Python numpy.bytes_() Examples

def test_iter_buffering_string():
    # Safe casting disallows shrinking strings
    a = np.array(['abc', 'a', 'abcd'], dtype=np.bytes_)
    assert_equal(a.dtype, np.dtype('S4'))
    assert_raises(TypeError, nditer, a, ['buffered'], ['readonly'],
                  op_dtypes='S2')
    i = nditer(a, ['buffered'], ['readonly'], op_dtypes='S6')
    assert_equal(i[0], b'abc')
    assert_equal(i[0].dtype, np.dtype('S6'))

    a = np.array(['abc', 'a', 'abcd'], dtype=np.unicode)
    assert_equal(a.dtype, np.dtype('U4'))
    assert_raises(TypeError, nditer, a, ['buffered'], ['readonly'],
                    op_dtypes='U2')
    i = nditer(a, ['buffered'], ['readonly'], op_dtypes='U6')
    assert_equal(i[0], u'abc')
    assert_equal(i[0].dtype, np.dtype('U6')) 

def _extract_edge_value(tree, edge):
    ft_idx = edge.calc_record.feature_idx
    split_type = edge.calc_record.split_type
    val = edge.value_encoded
    pivot = edge.calc_record.pivot
    if split_type is CalcRecord.NUM:
        if val == SplitRecord.GREATER:
            return ">{0:.2f}".format(pivot)
        else:
            return "<={0:.2f}".format(pivot)
    elif tree.X_encoders is not None:
        value = tree.X_encoders[ft_idx].single_inv_transform(val)
        if isinstance(value, np.bytes_):
            return value.decode('UTF-8')
        else:
            return value
    else:
        return val 

def get_data(self, path, prefix=''):
        item = self.store[path]
        path = '{}/{}'.format(prefix, path)
        keys = [i for i in item.keys()]
        data = {'path': path}
        # print(path)
        for k in keys:
            if not isinstance(item[k], h5py.Group):
                dataset = np.array(item[k].value)

                if type(dataset) is np.ndarray:
                    if dataset.size != 0:
                        if type(dataset[0]) is np.bytes_:
                            dataset = [a.decode('ascii') for a in dataset]

                data.update({k: dataset})
        return data 

def h5py_dataset_iterator(self,g, prefix=''):
        for key in g.keys():
            item = g[key]
            path = '{}/{}'.format(prefix, key)
            keys = [i for i in item.keys()]
            if isinstance(item[keys[0]], h5py.Dataset): # test for dataset
                data = {'path':path}
                for k in keys:
                    if not isinstance(item[k], h5py.Group):
                        dataset = np.array(item[k].value)

                        if type(dataset) is np.ndarray:
                            if dataset.size != 0:
                                if type(dataset[0]) is np.bytes_:
                                    dataset = [a.decode('ascii') for a in dataset]

                        data.update({k:dataset})

                yield data
            else: # test for group (go down)
                yield from self.h5py_dataset_iterator(item, path) 

def test_iter_buffering_string():
    # Safe casting disallows shrinking strings
    a = np.array(['abc', 'a', 'abcd'], dtype=np.bytes_)
    assert_equal(a.dtype, np.dtype('S4'))
    assert_raises(TypeError, nditer, a, ['buffered'], ['readonly'],
                  op_dtypes='S2')
    i = nditer(a, ['buffered'], ['readonly'], op_dtypes='S6')
    assert_equal(i[0], b'abc')
    assert_equal(i[0].dtype, np.dtype('S6'))

    a = np.array(['abc', 'a', 'abcd'], dtype=np.unicode)
    assert_equal(a.dtype, np.dtype('U4'))
    assert_raises(TypeError, nditer, a, ['buffered'], ['readonly'],
                    op_dtypes='U2')
    i = nditer(a, ['buffered'], ['readonly'], op_dtypes='U6')
    assert_equal(i[0], u'abc')
    assert_equal(i[0].dtype, np.dtype('U6')) 

def test_iter_buffering_string():
    # Safe casting disallows shrinking strings
    a = np.array(['abc', 'a', 'abcd'], dtype=np.bytes_)
    assert_equal(a.dtype, np.dtype('S4'))
    assert_raises(TypeError, nditer, a, ['buffered'], ['readonly'],
                  op_dtypes='S2')
    i = nditer(a, ['buffered'], ['readonly'], op_dtypes='S6')
    assert_equal(i[0], b'abc')
    assert_equal(i[0].dtype, np.dtype('S6'))

    a = np.array(['abc', 'a', 'abcd'], dtype=np.unicode)
    assert_equal(a.dtype, np.dtype('U4'))
    assert_raises(TypeError, nditer, a, ['buffered'], ['readonly'],
                    op_dtypes='U2')
    i = nditer(a, ['buffered'], ['readonly'], op_dtypes='U6')
    assert_equal(i[0], u'abc')
    assert_equal(i[0].dtype, np.dtype('U6')) 

def _randomize_row(id_num):
    """Returns a row with random values"""
    row_dict = {
        TestSchema.id.name: np.int64(id_num),
        TestSchema.id2.name: np.int32(id_num % 2),
        TestSchema.id_float.name: np.float64(id_num),
        TestSchema.id_odd.name: np.bool_(id_num % 2),
        TestSchema.partition_key.name: np.unicode_('p_{}'.format(int(id_num / 10))),
        TestSchema.python_primitive_uint8.name: np.random.randint(0, 255, dtype=np.uint8),
        TestSchema.image_png.name: np.random.randint(0, 255, _DEFAULT_IMAGE_SIZE).astype(np.uint8),
        TestSchema.matrix.name: np.random.random(size=_DEFAULT_IMAGE_SIZE).astype(np.float32),
        TestSchema.decimal.name: Decimal(np.random.randint(0, 255) / Decimal(100)),
        TestSchema.matrix_uint16.name: np.random.randint(0, 2 ** 16 - 1, _DEFAULT_IMAGE_SIZE).astype(np.uint16),
        TestSchema.matrix_uint32.name: np.random.randint(0, 2 ** 32 - 1, _DEFAULT_IMAGE_SIZE).astype(np.uint32),
        TestSchema.matrix_string.name: np.asarray(_random_binary_string_matrix(2, 3, 10)).astype(np.bytes_),
        TestSchema.empty_matrix_string.name: np.asarray([], dtype=np.string_),
        TestSchema.matrix_nullable.name: None,
        TestSchema.sensor_name.name: np.asarray(['test_sensor'], dtype=np.unicode_),
        TestSchema.string_array_nullable.name:
            None if id_num % 5 == 0 else np.asarray([], dtype=np.unicode_)
            if id_num % 4 == 0 else np.asarray([str(i + id_num) for i in range(2)], dtype=np.unicode_),
        TestSchema.integer_nullable.name: None if id_num % 2 else np.int32(id_num),
    }
    return row_dict 

def h5py_dataset_iterator(self, g, prefix=''):
    for key in g.keys():
      item = g[key]
      path = '{}/{}'.format(prefix, key)
      keys = [i for i in item.keys()]
      if isinstance(item[keys[0]], h5py.Dataset):  # test for dataset
        data = {'path': path}
        for k in keys:
          if not isinstance(item[k], h5py.Group):
            dataset = np.array(item[k].value)

            if type(dataset) is np.ndarray:
              if dataset.size != 0:
                if type(dataset[0]) is np.bytes_:
                  dataset = [a.decode('ascii') for a in dataset]

            data.update({k: dataset})

        yield data
      else:  # test for group (go down)
        for s in self.h5py_dataset_iterator(item, path):
          yield s 

def get_data(self, path, prefix=''):
    item = self.store[path]
    path = '{}/{}'.format(prefix, path)
    keys = [i for i in item.keys()]
    data = {'path': path}
    # print(path)
    for k in keys:
      if not isinstance(item[k], h5py.Group):
        dataset = np.array(item[k].value)

        if type(dataset) is np.ndarray:
          if dataset.size != 0:
            if type(dataset[0]) is np.bytes_:
              dataset = [a.decode('ascii') for a in dataset]

        data.update({k: dataset})
    return data 

def test_iter_buffering_string():
    # Safe casting disallows shrinking strings
    a = np.array(['abc', 'a', 'abcd'], dtype=np.bytes_)
    assert_equal(a.dtype, np.dtype('S4'))
    assert_raises(TypeError, nditer, a, ['buffered'], ['readonly'],
                  op_dtypes='S2')
    i = nditer(a, ['buffered'], ['readonly'], op_dtypes='S6')
    assert_equal(i[0], b'abc')
    assert_equal(i[0].dtype, np.dtype('S6'))

    a = np.array(['abc', 'a', 'abcd'], dtype=np.unicode)
    assert_equal(a.dtype, np.dtype('U4'))
    assert_raises(TypeError, nditer, a, ['buffered'], ['readonly'],
                    op_dtypes='U2')
    i = nditer(a, ['buffered'], ['readonly'], op_dtypes='U6')
    assert_equal(i[0], u'abc')
    assert_equal(i[0].dtype, np.dtype('U6')) 

def _getconv(dtype):
    """ Find the correct dtype converter. Adapted from matplotlib """
    typ = dtype.type
    if issubclass(typ, np.bool_):
        return lambda x: bool(int(x))
    if issubclass(typ, np.uint64):
        return np.uint64
    if issubclass(typ, np.int64):
        return np.int64
    if issubclass(typ, np.integer):
        return lambda x: int(float(x))
    elif issubclass(typ, np.floating):
        return float
    elif issubclass(typ, np.complex):
        return complex
    elif issubclass(typ, np.bytes_):
        return bytes
    else:
        return str 

def test_iter_buffering_string():
    # Safe casting disallows shrinking strings
    a = np.array(['abc', 'a', 'abcd'], dtype=np.bytes_)
    assert_equal(a.dtype, np.dtype('S4'));
    assert_raises(TypeError, nditer, a, ['buffered'], ['readonly'],
                    op_dtypes='S2')
    i = nditer(a, ['buffered'], ['readonly'], op_dtypes='S6')
    assert_equal(i[0], asbytes('abc'))
    assert_equal(i[0].dtype, np.dtype('S6'))

    a = np.array(['abc', 'a', 'abcd'], dtype=np.unicode)
    assert_equal(a.dtype, np.dtype('U4'));
    assert_raises(TypeError, nditer, a, ['buffered'], ['readonly'],
                    op_dtypes='U2')
    i = nditer(a, ['buffered'], ['readonly'], op_dtypes='U6')
    assert_equal(i[0], sixu('abc'))
    assert_equal(i[0].dtype, np.dtype('U6')) 

def test_iter_buffering_string():
    # Safe casting disallows shrinking strings
    a = np.array(['abc', 'a', 'abcd'], dtype=np.bytes_)
    assert_equal(a.dtype, np.dtype('S4'))
    assert_raises(TypeError, nditer, a, ['buffered'], ['readonly'],
                  op_dtypes='S2')
    i = nditer(a, ['buffered'], ['readonly'], op_dtypes='S6')
    assert_equal(i[0], asbytes('abc'))
    assert_equal(i[0].dtype, np.dtype('S6'))

    a = np.array(['abc', 'a', 'abcd'], dtype=np.unicode)
    assert_equal(a.dtype, np.dtype('U4'))
    assert_raises(TypeError, nditer, a, ['buffered'], ['readonly'],
                    op_dtypes='U2')
    i = nditer(a, ['buffered'], ['readonly'], op_dtypes='U6')
    assert_equal(i[0], sixu('abc'))
    assert_equal(i[0].dtype, np.dtype('U6')) 

def _getconv(dtype):
    typ = dtype.type
    if issubclass(typ, np.bool_):
        return lambda x: bool(int(x))
    if issubclass(typ, np.uint64):
        return np.uint64
    if issubclass(typ, np.int64):
        return np.int64
    if issubclass(typ, np.integer):
        return lambda x: int(float(x))
    elif issubclass(typ, np.floating):
        return float
    elif issubclass(typ, np.complex):
        return complex
    elif issubclass(typ, np.bytes_):
        return bytes
    else:
        return str 

def test_str_dtype(self):
        # see gh-8033
        c = ["str1", "str2"]

        for dt in (str, np.bytes_):
            a = np.array(["str1", "str2"], dtype=dt)
            x = np.loadtxt(c, dtype=dt)
            assert_array_equal(x, a) 

def test_str_dtype(self):
        # see gh-8033
        c = ["str1", "str2"]

        for dt in (str, np.bytes_):
            a = np.array(["str1", "str2"], dtype=dt)
            x = np.loadtxt(c, dtype=dt)
            assert_array_equal(x, a) 

def _getconv(dtype):
    """ Find the correct dtype converter. Adapted from matplotlib """

    def floatconv(x):
        x.lower()
        if '0x' in x:
            return float.fromhex(x)
        return float(x)

    typ = dtype.type
    if issubclass(typ, np.bool_):
        return lambda x: bool(int(x))
    if issubclass(typ, np.uint64):
        return np.uint64
    if issubclass(typ, np.int64):
        return np.int64
    if issubclass(typ, np.integer):
        return lambda x: int(float(x))
    elif issubclass(typ, np.longdouble):
        return np.longdouble
    elif issubclass(typ, np.floating):
        return floatconv
    elif issubclass(typ, complex):
        return lambda x: complex(asstr(x).replace('+-', '-'))
    elif issubclass(typ, np.bytes_):
        return asbytes
    elif issubclass(typ, np.unicode_):
        return asunicode
    else:
        return asstr

# amount of lines loadtxt reads in one chunk, can be overridden for testing 

def test_scalar_copy(self):
        scalar_types = set(np.sctypeDict.values())
        values = {
            np.void: b"a",
            np.bytes_: b"a",
            np.unicode_: "a",
            np.datetime64: "2017-08-25",
        }
        for sctype in scalar_types:
            item = sctype(values.get(sctype, 1))
            item2 = copy.copy(item)
            assert_equal(item, item2) 

def opener(filename):
    """
    Determines if a file is compressed or not
    """
    import gzip
    f = open(filename, 'rb')
    # print("gzip or not?", f.read(2))

    if f.read(2) == b'\x1f\x8b':
        f.seek(0)
        return gzip.GzipFile(fileobj=f)
    else:
        f.seek(0)
        return f


# def check_chrom_str_bytes(pChrom, pInstanceToCompare):
#     """
#     Checks and changes pChroms to str or bytes depending on datatype
#     of pInstanceToCompare
#     """
#     if type(next(iter(pInstanceToCompare))) is str:
#         pChrom = toString(pChrom)
#     elif type(next(iter(pInstanceToCompare))) in [bytes, np.bytes_]:
#         pChrom = toBytes(pChrom)
#     return pChrom 

def _getconv(dtype):
    """ Find the correct dtype converter. Adapted from matplotlib """

    def floatconv(x):
        x.lower()
        if b'0x' in x:
            return float.fromhex(asstr(x))
        return float(x)

    typ = dtype.type
    if issubclass(typ, np.bool_):
        return lambda x: bool(int(x))
    if issubclass(typ, np.uint64):
        return np.uint64
    if issubclass(typ, np.int64):
        return np.int64
    if issubclass(typ, np.integer):
        return lambda x: int(float(x))
    elif issubclass(typ, np.longdouble):
        return np.longdouble
    elif issubclass(typ, np.floating):
        return floatconv
    elif issubclass(typ, np.complex):
        return lambda x: complex(asstr(x))
    elif issubclass(typ, np.bytes_):
        return asbytes
    else:
        return asstr 

def _getconv(dtype):
    """ Find the correct dtype converter. Adapted from matplotlib """

    def floatconv(x):
        x.lower()
        if '0x' in x:
            return float.fromhex(x)
        return float(x)

    typ = dtype.type
    if issubclass(typ, np.bool_):
        return lambda x: bool(int(x))
    if issubclass(typ, np.uint64):
        return np.uint64
    if issubclass(typ, np.int64):
        return np.int64
    if issubclass(typ, np.integer):
        return lambda x: int(float(x))
    elif issubclass(typ, np.longdouble):
        return np.longdouble
    elif issubclass(typ, np.floating):
        return floatconv
    elif issubclass(typ, complex):
        return lambda x: complex(asstr(x).replace('+-', '-'))
    elif issubclass(typ, np.bytes_):
        return asbytes
    elif issubclass(typ, np.unicode_):
        return asunicode
    else:
        return asstr

# amount of lines loadtxt reads in one chunk, can be overridden for testing 

def test_scalar_copy(self):
        scalar_types = set(np.sctypeDict.values())
        values = {
            np.void: b"a",
            np.bytes_: b"a",
            np.unicode_: "a",
            np.datetime64: "2017-08-25",
        }
        for sctype in scalar_types:
            item = sctype(values.get(sctype, 1))
            item2 = copy.copy(item)
            assert_equal(item, item2) 

def _getconv(dtype):
    """ Find the correct dtype converter. Adapted from matplotlib """

    def floatconv(x):
        x.lower()
        if '0x' in x:
            return float.fromhex(x)
        return float(x)

    typ = dtype.type
    if issubclass(typ, np.bool_):
        return lambda x: bool(int(x))
    if issubclass(typ, np.uint64):
        return np.uint64
    if issubclass(typ, np.int64):
        return np.int64
    if issubclass(typ, np.integer):
        return lambda x: int(float(x))
    elif issubclass(typ, np.longdouble):
        return np.longdouble
    elif issubclass(typ, np.floating):
        return floatconv
    elif issubclass(typ, complex):
        return lambda x: complex(asstr(x).replace('+-', '-'))
    elif issubclass(typ, np.bytes_):
        return asbytes
    elif issubclass(typ, np.unicode_):
        return asunicode
    else:
        return asstr

# amount of lines loadtxt reads in one chunk, can be overridden for testing 

def test_str_dtype(self):
        # see gh-8033
        c = ["str1", "str2"]

        for dt in (str, np.bytes_):
            a = np.array(["str1", "str2"], dtype=dt)
            x = np.loadtxt(c, dtype=dt)
            assert_array_equal(x, a) 

def _ensure_decoded(s):
    """ if we have bytes, decode them to unicode """
    if isinstance(s, (np.bytes_, bytes)):
        s = s.decode(pd.get_option('display.encoding'))
    return s 

def check_chrom_str_bytes(pIteratableObj, pObj):
    # determine type
    if isinstance(pObj, list) and len(pObj) > 0:
        type_ = type(pObj[0])
    else:
        type_ = type(pObj)
    if not isinstance(type(next(iter(pIteratableObj))), type_):
        if type(next(iter(pIteratableObj))) is str:
            pObj = toString(pObj)
        elif type(next(iter(pIteratableObj))) in [bytes, np.bytes_]:
            pObj = toBytes(pObj)
    return pObj 

def toBytes(s):
    """
    Like toString, but for functions requiring bytes in python3
    """
    if sys.version_info[0] == 2:
        return s
    if isinstance(s, bytes):
        return s
    # if isinstance(s, np.bytes_):
    #     return np.bytes_(s)
    if isinstance(s, str):
        return bytes(s, 'ascii')
    if isinstance(s, list):
        return [toBytes(x) for x in s]
    return s 

def toString(s):
    """
    This takes care of python2/3 differences
    """
    if isinstance(s, str):
        return s
    if isinstance(s, bytes):  # or isinstance(s, np.bytes_):
        if sys.version_info[0] == 2:
            return str(s)
        return s.decode('ascii')
    if isinstance(s, list):
        return [toString(x) for x in s]
    if isinstance(s, np.ndarray):
        return s.astype(str)
    return s 

def decode_ascii(s):
        if isinstance(s, bytes):
            return s.decode('ascii')
        elif (isinstance(s, numpy.ndarray) and
              issubclass(s.dtype.type, numpy.bytes_)):
            # np.char.encode/decode annoyingly don't preserve the type of the
            # array, hence the view() call
            # It also doesn't necessarily preserve widths of the strings,
            # hence the astype()
            ns = numpy.char.decode(s, 'ascii').view(type(s))
            if ns.dtype.itemsize / 4 != s.dtype.itemsize:
                ns = ns.astype((numpy.str_, s.dtype.itemsize))
            return ns
        return s 

def encode_ascii(s):
        if isinstance(s, str):
            return s.encode('ascii')
        elif isinstance(s, numpy.ndarray) and \
                issubclass(s.dtype.type, numpy.str_):
            ns = numpy.char.encode(s, 'ascii').view(type(s))
            if ns.dtype.itemsize != s.dtype.itemsize / 4:
                ns = ns.astype((numpy.bytes_, s.dtype.itemsize / 4))
            return ns
        return s