How to use pydra - 10 common examples

def splitter_validation(self):
        """ validating if the splitter is correct (after all states are connected)"""
        for spl in self.splitter_rpn_compact:
            if not (
                spl in [".", "*"]
                or spl.startswith("_")
                or spl.split(".")[0] == self.name
            ):
                raise hlpst.PydraStateError(
                    "can't include {} in the splitter, consider using _{}".format(
                        spl, spl.split(".")[0]
                    )

TODO

        """
        self.state.prepare_states(self.inputs)
        self.state.prepare_inputs()
        if state_index is not None:
            inputs_copy = deepcopy(self.inputs)
            for key, ind in self.state.inputs_ind[state_index].items():
                setattr(
                    inputs_copy,
                    key.split(".")[1],
                    getattr(inputs_copy, key.split(".")[1])[ind],
                )
            input_hash = inputs_copy.hash
            if is_workflow(self):
                con_hash = hash_function(self._connections)
                hash_list = [input_hash, con_hash]
                checksum_ind = create_checksum(
                    self.__class__.__name__, self._checksum_wf(input_hash)
                )
            else:
                checksum_ind = create_checksum(self.__class__.__name__, input_hash)
            return checksum_ind
        else:
            checksum_list = []
            for ind in range(len(self.state.inputs_ind)):
                checksum_list.append(self.checksum_states(state_index=ind))
            return checksum_list

def split(self, splitter, overwrite=False, **kwargs):
        """
        Run this task parametrically over lists of splitted inputs.

        Parameters
        ----------
        splitter :
            TODO
        overwrite : :obj:`bool`
            TODO

        """
        splitter = hlpst.add_name_splitter(splitter, self.name)
        # if user want to update the splitter, overwrite has to be True
        if self.state and not overwrite and self.state.splitter != splitter:
            raise Exception(
                "splitter has been already set, "
                "if you want to overwrite it - use overwrite=True"
            )
        if kwargs:
            self.inputs = attr.evolve(self.inputs, **kwargs)
            self.state_inputs = kwargs
        if not self.state or splitter != self.state.splitter:
            self.set_state(splitter)
        return self

def combine(self, combiner, overwrite=False):
        """
        Combine inputs parameterized by one or more previous tasks.

        Parameters
        ----------
        combiner :
            TODO
        overwrite : :obj:`bool`
            TODO

        """
        if not isinstance(combiner, (str, list)):
            raise Exception("combiner has to be a string or a list")
        combiner = hlpst.add_name_combiner(ensure_list(combiner), self.name)
        if (
            self.state
            and self.state.combiner
            and combiner != self.state.combiner
            and not overwrite
        ):
            raise Exception(
                "combiner has been already set, "
                "if you want to overwrite it - use overwrite=True"
            )
        if not self.state:
            self.split(splitter=None)
            # a task can have a combiner without a splitter
            # if is connected to one with a splitter;
            # self.fut_combiner will be used later as a combiner
            self.fut_combiner = combiner

def split(self, splitter, overwrite=False, **kwargs):
        """
        Run this task parametrically over lists of splitted inputs.

        Parameters
        ----------
        splitter :
            TODO
        overwrite : :obj:`bool`
            TODO

        """
        splitter = hlpst.add_name_splitter(splitter, self.name)
        # if user want to update the splitter, overwrite has to be True
        if self.state and not overwrite and self.state.splitter != splitter:
            raise Exception(
                "splitter has been already set, "
                "if you want to overwrite it - use overwrite=True"
            )
        if kwargs:
            self.inputs = attr.evolve(self.inputs, **kwargs)
            self.state_inputs = kwargs
        if not self.state or splitter != self.state.splitter:
            self.set_state(splitter)
        return self

def git_versions_from_keywords(keywords, tag_prefix, verbose):
    """Get version information from git keywords."""
    if not keywords:
        raise NotThisMethod("no keywords at all, weird")
    date = keywords.get("date")
    if date is not None:
        # git-2.2.0 added "%cI", which expands to an ISO-8601 -compliant
        # datestamp. However we prefer "%ci" (which expands to an "ISO-8601
        # -like" string, which we must then edit to make compliant), because
        # it's been around since git-1.5.3, and it's too difficult to
        # discover which version we're using, or to work around using an
        # older one.
        date = date.strip().replace(" ", "T", 1).replace(" ", "", 1)
    refnames = keywords["refnames"].strip()
    if refnames.startswith("$Format"):
        if verbose:
            print("keywords are unexpanded, not using")
        raise NotThisMethod("unexpanded keywords, not a git-archive tarball")
    refs = set([r.strip() for r in refnames.strip("()").split(",")])
    # starting in git-1.8.3, tags are listed as "tag: foo-1.0" instead of

# this to find the root from __file__.
        for i in cfg.versionfile_source.split("/"):
            root = os.path.dirname(root)
    except NameError:
        return {
            "version": "0+unknown",
            "full-revisionid": None,
            "dirty": None,
            "error": "unable to find root of source tree",
            "date": None,
        }

    try:
        pieces = git_pieces_from_vcs(cfg.tag_prefix, root, verbose)
        return render(pieces, cfg.style)
    except NotThisMethod:
        pass

    try:
        if cfg.parentdir_prefix:
            return versions_from_parentdir(cfg.parentdir_prefix, root, verbose)
    except NotThisMethod:
        pass

    return {
        "version": "0+unknown",
        "full-revisionid": None,
        "dirty": None,
        "error": "unable to compute version",
        "date": None,
    }

if not keywords:
        raise NotThisMethod("no keywords at all, weird")
    date = keywords.get("date")
    if date is not None:
        # git-2.2.0 added "%cI", which expands to an ISO-8601 -compliant
        # datestamp. However we prefer "%ci" (which expands to an "ISO-8601
        # -like" string, which we must then edit to make compliant), because
        # it's been around since git-1.5.3, and it's too difficult to
        # discover which version we're using, or to work around using an
        # older one.
        date = date.strip().replace(" ", "T", 1).replace(" ", "", 1)
    refnames = keywords["refnames"].strip()
    if refnames.startswith("$Format"):
        if verbose:
            print("keywords are unexpanded, not using")
        raise NotThisMethod("unexpanded keywords, not a git-archive tarball")
    refs = set([r.strip() for r in refnames.strip("()").split(",")])
    # starting in git-1.8.3, tags are listed as "tag: foo-1.0" instead of
    # just "foo-1.0". If we see a "tag: " prefix, prefer those.
    TAG = "tag: "
    tags = set([r[len(TAG) :] for r in refs if r.startswith(TAG)])
    if not tags:
        # Either we're using git < 1.8.3, or there really are no tags. We use
        # a heuristic: assume all version tags have a digit. The old git %d
        # expansion behaves like git log --decorate=short and strips out the
        # refs/heads/ and refs/tags/ prefixes that would let us distinguish
        # between branches and tags. By ignoring refnames without digits, we
        # filter out many common branch names like "release" and
        # "stabilization", as well as "HEAD" and "master".
        tags = set([r for r in refs if re.search(r"\d", r)])
        if verbose:
            print("discarding '%s', no digits" % ",".join(refs - tags))

"""
        self.state.prepare_states(self.inputs)
        self.state.prepare_inputs()
        if state_index is not None:
            inputs_copy = deepcopy(self.inputs)
            for key, ind in self.state.inputs_ind[state_index].items():
                setattr(
                    inputs_copy,
                    key.split(".")[1],
                    getattr(inputs_copy, key.split(".")[1])[ind],
                )
            input_hash = inputs_copy.hash
            if is_workflow(self):
                con_hash = hash_function(self._connections)
                hash_list = [input_hash, con_hash]
                checksum_ind = create_checksum(
                    self.__class__.__name__, self._checksum_wf(input_hash)
                )
            else:
                checksum_ind = create_checksum(self.__class__.__name__, input_hash)
            return checksum_ind
        else:
            checksum_list = []
            for ind in range(len(self.state.inputs_ind)):
                checksum_list.append(self.checksum_states(state_index=ind))
            return checksum_list

inputs_copy = deepcopy(self.inputs)
            for key, ind in self.state.inputs_ind[state_index].items():
                setattr(
                    inputs_copy,
                    key.split(".")[1],
                    getattr(inputs_copy, key.split(".")[1])[ind],
                )
            input_hash = inputs_copy.hash
            if is_workflow(self):
                con_hash = hash_function(self._connections)
                hash_list = [input_hash, con_hash]
                checksum_ind = create_checksum(
                    self.__class__.__name__, self._checksum_wf(input_hash)
                )
            else:
                checksum_ind = create_checksum(self.__class__.__name__, input_hash)
            return checksum_ind
        else:
            checksum_list = []
            for ind in range(len(self.state.inputs_ind)):
                checksum_list.append(self.checksum_states(state_index=ind))
            return checksum_list