Python feather.write_dataframe方法代码示例

# 需要导入模块: import feather [as 别名]
# 或者: from feather import write_dataframe [as 别名]
def health_xml_to_feather(zip_file, output_file, remove_zip=False):
    with tempfile.TemporaryDirectory() as tmpdirname:
        f = zipfile.ZipFile(zip_file, "r")
        f.extractall(tmpdirname)
        xml_path = os.path.join(tmpdirname, "apple_health_export/export.xml")
        tree = etree.parse(xml_path)
        records = tree.xpath("//Record")
        df = pd.DataFrame([{key: r.get(key) for key in ALL_KEYS}
                           for r in records])

        # Clean up key types
        for k in DATETIME_KEYS:
            df[k] = pd.to_datetime(df[k])
        for k in NUMERIC_KEYS:
            # some rows have non-numeric values, so coerce and drop NaNs
            df[k] = pd.to_numeric(df[k], errors="coerce")
            df = df[df["value"].notnull()]

        feather.write_dataframe(df, output_file)

    if remove_zip:
        os.remove(zip_file) 

# 需要导入模块: import feather [as 别名]
# 或者: from feather import write_dataframe [as 别名]
def save(data, filename):
    """Pickles the passed data (with the highest available protocol) to disk using the passed filename.
    If the filename ends in '.gz' then the data will additionally be GZIPed before saving.
    If filename ends with '.feather' or '.fthr', mlcrate will try to save the file using feather (for dataframes).
    Note that feather does not support compression.

    Keyword arguments:
    data -- The python object to pickle to disk (use a dict or list to save multiple objects)
    filename -- String with the relative filename to save the data to. By convention should end in '.pkl' or 'pkl.gz' or '.feather'
    """
    folders = os.path.dirname(filename)
    if folders:
        os.makedirs(folders, exist_ok=True)

    fl = filename.lower()
    if fl.endswith('.gz'):
        if fl.endswith('.feather.gz') or fl.endswith('.fthr.gz'):
            # Since feather doesn't support writing to the file handle, we can't easily point it to gzip.
            raise NotImplementedError('Saving to compressed .feather not currently supported.')
        else:
            fp = gzip.open(filename, 'wb')
            pickle.dump(data, fp, protocol=pickle.HIGHEST_PROTOCOL)
    else:
        if fl.endswith('.feather') or fl.endswith('.fthr'):
            if str(type(data)) != "<class 'pandas.core.frame.DataFrame'>":
                raise TypeError('.feather format can only be used to save pandas DataFrames')
            import feather
            feather.write_dataframe(data, filename)
        else:
            fp = open(filename, 'wb')
            pickle.dump(data, fp, protocol=pickle.HIGHEST_PROTOCOL) 

# 需要导入模块: import feather [as 别名]
# 或者: from feather import write_dataframe [as 别名]
def _dump_table(self, dst, fmt='feather', components=None, *args, **kwargs):
        """ Save batch data to table formats

        Args:
          dst: str - a path to dump into
          fmt: str - format: feather, hdf5, csv
          components: str or tuple - one or several component names
        """
        filename = dst

        components = tuple(components or self.components)
        data_dict = {}
        for comp in components:
            comp_data = self.get(component=comp)
            if isinstance(comp_data, pd.DataFrame):
                data_dict.update(comp_data.to_dict('series'))
            elif isinstance(comp_data, np.ndarray):
                if comp_data.ndim > 1:
                    columns = [comp + str(i) for i in range(comp_data.shape[1])]
                    comp_dict = zip(columns, (comp_data[:, i] for i in range(comp_data.shape[1])))
                    data_dict.update({comp: comp_dict})
                else:
                    data_dict.update({comp: comp_data})
            else:
                data_dict.update({comp: comp_data})
        _data = pd.DataFrame(data_dict)

        if fmt == 'feather':
            feather.write_dataframe(_data, filename, *args, **kwargs)
        elif fmt == 'hdf5':
            _data.to_hdf(filename, *args, **kwargs)   # pylint:disable=no-member
        elif fmt == 'csv':
            _data.to_csv(filename, *args, **kwargs)   # pylint:disable=no-member
        else:
            raise ValueError('Unknown format %s' % fmt)

        return self 

# 需要导入模块: import feather [as 别名]
# 或者: from feather import write_dataframe [as 别名]
def save_df(df, path, index=False):
    if path == '-' or path is None:
        print(default_csv_writer(df, None, index=index))
    elif file_format(path) != 'feather':
        default_csv_writer(df, path, index=index)
    elif featherpmm and feather:
        featherpmm.write_dataframe(featherpmm.Dataset(df, name='verification'),
                                   path)
    elif feather:
        feather.write_dataframe(df, path)
    else:
        raise Exception('The Python feather module is not installed.\n'
                        'Use:\n    pip install feather-format\n'
                        'to add capability.\n') 

# 需要导入模块: import feather [as 别名]
# 或者: from feather import write_dataframe [as 别名]
def to_feather(df, path):
    """
    Write a DataFrame to the feather-format

    Parameters
    ----------
    df : DataFrame
    path : string file path, or file-like object

    """
    path = _stringify_path(path)
    if not isinstance(df, DataFrame):
        raise ValueError("feather only support IO with DataFrames")

    feather = _try_import()
    valid_types = {'string', 'unicode'}

    # validate index
    # --------------

    # validate that we have only a default index
    # raise on anything else as we don't serialize the index

    if not isinstance(df.index, Int64Index):
        raise ValueError("feather does not support serializing {} "
                         "for the index; you can .reset_index()"
                         "to make the index into column(s)".format(
                             type(df.index)))

    if not df.index.equals(RangeIndex.from_range(range(len(df)))):
        raise ValueError("feather does not support serializing a "
                         "non-default index for the index; you "
                         "can .reset_index() to make the index "
                         "into column(s)")

    if df.index.name is not None:
        raise ValueError("feather does not serialize index meta-data on a "
                         "default index")

    # validate columns
    # ----------------

    # must have value column names (strings only)
    if df.columns.inferred_type not in valid_types:
        raise ValueError("feather must have string column names")

    feather.write_dataframe(df, path)