Python numpy.core.multiarray.dtype() Examples

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 _set_array_types():
    ibytes = [1, 2, 4, 8, 16, 32, 64]
    fbytes = [2, 4, 8, 10, 12, 16, 32, 64]
    for bytes in ibytes:
        bits = 8*bytes
        _add_array_type('int', bits)
        _add_array_type('uint', bits)
    for bytes in fbytes:
        bits = 8*bytes
        _add_array_type('float', bits)
        _add_array_type('complex', 2*bits)
    _gi = dtype('p')
    if _gi.type not in sctypes['int']:
        indx = 0
        sz = _gi.itemsize
        _lst = sctypes['int']
        while (indx < len(_lst) and sz >= _lst[indx](0).itemsize):
            indx += 1
        sctypes['int'].insert(indx, _gi.type)
        sctypes['uint'].insert(indx, dtype('P').type) 

def _mean(a, axis=None, dtype=None, out=None, keepdims=False):
    arr = asanyarray(a)

    rcount = _count_reduce_items(arr, axis)
    # Make this warning show up first
    if rcount == 0:
        warnings.warn("Mean of empty slice.", RuntimeWarning)

    # Cast bool, unsigned int, and int to float64 by default
    if dtype is None and issubclass(arr.dtype.type, (nt.integer, nt.bool_)):
        dtype = mu.dtype('f8')

    ret = umr_sum(arr, axis, dtype, out, keepdims)
    if isinstance(ret, mu.ndarray):
        ret = um.true_divide(
                ret, rcount, out=ret, casting='unsafe', subok=False)
    elif hasattr(ret, 'dtype'):
        ret = ret.dtype.type(ret / rcount)
    else:
        ret = ret / rcount

    return ret 

def test_column_subset_detect_empty(self):
        """
        Tests that when ordered=False, validation is possible by
        passing a subset of the columns contained in the schema

        Schema         a                b* (validation)
        Data Frame     b (error)        a

        column* is not being passed

        There will be an error if other than zero errors are found.
        """

        df = pd.read_csv(StringIO('''
b,a
 1,1
2,3
3,3
        '''), sep=',', header=0, dtype=str)
        # should detect no errors
        results_empty = self.schema.validate(df, columns=['a'])

        self.assertEqual(len(results_empty), 0, 'There should be no errors') 

def test_mixed_columns(self):
        """
        Tests that when ordered=True, the schema columns are associated with data frame columns by position, not name.

        In this case, the schema's column order is [a, b], while the data frame's order is [b, a]. There is an error in
        column b in the data frame (leading whitespace), and a validation on column a in the schema.

        Schema         a (validation)   b
        Data Frame     b (error)        a

        Thus there will only be an error if column b in the schema is linked to column a in the data frame,
        as is correct behaviour when ordered=True.
        """
        df = pd.read_csv(StringIO('''
b,a
 1,1
2,3
3,3
        '''), sep=',', header=0, dtype=str)
        results = self.schema.validate(df)

        self.assertEqual(len(results), 1, 'There should be 1 error')
        self.assertEqual(results[0].row, 0)
        self.assertEqual(results[0].column, 'b', 'The Schema object is not associating columns and column schemas by position') 

def _set_array_types():
    ibytes = [1, 2, 4, 8, 16, 32, 64]
    fbytes = [2, 4, 8, 10, 12, 16, 32, 64]
    for bytes in ibytes:
        bits = 8*bytes
        _add_array_type('int', bits)
        _add_array_type('uint', bits)
    for bytes in fbytes:
        bits = 8*bytes
        _add_array_type('float', bits)
        _add_array_type('complex', 2*bits)
    _gi = dtype('p')
    if _gi.type not in sctypes['int']:
        indx = 0
        sz = _gi.itemsize
        _lst = sctypes['int']
        while (indx < len(_lst) and sz >= _lst[indx](0).itemsize):
            indx += 1
        sctypes['int'].insert(indx, _gi.type)
        sctypes['uint'].insert(indx, dtype('P').type) 

def test_column_subset_error(self):
        """
        Tests that when ordered=False, validation is possible by
        passing a subset of the columns contained in the schema

        Schema         a                b (validation)
        Data Frame     b (error)        a

        There will be an error if a column different than 'a' or 'b' is passed
        """

        df = pd.read_csv(StringIO('''
b,a
 1,1
2,3
3,3
        '''), sep=',', header=0, dtype=str)

        # should raise a PanSchArgumentError
        self.assertRaises(PanSchArgumentError, self.schema.validate, df, columns=['c']) 

def _set_array_types():
    ibytes = [1, 2, 4, 8, 16, 32, 64]
    fbytes = [2, 4, 8, 10, 12, 16, 32, 64]
    for bytes in ibytes:
        bits = 8*bytes
        _add_array_type('int', bits)
        _add_array_type('uint', bits)
    for bytes in fbytes:
        bits = 8*bytes
        _add_array_type('float', bits)
        _add_array_type('complex', 2*bits)
    _gi = dtype('p')
    if _gi.type not in sctypes['int']:
        indx = 0
        sz = _gi.itemsize
        _lst = sctypes['int']
        while (indx < len(_lst) and sz >= _lst[indx](0).itemsize):
            indx += 1
        sctypes['int'].insert(indx, _gi.type)
        sctypes['uint'].insert(indx, dtype('P').type) 

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, align)
    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)


# construct an array_protocol descriptor list
#  from the fields attribute of a descriptor
# This calls itself recursively but should eventually hit
#  a descriptor that has no fields and then return
#  a simple typestring 

def _prod(a, axis=None, dtype=None, out=None, keepdims=False,
          initial=_NoValue):
    return umr_prod(a, axis, dtype, out, keepdims, initial) 

def _prod(a, axis=None, dtype=None, out=None, keepdims=False,
          initial=_NoValue):
    return umr_prod(a, axis, dtype, out, keepdims, initial) 

def _all(a, axis=None, dtype=None, out=None, keepdims=False):
    return umr_all(a, axis, dtype, out, keepdims) 

def _mean(a, axis=None, dtype=None, out=None, keepdims=False):
    arr = asanyarray(a)

    is_float16_result = False
    rcount = _count_reduce_items(arr, axis)
    # Make this warning show up first
    if rcount == 0:
        warnings.warn("Mean of empty slice.", RuntimeWarning, stacklevel=2)

    # Cast bool, unsigned int, and int to float64 by default
    if dtype is None:
        if issubclass(arr.dtype.type, (nt.integer, nt.bool_)):
            dtype = mu.dtype('f8')
        elif issubclass(arr.dtype.type, nt.float16):
            dtype = mu.dtype('f4')
            is_float16_result = True

    ret = umr_sum(arr, axis, dtype, out, keepdims)
    if isinstance(ret, mu.ndarray):
        ret = um.true_divide(
                ret, rcount, out=ret, casting='unsafe', subok=False)
        if is_float16_result and out is None:
            ret = arr.dtype.type(ret)
    elif hasattr(ret, 'dtype'):
        if is_float16_result:
            ret = arr.dtype.type(ret / rcount)
        else:
            ret = ret.dtype.type(ret / rcount)
    else:
        ret = ret / rcount

    return ret 

def _std(a, axis=None, dtype=None, out=None, ddof=0, keepdims=False):
    ret = _var(a, axis=axis, dtype=dtype, out=out, ddof=ddof,
               keepdims=keepdims)

    if isinstance(ret, mu.ndarray):
        ret = um.sqrt(ret, out=ret)
    elif hasattr(ret, 'dtype'):
        ret = ret.dtype.type(um.sqrt(ret))
    else:
        ret = um.sqrt(ret)

    return ret 

def bitname(obj):
    """Return a bit-width name for a given type object"""
    bits = _bits_of(obj)
    dt = dtype(obj)
    char = dt.kind
    base = _kind_name(dt)

    if base == 'object':
        bits = 0

    if bits != 0:
        char = "%s%d" % (char, bits // 8)

    return base, bits, char 

def _mean(a, axis=None, dtype=None, out=None, keepdims=False):
    arr = asanyarray(a)

    is_float16_result = False
    rcount = _count_reduce_items(arr, axis)
    # Make this warning show up first
    if rcount == 0:
        warnings.warn("Mean of empty slice.", RuntimeWarning, stacklevel=2)

    # Cast bool, unsigned int, and int to float64 by default
    if dtype is None:
        if issubclass(arr.dtype.type, (nt.integer, nt.bool_)):
            dtype = mu.dtype('f8')
        elif issubclass(arr.dtype.type, nt.float16):
            dtype = mu.dtype('f4')
            is_float16_result = True

    ret = umr_sum(arr, axis, dtype, out, keepdims)
    if isinstance(ret, mu.ndarray):
        ret = um.true_divide(
                ret, rcount, out=ret, casting='unsafe', subok=False)
        if is_float16_result and out is None:
            ret = arr.dtype.type(ret)
    elif hasattr(ret, 'dtype'):
        if is_float16_result:
            ret = arr.dtype.type(ret / rcount)
        else:
            ret = ret.dtype.type(ret / rcount)
    else:
        ret = ret / rcount

    return ret 

def _std(a, axis=None, dtype=None, out=None, ddof=0, keepdims=False):
    ret = _var(a, axis=axis, dtype=dtype, out=out, ddof=ddof,
               keepdims=keepdims)

    if isinstance(ret, mu.ndarray):
        ret = um.sqrt(ret, out=ret)
    elif hasattr(ret, 'dtype'):
        ret = ret.dtype.type(um.sqrt(ret))
    else:
        ret = um.sqrt(ret)

    return ret 

def _bits_of(obj):
    try:
        info = next(v for v in _concrete_typeinfo.values() if v.type is obj)
    except StopIteration:
        if obj in _abstract_types.values():
            raise ValueError("Cannot count the bits of an abstract type")

        # some third-party type - make a best-guess
        return dtype(obj).itemsize * 8
    else:
        return info.bits 

def _sum(a, axis=None, dtype=None, out=None, keepdims=False,
         initial=_NoValue):
    return umr_sum(a, axis, dtype, out, keepdims, initial) 

def _sum(a, axis=None, dtype=None, out=None, keepdims=False,
         initial=_NoValue):
    return umr_sum(a, axis, dtype, out, keepdims, initial) 

def bitname(obj):
    """Return a bit-width name for a given type object"""
    bits = _bits_of(obj)
    dt = dtype(obj)
    char = dt.kind
    base = _kind_name(dt)

    if base == 'object':
        bits = 0

    if bits != 0:
        char = "%s%d" % (char, bits // 8)

    return base, bits, char 

def _bits_of(obj):
    try:
        info = next(v for v in _concrete_typeinfo.values() if v.type is obj)
    except StopIteration:
        if obj in _abstract_types.values():
            raise ValueError("Cannot count the bits of an abstract type")

        # some third-party type - make a best-guess
        return dtype(obj).itemsize * 8
    else:
        return info.bits 

def _std(a, axis=None, dtype=None, out=None, ddof=0, keepdims=False):
    ret = _var(a, axis=axis, dtype=dtype, out=out, ddof=ddof,
               keepdims=keepdims)

    if isinstance(ret, mu.ndarray):
        ret = um.sqrt(ret, out=ret)
    else:
        ret = ret.dtype.type(um.sqrt(ret))

    return ret 

def _all(a, axis=None, dtype=None, out=None, keepdims=False):
    return um.logical_and.reduce(a, axis=axis, dtype=dtype, out=out,
                                 keepdims=keepdims) 

def _any(a, axis=None, dtype=None, out=None, keepdims=False):
    return um.logical_or.reduce(a, axis=axis, dtype=dtype, out=out,
                                keepdims=keepdims) 

def _prod(a, axis=None, dtype=None, out=None, keepdims=False):
    return um.multiply.reduce(a, axis=axis, dtype=dtype,
                            out=out, keepdims=keepdims) 

def _sum(a, axis=None, dtype=None, out=None, keepdims=False):
    return um.add.reduce(a, axis=axis, dtype=dtype,
                            out=out, keepdims=keepdims) 

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 _bits_of(obj):
    try:
        info = next(v for v in _concrete_typeinfo.values() if v.type is obj)
    except StopIteration:
        if obj in _abstract_types.values():
            raise ValueError("Cannot count the bits of an abstract type")

        # some third-party type - make a best-guess
        return dtype(obj).itemsize * 8
    else:
        return info.bits 

def test_mixed_columns(self):
        """
        Tests that when ordered=False, the schema columns are
        associated with data frame columns by name, not position.
        In this case, the schema's column order is [a, b], while
         the data frame's order is [b, a]. There is an error in
        column b in the data frame (leading whitespace), and a
        validation on column b in the schema.

        Schema         a                b (validation)
        Data Frame     b (error)        a

        Thus there will only be an error if column b in the schema
        is linked to column b in the data frame, as is correct
        behaviour.
        """

        df = pd.read_csv(StringIO('''
b,a
 1,1
2,3
3,3
        '''), sep=',', header=0, dtype=str)
        results = self.schema.validate(df)

        self.assertEqual(len(results), 1, 'There should be 1 error')
        self.assertEqual(results[0].row, 0)
        self.assertEqual(results[0].column, 'b', 'The Schema object is not associating columns and column schemas by name')