Python multiarray.dtype函数代码示例

def _add_trailing_padding(value, padding):
    """Inject the specified number of padding bytes at the end of a dtype"""
    from numpy.core.multiarray import dtype

    if value.fields is None:
        vfields = {'f0': (value, 0)}
    else:
        vfields = dict(value.fields)

    if value.names and value.names[-1] == '' and \
           value[''].char == 'V':
        # A trailing padding field is already present
        vfields[''] = ('V%d' % (vfields[''][0].itemsize + padding),
                       vfields[''][1])
        value = dtype(vfields)
    else:
        # Get a free name for the padding field
        j = 0
        while True:
            name = 'pad%d' % j
            if name not in vfields:
                vfields[name] = ('V%d' % padding, value.itemsize)
                break
            j += 1

        value = dtype(vfields)
        if '' not in vfields:
            # Strip out the name of the padding field
            names = list(value.names)
            names[-1] = ''
            value.names = tuple(names)
    return value

def _usefields(adict, align):
    from multiarray import dtype
    try:
        names = adict[-1]
    except KeyError:
        names = None
    if names is None:
        names, formats, offsets, titles = _makenames_list(adict)
    else:
        formats = []
        offsets = []
        titles = []
        for name in names:
            res = adict[name]
            formats.append(res[0])
            offsets.append(res[1])
            if (len(res) > 2):
                titles.append(res[2])
            else:
                titles.append(None)

    return dtype({"names" : names,
                  "formats" : formats,
                  "offsets" : offsets,
                  "titles" : titles}, align)

def _makenames_list(adict):
    from multiarray import dtype
    allfields = []
    fnames = adict.keys()
    for fname in fnames:
        obj = adict[fname]
        n = len(obj)
        if not isinstance(obj, tuple) or n not in [2,3]:
            raise ValueError, "entry not a 2- or 3- tuple"
        if (n > 2) and (obj[2] == fname):
            continue
        num = int(obj[1])
        if (num < 0):
            raise ValueError, "invalid offset."
        format = dtype(obj[0])
        if (format.itemsize == 0):
            raise ValueError, "all itemsizes must be fixed."
        if (n > 2):
            title = obj[2]
        else:
            title = None
        allfields.append((fname, format, num, title))
    # sort by offsets
    allfields.sort(lambda x,y: cmp(x[2],y[2]))
    names = [x[0] for x in allfields]
    formats = [x[1] for x in allfields]
    offsets = [x[2] for x in allfields]
    titles = [x[3] for x in allfields]

    return names, formats, offsets, titles

def _getintp_ctype():
    from multiarray import dtype
    val = _getintp_ctype.cache
    if val is not None:
        return val
    char = dtype('p').char
    import ctypes
    if (char == 'i'):
        val = ctypes.c_int
    elif char == 'l':
        val = ctypes.c_long
    elif char == 'q':
        val = ctypes.c_longlong
    else:
        val = ctypes.c_long
    _getintp_ctype.cache = val
    return val

def _getintp_ctype():
    from multiarray import dtype

    val = _getintp_ctype.cache
    if val is not None:
        return val
    char = dtype("p").char
    import ctypes

    if char == "i":
        val = ctypes.c_int
    elif char == "l":
        val = ctypes.c_long
    elif char == "q":
        val = ctypes.c_longlong
    else:
        val = ctypes.c_long
    _getintp_ctype.cache = val
    return val

def _dtype_from_pep3118(spec, byteorder='@', is_subdtype=False):
    from numpy.core.multiarray import dtype

    fields = {}
    offset = 0
    explicit_name = False
    this_explicit_name = False
    common_alignment = 1
    is_padding = False
    last_offset = 0

    dummy_name_index = [0]
    def next_dummy_name():
        dummy_name_index[0] += 1
    def get_dummy_name():
        while True:
            name = 'f%d' % dummy_name_index[0]
            if name not in fields:
                return name
            next_dummy_name()

    # Parse spec
    while spec:
        value = None

        # End of structure, bail out to upper level
        if spec[0] == '}':
            spec = spec[1:]
            break

        # Sub-arrays (1)
        shape = None
        if spec[0] == '(':
            j = spec.index(')')
            shape = tuple(map(int, spec[1:j].split(',')))
            spec = spec[j+1:]

        # Byte order
        if spec[0] in ('@', '=', '<', '>', '^', '!'):
            byteorder = spec[0]
            if byteorder == '!':
                byteorder = '>'
            spec = spec[1:]

        # Byte order characters also control native vs. standard type sizes
        if byteorder in ('@', '^'):
            type_map = _pep3118_native_map
            type_map_chars = _pep3118_native_typechars
        else:
            type_map = _pep3118_standard_map
            type_map_chars = _pep3118_standard_typechars

        # Item sizes
        itemsize = 1
        if spec[0].isdigit():
            j = 1
            for j in xrange(1, len(spec)):
                if not spec[j].isdigit():
                    break
            itemsize = int(spec[:j])
            spec = spec[j:]

        # Data types
        is_padding = False

        if spec[:2] == 'T{':
            value, spec, align, next_byteorder = _dtype_from_pep3118(
                spec[2:], byteorder=byteorder, is_subdtype=True)
        elif spec[0] in type_map_chars:
            next_byteorder = byteorder
            if spec[0] == 'Z':
                j = 2
            else:
                j = 1
            typechar = spec[:j]
            spec = spec[j:]
            is_padding = (typechar == 'x')
            dtypechar = type_map[typechar]
            if dtypechar in 'USV':
                dtypechar += '%d' % itemsize
                itemsize = 1
            numpy_byteorder = {'@': '=', '^': '='}.get(byteorder, byteorder)
            value = dtype(numpy_byteorder + dtypechar)
            align = value.alignment
        else:
            raise ValueError("Unknown PEP 3118 data type specifier %r" % spec)

        #
        # Native alignment may require padding
        #
        # Here we assume that the presence of a '@' character implicitly implies
        # that the start of the array is *already* aligned.
        #
        extra_offset = 0
        if byteorder == '@':
            start_padding = (-offset) % align
            intra_padding = (-value.itemsize) % align

            offset += start_padding

#.........这里部分代码省略.........

def loadtxt(fname, dtype=float, comments='#', delimiter=None, converters=None,
            skiprows=0, usecols=None, unpack=False):
    """
    Load ASCII data from fname into an array and return the array.

    The data must be regular, same number of values in every row

    fname can be a filename or a file handle.  Support for gzipped files is
    automatic, if the filename ends in .gz

    See scipy.loadmat to read and write matfiles.

    Example usage:

      X = loadtxt('test.dat')  # data in two columns
      t = X[:,0]
      y = X[:,1]

    Alternatively, you can do the same with "unpack"; see below

      X = loadtxt('test.dat')    # a matrix of data
      x = loadtxt('test.dat')    # a single column of data


    dtype - the data-type of the resulting array.  If this is a
    record data-type, the the resulting array will be 1-d and each row will
    be interpreted as an element of the array. The number of columns
    used must match the number of fields in the data-type in this case. 
    
    comments - the character used to indicate the start of a comment
    in the file

    delimiter is a string-like character used to seperate values in the
    file. If delimiter is unspecified or none, any whitespace string is
    a separator.

    converters, if not None, is a dictionary mapping column number to
    a function that will convert that column to a float.  Eg, if
    column 0 is a date string: converters={0:datestr2num}

    skiprows is the number of rows from the top to skip

    usecols, if not None, is a sequence of integer column indexes to
    extract where 0 is the first column, eg usecols=(1,4,5) to extract
    just the 2nd, 5th and 6th columns

    unpack, if True, will transpose the matrix allowing you to unpack
    into named arguments on the left hand side

        t,y = load('test.dat', unpack=True) # for  two column data
        x,y,z = load('somefile.dat', usecols=(3,5,7), unpack=True)

    """

    if _string_like(fname):
        if fname.endswith('.gz'):
            import gzip
            fh = gzip.open(fname)
        else:
            fh = file(fname)
    elif hasattr(fname, 'seek'):
        fh = fname
    else:
        raise ValueError('fname must be a string or file handle')
    X = []

    dtype = multiarray.dtype(dtype)
    defconv = _getconv(dtype)
    converterseq = None    
    if converters is None:
        converters = {}
        if dtype.names is not None:
            converterseq = [_getconv(dtype.fields[name][0]) \
                            for name in dtype.names]
            
    for i,line in enumerate(fh):
        if i<skiprows: continue
        line = line[:line.find(comments)].strip()
        if not len(line): continue
        vals = line.split(delimiter)
        if converterseq is None:
           converterseq = [converters.get(j,defconv) \
                           for j in xrange(len(vals))]
        if usecols is not None:
            row = [converterseq[j](vals[j]) for j in usecols]
        else:
            row = [converterseq[j](val) for j,val in enumerate(vals)]
        if dtype.names is not None:
            row = tuple(row)
        X.append(row)

    X = array(X, dtype)
    r,c = X.shape
    if r==1 or c==1:
        X.shape = max([r,c]),
    if unpack: return X.T
    else:  return X