def snapped_coordinates(self, value):
value = validators.iterable(value,
allow_empty=True,
minimum_length=2,
maximum_length=2)
self.snapped_longitude = value[0]
self.snapped_latitude = value[1]
def align_max_deviation(self, val: Tuple[float, float]):
val = validators.iterable(
val, minimum_length=2, maximum_length=2, allow_empty=True
)
self._align_max_deviation = val if val is None else tuple([
validators.numeric(i, minimum=0) for i in val
])
def ground_temperatures(self, value):
if checkers.is_numeric(value):
ground_temperatures = [value] * 12
elif checkers.is_iterable(value):
ground_temperature = validators.iterable(value,
minimum_length=12,
maximum_length=12)
ground_temperatures = [temp for temp in ground_temperature]
else:
raise ValueError(
"Input error for value 'ground_temperature'. Value must "
"be numeric or an iterable of length 12.")
self._ground_temperatures = ground_temperatures
def is_iterable(obj,
forbid_literals = (str, bytes),
minimum_length = None,
maximum_length = None,
**kwargs):
"""Indicate whether ``obj`` is iterable.
:param forbid_literals: A collection of literals that will be considered invalid
even if they are (actually) iterable. Defaults to a :class:`tuple <python:tuple>`
containing :class:`str <python:str>` and :class:`bytes <python:bytes>`.
:type forbid_literals: iterable
:param minimum_length: If supplied, indicates the minimum number of members
needed to be valid.
:type minimum_length: :class:`int <python:int>`
:param maximum_length: If supplied, indicates the minimum number of members
needed to be valid.
:type maximum_length: :class:`int <python:int>`
:returns: ``True`` if ``obj`` is a valid iterable, ``False`` if not.
:rtype: :class:`bool <python:bool>`
:raises SyntaxError: if ``kwargs`` contains duplicate keyword parameters or duplicates
keyword parameters passed to the underlying validator
"""
if obj is None:
return False
if obj in forbid_literals:
return False
try:
obj = validators.iterable(obj,
allow_empty = True,
forbid_literals = forbid_literals,
minimum_length = minimum_length,
maximum_length = maximum_length,
**kwargs)
assert isinstance(obj, Iterable)
except SyntaxError as error:
raise error
except Exception:
return False
return True
def missing_range_metadata(self, value):
value = validators.iterable(value, allow_empty = True)
if not value:
self._missing_range_metadata = None
else:
ranges = [validators.dict(x, allow_empty = False) for x in value]
validated_ranges = []
for range in ranges:
if 'high' not in range or 'low' not in range:
raise ValueError('missing_range_metadata requires a "high" and "low"'
' boundary to be defined.')
validated_range = {
'high': validators.numeric(range.get('high'), allow_empty = False),
'low': validators.numeric(range.get('low'), allow_empty = False)
}
validated_ranges.append(validated_range)
self._missing_range_metadata = validated_ranges
def iterable__to_dict(iterable,
format,
max_nesting=0,
current_nesting=0,
is_dumping=False,
config_set=None):
"""Given an iterable, traverse it and execute ``_to_dict()`` if present.
:param iterable: An iterable to traverse.
:type iterable: iterable
:param format: The format to which the :class:`dict <python:dict>` will
ultimately be serialized. Accepts: ``'csv'``, ``'json'``, ``'yaml'``, and
``'dict'``.
:type format: :class:`str <python:str>`
:param max_nesting: The maximum number of levels that the resulting
:class:`dict <python:dict>` object can be nested. If set to ``0``, will
not nest other serializable objects. Defaults to ``0``.
:type max_nesting: :class:`int <python:int>`
:param current_nesting: The current nesting level at which the
:class:`dict <python:dict>` representation will reside. Defaults to ``0``.
:type current_nesting: :class:`int <python:int>`
:param is_dumping: If ``True``, returns all attributes. Defaults to ``False``.
:type is_dumping: :class:`bool <python:bool>`
:param config_set: If not :obj:`None <python:None>`, the named configuration set
to use when processing the input. Defaults to :obj:`None <python:None>`.
:type config_set: :class:`str <python:str>` / :obj:`None <python:None>`
:returns: Collection of values, possibly converted to :class:`dict <python:dict>`
objects.
:rtype: :class:`list <python:list>` of objects
:raises InvalidFormatError: if ``format`` is not an acceptable value
:raises ValueError: if ``iterable`` is not an iterable
"""
next_nesting = current_nesting + 1
if format not in ['csv', 'json', 'yaml', 'dict']:
raise InvalidFormatError("format '%s' not supported" % format)
iterable = validators.iterable(iterable,
allow_empty=True,
forbid_literals=(str, bytes, dict))
if iterable is None:
return []
if current_nesting > max_nesting:
raise MaximumNestingExceededError(
'current nesting level (%s) exceeds maximum %s' %
(current_nesting, max_nesting))
items = []
for item in iterable:
try:
new_item = item._to_dict(format,
max_nesting=max_nesting,
current_nesting=next_nesting,
is_dumping=is_dumping,
config_set=config_set)
except AttributeError:
try:
new_item = iterable__to_dict(item,
format,
max_nesting=max_nesting,
current_nesting=next_nesting,
is_dumping=is_dumping,
config_set=config_set)
except NotAnIterableError:
new_item = item
items.append(new_item)
return items
def from_iterable(value):
return validators.iterable(value, allow_empty=True)
def backoff(to_execute,
args = None,
kwargs = None,
strategy = None,
retry_execute = None,
retry_args = None,
retry_kwargs = None,
max_tries = None,
max_delay = None,
catch_exceptions = None,
on_failure = None,
on_success = None):
"""Retry a function call multiple times with a delay per the strategy given.
:param to_execute: The function call that is to be attempted.
:type to_execute: callable
:param args: The positional arguments to pass to the function on the first attempt.
If ``retry_args`` is :class:`None <python:None>`, will re-use these
arguments on retry attempts as well.
:type args: iterable / :class:`None <python:None>`.
:param kwargs: The keyword arguments to pass to the function on the first attempt.
If ``retry_kwargs`` is :class:`None <python:None>`, will re-use these keyword
arguments on retry attempts as well.
:type kwargs: :class:`dict <python:dict>` / :class:`None <python:None>`
:param strategy: The :class:`BackoffStrategy` to use when determining the
delay between retry attempts.
If :class:`None <python:None>`, defaults to :class:`Exponential`.
:type strategy: :class:`BackoffStrategy`
:param retry_execute: The function to call on retry attempts.
If :class:`None <python:None>`, will retry ``to_execute``.
Defaults to :class:`None <python:None>`.
:type retry_execute: callable / :class:`None <python:None>`
:param retry_args: The positional arguments to pass to the function on retry attempts.
If :class:`None <python:None>`, will re-use ``args``.
Defaults to :class:`None <python:None>`.
:type retry_args: iterable / :class:`None <python:None>`
:param retry_kwargs: The keyword arguments to pass to the function on retry attempts.
If :class:`None <python:None>`, will re-use ``kwargs``.
Defaults to :class:`None <python:None>`.
:type subsequent_kwargs: :class:`dict <python:dict>` / :class:`None <python:None>`
:param max_tries: The maximum number of times to attempt the call.
If :class:`None <python:None>`, will apply an environment variable
``BACKOFF_DEFAULT_TRIES``. If that environment variable is not set, will
apply a default of ``3``.
:type max_tries: int / :class:`None <python:None>`
:param max_delay: The maximum number of seconds to wait befor giving up
once and for all. If :class:`None <python:None>`, will apply an environment variable
``BACKOFF_DEFAULT_DELAY`` if that environment variable is set. If it is not
set, will not apply a max delay at all.
:type max_delay: :class:`None <python:None>` / int
:param catch_exceptions: The ``type(exception)`` to catch and retry. If
:class:`None <python:None>`, will catch all exceptions.
Defaults to :class:`None <python:None>`.
.. caution::
The iterable must contain one or more types of exception *instances*, and not
class objects. For example:
.. code-block:: python
# GOOD:
catch_exceptions = (type(ValueError()), type(TypeError()))
# BAD:
catch_exceptions = (type(ValueError), type(ValueError))
# BAD:
catch_exceptions = (ValueError, TypeError)
# BAD:
catch_exceptions = (ValueError(), TypeError())
:type catch_exceptions: iterable of form ``[type(exception()), ...]``
:param on_failure: The :class:`exception <python:Exception>` or function to call
when all retry attempts have failed.
If :class:`None <python:None>`, will raise the last-caught
:class:`exception <python:Exception>`.
If an :class:`exception <python:Exception>`, will raise the exception with
the same message as the last-caught exception.
If a function, will call the function and pass the last-raised exception, its
message, and stacktrace to the function.
Defaults to :class:`None <python:None>`.
:type on_failure: :class:`Exception <python:Exception>` / function /
:class:`None <python:None>`
:param on_success: The function to call when the operation was successful.
The function receives the result of the ``to_execute`` or ``retry_execute``
function that was successful, and is called before that result is returned
to whatever code called the backoff function. If :class:`None <python:None>`,
will just return the result of ``to_execute`` or ``retry_execute`` without
calling a handler.
Defaults to :class:`None <python:None>`.
:type on_success: callable / :class:`None <python:None>`
:returns: The result of the attempted function.
Example:
.. code-block:: python
from backoff_utils import backoff
def some_function(arg1, arg2, kwarg1 = None):
# Function does something
pass
result = backoff(some_function,
args = ['value1', 'value2'],
kwargs = { 'kwarg1': 'value3' },
max_tries = 3,
max_delay = 30,
strategy = strategies.Exponential)
"""
# pylint: disable=too-many-branches,too-many-statements
if to_execute is None:
raise ValueError('to_execute cannot be None')
elif not checkers.is_callable(to_execute):
raise TypeError('to_execute must be callable')
if strategy is None:
strategy = strategies.Exponential
if not hasattr(strategy, 'IS_INSTANTIATED'):
raise TypeError('strategy must be a BackoffStrategy or descendent')
if not strategy.IS_INSTANTIATED:
test_strategy = strategy(attempt = 0)
else:
test_strategy = strategy
if not checkers.is_type(test_strategy, 'BackoffStrategy'):
raise TypeError('strategy must be a BackoffStrategy or descendent')
if args:
args = validators.iterable(args)
if kwargs:
kwargs = validators.dict(kwargs)
if retry_execute is None:
retry_execute = to_execute
elif not checkers.is_callable(retry_execute):
raise TypeError('retry_execute must be None or a callable')
if not retry_args:
retry_args = args
else:
retry_args = validators.iterable(retry_args)
if not retry_kwargs:
retry_kwargs = kwargs
else:
retry_kwargs = validators.dict(retry_kwargs)
if max_tries is None:
max_tries = DEFAULT_MAX_TRIES
max_tries = validators.integer(max_tries)
if max_delay is None:
max_delay = DEFAULT_MAX_DELAY
if catch_exceptions is None:
catch_exceptions = [type(Exception())]
else:
if not checkers.is_iterable(catch_exceptions):
catch_exceptions = [catch_exceptions]
catch_exceptions = validators.iterable(catch_exceptions)
if on_failure is not None and not checkers.is_callable(on_failure):
raise TypeError('on_failure must be None or a callable')
if on_success is not None and not checkers.is_callable(on_success):
raise TypeError('on_success must be None or a callable')
cached_error = None
return_value = None
returned = False
failover_counter = 0
start_time = datetime.utcnow()
while failover_counter <= (max_tries):
elapsed_time = (datetime.utcnow() - start_time).total_seconds()
if max_delay is not None and elapsed_time >= max_delay:
if cached_error is None:
raise BackoffTimeoutError('backoff timed out after:'
' {}s'.format(elapsed_time))
else:
_handle_failure(on_failure, cached_error)
if failover_counter == 0:
try:
if args is not None and kwargs is not None:
return_value = to_execute(*args, **kwargs)
elif args is not None:
return_value = to_execute(*args)
elif kwargs is not None:
return_value = to_execute(**kwargs)
else:
return_value = to_execute()
returned = True
break
except Exception as error: # pylint: disable=broad-except
if type(error) in catch_exceptions:
cached_error = error
strategy.delay(failover_counter)
failover_counter += 1
continue
else:
_handle_failure(on_failure = on_failure,
error = error)
return
else:
try:
if retry_args is not None and retry_kwargs is not None:
return_value = retry_execute(*retry_args, **retry_kwargs)
elif retry_args is not None:
return_value = retry_execute(*retry_args)
elif retry_kwargs is not None:
return_value = retry_execute(**retry_kwargs)
else:
return_value = retry_execute()
returned = True
break
except Exception as error: # pylint: disable=broad-except
if type(error) in catch_exceptions:
strategy.delay(failover_counter)
cached_error = error
failover_counter += 1
continue
else:
_handle_failure(on_failure = on_failure,
error = error)
return
if not returned:
_handle_failure(on_failure = on_failure,
error = cached_error)
return
elif returned and on_success is not None:
on_success(return_value)
return return_value
def _read_spss(data: Union[bytes, BytesIO, 'os.PathLike[Any]'],
limit: Optional[int] = None,
offset: int = 0,
exclude_variables: Optional[List[str]] = None,
include_variables: Optional[List[str]] = None,
metadata_only: bool = False,
apply_labels: bool = False,
labels_as_categories: bool = True,
missing_as_NaN: bool = False,
convert_datetimes: bool = True,
dates_as_datetime64: bool = False,
**kwargs):
"""Internal function that reads an SPSS (.sav or .zsav) file and returns a
:class:`tuple <python:tuple>` with a Pandas
:class:`DataFrame <pandas:pandas.DataFrame>` object and a metadata
:class:`dict <python:dict>`.
:param data: The SPSS data to load. Accepts either a series of bytes or a filename.
:type data: Path-like filename, :class:`bytes <python:bytes>` or
:class:`BytesIO <python:io.bytesIO>`
:param limit: The number of records to read from the data. If :obj:`None <python:None>`
will return all records. Defaults to :obj:`None <python:None>`.
:type limit: :class:`int <python:int>` or :obj:`None <python:None>`
:param offset: The record at which to start reading the data. Defaults to 0 (first
record).
:type offset: :class:`int <python:int>`
:param exclude_variables: A list of the variables that should be ignored when reading
data. Defaults to :obj:`None <python:None>`.
:type exclude_variables: iterable of :class:`str <python:str>` or
:obj:`None <python:None>`
:param include_variables: A list of the variables that should be explicitly included
when reading data. Defaults to :obj:`None <python:None>`.
:type include_variables: iterable of :class:`str <python:str>` or
:obj:`None <python:None>`
:param metadata_only: If ``True``, will return no data records in the resulting
:class:`DataFrame <pandas:pandas.DataFrame>` but will return a complete metadata
:class:`dict <python:dict>`. Defaults to ``False``.
:type metadata_only: :class:`bool <python:bool>`
:param apply_labels: If ``True``, converts the numerically-coded values in the raw
data to their human-readable labels. Defaults to ``False``.
:type apply_labels: :class:`bool <python:bool>`
:param labels_as_categories: If ``True``, will convert labeled or formatted values to
Pandas :term:`categories <pandas:category>`. Defaults to ``True``.
.. caution::
This parameter will only have an effect if the ``apply_labels`` parameter is
``True``.
:type labels_as_categories: :class:`bool <python:bool>`
:param missing_as_NaN: If ``True``, will return any missing values as
:class:`NaN <pandas:NaN>`. Otherwise will return missing values as per the
configuration of missing value representation stored in the underlying SPSS data.
Defaults to ``False``, which applies the missing value representation configured in
the SPSS data itself.
:type missing_as_NaN: :class:`bool <python:bool>`
:param convert_datetimes: if ``True``, will convert the native integer representation
of datetime values in the SPSS data to Pythonic
:class:`datetime <python:datetime.datetime>`, or
:class:`date <python:datetime.date>`, etc. representations (or Pandas
:class:`datetime64 <pandas:datetime64>`, depending on the ``dates_as_datetime64``
parameter). If ``False``, will leave the original integer representation. Defaults
to ``True``.
:type convert_datetimes: :class:`bool <python:bool>`
:param dates_as_datetime64: If ``True``, will return any date values as Pandas
:class:`datetime64 <pandas.datetime64>` types. Defaults to ``False``.
.. caution::
This parameter is only applied if ``convert_datetimes`` is set to ``True``.
:type dates_as_datetime64: :class:`bool <python:bool>`
:returns: A :class:`DataFrame <pandas:DataFrame>` representation of the SPSS data (or
:obj:`None <python:None>`) and a :class:`Metadata` representation of the dataset's
metadata / data map.
:rtype: :class:`pandas.DataFrame <pandas:DataFrame>`/:obj:`None <python:None>` and
:class:`Metadata`
"""
if not any([
checkers.is_file(data),
checkers.is_bytesIO(data),
checkers.is_type(data, bytes)
]):
raise errors.InvalidDataFormatError(
'data must be a filename, BytesIO, or bytes '
f'object. Was: {data.__class__.__name__}')
limit = validators.integer(limit, allow_empty=True, minimum=0)
offset = validators.integer(offset, minimum=0)
exclude_variables = validators.iterable(exclude_variables,
allow_empty=True)
if exclude_variables:
exclude_variables = [validators.string(x) for x in exclude_variables]
include_variables = validators.iterable(include_variables,
allow_empty=True)
if include_variables:
include_variables = [validators.string(x) for x in include_variables]
if not checkers.is_file(data):
with tempfile.NamedTemporaryFile(delete=False) as temp_file:
temp_file.write(data)
temp_file_name = temp_file.name
df, meta = pyreadstat.read_sav(
temp_file_name,
metadataonly=metadata_only,
dates_as_pandas_datetime=dates_as_datetime64,
apply_value_formats=apply_labels,
formats_as_category=labels_as_categories,
usecols=include_variables,
user_missing=not missing_as_NaN,
disable_datetime_conversion=not convert_datetimes,
row_limit=limit or 0,
row_offset=offset,
**kwargs)
os.remove(temp_file_name)
else:
df, meta = pyreadstat.read_sav(
data,
metadataonly=metadata_only,
dates_as_pandas_datetime=dates_as_datetime64,
apply_value_formats=apply_labels,
formats_as_category=labels_as_categories,
usecols=include_variables,
user_missing=not missing_as_NaN,
disable_datetime_conversion=not convert_datetimes,
row_limit=limit or 0,
row_offset=offset,
**kwargs)
metadata = Metadata.from_pyreadstat(meta)
if exclude_variables:
df = df.drop(exclude_variables, axis=1)
if metadata.column_metadata:
for variable in exclude_variables:
metadata.column_metadata.pop(variable, None)
return df, metadata
def video_hunt_keys(self, val: list):
self._video_hunt_keys = validators.iterable(val, allow_empty=True)
def video_hunt_embeddings(self, val: List[List[float]]):
self._video_hunt_embeddings = validators.iterable(
val, allow_empty=True
)
