Python numpy.string() Examples

def get_bases(self):
        "get bases from SpaceGroup element"
        # lattice parameters
        bases = []
        for elem in self.tree.iter():
            if elem.tag == 'SpaceGroup':
                for attr in ['AVector', 'BVector', 'CVector']:
                    basis = elem.attrib[attr]  # string
                    basis = [float(i.strip()) for i in basis.split(',')]
                    bases.append(basis)
                break
        bases = np.array(bases)
        #set base constant as 1.0
        self.bases_const = 1.0

        return bases 

def __init__(self, filename):
        """
        Create a Material Studio *.arc file class.

        Example:

        >>> a = ArcFile("00-05.arc")

        Class attributes descriptions
        ================================================================
         Attribute         Description
         ===============  ==============================================
         filename          string, name of arc file.
         coords_iterator   generator, yield Cartisan coordinates in
                           numpy array.
         lengths           list of float, lengths of lattice axes.
         angles            list of float, angles of lattice axes.
        ================  ==============================================
        """
        super(ArcFile, self).__init__(filename)

        # Set logger.
        self.__logger = logging.getLogger("vaspy.ArcFile") 

def __init__(self, filename='XDATCAR'):
        """
        Class to generate XDATCAR objects.

        Example:

        >>> a = XdatCar()

        Class attributes descriptions
        =======================================================================
          Attribute      Description
          ============  =======================================================
          filename       string, name of the file the direct coordiante data
                         stored in
          bases_const    float, lattice bases constant
          bases          np.array, bases of POSCAR
          natom          int, the number of total atom number
          atom_types     list of strings, atom types
          tf             list of list, T&F info of atoms
          info_nline     int, line numbers of lattice info
          ============  =======================================================
        """
        AtomCo.__init__(self, filename)
        self.info_nline = 7  # line numbers of lattice info
        self.load() 

def validate_col(self, itemsize=None):
        """ validate this column: return the compared against itemsize """

        # validate this column for string truncation (or reset to the max size)
        if _ensure_decoded(self.kind) == u'string':
            c = self.col
            if c is not None:
                if itemsize is None:
                    itemsize = self.itemsize
                if c.itemsize < itemsize:
                    raise ValueError(
                        "Trying to store a string with len [{itemsize}] in "
                        "[{cname}] column but\nthis column has a limit of "
                        "[{c_itemsize}]!\nConsider using min_itemsize to "
                        "preset the sizes on these columns".format(
                            itemsize=itemsize, cname=self.cname,
                            c_itemsize=c.itemsize))
                return c.itemsize

        return None 

def generate(self, where):
        """ where can be a : dict,list,tuple,string """
        if where is None:
            return None

        q = self.table.queryables()
        try:
            return Expr(where, queryables=q, encoding=self.table.encoding)
        except NameError:
            # raise a nice message, suggesting that the user should use
            # data_columns
            raise ValueError(
                "The passed where expression: {0}\n"
                "            contains an invalid variable reference\n"
                "            all of the variable references must be a "
                "reference to\n"
                "            an axis (e.g. 'index' or 'columns'), or a "
                "data_column\n"
                "            The currently defined references are: {1}\n"
                .format(where, ','.join(q.keys()))
            ) 

def min(self):
    """Returns the minimum representable value in this data type.

    Raises:
      TypeError: if this is a non-numeric, unordered, or quantized type.

    """
    if (self.is_quantized or self.base_dtype in
        (bool, string, complex64, complex128)):
      raise TypeError("Cannot find minimum value of %s." % self)

    # there is no simple way to get the min value of a dtype, we have to check
    # float and int types separately
    try:
      return np.finfo(self.as_numpy_dtype()).min
    except:  # bare except as possible raises by finfo not documented
      try:
        return np.iinfo(self.as_numpy_dtype()).min
      except:
        raise TypeError("Cannot find minimum value of %s." % self) 

def max(self):
    """Returns the maximum representable value in this data type.

    Raises:
      TypeError: if this is a non-numeric, unordered, or quantized type.

    """
    if (self.is_quantized or self.base_dtype in
        (bool, string, complex64, complex128)):
      raise TypeError("Cannot find maximum value of %s." % self)

    # there is no simple way to get the max value of a dtype, we have to check
    # float and int types separately
    try:
      return np.finfo(self.as_numpy_dtype()).max
    except:  # bare except as possible raises by finfo not documented
      try:
        return np.iinfo(self.as_numpy_dtype()).max
      except:
        raise TypeError("Cannot find maximum value of %s." % self) 

def min(self):
    """Returns the minimum representable value in this data type.

    Raises:
      TypeError: if this is a non-numeric, unordered, or quantized type.

    """
    if (self.is_quantized or self.base_dtype in
        (bool, string, complex64, complex128)):
      raise TypeError("Cannot find minimum value of %s." % self)

    # there is no simple way to get the min value of a dtype, we have to check
    # float and int types separately
    try:
      return np.finfo(self.as_numpy_dtype()).min
    except:  # bare except as possible raises by finfo not documented
      try:
        return np.iinfo(self.as_numpy_dtype()).min
      except:
        raise TypeError("Cannot find minimum value of %s." % self) 

def max(self):
    """Returns the maximum representable value in this data type.

    Raises:
      TypeError: if this is a non-numeric, unordered, or quantized type.

    """
    if (self.is_quantized or self.base_dtype in
        (bool, string, complex64, complex128)):
      raise TypeError("Cannot find maximum value of %s." % self)

    # there is no simple way to get the max value of a dtype, we have to check
    # float and int types separately
    try:
      return np.finfo(self.as_numpy_dtype()).max
    except:  # bare except as possible raises by finfo not documented
      try:
        return np.iinfo(self.as_numpy_dtype()).max
      except:
        raise TypeError("Cannot find maximum value of %s." % self) 

def validate_col(self, itemsize=None):
        """ validate this column: return the compared against itemsize """

        # validate this column for string truncation (or reset to the max size)
        if _ensure_decoded(self.kind) == u('string'):
            c = self.col
            if c is not None:
                if itemsize is None:
                    itemsize = self.itemsize
                if c.itemsize < itemsize:
                    raise ValueError(
                        "Trying to store a string with len [%s] in [%s] "
                        "column but\nthis column has a limit of [%s]!\n"
                        "Consider using min_itemsize to preset the sizes on "
                        "these columns" % (itemsize, self.cname, c.itemsize))
                return c.itemsize

        return None 

def generate(self, where):
        """ where can be a : dict,list,tuple,string """
        if where is None:
            return None

        q = self.table.queryables()
        try:
            return Expr(where, queryables=q, encoding=self.table.encoding)
        except NameError:
            # raise a nice message, suggesting that the user should use
            # data_columns
            raise ValueError(
                "The passed where expression: {0}\n"
                "            contains an invalid variable reference\n"
                "            all of the variable references must be a "
                "reference to\n"
                "            an axis (e.g. 'index' or 'columns'), or a "
                "data_column\n"
                "            The currently defined references are: {1}\n"
                .format(where, ','.join(q.keys()))
            ) 

def min(self):
    """Returns the minimum representable value in this data type.

    Raises:
      TypeError: if this is a non-numeric, unordered, or quantized type.

    """
    if (self.is_quantized or self.base_dtype in
        (bool, string, complex64, complex128)):
      raise TypeError("Cannot find minimum value of %s." % self)

    # there is no simple way to get the min value of a dtype, we have to check
    # float and int types separately
    try:
      return np.finfo(self.as_numpy_dtype()).min
    except:  # bare except as possible raises by finfo not documented
      try:
        return np.iinfo(self.as_numpy_dtype()).min
      except:
        raise TypeError("Cannot find minimum value of %s." % self) 

def max(self):
    """Returns the maximum representable value in this data type.

    Raises:
      TypeError: if this is a non-numeric, unordered, or quantized type.

    """
    if (self.is_quantized or self.base_dtype in
        (bool, string, complex64, complex128)):
      raise TypeError("Cannot find maximum value of %s." % self)

    # there is no simple way to get the max value of a dtype, we have to check
    # float and int types separately
    try:
      return np.finfo(self.as_numpy_dtype()).max
    except:  # bare except as possible raises by finfo not documented
      try:
        return np.iinfo(self.as_numpy_dtype()).max
      except:
        raise TypeError("Cannot find maximum value of %s." % self) 

def validate_col(self, itemsize=None):
        """ validate this column: return the compared against itemsize """

        # validate this column for string truncation (or reset to the max size)
        if _ensure_decoded(self.kind) == u'string':
            c = self.col
            if c is not None:
                if itemsize is None:
                    itemsize = self.itemsize
                if c.itemsize < itemsize:
                    raise ValueError(
                        "Trying to store a string with len [{itemsize}] in "
                        "[{cname}] column but\nthis column has a limit of "
                        "[{c_itemsize}]!\nConsider using min_itemsize to "
                        "preset the sizes on these columns".format(
                            itemsize=itemsize, cname=self.cname,
                            c_itemsize=c.itemsize))
                return c.itemsize

        return None 

def generate(self, where):
        """ where can be a : dict,list,tuple,string """
        if where is None:
            return None

        q = self.table.queryables()
        try:
            return Expr(where, queryables=q, encoding=self.table.encoding)
        except NameError:
            # raise a nice message, suggesting that the user should use
            # data_columns
            raise ValueError(
                "The passed where expression: {0}\n"
                "            contains an invalid variable reference\n"
                "            all of the variable references must be a "
                "reference to\n"
                "            an axis (e.g. 'index' or 'columns'), or a "
                "data_column\n"
                "            The currently defined references are: {1}\n"
                .format(where, ','.join(q.keys()))
            ) 

def min(self):
        """Returns the minimum representable value in this data type.

        Raises:
          TypeError: if this is a non-numeric, unordered, or quantized type.
        """
        if self.is_quantized or self.base_dtype in (
            bool,
            string,
            complex64,
            complex128,
        ):
            raise TypeError("Cannot find minimum value of %s." % self)

        # there is no simple way to get the min value of a dtype, we have to check
        # float and int types separately
        try:
            return np.finfo(self.as_numpy_dtype).min
        except:  # bare except as possible raises by finfo not documented
            try:
                return np.iinfo(self.as_numpy_dtype).min
            except:
                if self.base_dtype == bfloat16:
                    return _np_bfloat16(float.fromhex("-0x1.FEp127"))
                raise TypeError("Cannot find minimum value of %s." % self) 

def max(self):
        """Returns the maximum representable value in this data type.

        Raises:
          TypeError: if this is a non-numeric, unordered, or quantized type.
        """
        if self.is_quantized or self.base_dtype in (
            bool,
            string,
            complex64,
            complex128,
        ):
            raise TypeError("Cannot find maximum value of %s." % self)

        # there is no simple way to get the max value of a dtype, we have to check
        # float and int types separately
        try:
            return np.finfo(self.as_numpy_dtype).max
        except:  # bare except as possible raises by finfo not documented
            try:
                return np.iinfo(self.as_numpy_dtype).max
            except:
                if self.base_dtype == bfloat16:
                    return _np_bfloat16(float.fromhex("0x1.FEp127"))
                raise TypeError("Cannot find maximum value of %s." % self) 

def __init__(self, filename):
        """
        Create a Material Studio *.xsd file class.

        Example:

        >>> a = XsdFile(filename='ts.xsd')

        Class attributes descriptions
        =======================================================================
          Attribute      Description
          ============  =======================================================
          filename       string, name of the file the direct coordiante data
                         stored in
          natom          int, the number of total atom number
          atom_types     list of strings, atom types
          atom_numbers   list of int, atom number of atoms in atoms
          atom_names     list of string,
                         Value of attribute 'Name' in Atom3d tag.
          tf             np.array, T & F info for atoms, dtype=np.string
          data           np.array, coordinates of atoms, dtype=float64
          bases          np.array, basis vectors of space, dtype=np.float64
          ============  =======================================================
        """
        super(XsdFile, self).__init__(filename)

        # Set logger.
        self.__logger = logging.getLogger("vaspy.XsdFile")

        # Load data in xsd.
        self.load() 

def get_name_info(self):
        """
        获取文件中能量，力等数据.
        """
        # Get info string.
        info = None
        for elem in self.tree.iter("SymmetrySystem"):
            info = elem.attrib.get('Name')
            break
        if info is None:
            return

        # Get thermo data.
        fieldnames = ["energy", "force", "magnetism", "path"]
        try:
            for key, value in zip(fieldnames, info.split()):
                if key != "path":
                    data = float(value.split(':')[-1].strip())
                else:
                    data = value.split(":")[-1].strip()
                setattr(self, key, data)
        except:
            # Set default values.
            self.force, self.energy, self.magnetism = 0.0, 0.0, 0.0

            msg = "No data info in Name property '{}'".format(info)
            self.__logger.warning(msg)
        finally:
            self.path = getcwd() 

def update_bases(self):
        "update bases value in ElementTree"
        bases = self.bases.tolist()
        bases_str = []
        # float -> string
        for basis in bases:
            xyz = ','.join([str(v) for v in basis])  # vector string
            bases_str.append(xyz)
        for elem in self.tree.iter('SpaceGroup'):
            elem.set('AVector', bases_str[0])
            elem.set('BVector', bases_str[1])
            elem.set('CVector', bases_str[2])
            break 

def load(self, content_list):
        """ Load all data in xyz file.
        """
        # Total number of all atoms.
        natom = int(content_list[0].strip())

        # The iteration step for this xyz file.
        step = int(str2list(content_list[1])[-1])

        # Get atom coordinate and number info
        data_list = [str2list(line) for line in content_list[2:]]
        data_array = np.array(data_list)      # dtype=np.string
        atoms_list = list(data_array[:, 0])   # 1st column
        data = np.float64(data_array[:, 1:])  # rest columns

        # Atom number for each atom
        atom_types = []
        for atom in atoms_list:
            if atom not in atom_types:
                atom_types.append(atom)
        atom_numbers = [atoms_list.count(atom) for atom in atom_types]

        # Set attributes.
        self.natom = natom
        self.step = step
        self.atom_types = atom_types
        self.atom_numbers = atom_numbers
        self.data = data 

def __init__(self, filename='POSCAR'):
        """
        Class to generate POSCAR or CONTCAR-like objects.

        Example:

        >>> a = PosCar(filename='POSCAR')

        Class attributes descriptions
        =======================================================================
          Attribute      Description
          ============  =======================================================
          filename       string, name of the file the direct coordiante data
                         stored in
          bases_const    float, lattice bases constant
          bases          np.array, bases of POSCAR
          natom          int, the number of total atom number
          atom_types     list of strings, atom types
          atom_numbers   list of int, same shape with atoms
                         atom number of atoms in atoms
          tf             list of list, T&F info of atoms
          data           np.array, coordinates of atoms, dtype=float64
          ============  =======================================================
        """
        AtomCo.__init__(self, filename)

        # Load all data in file
        self.load()
        self.verify() 

def __init__(self, filename):
        """
        Class for *.cif files.

        Example:

        >>> a = CifFile(filename='ts.cif')

        Class attributes descriptions
        =======================================================================
          Attribute         Description
          ===============  ====================================================
          filename         string, name of the file the direct coordiante data
                           stored in
          natom            int, the number of total atom number
          atom_types       list of strings, atom types
          atom_numbers     list of int, atom number of atoms in atoms
          atom_names       list of string,
                           Value of attribute 'Name' in Atom3d tag.
          data             np.array, coordinates of atoms, dtype=float64

          cell_length_a    float, length of cell vector a
          cell_length_a    float, length of cell vector b
          cell_length_c    float, length of cell vector c
          cell_angle_alpha float, angle of cell alpha
          cell_angle_beta  float, angle of cell beta
          cell_angle_gamma float, angle of cell gamma
          ===============  ====================================================
        """
        super(CifFile, self).__init__(filename)
        self.__logger = logging.getLogger("vaspy.CifCar")
        self.load() 

def _ensure_str(name):
    """Ensure that an index / column name is a str (python 3) or
    unicode (python 2); otherwise they may be np.string dtype.
    Non-string dtypes are passed through unchanged.

    https://github.com/pandas-dev/pandas/issues/13492
    """
    if isinstance(name, compat.string_types):
        name = compat.text_type(name)
    return name 

def maybe_set_size(self, min_itemsize=None):
        """ maybe set a string col itemsize:
               min_itemsize can be an integer or a dict with this columns name
               with an integer size """
        if _ensure_decoded(self.kind) == u'string':

            if isinstance(min_itemsize, dict):
                min_itemsize = min_itemsize.get(self.name)

            if min_itemsize is not None and self.typ.itemsize < min_itemsize:
                self.typ = _tables(
                ).StringCol(itemsize=min_itemsize, pos=self.pos) 

def write_metadata(self, key, values):
        """
        write out a meta data array to the key as a fixed-format Series

        Parameters
        ----------
        key : string
        values : ndarray

        """
        values = Series(values)
        self.parent.put(self._get_metadata_path(key), values, format='table',
                        encoding=self.encoding, errors=self.errors,
                        nan_rep=self.nan_rep) 

def _set_tz(values, tz, preserve_UTC=False, coerce=False):
    """
    coerce the values to a DatetimeIndex if tz is set
    preserve the input shape if possible

    Parameters
    ----------
    values : ndarray
    tz : string/pickled tz object
    preserve_UTC : boolean,
        preserve the UTC of the result
    coerce : if we do not have a passed timezone, coerce to M8[ns] ndarray
    """
    if tz is not None:
        name = getattr(values, 'name', None)
        values = values.ravel()
        tz = timezones.get_timezone(_ensure_decoded(tz))
        values = DatetimeIndex(values, name=name)
        if values.tz is None:
            values = values.tz_localize('UTC').tz_convert(tz)
        if preserve_UTC:
            if tz == 'UTC':
                values = list(values)
    elif coerce:
        values = np.asarray(values, dtype='M8[ns]')

    return values 

def _unconvert_index(data, kind, encoding=None, errors='strict'):
    kind = _ensure_decoded(kind)
    if kind == u'datetime64':
        index = DatetimeIndex(data)
    elif kind == u'timedelta64':
        index = TimedeltaIndex(data)
    elif kind == u'datetime':
        index = np.asarray([datetime.fromtimestamp(v) for v in data],
                           dtype=object)
    elif kind == u'date':
        try:
            index = np.asarray(
                [date.fromordinal(v) for v in data], dtype=object)
        except (ValueError):
            index = np.asarray(
                [date.fromtimestamp(v) for v in data], dtype=object)
    elif kind in (u'integer', u'float'):
        index = np.asarray(data)
    elif kind in (u'string'):
        index = _unconvert_string_array(data, nan_rep=None, encoding=encoding,
                                        errors=errors)
    elif kind == u'object':
        index = np.asarray(data[0])
    else:  # pragma: no cover
        raise ValueError('unrecognized index type {kind}'.format(kind=kind))
    return index 

def _convert_string_array(data, encoding, errors, itemsize=None):
    """
    we take a string-like that is object dtype and coerce to a fixed size
    string type

    Parameters
    ----------
    data : a numpy array of object dtype
    encoding : None or string-encoding
    errors : handler for encoding errors
    itemsize : integer, optional, defaults to the max length of the strings

    Returns
    -------
    data in a fixed-length string dtype, encoded to bytes if needed
    """

    # encode if needed
    if encoding is not None and len(data):
        data = Series(data.ravel()).str.encode(
            encoding, errors).values.reshape(data.shape)

    # create the sized dtype
    if itemsize is None:
        ensured = ensure_object(data.ravel())
        itemsize = max(1, libwriters.max_len_string_array(ensured))

    data = np.asarray(data, dtype="S{size}".format(size=itemsize))
    return data 

def _unconvert_string_array(data, nan_rep=None, encoding=None,
                            errors='strict'):
    """
    inverse of _convert_string_array

    Parameters
    ----------
    data : fixed length string dtyped array
    nan_rep : the storage repr of NaN, optional
    encoding : the encoding of the data, optional
    errors : handler for encoding errors, default 'strict'

    Returns
    -------
    an object array of the decoded data

    """
    shape = data.shape
    data = np.asarray(data.ravel(), dtype=object)

    # guard against a None encoding in PY3 (because of a legacy
    # where the passed encoding is actually None)
    encoding = _ensure_encoding(encoding)
    if encoding is not None and len(data):

        itemsize = libwriters.max_len_string_array(ensure_object(data))
        if compat.PY3:
            dtype = "U{0}".format(itemsize)
        else:
            dtype = "S{0}".format(itemsize)

        if isinstance(data[0], compat.binary_type):
            data = Series(data).str.decode(encoding, errors=errors).values
        else:
            data = data.astype(dtype, copy=False).astype(object, copy=False)

    if nan_rep is None:
        nan_rep = 'nan'

    data = libwriters.string_array_replace_from_nan_rep(data, nan_rep)
    return data.reshape(shape)