def test_explicit_dtype(self):
"Test tsfromtxt with an explicit dtype."
dstr = "2009-01-14 12:00; 23; 46"
test = tsfromtxt(StringIO.StringIO(dstr,),
delimiter=";", datecols=0, freq='H')
self.failUnless(test.dtype.names is not None)
assert_equal(test['f1'], 23)
assert_equal(test['f2'], 46)
#
dstr = "2009-01-14 12:00; 23; 46"
test = tsfromtxt(StringIO.StringIO(dstr,),
delimiter=";", datecols=0, dtype=int, freq='H')
assert(test.dtype.names is None)
assert_equal(test, [[23, 46]])
def test_missing_values_no_names(self):
"Make sure that floating point missing values are kept if no names"
a = "AAA,2010,1,-9\nBBB,2010,2,2"
dateconv = lambda y, m: Date('M', year=int(y), month=int(m))
kwargs = dict(freq='M', delimiter=',', dateconverter=dateconv,
missing_values= -9,
datecols=(1, 2), usecols=(1, 2, 3), names="A")
test = tsfromtxt(StringIO.StringIO(a), **kwargs)
assert_equal(test.mask, np.array([(1,), (0,)], dtype=[('A', bool)]))
def test_explicit_names_with_usecols(self):
"Make sure the proper names are given to entries when usecols is not None"
a = "AAA,2010,1,1,2,3\nBBB,2010,2,10,20,30"
dateconv = lambda y, m: Date('M', year=int(y), month=int(m))
kwargs = dict(freq='M', delimiter=',', dateconverter=dateconv,
datecols=(1, 2), usecols=(1, 2, 3, 5), names="A, C")
test = tsfromtxt(StringIO.StringIO(a), **kwargs)
ctrl = time_series([(1, 3), (10, 30)],
start_date=Date('M', '2010-01'),
dtype=[('A', int), ('C', int)])
assert_equal(test, ctrl)
def test_explicit_names(self):
"Test w/ explicit dtype (and explicit float)"
data = "200510, 380.00, 386.30\n200511, 386.85, 388.55\n"
dconverter = lambda x: Date("M", "%s-%s" % (x[:4], x[4:6]))
kwargs = dict(delimiter=",", datecols=0, dateconverter=dconverter)
ctrl = time_series([(380., 386.30), (386.85, 388.55)],
start_date="2005-10", freq="M",
dtype=[('open', "f4"), ('close', "f4")])
test = tsfromtxt(StringIO.StringIO(data),
dtype=[('open', "f4"), ('close', "f4")],
**kwargs)
assert_equal(test, ctrl)
def test_with_converter(self):
"Test tsfromtxt w/ an explicit converter"
input = StringIO.StringIO("2001-01, 00mm\n2002-01, 10mm\n2003-01, 00mm")
conv = converter = {1: lambda s:float(s.split('mm')[0])}
test = tsfromtxt(input, delimiter=',', converters=conv, datecols=0,
freq='M', dtype=float)
control = time_series([0., 10., 0.],
dates=['2001-01', '2002-01', '2003-01'],
freq='M')
assert(isinstance(test, TimeSeries))
assert_equal(test, control)
assert_equal(test.dates, control.dates)
def test_with_negative_datecols(self):
"Test negative datecols"
data = "380.00, 386.30, 200510\n386.85, 388.55, 200511\n"
dconverter = lambda x: Date("M", "%s-%s" % (x[:4], x[4:6]))
kwargs = dict(delimiter=",", datecols= -1, dateconverter=dconverter)
ctrl = time_series([(380., 386.30), (386.85, 388.55)],
start_date="2005-10", freq="M",
dtype=[('open', "f4"), ('close', "f4")])
test = tsfromtxt(StringIO.StringIO(data),
dtype=[('open', "f4"), ('close', "f4")],
**kwargs)
assert_equal(test, ctrl)
def test_explicit_dtype_with_explicit_float(self):
"Test w/ explicit dtype (and explicit float)"
data = "200510, 380.00, 386.30\n200511, 386.85, 388.55\n"
dconverter = lambda x: Date("M", "%s-%s" % (x[:4], x[4:6]))
kwargs = dict(delimiter=",", datecols=0, dateconverter=dconverter)
ctrl = time_series([(380., 386.30), (386.85, 388.55)],
start_date="2005-10",
freq="M",
dtype=[('open', "f4"), ('close', "f4")])
test = tsfromtxt(StringIO.StringIO(data),
dtype=[('open', "f4"), ('close', "f4")],
**kwargs)
assert_equal(test, ctrl)
def test_with_negative_datecols(self):
"Test negative datecols"
data = "380.00, 386.30, 200510\n386.85, 388.55, 200511\n"
dconverter = lambda x: Date("M", "%s-%s" % (x[:4], x[4:6]))
kwargs = dict(delimiter=",", datecols=-1, dateconverter=dconverter)
ctrl = time_series([(380., 386.30), (386.85, 388.55)],
start_date="2005-10",
freq="M",
dtype=[('open', "f4"), ('close', "f4")])
test = tsfromtxt(StringIO.StringIO(data),
dtype=[('open', "f4"), ('close', "f4")],
**kwargs)
assert_equal(test, ctrl)
def test_nodateinfo(self):
# No dates column specified: crash.
"Test no date info"
fcontent = StringIO.StringIO("""#
'Dates', 'One (S)','Two (I)','Three (F)','Four (M)','Five (-)','Six (C)'
'2007-01', 'strings',1,1.0,'mixed column',,1
'2007-02', 'with embedded "double quotes"',2,2.0,1.0,,1
'2007-03', 'strings',3,3.0E5,3,,1
'2007-05','strings',4,-1e-10,,,1
""")
try:
test = tsfromtxt(fcontent, delimiter=",", names="A,B,C,D,E,F,G")
except TypeError:
pass
def test_nodateinfo(self):
# No dates column specified: crash.
"Test no date info"
fcontent = StringIO.StringIO("""#
'Dates', 'One (S)','Two (I)','Three (F)','Four (M)','Five (-)','Six (C)'
'2007-01', 'strings',1,1.0,'mixed column',,1
'2007-02', 'with embedded "double quotes"',2,2.0,1.0,,1
'2007-03', 'strings',3,3.0E5,3,,1
'2007-05','strings',4,-1e-10,,,1
""")
try:
test = tsfromtxt(fcontent, delimiter=",", names="A,B,C,D,E,F,G")
except TypeError:
pass
def test_explicit_structured_dtype(self):
"Test tsfromtxt with an explicit structured dtype"
data = StringIO.StringIO("2007,12,31,24,34,56,0")
dateconverter = lambda y, m, d: Date('D', year=int(y), month=int(m),
day=int(d))
ndtype = [('tobs', int), ('tmin', float), ('tmax', float),
('rain', float)]
test = tsfromtxt(data, delimiter=",", dtype=ndtype,
datecols=(0, 1, 2), dateconverter=dateconverter)
control = time_series([(24, 34.0, 56.0, 0.0)],
dtype=ndtype,
start_date=Date('D', '2007-12-01'))
assert_equal(test, control)
#
data = StringIO.StringIO("2007,12,31,24,34,56,0")
ndtype = [('tobs', int), ('tmin', int), ('tmax', int),
('rain', complex)]
test = tsfromtxt(data, delimiter=",", dtype=ndtype,
datecols=(0, 1, 2), dateconverter=dateconverter)
control = time_series([(24, 34.0, 56.0, 0.0)],
dtype=ndtype,
start_date=Date('D', '2007-12-01'))
assert_equal(test, control)
def test_dates_on_several_columns(self):
"Test tsfromtxt when the date spans several columns."
datatxt = """
2001, 01, 0.0, 10.
2001, 02, 1.1, 11.
2001, 02, 2.2, 12.
"""
data = StringIO.StringIO(datatxt)
dateconverter = lambda y, m: Date('M', year=int(y), month=int(m))
test = tsfromtxt(data, delimiter=',', dtype=float, datecols=(0, 1),
dateconverter=dateconverter)
assert_equal(test, [[0., 10.], [1.1, 11.], [2.2, 12.]])
assert_equal(test.dates,
date_array(['2001-01', '2001-02', '2001-02'], freq='M'))
def test_explicit_names_with_usecols(self):
"Make sure the proper names are given to entries when usecols is not None"
a = "AAA,2010,1,1,2,3\nBBB,2010,2,10,20,30"
dateconv = lambda y, m: Date('M', year=int(y), month=int(m))
kwargs = dict(freq='M',
delimiter=',',
dateconverter=dateconv,
datecols=(1, 2),
usecols=(1, 2, 3, 5),
names="A, C")
test = tsfromtxt(StringIO.StringIO(a), **kwargs)
ctrl = time_series([(1, 3), (10, 30)],
start_date=Date('M', '2010-01'),
dtype=[('A', int), ('C', int)])
assert_equal(test, ctrl)
def test_with_datecols(self):
"Test two datecols"
fcontent = StringIO.StringIO("""
year, month, A, B
2009, 01, 1, 1.
2009, 03, 3, 3.
""")
dateconv = lambda y, m: Date("M", year=int(y), month=int(m))
test = tsfromtxt(fcontent, delimiter=",", skip_header=1, names=True,
converters={'dates': dateconv}, datecols=(0, 1))
dates = date_array(['2009-01', '2009-03'], freq='M')
assert_equal(test.dates.tovalue(), dates)
assert_equal(test['A'], [1, 3])
assert_equal(test['B'], [1., 3.])
assert_equal(test.dtype, np.dtype([('A', int), ('B', float)]))
def test_with_converter(self):
"Test tsfromtxt w/ an explicit converter"
input = StringIO.StringIO(
"2001-01, 00mm\n2002-01, 10mm\n2003-01, 00mm")
conv = converter = {1: lambda s: float(s.split('mm')[0])}
test = tsfromtxt(input,
delimiter=',',
converters=conv,
datecols=0,
freq='M',
dtype=float)
control = time_series([0., 10., 0.],
dates=['2001-01', '2002-01', '2003-01'],
freq='M')
assert (isinstance(test, TimeSeries))
assert_equal(test, control)
assert_equal(test.dates, control.dates)
def test_dates_on_several_columns(self):
"Test tsfromtxt when the date spans several columns."
datatxt = """
2001, 01, 0.0, 10.
2001, 02, 1.1, 11.
2001, 02, 2.2, 12.
"""
data = StringIO.StringIO(datatxt)
dateconverter = lambda y, m: Date('M', year=int(y), month=int(m))
test = tsfromtxt(data,
delimiter=',',
dtype=float,
datecols=(0, 1),
dateconverter=dateconverter)
assert_equal(test, [[0., 10.], [1.1, 11.], [2.2, 12.]])
assert_equal(test.dates,
date_array(['2001-01', '2001-02', '2001-02'], freq='M'))
def test_with_datecols(self):
"Test two datecols"
fcontent = StringIO.StringIO("""
year, month, A, B
2009, 01, 1, 1.
2009, 03, 3, 3.
""")
dateconv = lambda y, m: Date("M", year=int(y), month=int(m))
test = tsfromtxt(fcontent,
delimiter=",",
skip_header=1,
names=True,
converters={'dates': dateconv},
datecols=(0, 1))
dates = date_array(['2009-01', '2009-03'], freq='M')
assert_equal(test.dates.tovalue(), dates)
assert_equal(test['A'], [1, 3])
assert_equal(test['B'], [1., 3.])
assert_equal(test.dtype, np.dtype([('A', int), ('B', float)]))
def test_with_names(self):
"Tests w/ names"
fcontent = StringIO.StringIO("""#
'Dates', 'One (S)','Two (I)','Three (F)','Four (M)','Five (-)','Six (C)'
'2007-01', 'strings',1,1.0,'mixed column',,1
'2007-02', 'with embedded "double quotes"',2,2.0,1.0,,1
'2007-03', 'strings',3,3.0E5,3,,1
'2007-05','strings',4,-1e-10,,,1
""")
test = tsfromtxt(fcontent, delimiter=",", datecols=0, skip_header=2,
names="A,B,C,D,E,F", freq='M')
assert(isinstance(test, TimeSeries))
dlist = ['2007-%02i' % i for i in (1, 2, 3, 5)]
assert_equal(test.dates.tovalue(),
date_array(dlist, freq='M').tovalue())
assert_equal(test.dtype.names, ['A', 'B', 'C', 'D', 'E', 'F'])
assert_equal(test['F'], [1, 1, 1, 1])
assert_equal(test['E'].mask, [1, 1, 1, 1])
assert_equal(test['C'], [1, 2, 300000, -1e-10])
def test_without_names(self):
"Test w/o names"
fcontent = StringIO.StringIO("""#
'Dates', 'One (S)','Two (I)','Three (F)','Four (M)','Five (-)','Six (C)'
'2007-01', 'strings',1,1.0,'mixed column',,1
'2007-02', 'with embedded "double quotes"',2,2.0,1.0,,1
'2007-03', 'strings',3,3.0E5,3,,1
'2007-05','strings',4,-1e-10,,,1
""")
test = tsfromtxt(fcontent,
delimiter=",",
skip_header=1,
names=True,
freq='M')
assert (isinstance(test, TimeSeries))
dlist = ['2007-%02i' % i for i in (1, 2, 3, 5)]
assert_equal(test.dates.tovalue(),
date_array(dlist, freq='M').tovalue())
assert_equal(test.dtype.names,
['One_S', 'Two_I', 'Three_F', 'Four_M', 'Five_', 'Six_C'])
assert_equal(test['Six_C'], [1, 1, 1, 1])
assert_equal(test['Five_'].mask, [1, 1, 1, 1])
assert_equal(test['Three_F'], [1, 2, 300000, -1e-10])
def test_unsorted_input(self):
"Test tsfromtxt when the dates of the input are not sorted."
datatxt = """dates,a,b
2007-04-02 01:00,,0.
2007-04-02 02:00,2.,20
2007-04-02 03:00,,
2007-04-02 00:00,0.,10.
2007-04-02 03:00,3.,30
2007-04-02 01:00,1.,10
2007-04-02 02:00,,
"""
data = StringIO.StringIO(datatxt)
dates = [Date('H', '2007-04-02 0%i:00' % hour)
for hour in (1, 2, 3, 0, 1, 2)]
controla = ma.masked_values([ 0, -1, 1, 2, -1, -1, 3], -1)
controlb = ma.masked_values([10, 0, 10, 20, -1, -1, 30], -1)
#
data = StringIO.StringIO(datatxt)
test = tsfromtxt(data, delimiter=',', names=True, freq='H')
assert_equal(test.dtype.names, ['a', 'b'])
assert_equal(test['a'], controla)
assert_equal(test['a'].mask, controla.mask)
assert_equal(test['b'], controlb)
assert_equal(test['b'].mask, controlb.mask)
