How to use in_range_strategy method in pandera

Best Python code snippet using pandera_python

checks.py

Source:checks.py Github

copy

Full Screen

1"""Data validation checks."""2import inspect3import operator4import re5from collections import ChainMap, namedtuple6from functools import partial, wraps7from itertools import chain8from typing import (9 Any,10 Callable,11 Dict,12 Iterable,13 List,14 Optional,15 Type,16 TypeVar,17 Union,18 no_type_check,19)20import pandas as pd21from . import check_utils, constants, errors22from . import strategies as st23CheckResult = namedtuple(24 "CheckResult",25 ["check_output", "check_passed", "checked_object", "failure_cases"],26)27GroupbyObject = Union[28 pd.core.groupby.SeriesGroupBy, pd.core.groupby.DataFrameGroupBy29]30SeriesCheckObj = Union[pd.Series, Dict[str, pd.Series]]31DataFrameCheckObj = Union[pd.DataFrame, Dict[str, pd.DataFrame]]32def register_check_statistics(statistics_args):33 """Decorator to set statistics based on Check method."""34 def register_check_statistics_decorator(class_method):35 @wraps(class_method)36 def _wrapper(cls, *args, **kwargs):37 args = list(args)38 arg_names = inspect.getfullargspec(class_method).args[1:]39 if not arg_names:40 arg_names = statistics_args41 args_dict = {**dict(zip(arg_names, args)), **kwargs}42 check = class_method(cls, *args, **kwargs)43 check.statistics = {44 stat: args_dict.get(stat) for stat in statistics_args45 }46 check.statistics_args = statistics_args47 return check48 return _wrapper49 return register_check_statistics_decorator50_T = TypeVar("_T", bound="_CheckBase")51class _CheckMeta(type): # pragma: no cover52 """Check metaclass."""53 REGISTERED_CUSTOM_CHECKS: Dict[str, Callable] = {} # noqa54 def __getattr__(cls, name: str) -> Any:55 """Prevent attribute errors for registered checks."""56 attr = ChainMap(cls.__dict__, cls.REGISTERED_CUSTOM_CHECKS).get(name)57 if attr is None:58 raise AttributeError(59 f"'{cls}' object has no attribute '{name}'. "60 "Make sure any custom checks have been registered "61 "using the extensions api."62 )63 return attr64 def __dir__(cls) -> Iterable[str]:65 """Allow custom checks to show up as attributes when autocompleting."""66 return chain(super().__dir__(), cls.REGISTERED_CUSTOM_CHECKS.keys())67 # pylint: disable=line-too-long68 # mypy has limited metaclass support so this doesn't pass typecheck69 # see https://mypy.readthedocs.io/en/stable/metaclasses.html#gotchas-and-limitations-of-metaclass-support70 # pylint: enable=line-too-long71 @no_type_check72 def __contains__(cls: Type[_T], item: Union[_T, str]) -> bool:73 """Allow lookups for registered checks."""74 if isinstance(item, cls):75 name = item.name76 return hasattr(cls, name)77 # assume item is str78 return hasattr(cls, item)79class _CheckBase(metaclass=_CheckMeta):80 """Check base class."""81 def __init__(82 self,83 check_fn: Union[84 Callable[[pd.Series], Union[pd.Series, bool]],85 Callable[[pd.DataFrame], Union[pd.DataFrame, pd.Series, bool]],86 ],87 groups: Optional[Union[str, List[str]]] = None,88 groupby: Optional[Union[str, List[str], Callable]] = None,89 ignore_na: bool = True,90 element_wise: bool = False,91 name: str = None,92 error: Optional[str] = None,93 raise_warning: bool = False,94 n_failure_cases: Union[int, None] = constants.N_FAILURE_CASES,95 title: Optional[str] = None,96 description: Optional[str] = None,97 **check_kwargs,98 ) -> None:99 """Apply a validation function to each element, Series, or DataFrame.100 :param check_fn: A function to check pandas data structure. For Column101 or SeriesSchema checks, if element_wise is True, this function102 should have the signature: ``Callable[[pd.Series],103 Union[pd.Series, bool]]``, where the output series is a boolean104 vector.105 If element_wise is False, this function should have the signature:106 ``Callable[[Any], bool]``, where ``Any`` is an element in the107 column.108 For DataFrameSchema checks, if element_wise=True, fn109 should have the signature: ``Callable[[pd.DataFrame],110 Union[pd.DataFrame, pd.Series, bool]]``, where the output dataframe111 or series contains booleans.112 If element_wise is True, fn is applied to each row in113 the dataframe with the signature ``Callable[[pd.Series], bool]``114 where the series input is a row in the dataframe.115 :param groups: The dict input to the `fn` callable will be constrained116 to the groups specified by `groups`.117 :param groupby: If a string or list of strings is provided, these118 columns are used to group the Column series. If a119 callable is passed, the expected signature is: ``Callable[120 [pd.DataFrame], pd.core.groupby.DataFrameGroupBy]``121 The the case of ``Column`` checks, this function has access to the122 entire dataframe, but ``Column.name`` is selected from this123 DataFrameGroupby object so that a SeriesGroupBy object is passed124 into ``check_fn``.125 Specifying the groupby argument changes the ``check_fn`` signature126 to:127 ``Callable[[Dict[Union[str, Tuple[str]], pd.Series]], Union[bool, pd.Series]]`` # noqa128 where the input is a dictionary mapping129 keys to subsets of the column/dataframe.130 :param ignore_na: If True, null values will be ignored when determining131 if a check passed or failed. For dataframes, ignores rows with any132 null value. *New in version 0.4.0*133 :param element_wise: Whether or not to apply validator in an134 element-wise fashion. If bool, assumes that all checks should be135 applied to the column element-wise. If list, should be the same136 number of elements as checks.137 :param name: optional name for the check.138 :param error: custom error message if series fails validation139 check.140 :param raise_warning: if True, raise a UserWarning and do not throw141 exception instead of raising a SchemaError for a specific check.142 This option should be used carefully in cases where a failing143 check is informational and shouldn't stop execution of the program.144 :param n_failure_cases: report the first n unique failure cases. If145 None, report all failure cases.146 :param title: A human-readable label for the check.147 :param description: An arbitrary textual description of the check.148 :param check_kwargs: key-word arguments to pass into ``check_fn``149 :example:150 >>> import pandas as pd151 >>> import pandera as pa152 >>>153 >>>154 >>> # column checks are vectorized by default155 >>> check_positive = pa.Check(lambda s: s > 0)156 >>>157 >>> # define an element-wise check158 >>> check_even = pa.Check(lambda x: x % 2 == 0, element_wise=True)159 >>>160 >>> # checks can be given human-readable metadata161 >>> check_with_metadata = pa.Check(162 ... lambda x: True,163 ... title="Always passes",164 ... description="This check always passes."165 ... )166 >>>167 >>> # specify assertions across categorical variables using `groupby`,168 >>> # for example, make sure the mean measure for group "A" is always169 >>> # larger than the mean measure for group "B"170 >>> check_by_group = pa.Check(171 ... lambda measures: measures["A"].mean() > measures["B"].mean(),172 ... groupby=["group"],173 ... )174 >>>175 >>> # define a wide DataFrame-level check176 >>> check_dataframe = pa.Check(177 ... lambda df: df["measure_1"] > df["measure_2"])178 >>>179 >>> measure_checks = [check_positive, check_even, check_by_group]180 >>>181 >>> schema = pa.DataFrameSchema(182 ... columns={183 ... "measure_1": pa.Column(int, checks=measure_checks),184 ... "measure_2": pa.Column(int, checks=measure_checks),185 ... "group": pa.Column(str),186 ... },187 ... checks=check_dataframe188 ... )189 >>>190 >>> df = pd.DataFrame({191 ... "measure_1": [10, 12, 14, 16],192 ... "measure_2": [2, 4, 6, 8],193 ... "group": ["B", "B", "A", "A"]194 ... })195 >>>196 >>> schema.validate(df)[["measure_1", "measure_2", "group"]]197 measure_1 measure_2 group198 0 10 2 B199 1 12 4 B200 2 14 6 A201 3 16 8 A202 See :ref:`here<checks>` for more usage details.203 """204 if element_wise and groupby is not None:205 raise errors.SchemaInitError(206 "Cannot use groupby when element_wise=True."207 )208 self._check_fn = check_fn209 self._check_kwargs = check_kwargs210 self.element_wise = element_wise211 self.error = error212 self.name = name or getattr(213 self._check_fn, "__name__", self._check_fn.__class__.__name__214 )215 self.ignore_na = ignore_na216 self.raise_warning = raise_warning217 self.n_failure_cases = n_failure_cases218 self.title = title219 self.description = description220 if groupby is None and groups is not None:221 raise ValueError(222 "`groupby` argument needs to be provided when `groups` "223 "argument is defined"224 )225 if isinstance(groupby, str):226 groupby = [groupby]227 self.groupby = groupby228 if isinstance(groups, str):229 groups = [groups]230 self.groups = groups231 self.failure_cases = None232 self._statistics = None233 @property234 def statistics(self) -> Dict[str, Any]:235 """Get check statistics."""236 return getattr(self, "_statistics")237 @statistics.setter238 def statistics(self, statistics):239 """Set check statistics."""240 self._statistics = statistics241 @staticmethod242 def _format_groupby_input(243 groupby_obj: GroupbyObject,244 groups: Optional[List[str]],245 ) -> Union[Dict[str, Union[pd.Series, pd.DataFrame]]]:246 """Format groupby object into dict of groups to Series or DataFrame.247 :param groupby_obj: a pandas groupby object.248 :param groups: only include these groups in the output.249 :returns: dictionary mapping group names to Series or DataFrame.250 """251 if groups is None:252 return dict(list(groupby_obj))253 group_keys = set(group_key for group_key, _ in groupby_obj)254 invalid_groups = [g for g in groups if g not in group_keys]255 if invalid_groups:256 raise KeyError(257 f"groups {invalid_groups} provided in `groups` argument not a valid group "258 f"key. Valid group keys: {group_keys}"259 )260 return {261 group_key: group262 for group_key, group in groupby_obj263 if group_key in groups264 }265 def _prepare_series_input(266 self,267 df_or_series: Union[pd.Series, pd.DataFrame],268 column: Optional[str] = None,269 ) -> SeriesCheckObj:270 """Prepare input for Column check.271 :param pd.Series series: one-dimensional ndarray with axis labels272 (including time series).273 :param pd.DataFrame dataframe_context: optional dataframe to supply274 when checking a Column in a DataFrameSchema.275 :returns: a Series, or a dictionary mapping groups to Series276 to be used by `_check_fn` and `_vectorized_check`277 """278 if check_utils.is_field(df_or_series):279 return df_or_series280 elif self.groupby is None:281 return df_or_series[column]282 elif isinstance(self.groupby, list):283 return self._format_groupby_input(284 df_or_series.groupby(self.groupby)[column],285 self.groups,286 )287 elif callable(self.groupby):288 return self._format_groupby_input(289 self.groupby(df_or_series)[column],290 self.groups,291 )292 raise TypeError("Type %s not recognized for `groupby` argument.")293 def _prepare_dataframe_input(294 self, dataframe: pd.DataFrame295 ) -> DataFrameCheckObj:296 """Prepare input for DataFrameSchema check.297 :param dataframe: dataframe to validate.298 :returns: a DataFrame, or a dictionary mapping groups to pd.DataFrame299 to be used by `_check_fn` and `_vectorized_check`300 """301 if self.groupby is None:302 return dataframe303 groupby_obj = dataframe.groupby(self.groupby)304 return self._format_groupby_input(groupby_obj, self.groups)305 def __call__(306 self,307 df_or_series: Union[pd.DataFrame, pd.Series],308 column: Optional[str] = None,309 ) -> CheckResult:310 # pylint: disable=too-many-branches311 """Validate pandas DataFrame or Series.312 :param df_or_series: pandas DataFrame of Series to validate.313 :param column: for dataframe checks, apply the check function to this314 column.315 :returns: CheckResult tuple containing:316 ``check_output``: boolean scalar, ``Series`` or ``DataFrame``317 indicating which elements passed the check.318 ``check_passed``: boolean scalar that indicating whether the check319 passed overall.320 ``checked_object``: the checked object itself. Depending on the321 options provided to the ``Check``, this will be a pandas Series,322 DataFrame, or if the ``groupby`` option is specified, a323 ``Dict[str, Series]`` or ``Dict[str, DataFrame]`` where the keys324 are distinct groups.325 ``failure_cases``: subset of the check_object that failed.326 """327 # prepare check object328 if check_utils.is_field(df_or_series) or (329 column is not None and check_utils.is_table(df_or_series)330 ):331 check_obj = self._prepare_series_input(df_or_series, column)332 elif check_utils.is_table(df_or_series):333 check_obj = self._prepare_dataframe_input(df_or_series)334 else:335 raise ValueError(336 f"object of type {type(df_or_series)} not supported. Must be "337 "a Series, a dictionary of Series, or DataFrame"338 )339 # apply check function to check object340 check_fn = partial(self._check_fn, **self._check_kwargs)341 if self.element_wise:342 check_output = (343 check_obj.apply(check_fn, axis=1) # type: ignore344 if check_utils.is_table(check_obj)345 else check_obj.map(check_fn) # type: ignore346 if check_utils.is_field(check_obj)347 else check_fn(check_obj)348 )349 else:350 # vectorized check function case351 check_output = check_fn(check_obj)352 # failure cases only apply when the check function returns a boolean353 # series that matches the shape and index of the check_obj354 if (355 isinstance(check_obj, dict)356 or isinstance(check_output, bool)357 or not check_utils.is_supported_check_obj(check_output)358 or check_obj.shape[0] != check_output.shape[0]359 or (check_obj.index != check_output.index).all()360 ):361 failure_cases = None362 elif check_utils.is_field(check_output):363 (364 check_output,365 failure_cases,366 ) = check_utils.prepare_series_check_output(367 check_obj,368 check_output,369 ignore_na=self.ignore_na,370 n_failure_cases=self.n_failure_cases,371 )372 elif check_utils.is_table(check_output):373 (374 check_output,375 failure_cases,376 ) = check_utils.prepare_dataframe_check_output(377 check_obj,378 check_output,379 df_orig=df_or_series,380 ignore_na=self.ignore_na,381 n_failure_cases=self.n_failure_cases,382 )383 else:384 raise TypeError(385 f"output type of check_fn not recognized: {type(check_output)}"386 )387 check_passed = (388 check_output.all()389 if check_utils.is_field(check_output)390 else check_output.all(axis=None)391 if check_utils.is_table(check_output)392 else check_output393 )394 return CheckResult(395 check_output, check_passed, check_obj, failure_cases396 )397 def __eq__(self, other: object) -> bool:398 if not isinstance(other, type(self)):399 return NotImplemented400 are_check_fn_objects_equal = (401 self._get_check_fn_code() == other._get_check_fn_code()402 )403 try:404 are_strategy_fn_objects_equal = all(405 getattr(self.__dict__.get("strategy"), attr)406 == getattr(other.__dict__.get("strategy"), attr)407 for attr in ["func", "args", "keywords"]408 )409 except AttributeError:410 are_strategy_fn_objects_equal = True411 are_all_other_check_attributes_equal = {412 k: v413 for k, v in self.__dict__.items()414 if k not in ["_check_fn", "strategy"]415 } == {416 k: v417 for k, v in other.__dict__.items()418 if k not in ["_check_fn", "strategy"]419 }420 return (421 are_check_fn_objects_equal422 and are_strategy_fn_objects_equal423 and are_all_other_check_attributes_equal424 )425 def _get_check_fn_code(self):426 check_fn = self.__dict__["_check_fn"]427 try:428 code = check_fn.__code__.co_code429 except AttributeError:430 # try accessing the functools.partial wrapper431 code = check_fn.func.__code__.co_code432 return code433 def __hash__(self) -> int:434 return hash(self._get_check_fn_code())435 def __repr__(self) -> str:436 return (437 f"<Check {self.name}: {self.error}>"438 if self.error is not None439 else f"<Check {self.name}>"440 )441class Check(_CheckBase):442 """Check a pandas Series or DataFrame for certain properties."""443 @classmethod444 @st.register_check_strategy(st.eq_strategy)445 @register_check_statistics(["value"])446 def equal_to(cls, value, **kwargs) -> "Check":447 """Ensure all elements of a series equal a certain value.448 *New in version 0.4.5*449 Alias: ``eq``450 :param value: All elements of a given :class:`pandas.Series` must have451 this value452 :param kwargs: key-word arguments passed into the `Check` initializer.453 :returns: :class:`Check` object454 """455 def _equal(series: pd.Series) -> pd.Series:456 """Comparison function for check"""457 return series == value458 return cls(459 _equal,460 name=cls.equal_to.__name__,461 error=f"equal_to({value})",462 **kwargs,463 )464 eq = equal_to465 @classmethod466 @st.register_check_strategy(st.ne_strategy)467 @register_check_statistics(["value"])468 def not_equal_to(cls, value, **kwargs) -> "Check":469 """Ensure no elements of a series equals a certain value.470 *New in version 0.4.5*471 Alias: ``ne``472 :param value: This value must not occur in the checked473 :class:`pandas.Series`.474 :param kwargs: key-word arguments passed into the `Check` initializer.475 :returns: :class:`Check` object476 """477 def _not_equal(series: pd.Series) -> pd.Series:478 """Comparison function for check"""479 return series != value480 return cls(481 _not_equal,482 name=cls.not_equal_to.__name__,483 error=f"not_equal_to({value})",484 **kwargs,485 )486 ne = not_equal_to487 @classmethod488 @st.register_check_strategy(st.gt_strategy)489 @register_check_statistics(["min_value"])490 def greater_than(cls, min_value, **kwargs) -> "Check":491 """Ensure values of a series are strictly greater than a minimum value.492 *New in version 0.4.5*493 Alias: ``gt``494 :param min_value: Lower bound to be exceeded. Must be a type comparable495 to the dtype of the :class:`pandas.Series` to be validated (e.g. a496 numerical type for float or int and a datetime for datetime).497 :param kwargs: key-word arguments passed into the `Check` initializer.498 :returns: :class:`Check` object499 """500 if min_value is None:501 raise ValueError("min_value must not be None")502 def _greater_than(series: pd.Series) -> pd.Series:503 """Comparison function for check"""504 return series > min_value505 return cls(506 _greater_than,507 name=cls.greater_than.__name__,508 error=f"greater_than({min_value})",509 **kwargs,510 )511 gt = greater_than512 @classmethod513 @st.register_check_strategy(st.ge_strategy)514 @register_check_statistics(["min_value"])515 def greater_than_or_equal_to(cls, min_value, **kwargs) -> "Check":516 """Ensure all values are greater or equal a certain value.517 *New in version 0.4.5*518 Alias: ``ge``519 :param min_value: Allowed minimum value for values of a series. Must be520 a type comparable to the dtype of the :class:`pandas.Series` to be521 validated.522 :param kwargs: key-word arguments passed into the `Check` initializer.523 :returns: :class:`Check` object524 """525 if min_value is None:526 raise ValueError("min_value must not be None")527 def _greater_or_equal(series: pd.Series) -> pd.Series:528 """Comparison function for check"""529 return series >= min_value530 return cls(531 _greater_or_equal,532 name=cls.greater_than_or_equal_to.__name__,533 error=f"greater_than_or_equal_to({min_value})",534 **kwargs,535 )536 ge = greater_than_or_equal_to537 @classmethod538 @st.register_check_strategy(st.lt_strategy)539 @register_check_statistics(["max_value"])540 def less_than(cls, max_value, **kwargs) -> "Check":541 """Ensure values of a series are strictly below a maximum value.542 *New in version 0.4.5*543 Alias: ``lt``544 :param max_value: All elements of a series must be strictly smaller545 than this. Must be a type comparable to the dtype of the546 :class:`pandas.Series` to be validated.547 :param kwargs: key-word arguments passed into the `Check` initializer.548 :returns: :class:`Check` object549 """550 if max_value is None:551 raise ValueError("max_value must not be None")552 def _less_than(series: pd.Series) -> pd.Series:553 """Comparison function for check"""554 return series < max_value555 return cls(556 _less_than,557 name=cls.less_than.__name__,558 error=f"less_than({max_value})",559 **kwargs,560 )561 lt = less_than562 @classmethod563 @st.register_check_strategy(st.le_strategy)564 @register_check_statistics(["max_value"])565 def less_than_or_equal_to(cls, max_value, **kwargs) -> "Check":566 """Ensure values are less than or equal to a maximum value.567 *New in version 0.4.5*568 Alias: ``le``569 :param max_value: Upper bound not to be exceeded. Must be a type570 comparable to the dtype of the :class:`pandas.Series` to be571 validated.572 :param kwargs: key-word arguments passed into the `Check` initializer.573 :returns: :class:`Check` object574 """575 if max_value is None:576 raise ValueError("max_value must not be None")577 def _less_or_equal(series: pd.Series) -> pd.Series:578 """Comparison function for check"""579 return series <= max_value580 return cls(581 _less_or_equal,582 name=cls.less_than_or_equal_to.__name__,583 error=f"less_than_or_equal_to({max_value})",584 **kwargs,585 )586 le = less_than_or_equal_to587 @classmethod588 @st.register_check_strategy(st.in_range_strategy)589 @register_check_statistics(590 ["min_value", "max_value", "include_min", "include_max"]591 )592 def in_range(593 cls, min_value, max_value, include_min=True, include_max=True, **kwargs594 ) -> "Check":595 """Ensure all values of a series are within an interval.596 :param min_value: Left / lower endpoint of the interval.597 :param max_value: Right / upper endpoint of the interval. Must not be598 smaller than min_value.599 :param include_min: Defines whether min_value is also an allowed value600 (the default) or whether all values must be strictly greater than601 min_value.602 :param include_max: Defines whether min_value is also an allowed value603 (the default) or whether all values must be strictly smaller than604 max_value.605 :param kwargs: key-word arguments passed into the `Check` initializer.606 Both endpoints must be a type comparable to the dtype of the607 :class:`pandas.Series` to be validated.608 :returns: :class:`Check` object609 """610 if min_value is None:611 raise ValueError("min_value must not be None")612 if max_value is None:613 raise ValueError("max_value must not be None")614 if max_value < min_value or (615 min_value == max_value and (not include_min or not include_max)616 ):617 raise ValueError(618 f"The combination of min_value = {min_value} and max_value = {max_value} "619 "defines an empty interval!"620 )621 # Using functions from operator module to keep conditions out of the622 # closure623 left_op = operator.le if include_min else operator.lt624 right_op = operator.ge if include_max else operator.gt625 def _in_range(series: pd.Series) -> pd.Series:626 """Comparison function for check"""627 return left_op(min_value, series) & right_op(max_value, series)628 return cls(629 _in_range,630 name=cls.in_range.__name__,631 error=f"in_range({min_value}, {max_value})",632 **kwargs,633 )634 @classmethod635 @st.register_check_strategy(st.isin_strategy)636 @register_check_statistics(["allowed_values"])637 def isin(cls, allowed_values: Iterable, **kwargs) -> "Check":638 """Ensure only allowed values occur within a series.639 :param allowed_values: The set of allowed values. May be any iterable.640 :param kwargs: key-word arguments passed into the `Check` initializer.641 :returns: :class:`Check` object642 .. note::643 It is checked whether all elements of a :class:`pandas.Series`644 are part of the set of elements of allowed values. If allowed645 values is a string, the set of elements consists of all distinct646 characters of the string. Thus only single characters which occur647 in allowed_values at least once can meet this condition. If you648 want to check for substrings use :func:`Check.str_is_substring`.649 """650 # Turn allowed_values into a set. Not only for performance but also651 # avoid issues with a mutable argument passed by reference which may be652 # changed from outside.653 try:654 allowed_values = frozenset(allowed_values)655 except TypeError as exc:656 raise ValueError(657 f"Argument allowed_values must be iterable. Got {allowed_values}"658 ) from exc659 def _isin(series: pd.Series) -> pd.Series:660 """Comparison function for check"""661 return series.isin(allowed_values)662 return cls(663 _isin,664 name=cls.isin.__name__,665 error=f"isin({set(allowed_values)})",666 **kwargs,667 )668 @classmethod669 @st.register_check_strategy(st.notin_strategy)670 @register_check_statistics(["forbidden_values"])671 def notin(cls, forbidden_values: Iterable, **kwargs) -> "Check":672 """Ensure some defined values don't occur within a series.673 :param forbidden_values: The set of values which should not occur. May674 be any iterable.675 :param raise_warning: if True, check raises UserWarning instead of676 SchemaError on validation.677 :returns: :class:`Check` object678 .. note::679 Like :func:`Check.isin` this check operates on single characters if680 it is applied on strings. A string as paraforbidden_valuesmeter681 forbidden_values is understood as set of prohibited characters. Any682 string of length > 1 can't be in it by design.683 """684 # Turn forbidden_values into a set. Not only for performance but also685 # avoid issues with a mutable argument passed by reference which may be686 # changed from outside.687 try:688 forbidden_values = frozenset(forbidden_values)689 except TypeError as exc:690 raise ValueError(691 f"Argument forbidden_values must be iterable. Got {forbidden_values}"692 ) from exc693 def _notin(series: pd.Series) -> pd.Series:694 """Comparison function for check"""695 return ~series.isin(forbidden_values)696 return cls(697 _notin,698 name=cls.notin.__name__,699 error=f"notin({set(forbidden_values)})",700 **kwargs,701 )702 @classmethod703 @st.register_check_strategy(st.str_matches_strategy)704 @register_check_statistics(["pattern"])705 def str_matches(cls, pattern: str, **kwargs) -> "Check":706 """Ensure that string values match a regular expression.707 :param pattern: Regular expression pattern to use for matching708 :param kwargs: key-word arguments passed into the `Check` initializer.709 :returns: :class:`Check` object710 The behaviour is as of :func:`pandas.Series.str.match`.711 """712 # By compiling the regex we get the benefit of an early argument check713 try:714 regex = re.compile(pattern)715 except TypeError as exc:716 raise ValueError(717 f'pattern="{pattern}" cannot be compiled as regular expression'718 ) from exc719 def _match(series: pd.Series) -> pd.Series:720 """721 Check if all strings in the series match the regular expression.722 """723 return series.str.match(regex, na=False)724 return cls(725 _match,726 name=cls.str_matches.__name__,727 error=f"str_matches({regex})",728 **kwargs,729 )730 @classmethod731 @st.register_check_strategy(st.str_contains_strategy)732 @register_check_statistics(["pattern"])733 def str_contains(cls, pattern: str, **kwargs) -> "Check":734 """Ensure that a pattern can be found within each row.735 :param pattern: Regular expression pattern to use for searching736 :param kwargs: key-word arguments passed into the `Check` initializer.737 :returns: :class:`Check` object738 The behaviour is as of :func:`pandas.Series.str.contains`.739 """740 # By compiling the regex we get the benefit of an early argument check741 try:742 regex = re.compile(pattern)743 except TypeError as exc:744 raise ValueError(745 f'pattern="{pattern}" cannot be compiled as regular expression'746 ) from exc747 def _contains(series: pd.Series) -> pd.Series:748 """Check if a regex search is successful within each value"""749 return series.str.contains(regex, na=False)750 return cls(751 _contains,752 name=cls.str_contains.__name__,753 error=f"str_contains({regex})",754 **kwargs,755 )756 @classmethod757 @st.register_check_strategy(st.str_startswith_strategy)758 @register_check_statistics(["string"])759 def str_startswith(cls, string: str, **kwargs) -> "Check":760 """Ensure that all values start with a certain string.761 :param string: String all values should start with762 :param kwargs: key-word arguments passed into the `Check` initializer.763 :returns: :class:`Check` object764 """765 def _startswith(series: pd.Series) -> pd.Series:766 """Returns true only for strings starting with string"""767 return series.str.startswith(string, na=False)768 return cls(769 _startswith,770 name=cls.str_startswith.__name__,771 error=f"str_startswith({string})",772 **kwargs,773 )774 @classmethod775 @st.register_check_strategy(st.str_endswith_strategy)776 @register_check_statistics(["string"])777 def str_endswith(cls, string: str, **kwargs) -> "Check":778 """Ensure that all values end with a certain string.779 :param string: String all values should end with780 :param kwargs: key-word arguments passed into the `Check` initializer.781 :returns: :class:`Check` object782 """783 def _endswith(series: pd.Series) -> pd.Series:784 """Returns true only for strings ending with string"""785 return series.str.endswith(string, na=False)786 return cls(787 _endswith,788 name=cls.str_endswith.__name__,789 error=f"str_endswith({string})",790 **kwargs,791 )792 @classmethod793 @st.register_check_strategy(st.str_length_strategy)794 @register_check_statistics(["min_value", "max_value"])795 def str_length(796 cls, min_value: int = None, max_value: int = None, **kwargs797 ) -> "Check":798 """Ensure that the length of strings is within a specified range.799 :param min_value: Minimum length of strings (default: no minimum)800 :param max_value: Maximum length of strings (default: no maximum)801 :param kwargs: key-word arguments passed into the `Check` initializer.802 :returns: :class:`Check` object803 """804 if min_value is None and max_value is None:805 raise ValueError(806 "At least a minimum or a maximum need to be specified. Got "807 "None."808 )809 if max_value is None:810 def _str_length(series: pd.Series) -> pd.Series:811 """Check for the minimum string length"""812 return series.str.len() >= min_value813 elif min_value is None:814 def _str_length(series: pd.Series) -> pd.Series:815 """Check for the maximum string length"""816 return series.str.len() <= max_value817 else:818 def _str_length(series: pd.Series) -> pd.Series:819 """Check for both, minimum and maximum string length"""820 return (series.str.len() <= max_value) & (821 series.str.len() >= min_value822 )823 return cls(824 _str_length,825 name=cls.str_length.__name__,826 error=f"str_length({min_value}, {max_value})",827 **kwargs,...

Full Screen

Full Screen

test_strategies.py

Source:test_strategies.py Github

copy

Full Screen

...199@hypothesis.given(st.data())200@hypothesis.settings(201 suppress_health_check=[hypothesis.HealthCheck.too_slow],202)203def test_in_range_strategy(data_type, chained, data):204 """Test the built-in in-range strategy can correctly generate data."""205 min_value, max_value = data.draw(value_ranges(data_type))206 hypothesis.assume(min_value < max_value)207 base_st_in_range = None208 if chained:209 if is_float(data_type):210 base_st_kwargs = {211 "exclude_min": False,212 "exclude_max": False,213 }214 else:215 base_st_kwargs = {}216 # constraining the strategy this way makes testing more efficient217 base_st_in_range = strategies.pandas_dtype_strategy(218 data_type,219 min_value=min_value,220 max_value=max_value,221 **base_st_kwargs, # type: ignore[arg-type]222 )223 strat = strategies.in_range_strategy(224 data_type,225 base_st_in_range,226 min_value=min_value,227 max_value=max_value,228 )229 assert min_value <= data.draw(strat) <= max_value230@pytest.mark.parametrize(231 "data_type",232 [data_type for data_type in SUPPORTED_DTYPES if data_type.continuous],233)234@pytest.mark.parametrize("chained", [True, False])235@hypothesis.given(st.data())236@hypothesis.settings(237 suppress_health_check=[hypothesis.HealthCheck.too_slow],...

Full Screen

Full Screen

Automation Testing Tutorials

Learn to execute automation testing from scratch with LambdaTest Learning Hub. Right from setting up the prerequisites to run your first automation test, to following best practices and diving deeper into advanced test scenarios. LambdaTest Learning Hubs compile a list of step-by-step guides to help you be proficient with different test automation frameworks i.e. Selenium, Cypress, TestNG etc.

LambdaTest Learning Hubs:

YouTube

You could also refer to video tutorials over LambdaTest YouTube channel to get step by step demonstration from industry experts.

Run pandera automation tests on LambdaTest cloud grid

Perform automation testing on 3000+ real desktop and mobile devices online.

Try LambdaTest Now !!

Get 100 minutes of automation test minutes FREE!!

Next-Gen App & Browser Testing Cloud

Was this article helpful?

Helpful

NotHelpful