# coding: utf-8
# Copyright (c) Max-Planck-Institut für Eisenforschung GmbH - Computational Materials Design (CM) Department
# Distributed under the terms of "New BSD License", see the LICENSE file.
"""
The JobPath class enables quick access to the HDF5 data file without loading the full object
"""
import os
from typing import Any, Tuple
from pyiron_base.jobs.job.base import JobCore
from pyiron_base.project.generic import Project
from pyiron_base.storage.hdfio import ProjectHDFio
__author__ = "Joerg Neugebauer, Jan Janssen"
__copyright__ = (
"Copyright 2020, Max-Planck-Institut für Eisenforschung GmbH - "
"Computational Materials Design (CM) Department"
)
__version__ = "1.0"
__maintainer__ = "Jan Janssen"
__email__ = "janssen@mpie.de"
__status__ = "production"
__date__ = "Sep 1, 2017"
[docs]
class JobPath(JobCore):
"""
The JobPath class is derived from the JobCore and is used as a lean version of the GenericJob class. Instead of
loading the full pyiron object the JobPath class only provides access to the HDF5 file, which should be enough
for most analysis.
Attributes:
.. attribute:: job_name
name of the job, which has to be unique within the project
.. attribute:: status
execution status of the job, can be one of the following [initialized, appended, created, submitted, running,
aborted, collect, suspended, refresh, busy, finished]
.. attribute:: job_id
unique id to identify the job in the pyiron database
.. attribute:: parent_id
job id of the predecessor job - the job which was executed before the current one in the current job series
.. attribute:: master_id
job id of the master job - a meta job which groups a series of jobs, which are executed either in parallel or in
serial.
.. attribute:: child_ids
list of child job ids - only meta jobs have child jobs - jobs which list the meta job as their master
.. attribute:: project
Project instance the jobs is located in
.. attribute:: project_hdf5
ProjectHDFio instance which points to the HDF5 file the job is stored in
.. attribute:: job_info_str
short string to describe the job by it is job_name and job ID - mainly used for logging
.. attribute:: working_directory
working directory of the job is executed in - outside the HDF5 file
.. attribute:: path
path to the job as a combination of absolute file system path and path within the HDF5 file.
.. attribute:: is_root
boolean if the HDF5 object is located at the root level of the HDF5 file
.. attribute:: is_open
boolean if the HDF5 file is currently opened - if an active file handler exists
.. attribute:: is_empty
boolean if the HDF5 file is empty
.. attribute:: base_name
name of the HDF5 file but without any file extension
.. attribute:: file_path
directory where the HDF5 file is located
.. attribute:: h5_path
path inside the HDF5 file - also stored as absolute path
"""
[docs]
def __init__(self, job_path: str):
"""
Load a job from the given path.
Args:
job_path (str): path to the job, must be of the form /path/to/file.h5/job_name
"""
job_path_lst = job_path.replace("\\", "/").split(".h5")
if len(job_path_lst) != 2:
raise ValueError
sub_job = job_path_lst[1]
h5_path = None
if sub_job is not None:
if len(sub_job.strip()) > 0:
h5_path = "/".join(sub_job.split("/")[:-1])
hdf_project = ProjectHDFio(
project=Project(os.path.dirname(job_path_lst[0])),
file_name=job_path_lst[0].split("/")[-1] + ".h5",
h5_path=h5_path,
mode="r",
)
super().__init__(project=hdf_project, job_name=job_path_lst[1].split("/")[-1])
[docs]
@classmethod
def from_job_id(cls, db, job_id: int) -> "JobPath":
"""
Load a job path from a database connection and the job id.
Args:
db (DatabaseAccess): database connection
job_id (int): Job ID in the database
"""
db_entry = db.get_item_by_id(job_id)
if db_entry is None:
raise ValueError("job ID {0} does not exist!".format(job_id))
return cls.from_db_entry(db_entry)
[docs]
@classmethod
def from_db_entry(cls, db_entry: dict) -> "JobPath":
"""
Load a job path from a database entry.
Args:
db_entry (dict): database entry {"job":, "subjob":, "projectpath":, "project":, "hamilton":, "hamversion":,
"status":} and optional entries are {"id":, "masterid":, "parentid":}
"""
hdf5_file = db_entry["subjob"].split("/")[1] + ".h5"
job_path = db_entry["projectpath"]
if job_path is None:
job_path = ""
job_path += db_entry["project"] + hdf5_file + db_entry["subjob"]
job = cls(job_path=job_path)
if "hamilton" in db_entry.keys():
job.__name__ = db_entry["hamilton"]
if "hamversion" in db_entry.keys():
job.__version__ = db_entry["hamversion"]
if "id" in db_entry.keys():
job._job_id = db_entry["id"]
if "status" in db_entry.keys():
job._status = db_entry["status"]
if "masterid" in db_entry.keys():
job._master_id = db_entry["masterid"]
if "parentid" in db_entry.keys():
job._parent_id = db_entry["parentid"]
return job
@property
def is_root(self) -> bool:
"""
Check if the current h5_path is pointing to the HDF5 root group.
Returns:
bool: [True/False]
"""
return self.project_hdf5.is_root
@property
def is_empty(self) -> bool:
"""
Check if the HDF5 file is empty
Returns:
bool: [True/False]
"""
return self.project_hdf5.is_empty
@property
def base_name(self) -> str:
"""
Name of the HDF5 file - but without the file extension .h5
Returns:
str: file name without the file extension
"""
return self.project_hdf5.base_name
@property
def file_path(self) -> str:
"""
Path where the HDF5 file is located - posixpath.dirname()
Returns:
str: HDF5 file location
"""
return self.project_hdf5.file_path
@property
def h5_path(self) -> str:
"""
Get the path in the HDF5 file starting from the root group - meaning this path starts with '/'
Returns:
str: HDF5 path
"""
return self.project_hdf5.h5_path
@h5_path.setter
def h5_path(self, path: str) -> None:
"""
Set the path in the HDF5 file starting from the root group
Args:
path (str): HDF5 path
"""
self.project_hdf5.h5_path = path
[docs]
def create_group(self, name: str) -> "pyiron_base.storage.hdfio.ProjectHDFio":
"""
Create an HDF5 group - similar to a folder in the filesystem - the HDF5 groups allow the users to structure their
data.
Args:
name (str): name of the HDF5 group
Returns:
FileHDFio: FileHDFio object pointing to the new group
"""
return self.project_hdf5.create_group(name)
[docs]
def open(self, h5_rel_path: str) -> "pyiron_base.storage.hdfio.ProjectHDFio":
"""
Create an HDF5 group and enter this specific group. If the group exists in the HDF5 path only the h5_path is
set correspondingly otherwise the group is created first.
Args:
h5_rel_path (str): relative path from the current HDF5 path - h5_path - to the new group
Returns:
FileHDFio: FileHDFio object pointing to the new group
"""
return self.project_hdf5.open(h5_rel_path)
[docs]
def close(self) -> None:
"""
Close the current HDF5 path and return to the path before the last open
"""
self.project_hdf5.close()
[docs]
def remove_file(self) -> None:
"""
Remove the HDF5 file with all the related content
"""
self.project_hdf5.remove_file()
[docs]
def put(self, key: str, value: Any) -> None:
"""
Store data inside the HDF5 file
Args:
key (str): key to store the data
value (pandas.DataFrame, pandas.Series, dict, list, float, int): basically any kind of data is supported
"""
self.project_hdf5.__setitem__(key, value)
[docs]
def listdirs(self) -> list:
"""
equivalent to os.listdirs (consider groups as equivalent to dirs)
Returns:
(list): list of groups in pytables for the path self.h5_path
"""
return self.project_hdf5.list_groups()
[docs]
def list_dirs(self) -> list:
"""
equivalent to os.listdirs (consider groups as equivalent to dirs)
Returns:
(list): list of groups in pytables for the path self.h5_path
"""
return self.project_hdf5.list_groups()
[docs]
def keys(self) -> list:
"""
List all groups and nodes of the HDF5 file - where groups are equivalent to directories and nodes to files.
Returns:
list: all groups and nodes
"""
return self.project_hdf5.keys()
[docs]
def values(self) -> list:
"""
List all values for all groups and nodes of the HDF5 file
Returns:
list: list of all values
"""
return self.project_hdf5.values()
[docs]
def items(self) -> Tuple[list, list]:
"""
List all keys and values as items of all groups and nodes of the HDF5 file
Returns:
list: list of sets (key, value)
"""
return self.project_hdf5.items()
[docs]
def groups(self) -> list:
"""
Filter HDF5 file by groups
Returns:
FileHDFio: an HDF5 file which is filtered by groups
"""
return self.project_hdf5.groups()
[docs]
def nodes(self) -> list:
"""
Filter HDF5 file by nodes
Returns:
FileHDFio: an HDF5 file which is filtered by nodes
"""
return self.project_hdf5.nodes()
def __enter__(self) -> "JobPath":
"""
Compatibility function for the with statement
"""
return self.project_hdf5.__enter__()
def __exit__(self, exc_type, exc_val, exc_tb):
"""
Compatibility function for the with statement
"""
self.project_hdf5.__exit__(exc_type=exc_type, exc_val=exc_val, exc_tb=exc_tb)
def __setitem__(self, key: str, value: Any) -> None:
"""
Store data inside the HDF5 file
Args:
key (str): key to store the data
value (pandas.DataFrame, pandas.Series, dict, list, float, int): basically any kind of data is supported
"""
self.project_hdf5.__setitem__(key, value)
def __delitem__(self, key: str) -> None:
"""
Delete item from the HDF5 file
Args:
key (str): key of the item to delete
"""
self.project_hdf5.__delitem__(key)
def __str__(self) -> str:
"""
Machine readable string representation
Returns:
str: list all nodes and groups as string
"""
return self.project_hdf5.__str__()
def __repr__(self) -> str:
"""
Human readable string representation
Returns:
str: list all nodes and groups as string
"""
return self.project_hdf5.__repr__()
def __del__(self) -> None:
"""
When the object is deleted the HDF5 file has to be closed
"""
try:
self.project_hdf5._store.close()
except AttributeError:
pass
