numpy.lib.npyio

Examples

>>> from io import StringIO
>>> text = StringIO("1312 foo\n1534  bar\n444   qux")

>>> regexp = r"(\d+)\s+(...)"  # match [digits, whitespace, anything]
>>> output = np.fromregex(text, regexp,
...                       [('num', np.int64), ('key', 'S3')])
>>> output
array([(1312, b'foo'), (1534, b'bar'), ( 444, b'qux')],
      dtype=[('num', '<i8'), ('key', 'S3')])
>>> output['num']
array([1312, 1534,  444])

Examples

>>> from io import StringIO
>>> import numpy as np

Comma delimited file with mixed dtype

>>> s = StringIO(u"1,1.3,abcde")
>>> data = np.genfromtxt(s, dtype=[('myint','i8'),('myfloat','f8'),
... ('mystring','S5')], delimiter=",")
>>> data
array((1, 1.3, b'abcde'),
      dtype=[('myint', '<i8'), ('myfloat', '<f8'), ('mystring', 'S5')])

Using dtype = None

>>> _ = s.seek(0) # needed for StringIO example only
>>> data = np.genfromtxt(s, dtype=None,
... names = ['myint','myfloat','mystring'], delimiter=",")
>>> data
array((1, 1.3, b'abcde'),
      dtype=[('myint', '<i8'), ('myfloat', '<f8'), ('mystring', 'S5')])

Specifying dtype and names

>>> _ = s.seek(0)
>>> data = np.genfromtxt(s, dtype="i8,f8,S5",
... names=['myint','myfloat','mystring'], delimiter=",")
>>> data
array((1, 1.3, b'abcde'),
      dtype=[('myint', '<i8'), ('myfloat', '<f8'), ('mystring', 'S5')])

An example with fixed-width columns

>>> s = StringIO(u"11.3abcde")
>>> data = np.genfromtxt(s, dtype=None, names=['intvar','fltvar','strvar'],
...     delimiter=[1,3,5])
>>> data
array((1, 1.3, b'abcde'),
      dtype=[('intvar', '<i8'), ('fltvar', '<f8'), ('strvar', 'S5')])

An example to show comments

>>> f = StringIO('''
... text,# of chars
... hello world,11
... numpy,5''')
>>> np.genfromtxt(f, dtype='S12,S12', delimiter=',')
array([(b'text', b''), (b'hello world', b'11'), (b'numpy', b'5')],
  dtype=[('f0', 'S12'), ('f1', 'S12')])

Examples

Store data to disk, and load it again:

>>> np.save('/tmp/123', np.array([[1, 2, 3], [4, 5, 6]]))
>>> np.load('/tmp/123.npy')
array([[1, 2, 3],
       [4, 5, 6]])

Store compressed data to disk, and load it again:

>>> a=np.array([[1, 2, 3], [4, 5, 6]])
>>> b=np.array([1, 2])
>>> np.savez('/tmp/123.npz', a=a, b=b)
>>> data = np.load('/tmp/123.npz')
>>> data['a']
array([[1, 2, 3],
       [4, 5, 6]])
>>> data['b']
array([1, 2])
>>> data.close()

Mem-map the stored array, and then access the second row directly from disk:

>>> X = np.load('/tmp/123.npy', mmap_mode='r')
>>> X[1, :]
memmap([4, 5, 6])

Examples

>>> from io import StringIO   # StringIO behaves like a file object
>>> c = StringIO("0 1\n2 3")
>>> np.loadtxt(c)
array([[0., 1.],
       [2., 3.]])

>>> d = StringIO("M 21 72\nF 35 58")
>>> np.loadtxt(d, dtype={'names': ('gender', 'age', 'weight'),
...                      'formats': ('S1', 'i4', 'f4')})
array([(b'M', 21, 72.), (b'F', 35, 58.)],
      dtype=[('gender', 'S1'), ('age', '<i4'), ('weight', '<f4')])

>>> c = StringIO("1,0,2\n3,0,4")
>>> x, y = np.loadtxt(c, delimiter=',', usecols=(0, 2), unpack=True)
>>> x
array([1., 3.])
>>> y
array([2., 4.])

The converters argument is used to specify functions to preprocess the text prior to parsing. converters can be a dictionary that maps preprocessing functions to each column:

>>> s = StringIO("1.618, 2.296\n3.141, 4.669\n")
>>> conv = {
...     0: lambda x: np.floor(float(x)),  # conversion fn for column 0
...     1: lambda x: np.ceil(float(x)),  # conversion fn for column 1
... }
>>> np.loadtxt(s, delimiter=",", converters=conv)
array([[1., 3.],
       [3., 5.]])

converters can be a callable instead of a dictionary, in which case it is applied to all columns:

>>> s = StringIO("0xDE 0xAD\n0xC0 0xDE")
>>> import functools
>>> conv = functools.partial(int, base=16)
>>> np.loadtxt(s, converters=conv)
array([[222., 173.],
       [192., 222.]])

This example shows how converters can be used to convert a field with a trailing minus sign into a negative number.

>>> s = StringIO('10.01 31.25-\n19.22 64.31\n17.57- 63.94')
>>> def conv(fld):
...     return -float(fld[:-1]) if fld.endswith(b'-') else float(fld)
...
>>> np.loadtxt(s, converters=conv)
array([[ 10.01, -31.25],
       [ 19.22,  64.31],
       [-17.57,  63.94]])

Using a callable as the converter can be particularly useful for handling values with different formatting, e.g. floats with underscores:

>>> s = StringIO("1 2.7 100_000")
>>> np.loadtxt(s, converters=float)
array([1.e+00, 2.7e+00, 1.e+05])

This idea can be extended to automatically handle values specified in many different formats:

>>> def conv(val):
...     try:
...         return float(val)
...     except ValueError:
...         return float.fromhex(val)
>>> s = StringIO("1, 2.5, 3_000, 0b4, 0x1.4000000000000p+2")
>>> np.loadtxt(s, delimiter=",", converters=conv, encoding=None)
array([1.0e+00, 2.5e+00, 3.0e+03, 1.8e+02, 5.0e+00])

Note that with the default encoding="bytes", the inputs to the converter function are latin-1 encoded byte strings. To deactivate the implicit encoding prior to conversion, use encoding=None

>>> s = StringIO('10.01 31.25-\n19.22 64.31\n17.57- 63.94')
>>> conv = lambda x: -float(x[:-1]) if x.endswith('-') else float(x)
>>> np.loadtxt(s, converters=conv, encoding=None)
array([[ 10.01, -31.25],
       [ 19.22,  64.31],
       [-17.57,  63.94]])

Support for quoted fields is enabled with the quotechar parameter. Comment and delimiter characters are ignored when they appear within a quoted item delineated by quotechar:

>>> s = StringIO('"alpha, #42", 10.0\n"beta, #64", 2.0\n')
>>> dtype = np.dtype([("label", "U12"), ("value", float)])
>>> np.loadtxt(s, dtype=dtype, delimiter=",", quotechar='"')
array([('alpha, #42', 10.), ('beta, #64',  2.)],
      dtype=[('label', '<U12'), ('value', '<f8')])

Quoted fields can be separated by multiple whitespace characters:

>>> s = StringIO('"alpha, #42"       10.0\n"beta, #64" 2.0\n')
>>> dtype = np.dtype([("label", "U12"), ("value", float)])
>>> np.loadtxt(s, dtype=dtype, delimiter=None, quotechar='"')
array([('alpha, #42', 10.), ('beta, #64',  2.)],
      dtype=[('label', '<U12'), ('value', '<f8')])

Two consecutive quote characters within a quoted field are treated as a single escaped character:

>>> s = StringIO('"Hello, my name is ""Monty""!"')
>>> np.loadtxt(s, dtype="U", delimiter=",", quotechar='"')
array('Hello, my name is "Monty"!', dtype='<U26')

Read subset of columns when all rows do not contain equal number of values:

>>> d = StringIO("1 2\n2 4\n3 9 12\n4 16 20")
>>> np.loadtxt(d, usecols=(0, 1))
array([[ 1.,  2.],
       [ 2.,  4.],
       [ 3.,  9.],
       [ 4., 16.]])

Examples

>>> from tempfile import TemporaryFile
>>> outfile = TemporaryFile()

>>> x = np.arange(10)
>>> np.save(outfile, x)

>>> _ = outfile.seek(0) # Only needed here to simulate closing & reopening file
>>> np.load(outfile)
array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9])

Examples

>>> x = y = z = np.arange(0.0,5.0,1.0)
>>> np.savetxt('test.out', x, delimiter=',')   # X is an array
>>> np.savetxt('test.out', (x,y,z))   # x,y,z equal sized 1D arrays
>>> np.savetxt('test.out', x, fmt='%1.4e')   # use exponential notation

Examples

>>> from tempfile import TemporaryFile
>>> outfile = TemporaryFile()
>>> x = np.arange(10)
>>> y = np.sin(x)

Using savez with *args, the arrays are saved with default names.

>>> np.savez(outfile, x, y)
>>> _ = outfile.seek(0) # Only needed here to simulate closing & reopening file
>>> npzfile = np.load(outfile)
>>> npzfile.files
['arr_0', 'arr_1']
>>> npzfile['arr_0']
array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9])

Using savez with **kwds, the arrays are saved with the keyword names.

>>> outfile = TemporaryFile()
>>> np.savez(outfile, x=x, y=y)
>>> _ = outfile.seek(0)
>>> npzfile = np.load(outfile)
>>> sorted(npzfile.files)
['x', 'y']
>>> npzfile['x']
array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9])

Examples

>>> test_array = np.random.rand(3, 2)
>>> test_vector = np.random.rand(4)
>>> np.savez_compressed('/tmp/123', a=test_array, b=test_vector)
>>> loaded = np.load('/tmp/123.npz')
>>> print(np.array_equal(test_array, loaded['a']))
True
>>> print(np.array_equal(test_vector, loaded['b']))
True