def test_usecols(self):
# Test the selection of columns
# Select 1 column
control = np.array([[1, 2], [3, 4]], float)
data = TextIO()
np.savetxt(data, control)
data.seek(0)
test = np.ndfromtxt(data, dtype=float, usecols=(1,))
assert_equal(test, control[:, 1])
#
control = np.array([[1, 2, 3], [3, 4, 5]], float)
data = TextIO()
np.savetxt(data, control)
data.seek(0)
test = np.ndfromtxt(data, dtype=float, usecols=(1, 2))
assert_equal(test, control[:, 1:])
# Testing with arrays instead of tuples.
data.seek(0)
test = np.ndfromtxt(data, dtype=float, usecols=np.array([1, 2]))
assert_equal(test, control[:, 1:])
python类ndfromtxt()的实例源码
def test_invalid_raise(self):
# Test invalid raise
data = ["1, 1, 1, 1, 1"] * 50
for i in range(5):
data[10 * i] = "2, 2, 2, 2 2"
data.insert(0, "a, b, c, d, e")
mdata = TextIO("\n".join(data))
#
kwargs = dict(delimiter=",", dtype=None, names=True)
# XXX: is there a better way to get the return value of the
# callable in assert_warns ?
ret = {}
def f(_ret={}):
_ret['mtest'] = np.ndfromtxt(mdata, invalid_raise=False, **kwargs)
assert_warns(ConversionWarning, f, _ret=ret)
mtest = ret['mtest']
assert_equal(len(mtest), 45)
assert_equal(mtest, np.ones(45, dtype=[(_, int) for _ in 'abcde']))
#
mdata.seek(0)
assert_raises(ValueError, np.ndfromtxt, mdata,
delimiter=",", names=True)
def test_auto_dtype_largeint(self):
# Regression test for numpy/numpy#5635 whereby large integers could
# cause OverflowErrors.
# Test the automatic definition of the output dtype
#
# 2**66 = 73786976294838206464 => should convert to float
# 2**34 = 17179869184 => should convert to int64
# 2**10 = 1024 => should convert to int (int32 on 32-bit systems,
# int64 on 64-bit systems)
data = TextIO('73786976294838206464 17179869184 1024')
test = np.ndfromtxt(data, dtype=None)
assert_equal(test.dtype.names, ['f0', 'f1', 'f2'])
assert_(test.dtype['f0'] == np.float)
assert_(test.dtype['f1'] == np.int64)
assert_(test.dtype['f2'] == np.integer)
assert_allclose(test['f0'], 73786976294838206464.)
assert_equal(test['f1'], 17179869184)
assert_equal(test['f2'], 1024)
def test_usecols(self):
# Test the selection of columns
# Select 1 column
control = np.array([[1, 2], [3, 4]], float)
data = TextIO()
np.savetxt(data, control)
data.seek(0)
test = np.ndfromtxt(data, dtype=float, usecols=(1,))
assert_equal(test, control[:, 1])
#
control = np.array([[1, 2, 3], [3, 4, 5]], float)
data = TextIO()
np.savetxt(data, control)
data.seek(0)
test = np.ndfromtxt(data, dtype=float, usecols=(1, 2))
assert_equal(test, control[:, 1:])
# Testing with arrays instead of tuples.
data.seek(0)
test = np.ndfromtxt(data, dtype=float, usecols=np.array([1, 2]))
assert_equal(test, control[:, 1:])
def test_invalid_raise(self):
# Test invalid raise
data = ["1, 1, 1, 1, 1"] * 50
for i in range(5):
data[10 * i] = "2, 2, 2, 2 2"
data.insert(0, "a, b, c, d, e")
mdata = TextIO("\n".join(data))
#
kwargs = dict(delimiter=",", dtype=None, names=True)
# XXX: is there a better way to get the return value of the
# callable in assert_warns ?
ret = {}
def f(_ret={}):
_ret['mtest'] = np.ndfromtxt(mdata, invalid_raise=False, **kwargs)
assert_warns(ConversionWarning, f, _ret=ret)
mtest = ret['mtest']
assert_equal(len(mtest), 45)
assert_equal(mtest, np.ones(45, dtype=[(_, int) for _ in 'abcde']))
#
mdata.seek(0)
assert_raises(ValueError, np.ndfromtxt, mdata,
delimiter=",", names=True)
def test_auto_dtype_largeint(self):
# Regression test for numpy/numpy#5635 whereby large integers could
# cause OverflowErrors.
# Test the automatic definition of the output dtype
#
# 2**66 = 73786976294838206464 => should convert to float
# 2**34 = 17179869184 => should convert to int64
# 2**10 = 1024 => should convert to int (int32 on 32-bit systems,
# int64 on 64-bit systems)
data = TextIO('73786976294838206464 17179869184 1024')
test = np.ndfromtxt(data, dtype=None)
assert_equal(test.dtype.names, ['f0', 'f1', 'f2'])
assert_(test.dtype['f0'] == np.float)
assert_(test.dtype['f1'] == np.int64)
assert_(test.dtype['f2'] == np.integer)
assert_allclose(test['f0'], 73786976294838206464.)
assert_equal(test['f1'], 17179869184)
assert_equal(test['f2'], 1024)
def test_usecols(self):
# Test the selection of columns
# Select 1 column
control = np.array([[1, 2], [3, 4]], float)
data = TextIO()
np.savetxt(data, control)
data.seek(0)
test = np.ndfromtxt(data, dtype=float, usecols=(1,))
assert_equal(test, control[:, 1])
#
control = np.array([[1, 2, 3], [3, 4, 5]], float)
data = TextIO()
np.savetxt(data, control)
data.seek(0)
test = np.ndfromtxt(data, dtype=float, usecols=(1, 2))
assert_equal(test, control[:, 1:])
# Testing with arrays instead of tuples.
data.seek(0)
test = np.ndfromtxt(data, dtype=float, usecols=np.array([1, 2]))
assert_equal(test, control[:, 1:])
def test_invalid_raise(self):
# Test invalid raise
data = ["1, 1, 1, 1, 1"] * 50
for i in range(5):
data[10 * i] = "2, 2, 2, 2 2"
data.insert(0, "a, b, c, d, e")
mdata = TextIO("\n".join(data))
#
kwargs = dict(delimiter=",", dtype=None, names=True)
# XXX: is there a better way to get the return value of the
# callable in assert_warns ?
ret = {}
def f(_ret={}):
_ret['mtest'] = np.ndfromtxt(mdata, invalid_raise=False, **kwargs)
assert_warns(ConversionWarning, f, _ret=ret)
mtest = ret['mtest']
assert_equal(len(mtest), 45)
assert_equal(mtest, np.ones(45, dtype=[(_, int) for _ in 'abcde']))
#
mdata.seek(0)
assert_raises(ValueError, np.ndfromtxt, mdata,
delimiter=",", names=True)
def test_auto_dtype_largeint(self):
# Regression test for numpy/numpy#5635 whereby large integers could
# cause OverflowErrors.
# Test the automatic definition of the output dtype
#
# 2**66 = 73786976294838206464 => should convert to float
# 2**34 = 17179869184 => should convert to int64
# 2**10 = 1024 => should convert to int (int32 on 32-bit systems,
# int64 on 64-bit systems)
data = TextIO('73786976294838206464 17179869184 1024')
test = np.ndfromtxt(data, dtype=None)
assert_equal(test.dtype.names, ['f0', 'f1', 'f2'])
assert test.dtype['f0'] == np.float
assert test.dtype['f1'] == np.int64
assert test.dtype['f2'] == np.integer
assert_allclose(test['f0'], 73786976294838206464.)
assert_equal(test['f1'], 17179869184)
assert_equal(test['f2'], 1024)
def test_usecols(self):
# Test the selection of columns
# Select 1 column
control = np.array([[1, 2], [3, 4]], float)
data = TextIO()
np.savetxt(data, control)
data.seek(0)
test = np.ndfromtxt(data, dtype=float, usecols=(1,))
assert_equal(test, control[:, 1])
#
control = np.array([[1, 2, 3], [3, 4, 5]], float)
data = TextIO()
np.savetxt(data, control)
data.seek(0)
test = np.ndfromtxt(data, dtype=float, usecols=(1, 2))
assert_equal(test, control[:, 1:])
# Testing with arrays instead of tuples.
data.seek(0)
test = np.ndfromtxt(data, dtype=float, usecols=np.array([1, 2]))
assert_equal(test, control[:, 1:])
def test_invalid_raise(self):
# Test invalid raise
data = ["1, 1, 1, 1, 1"] * 50
for i in range(5):
data[10 * i] = "2, 2, 2, 2 2"
data.insert(0, "a, b, c, d, e")
mdata = TextIO("\n".join(data))
#
kwargs = dict(delimiter=",", dtype=None, names=True)
# XXX: is there a better way to get the return value of the
# callable in assert_warns ?
ret = {}
def f(_ret={}):
_ret['mtest'] = np.ndfromtxt(mdata, invalid_raise=False, **kwargs)
assert_warns(ConversionWarning, f, _ret=ret)
mtest = ret['mtest']
assert_equal(len(mtest), 45)
assert_equal(mtest, np.ones(45, dtype=[(_, int) for _ in 'abcde']))
#
mdata.seek(0)
assert_raises(ValueError, np.ndfromtxt, mdata,
delimiter=",", names=True)
def test_auto_dtype_largeint(self):
# Regression test for numpy/numpy#5635 whereby large integers could
# cause OverflowErrors.
# Test the automatic definition of the output dtype
#
# 2**66 = 73786976294838206464 => should convert to float
# 2**34 = 17179869184 => should convert to int64
# 2**10 = 1024 => should convert to int (int32 on 32-bit systems,
# int64 on 64-bit systems)
data = TextIO('73786976294838206464 17179869184 1024')
test = np.ndfromtxt(data, dtype=None)
assert_equal(test.dtype.names, ['f0', 'f1', 'f2'])
assert_(test.dtype['f0'] == np.float)
assert_(test.dtype['f1'] == np.int64)
assert_(test.dtype['f2'] == np.integer)
assert_allclose(test['f0'], 73786976294838206464.)
assert_equal(test['f1'], 17179869184)
assert_equal(test['f2'], 1024)
def test_usecols(self):
# Test the selection of columns
# Select 1 column
control = np.array([[1, 2], [3, 4]], float)
data = TextIO()
np.savetxt(data, control)
data.seek(0)
test = np.ndfromtxt(data, dtype=float, usecols=(1,))
assert_equal(test, control[:, 1])
#
control = np.array([[1, 2, 3], [3, 4, 5]], float)
data = TextIO()
np.savetxt(data, control)
data.seek(0)
test = np.ndfromtxt(data, dtype=float, usecols=(1, 2))
assert_equal(test, control[:, 1:])
# Testing with arrays instead of tuples.
data.seek(0)
test = np.ndfromtxt(data, dtype=float, usecols=np.array([1, 2]))
assert_equal(test, control[:, 1:])
def test_invalid_raise(self):
# Test invalid raise
data = ["1, 1, 1, 1, 1"] * 50
for i in range(5):
data[10 * i] = "2, 2, 2, 2 2"
data.insert(0, "a, b, c, d, e")
mdata = TextIO("\n".join(data))
#
kwargs = dict(delimiter=",", dtype=None, names=True)
# XXX: is there a better way to get the return value of the
# callable in assert_warns ?
ret = {}
def f(_ret={}):
_ret['mtest'] = np.ndfromtxt(mdata, invalid_raise=False, **kwargs)
assert_warns(ConversionWarning, f, _ret=ret)
mtest = ret['mtest']
assert_equal(len(mtest), 45)
assert_equal(mtest, np.ones(45, dtype=[(_, int) for _ in 'abcde']))
#
mdata.seek(0)
assert_raises(ValueError, np.ndfromtxt, mdata,
delimiter=",", names=True)
def test_auto_dtype_largeint(self):
# Regression test for numpy/numpy#5635 whereby large integers could
# cause OverflowErrors.
# Test the automatic definition of the output dtype
#
# 2**66 = 73786976294838206464 => should convert to float
# 2**34 = 17179869184 => should convert to int64
# 2**10 = 1024 => should convert to int (int32 on 32-bit systems,
# int64 on 64-bit systems)
data = TextIO('73786976294838206464 17179869184 1024')
test = np.ndfromtxt(data, dtype=None)
assert_equal(test.dtype.names, ['f0', 'f1', 'f2'])
assert_(test.dtype['f0'] == np.float)
assert_(test.dtype['f1'] == np.int64)
assert_(test.dtype['f2'] == np.integer)
assert_allclose(test['f0'], 73786976294838206464.)
assert_equal(test['f1'], 17179869184)
assert_equal(test['f2'], 1024)
def test_usecols(self):
# Test the selection of columns
# Select 1 column
control = np.array([[1, 2], [3, 4]], float)
data = TextIO()
np.savetxt(data, control)
data.seek(0)
test = np.ndfromtxt(data, dtype=float, usecols=(1,))
assert_equal(test, control[:, 1])
#
control = np.array([[1, 2, 3], [3, 4, 5]], float)
data = TextIO()
np.savetxt(data, control)
data.seek(0)
test = np.ndfromtxt(data, dtype=float, usecols=(1, 2))
assert_equal(test, control[:, 1:])
# Testing with arrays instead of tuples.
data.seek(0)
test = np.ndfromtxt(data, dtype=float, usecols=np.array([1, 2]))
assert_equal(test, control[:, 1:])
def test_invalid_raise(self):
# Test invalid raise
data = ["1, 1, 1, 1, 1"] * 50
for i in range(5):
data[10 * i] = "2, 2, 2, 2 2"
data.insert(0, "a, b, c, d, e")
mdata = TextIO("\n".join(data))
#
kwargs = dict(delimiter=",", dtype=None, names=True)
# XXX: is there a better way to get the return value of the
# callable in assert_warns ?
ret = {}
def f(_ret={}):
_ret['mtest'] = np.ndfromtxt(mdata, invalid_raise=False, **kwargs)
assert_warns(ConversionWarning, f, _ret=ret)
mtest = ret['mtest']
assert_equal(len(mtest), 45)
assert_equal(mtest, np.ones(45, dtype=[(_, int) for _ in 'abcde']))
#
mdata.seek(0)
assert_raises(ValueError, np.ndfromtxt, mdata,
delimiter=",", names=True)
def test_auto_dtype_largeint(self):
# Regression test for numpy/numpy#5635 whereby large integers could
# cause OverflowErrors.
# Test the automatic definition of the output dtype
#
# 2**66 = 73786976294838206464 => should convert to float
# 2**34 = 17179869184 => should convert to int64
# 2**10 = 1024 => should convert to int (int32 on 32-bit systems,
# int64 on 64-bit systems)
data = TextIO('73786976294838206464 17179869184 1024')
test = np.ndfromtxt(data, dtype=None)
assert_equal(test.dtype.names, ['f0', 'f1', 'f2'])
assert_(test.dtype['f0'] == np.float)
assert_(test.dtype['f1'] == np.int64)
assert_(test.dtype['f2'] == np.integer)
assert_allclose(test['f0'], 73786976294838206464.)
assert_equal(test['f1'], 17179869184)
assert_equal(test['f2'], 1024)
def test_record(self):
# Test w/ explicit dtype
data = TextIO('1 2\n3 4')
test = np.ndfromtxt(data, dtype=[('x', np.int32), ('y', np.int32)])
control = np.array([(1, 2), (3, 4)], dtype=[('x', 'i4'), ('y', 'i4')])
assert_equal(test, control)
#
data = TextIO('M 64.0 75.0\nF 25.0 60.0')
descriptor = {'names': ('gender', 'age', 'weight'),
'formats': ('S1', 'i4', 'f4')}
control = np.array([('M', 64.0, 75.0), ('F', 25.0, 60.0)],
dtype=descriptor)
test = np.ndfromtxt(data, dtype=descriptor)
assert_equal(test, control)
def test_array(self):
# Test outputing a standard ndarray
data = TextIO('1 2\n3 4')
control = np.array([[1, 2], [3, 4]], dtype=int)
test = np.ndfromtxt(data, dtype=int)
assert_array_equal(test, control)
#
data.seek(0)
control = np.array([[1, 2], [3, 4]], dtype=float)
test = np.loadtxt(data, dtype=float)
assert_array_equal(test, control)
def test_1D(self):
# Test squeezing to 1D
control = np.array([1, 2, 3, 4], int)
#
data = TextIO('1\n2\n3\n4\n')
test = np.ndfromtxt(data, dtype=int)
assert_array_equal(test, control)
#
data = TextIO('1,2,3,4\n')
test = np.ndfromtxt(data, dtype=int, delimiter=',')
assert_array_equal(test, control)
def test_comments(self):
# Test the stripping of comments
control = np.array([1, 2, 3, 5], int)
# Comment on its own line
data = TextIO('# comment\n1,2,3,5\n')
test = np.ndfromtxt(data, dtype=int, delimiter=',', comments='#')
assert_equal(test, control)
# Comment at the end of a line
data = TextIO('1,2,3,5# comment\n')
test = np.ndfromtxt(data, dtype=int, delimiter=',', comments='#')
assert_equal(test, control)
def test_skiprows(self):
# Test row skipping
control = np.array([1, 2, 3, 5], int)
kwargs = dict(dtype=int, delimiter=',')
#
data = TextIO('comment\n1,2,3,5\n')
test = np.ndfromtxt(data, skip_header=1, **kwargs)
assert_equal(test, control)
#
data = TextIO('# comment\n1,2,3,5\n')
test = np.loadtxt(data, skiprows=1, **kwargs)
assert_equal(test, control)
def test_auto_dtype(self):
# Test the automatic definition of the output dtype
data = TextIO('A 64 75.0 3+4j True\nBCD 25 60.0 5+6j False')
test = np.ndfromtxt(data, dtype=None)
control = [np.array([b'A', b'BCD']),
np.array([64, 25]),
np.array([75.0, 60.0]),
np.array([3 + 4j, 5 + 6j]),
np.array([True, False]), ]
assert_equal(test.dtype.names, ['f0', 'f1', 'f2', 'f3', 'f4'])
for (i, ctrl) in enumerate(control):
assert_equal(test['f%i' % i], ctrl)
def test_auto_dtype_uniform(self):
# Tests whether the output dtype can be uniformized
data = TextIO('1 2 3 4\n5 6 7 8\n')
test = np.ndfromtxt(data, dtype=None)
control = np.array([[1, 2, 3, 4], [5, 6, 7, 8]])
assert_equal(test, control)
def test_fancy_dtype(self):
# Check that a nested dtype isn't MIA
data = TextIO('1,2,3.0\n4,5,6.0\n')
fancydtype = np.dtype([('x', int), ('y', [('t', int), ('s', float)])])
test = np.ndfromtxt(data, dtype=fancydtype, delimiter=',')
control = np.array([(1, (2, 3.0)), (4, (5, 6.0))], dtype=fancydtype)
assert_equal(test, control)
def test_names_overwrite(self):
# Test overwriting the names of the dtype
descriptor = {'names': ('g', 'a', 'w'),
'formats': ('S1', 'i4', 'f4')}
data = TextIO(b'M 64.0 75.0\nF 25.0 60.0')
names = ('gender', 'age', 'weight')
test = np.ndfromtxt(data, dtype=descriptor, names=names)
descriptor['names'] = names
control = np.array([('M', 64.0, 75.0),
('F', 25.0, 60.0)], dtype=descriptor)
assert_equal(test, control)
def test_autonames_and_usecols(self):
# Tests names and usecols
data = TextIO('A B C D\n aaaa 121 45 9.1')
test = np.ndfromtxt(data, usecols=('A', 'C', 'D'),
names=True, dtype=None)
control = np.array(('aaaa', 45, 9.1),
dtype=[('A', '|S4'), ('C', int), ('D', float)])
assert_equal(test, control)
def test_converters_with_usecols_and_names(self):
# Tests names and usecols
data = TextIO('A B C D\n aaaa 121 45 9.1')
test = np.ndfromtxt(data, usecols=('A', 'C', 'D'), names=True,
dtype=None, converters={'C': lambda s: 2 * int(s)})
control = np.array(('aaaa', 90, 9.1),
dtype=[('A', '|S4'), ('C', int), ('D', float)])
assert_equal(test, control)
def test_converters_cornercases(self):
# Test the conversion to datetime.
converter = {
'date': lambda s: strptime(s, '%Y-%m-%d %H:%M:%SZ')}
data = TextIO('2009-02-03 12:00:00Z, 72214.0')
test = np.ndfromtxt(data, delimiter=',', dtype=None,
names=['date', 'stid'], converters=converter)
control = np.array((datetime(2009, 2, 3), 72214.),
dtype=[('date', np.object_), ('stid', float)])
assert_equal(test, control)
