Module `preprocessor.spec`

Classes

class Field (name: str, label: str, meta: FieldMeta, gen_type: GenType, data: FieldData, custom: Dict[int, Any], restricted: bool, is_masked: Optional[bool] = None, generator: Optional[Generator] = None)

Field(name: str, label: str, meta: preprocessor.spec.FieldMeta, gen_type: preprocessor.spec.GenType, data: preprocessor.spec.FieldData, custom: Dict[int, Any], restricted: bool, is_masked: Optional[bool] = None, generator: Optional[preprocessor.spec.Generator] = None)

Class variables

var custom : Dict[int, Any]
var data : FieldData
var gen_type : GenType
var generator : Optional[Generator]
var is_masked : Optional[bool]
var label : str
var meta : FieldMeta
var name : str
var restricted : bool

Static methods

def from_dict(kvs: Union[dict, list, str, int, float, bool, ForwardRef(None)], *, infer_missing=False) -> ~A
def from_json(s: Union[str, bytes, bytearray], *, parse_float=None, parse_int=None, parse_constant=None, infer_missing=False, **kw) -> ~A
def schema(*, infer_missing: bool = False, only=None, exclude=(), many: bool = False, context=None, load_only=(), dump_only=(), partial: bool = False, unknown=None) -> dataclasses_json.mm.SchemaF[~A]

Methods

def from_field(self, from_field)
def generate_data(self, count)
def set_random(self)
def set_sample(self, df)
def to_dict(self, encode_json=False) -> Dict[str, Union[dict, list, str, int, float, bool, ForwardRef(None)]]
def to_json(self, *, skipkeys: bool = False, ensure_ascii: bool = True, check_circular: bool = True, allow_nan: bool = True, indent: Union[int, str, ForwardRef(None)] = None, separators: Tuple[str, str] = None, default: Callable = None, sort_keys: bool = False, **kw) -> str

class FieldData (random: List[Any], sample: List[Any])

FieldData(random: List[Any], sample: List[Any])

Class variables

var random : List[Any]
var sample : List[Any]

Static methods

def from_dict(kvs: Union[dict, list, str, int, float, bool, ForwardRef(None)], *, infer_missing=False) -> ~A
def from_json(s: Union[str, bytes, bytearray], *, parse_float=None, parse_int=None, parse_constant=None, infer_missing=False, **kw) -> ~A
def schema(*, infer_missing: bool = False, only=None, exclude=(), many: bool = False, context=None, load_only=(), dump_only=(), partial: bool = False, unknown=None) -> dataclasses_json.mm.SchemaF[~A]

Methods

def to_dict(self, encode_json=False) -> Dict[str, Union[dict, list, str, int, float, bool, ForwardRef(None)]]
def to_json(self, *, skipkeys: bool = False, ensure_ascii: bool = True, check_circular: bool = True, allow_nan: bool = True, indent: Union[int, str, ForwardRef(None)] = None, separators: Tuple[str, str] = None, default: Callable = None, sort_keys: bool = False, **kw) -> str

class FieldMeta (type: SupportedType, range: Optional[Range], decimals: Optional[int], length: Optional[Range], has_inf: Optional[bool] = None, has_neg_inf: Optional[bool] = None, has_nan: Optional[bool] = None, word_mode: Optional[int] = None)

FieldMeta(type: preprocessor.spec.SupportedType, range: Optional[preprocessor.spec.Range], decimals: Optional[int], length: Optional[preprocessor.spec.Range], has_inf: Optional[bool] = None, has_neg_inf: Optional[bool] = None, has_nan: Optional[bool] = None, word_mode: Optional[int] = None)

Class variables

var decimals : Optional[int]
var has_inf : Optional[bool]
var has_nan : Optional[bool]
var has_neg_inf : Optional[bool]
var length : Optional[Range]
var range : Optional[Range]
var type : SupportedType
var word_mode : Optional[int]

Static methods

def from_dict(kvs: Union[dict, list, str, int, float, bool, ForwardRef(None)], *, infer_missing=False) -> ~A
def from_json(s: Union[str, bytes, bytearray], *, parse_float=None, parse_int=None, parse_constant=None, infer_missing=False, **kw) -> ~A
def schema(*, infer_missing: bool = False, only=None, exclude=(), many: bool = False, context=None, load_only=(), dump_only=(), partial: bool = False, unknown=None) -> dataclasses_json.mm.SchemaF[~A]

Methods

def to_dict(self, encode_json=False) -> Dict[str, Union[dict, list, str, int, float, bool, ForwardRef(None)]]
def to_json(self, *, skipkeys: bool = False, ensure_ascii: bool = True, check_circular: bool = True, allow_nan: bool = True, indent: Union[int, str, ForwardRef(None)] = None, separators: Tuple[str, str] = None, default: Callable = None, sort_keys: bool = False, **kw) -> str

class FieldOverride (name: str, label: Optional[str] = None, gen_type: Optional[GenType] = None, custom: Optional[Dict[int, Any]] = None, restricted: Optional[bool] = None, is_masked: Optional[bool] = None, generator: Optional[Generator] = None)

FieldOverride(name: str, label: Optional[str] = None, gen_type: Optional[preprocessor.spec.GenType] = None, custom: Optional[Dict[int, Any]] = None, restricted: Optional[bool] = None, is_masked: Optional[bool] = None, generator: Optional[preprocessor.spec.Generator] = None)

Class variables

var custom : Optional[Dict[int, Any]]
var gen_type : Optional[GenType]
var generator : Optional[Generator]
var is_masked : Optional[bool]
var label : Optional[str]
var name : str
var restricted : Optional[bool]

Static methods

def from_dict(kvs: Union[dict, list, str, int, float, bool, ForwardRef(None)], *, infer_missing=False) -> ~A
def from_json(s: Union[str, bytes, bytearray], *, parse_float=None, parse_int=None, parse_constant=None, infer_missing=False, **kw) -> ~A
def schema(*, infer_missing: bool = False, only=None, exclude=(), many: bool = False, context=None, load_only=(), dump_only=(), partial: bool = False, unknown=None) -> dataclasses_json.mm.SchemaF[~A]

Methods

def to_dict(self, encode_json=False) -> Dict[str, Union[dict, list, str, int, float, bool, ForwardRef(None)]]
def to_json(self, *, skipkeys: bool = False, ensure_ascii: bool = True, check_circular: bool = True, allow_nan: bool = True, indent: Union[int, str, ForwardRef(None)] = None, separators: Tuple[str, str] = None, default: Callable = None, sort_keys: bool = False, **kw) -> str

class GenType (value, names=None, *, module=None, qualname=None, type=None, start=1)

An enumeration.

Ancestors

enum.Enum

Class variables

var Random
var Sample

class Generator (type: str, params: Optional[Dict[str, Any]] = None)

Generator(type: str, params: Optional[Dict[str, Any]] = None)

Class variables

var params : Optional[Dict[str, Any]]
var type : str

Static methods

def from_dict(kvs: Union[dict, list, str, int, float, bool, ForwardRef(None)], *, infer_missing=False) -> ~A
def from_json(s: Union[str, bytes, bytearray], *, parse_float=None, parse_int=None, parse_constant=None, infer_missing=False, **kw) -> ~A
def schema(*, infer_missing: bool = False, only=None, exclude=(), many: bool = False, context=None, load_only=(), dump_only=(), partial: bool = False, unknown=None) -> dataclasses_json.mm.SchemaF[~A]

Methods

def to_dict(self, encode_json=False) -> Dict[str, Union[dict, list, str, int, float, bool, ForwardRef(None)]]
def to_json(self, *, skipkeys: bool = False, ensure_ascii: bool = True, check_circular: bool = True, allow_nan: bool = True, indent: Union[int, str, ForwardRef(None)] = None, separators: Tuple[str, str] = None, default: Callable = None, sort_keys: bool = False, **kw) -> str

class Range (min: float, max: float)

Range(min: float, max: float)

Class variables

var max : float
var min : float

Static methods

def from_dict(kvs: Union[dict, list, str, int, float, bool, ForwardRef(None)], *, infer_missing=False) -> ~A
def from_json(s: Union[str, bytes, bytearray], *, parse_float=None, parse_int=None, parse_constant=None, infer_missing=False, **kw) -> ~A
def schema(*, infer_missing: bool = False, only=None, exclude=(), many: bool = False, context=None, load_only=(), dump_only=(), partial: bool = False, unknown=None) -> dataclasses_json.mm.SchemaF[~A]

Methods

def to_dict(self, encode_json=False) -> Dict[str, Union[dict, list, str, int, float, bool, ForwardRef(None)]]
def to_json(self, *, skipkeys: bool = False, ensure_ascii: bool = True, check_circular: bool = True, allow_nan: bool = True, indent: Union[int, str, ForwardRef(None)] = None, separators: Tuple[str, str] = None, default: Callable = None, sort_keys: bool = False, **kw) -> str

class Spec (fields: List[Field])

Spec(fields: List[preprocessor.spec.Field])

Class variables

var fields : List[Field]

Static methods

def from_dataframe(df: pandas.core.frame.DataFrame, size: Optional[int] = None, custom: Optional[Dict] = None, is_masked: bool = True, unmask_columns: Optional[List[str]] = None) -> Spec

Generate a dataset .spec from a dataframe

Args

df : pd.DataFrame: The source dataframe
size : Optional[int], optional: Number of records to include in sample (mock) data. Default is 10.
custom : Optional[Dict], optional: Custom values to add to the spec. Dict must contain fieldnames that match the columns in the dataframe, values become custom values for that field in the spec. Defaults to None.
is_masked : bool, optional: Should all fields be masked? Defaults to True.
unmask_columns : Optional[List[str]], optional: Individual fields to unmask, overriding is_masked=True. Defaults to None.

Raises

Exception: "Unable to detect column type."
Exception: "Unable to find column '{col}' from unmask_columns list."

Returns

Spec: The Spec which describes the data from the dataframe.

def from_dict(kvs: Union[dict, list, str, int, float, bool, ForwardRef(None)], *, infer_missing=False) -> ~A

def from_json(s: Union[str, bytes, bytearray], *, parse_float=None, parse_int=None, parse_constant=None, infer_missing=False, **kw) -> ~A

def schema(*, infer_missing: bool = False, only=None, exclude=(), many: bool = False, context=None, load_only=(), dump_only=(), partial: bool = False, unknown=None) -> dataclasses_json.mm.SchemaF[~A]

Instance variables

var unrestricted_fields : Iterator[Field]

Methods

def apply_override(self, overrides: List[FieldOverride])
def as_frame(self) -> pandas.core.frame.DataFrame
def to_dict(self, encode_json=False) -> Dict[str, Union[dict, list, str, int, float, bool, ForwardRef(None)]]
def to_json(self, *, skipkeys: bool = False, ensure_ascii: bool = True, check_circular: bool = True, allow_nan: bool = True, indent: Union[int, str, ForwardRef(None)] = None, separators: Tuple[str, str] = None, default: Callable = None, sort_keys: bool = False, **kw) -> str

class SupportedType (value, names=None, *, module=None, qualname=None, type=None, start=1)

An enumeration.

Ancestors

builtins.str
enum.Enum

Class variables

var Bool
var Float64
var Int64
var String