titanicprediction.entities package

Submodules

titanicprediction.entities.core module

class titanicprediction.entities.core.Dataset(features: pandas.core.frame.DataFrame, target: pandas.core.series.Series | None, feature_names: list[str], target_name: str | None, metadata: dict[str, Any] = None)

Bases: object

__init__(features: DataFrame, target: Series | None, feature_names: list[str], target_name: str | None, metadata: dict[str, Any] = None) → None

describe() → dict[str, Any]

feature_names: list[str]

features: DataFrame

get_feature_types() → dict[str, str]

get_shape() → tuple[int, int]

metadata: dict[str, Any] = None

split(ratio: float) → tuple[Dataset, Dataset]

target: Series | None

target_name: str | None

class titanicprediction.entities.core.FeatureImpactAnalysis(feature_name: str, impact_score: float, weight: float, feature_value: float, contribution: float)

Bases: object

__init__(feature_name: str, impact_score: float, weight: float, feature_value: float, contribution: float) → None

contribution: float

feature_name: str

feature_value: float

impact_score: float

weight: float

class titanicprediction.entities.core.Gender(*values)

Bases: Enum

female = 1

male = 0

class titanicprediction.entities.core.Passenger(passenger_id: int, survived: bool | None, pclass: Literal[1, 2, 3], name: str, sex: Literal['male', 'female'], age: float | None, sibsp: int, parch: int, fare: float, embarked: Literal['C', 'Q', 'S'] | None, cabin: str | None, title: Literal['Mr', 'Mrs', 'Miss', 'Master', 'Dr', 'Rev', 'Other'] | None, ticket: str | None)

Bases: object

__init__(passenger_id: int, survived: bool | None, pclass: Literal[1, 2, 3], name: str, sex: Literal['male', 'female'], age: float | None, sibsp: int, parch: int, fare: float, embarked: Literal['C', 'Q', 'S'] | None, cabin: str | None, title: Literal['Mr', 'Mrs', 'Miss', 'Master', 'Dr', 'Rev', 'Other'] | None, ticket: str | None) → None

age: float | None

cabin: str | None

embarked: Literal['C', 'Q', 'S'] | None

fare: float

get_missing_fields() → list[str]

is_valid() → bool

name: str

parch: int

passenger_id: int

pclass: Literal[1, 2, 3]

sex: Literal['male', 'female']

sibsp: int

survived: bool | None

ticket: str | None

title: Literal['Mr', 'Mrs', 'Miss', 'Master', 'Dr', 'Rev', 'Other'] | None

validate() → bool

class titanicprediction.entities.core.PredictionExplanation(prediction: bool, probability: float, feature_impacts: list[titanicprediction.entities.core.FeatureImpactAnalysis], decision_factors: list[str], confidence_level: str)

Bases: object

__init__(prediction: bool, probability: float, feature_impacts: list[FeatureImpactAnalysis], decision_factors: list[str], confidence_level: str) → None

confidence_level: str

decision_factors: list[str]

feature_impacts: list[FeatureImpactAnalysis]

prediction: bool

probability: float

class titanicprediction.entities.core.TrainedModel(weights: numpy.ndarray, bias: float, feature_names: list[str], training_metrics: dict[str, float], validation_metrics: dict[str, float], training_history: list[float], model_config: dict[str, Any], preprocessing_artifacts: dict[str, Any] | None = None)

Bases: object

__init__(weights: ndarray, bias: float, feature_names: list[str], training_metrics: dict[str, float], validation_metrics: dict[str, float], training_history: list[float], model_config: dict[str, Any], preprocessing_artifacts: dict[str, Any] | None = None) → None

bias: float

feature_names: list[str]

get_feature_importance() → dict[str, float]

model_config: dict[str, Any]

predict(features: ndarray) → ndarray

predict_proba(features: ndarray) → ndarray

preprocessing_artifacts: dict[str, Any] | None = None

training_history: list[float]

training_metrics: dict[str, float]

validation_metrics: dict[str, float]

weights: ndarray

Module contents