How to use the pycldf.dataset function in pycldf

To help you get started, we’ve selected a few pycldf examples, based on popular ways it is used in public projects.

Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.

github lingpy / lingpy / lingpy / basic / wordlist.py View on Github external
}
        kwargs.update(kw)
        
        if isinstance(namespace, tuple):
            namespace = dict(namespace)

        # get the datatypes from configuration as to namespace
        datatypes = read_conf(kwargs['conf'])[1]

        # Load the dataset.
        fname = Path(path)
        if not fname.exists():
            raise compat.FileNotFoundError(
                '{:} does not exist'.format(fname))
        if fname.suffix == '.json':
            dataset = pycldf.dataset.Dataset.from_metadata(fname)
        else:
            dataset = pycldf.dataset.Dataset.from_data(fname)

        if dataset.module == "Wordlist":
            # First, make a list of cognate codes if they are in a separate table.
            cognateset_assignments = {}
            try:
                form_reference = dataset["CognateTable", "formReference"].name
                for row in dataset["CognateTable"].iterdicts():
                    cognateset_assignments[row[form_reference]] = row
            except KeyError:
                # Either there are no cognate codes, or they are in the form
                # table. Both options are fine.
                pass

            f_id = dataset["FormTable", "id"].name
github lingpy / lingpy / lingpy / basic / wordlist.py View on Github external
if isinstance(namespace, tuple):
            namespace = dict(namespace)

        # get the datatypes from configuration as to namespace
        datatypes = read_conf(kwargs['conf'])[1]

        # Load the dataset.
        fname = Path(path)
        if not fname.exists():
            raise compat.FileNotFoundError(
                '{:} does not exist'.format(fname))
        if fname.suffix == '.json':
            dataset = pycldf.dataset.Dataset.from_metadata(fname)
        else:
            dataset = pycldf.dataset.Dataset.from_data(fname)

        if dataset.module == "Wordlist":
            # First, make a list of cognate codes if they are in a separate table.
            cognateset_assignments = {}
            try:
                form_reference = dataset["CognateTable", "formReference"].name
                for row in dataset["CognateTable"].iterdicts():
                    cognateset_assignments[row[form_reference]] = row
            except KeyError:
                # Either there are no cognate codes, or they are in the form
                # table. Both options are fine.
                pass

            f_id = dataset["FormTable", "id"].name

            # Access columns by type, not by name.
github lmaurits / BEASTling / beastling / fileio / datareaders.py View on Github external
Parameters
    ----------
    fname : str or Path
        Path to a CLDF dataset

    Returns
    -------
    Dataset
    """
    fname = Path(fname)
    if not fname.exists():
        raise FileNotFoundError(
            '{:} does not exist'.format(fname))
    if fname.suffix == '.json':
        return pycldf.dataset.Dataset.from_metadata(fname)
    return pycldf.dataset.Dataset.from_data(fname)
github lmaurits / BEASTling / beastling / fileio / datareaders.py View on Github external
Parameters
    ----------
    fname : str or Path
        Path to a CLDF dataset

    Returns
    -------
    Dataset
    """
    fname = Path(fname)
    if not fname.exists():
        raise FileNotFoundError(
            '{:} does not exist'.format(fname))
    if fname.suffix == '.json':
        return pycldf.dataset.Dataset.from_metadata(fname)
    return pycldf.dataset.Dataset.from_data(fname)
github clld / clld / src / clld / web / adapters / cldf.py View on Github external
def create(self, req, filename=None, verbose=True, outfile=None):
        cldf_cfg = req.registry.getUtility(ICldfConfig)

        with TemporaryDirectory() as tmpd:
            cls = getattr(dataset, cldf_cfg.module)
            ds = cls.in_dir(tmpd)
            ds.properties['dc:bibliographicCitation'] = text_citation(req, req.dataset)
            ds.properties['dc:publisher'] = '%s, %s' % (
                req.dataset.publisher_name, req.dataset.publisher_place)
            ds.properties['dc:license'] = req.dataset.license
            ds.properties['dc:issued'] = req.dataset.published.isoformat()
            ds.properties['dc:title'] = req.dataset.name
            ds.properties['dc:creator'] = req.dataset.formatted_editors()
            ds.properties['dc:identifier'] = req.resource_url(req.dataset)
            ds.properties['dcat:accessURL'] = req.route_url('download')
            if DBSession.query(Sentence).count():
                ds.add_component('ExampleTable')
            if DBSession.query(DomainElement).count():
                ds.add_component('CodeTable', {'name': 'Number', 'datatype': 'integer'})
            ds.add_component('ParameterTable')
            ds.add_component('LanguageTable')

pycldf

A python library to read and write CLDF datasets

Apache-2.0
Latest version published 2 months ago

Package Health Score

73 / 100
Full package analysis