: from pyvttbl import DataFrame [as 别名]
# 或者: from pyvttbl.DataFrame import pivot [as 别名]
    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))

# 需要导入模块: from pyvttbl import DataFrame [as 别名]
# 或者: from pyvttbl.DataFrame import pivot [as 别名]
 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)

# 需要导入模块: from pyvttbl import DataFrame [as 别名]
# 或者: from pyvttbl.DataFrame import pivot [as 别名]
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

# 需要导入模块: from pyvttbl import DataFrame [as 别名]
# 或者: from pyvttbl.DataFrame import pivot [as 别名]
    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))

# 需要导入模块: from pyvttbl import DataFrame [as 别名]
# 或者: from pyvttbl.DataFrame import pivot [as 别名]
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

# 需要导入模块: from pyvttbl import DataFrame [as 别名]
# 或者: from pyvttbl.DataFrame import pivot [as 别名]
    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)

# 需要导入模块: from pyvttbl import DataFrame [as 别名]
# 或者: from pyvttbl.DataFrame import pivot [as 别名]
    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)

# 需要导入模块: from pyvttbl import DataFrame [as 别名]
# 或者: from pyvttbl.DataFrame import pivot [as 别名]
    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]))

# 需要导入模块: from pyvttbl import DataFrame [as 别名]
# 或者: from pyvttbl.DataFrame import pivot [as 别名]
    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)

# 需要导入模块: from pyvttbl import DataFrame [as 别名]
# 或者: from pyvttbl.DataFrame import pivot [as 别名]
    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)

# 需要导入模块: from pyvttbl import DataFrame [as 别名]
# 或者: from pyvttbl.DataFrame import pivot [as 别名]
    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:]))

# 需要导入模块: from pyvttbl import DataFrame [as 别名]
# 或者: from pyvttbl.DataFrame import pivot [as 别名]
    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:]))

# 需要导入模块: from pyvttbl import DataFrame [as 别名]
# 或者: from pyvttbl.DataFrame import pivot [as 别名]
    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)