AdaBoost

toyml.ensemble.adaboost.AdaBoost dataclass

AdaBoost(weak_learner: Type[BaseWeakLeaner], n_weak_learner: int = 5, predict_labels_: Optional[list[int]] = None, training_error_rate_: Optional[float] = None, _n: int = -1, _labels: list[int] = list(), _weights: list[float] = list(), _base_clf_labels: list[list[int]] = list(), _weak_learner_predicts: List[Callable[..., Any]] = list(), _alphas: list[float] = list())

The implementation of AdaBoost algorithm.

Examples:

>>> from toyml.ensemble.adaboost import AdaBoost, OneDimensionClassifier
>>> dataset = [[0], [1], [2], [3], [4], [5], [6], [7], [8], [9]]
>>> labels = [1, 1, 1, -1, -1, -1, 1, 1, 1, -1]
>>> ada = AdaBoost(weak_learner=OneDimensionClassifier, n_weak_learner=3).fit(dataset, labels)
>>> print(f"Training dataset error rate: {ada.training_error_rate_}")
Training dataset error rate: 0.0
>>> test_sample = [1.5]
>>> print(f"The label of {test_sample} is {ada.predict(test_sample)}")
The label of [1.5] is 1

References

1. Li Hang
2. Zhou Zhihua

weak_learner instance-attribute

weak_learner: Type[BaseWeakLeaner]

The weak learner to be used in the AdaBoost algorithm.

n_weak_learner class-attribute instance-attribute

n_weak_learner: int = 5

The number of weak learners to be used in the AdaBoost algorithm.

predict_labels_ class-attribute instance-attribute

predict_labels_: Optional[list[int]] = None

The prediction labels of the training dataset.

training_error_rate_ class-attribute instance-attribute

training_error_rate_: Optional[float] = None

The error rate of the training dataset.

fit

fit(dataset: list[list[float]], labels: list[int]) -> AdaBoost

Fit the AdaBoost model.

Source code in toyml/ensemble/adaboost.py

def fit(
    self,
    dataset: list[list[float]],
    labels: list[int],
) -> AdaBoost:
    """
    Fit the AdaBoost model.
    """
    self._labels = labels
    # for model training(Gm)
    self._n = len(labels)
    self._weights: Any = [1.0 / self._n] * self._n
    # we use -2 to initialize the class which can handle cases
    # such as multi-classes(0, 1, 2, ...) and binary classes(-1, 1)
    self._base_clf_labels = [[-2] * self._n for _ in range(self.n_weak_learner)]
    # base clf models
    self._weak_learner_predicts: List[Callable[..., int]] = []
    self._alphas = [0.0] * self.n_weak_learner

    for m in range(self.n_weak_learner):
        model = self.weak_learner().fit(dataset, self._weights, self._labels)
        self._base_clf_labels[m] = model.get_predict_labels()
        self._weak_learner_predicts.append(model.predict)
        error_rate = model.get_error_rate()
        # Warning when the error rate is too large
        if error_rate > 0.5:
            logger.warning(f"Weak learner error rate = {error_rate} < 0.5")
        alpha = 0.5 * math.log((1 - error_rate) / error_rate)
        self._alphas[m] = alpha
        # update the weights
        weights = [0.0] * self._n
        for i in range(self._n):
            weights[i] = self._weights[i] * math.exp(-alpha * self._labels[i] * self._base_clf_labels[m][i])
        self._weights = [weight / sum(weights) for weight in weights]
    # collect training dataset result
    self.predict_labels_ = [self.predict(x) for x in dataset]
    self.training_error_rate_ = sum(self.predict_labels_[i] != self._labels[i] for i in range(self._n)) / self._n
    return self

predict

predict(x: list[float]) -> int

Predict the label of the input sample.

Source code in toyml/ensemble/adaboost.py

def predict(self, x: list[float]) -> int:
    """
    Predict the label of the input sample.
    """
    ensemble_predict = 0
    for m in range(self.n_weak_learner):
        model_predict = self._weak_learner_predicts[m]
        ensemble_predict += self._alphas[m] * model_predict(x)
    if ensemble_predict >= 0:
        return 1
    else:
        return -1

toyml.ensemble.adaboost.OneDimensionClassifier dataclass

OneDimensionClassifier(_sign_mode: SignMode = POS_NEG, _best_cut: float = inf, error_rate_: float = inf, predict_labels_: Optional[list[int]] = None)

Bases: BaseWeakLeaner

Binary classifier with one dimension feature.

Ref: Li Hang, 1 ed, E8.1.3

fit

fit(dataset: list[list[float]], weights: list[float], labels: list[int]) -> OneDimensionClassifier

Fit the one-dimension classifier.

Source code in toyml/ensemble/adaboost.py

def fit(
    self,
    dataset: list[list[float]],
    weights: list[float],
    labels: list[int],
) -> OneDimensionClassifier:
    """
    Fit the one-dimension classifier.
    """
    # search for the best cut point
    sign_mode, best_cut, best_error_rate = self.get_best_cut(dataset, weights, labels)
    self.error_rate_ = best_error_rate
    self._best_cut = best_cut
    self._sign_mode = sign_mode
    # get labels
    self.predict_labels_ = [0] * len(labels)
    for i, x in enumerate(dataset):
        self.predict_labels_[i] = self.predict(x)
    return self

predict

predict(x: list[float]) -> int

Predict the label of the input sample.

Source code in toyml/ensemble/adaboost.py

def predict(self, x: list[float]) -> int:
    """
    Predict the label of the input sample.
    """
    if self._best_cut is None:
        raise ValueError("The model is not fitted yet!")
    if self._sign_mode == "POS_NEG":
        if x[0] <= self._best_cut:
            return 1
        else:
            return -1
    if x[0] <= self._best_cut:
        return -1
    else:
        return 1

get_error_rate

get_error_rate() -> float

Get the error rate of the training dataset.

Source code in toyml/ensemble/adaboost.py

def get_error_rate(self) -> float:
    """
    Get the error rate of the training dataset.
    """
    if self.error_rate_ is None:
        raise ValueError("The model is not fitted yet!")
    return self.error_rate_

get_predict_labels

get_predict_labels() -> list[int]

Get the prediction labels of the training dataset.

Source code in toyml/ensemble/adaboost.py

def get_predict_labels(self) -> list[int]:
    """
    Get the prediction labels of the training dataset.
    """
    if self.predict_labels_ is None:
        raise ValueError("The model is not fitted yet!")
    return self.predict_labels_

get_best_cut

get_best_cut(dataset: list[list[float]], weights: list[float], labels: list[int]) -> tuple[SignMode, float, float]

Get the best cut of the training dataset.

Source code in toyml/ensemble/adaboost.py

def get_best_cut(
    self, dataset: list[list[float]], weights: list[float], labels: list[int]
) -> tuple[SignMode, float, float]:
    """
    Get the best cut of the training dataset.
    """
    points = [x[0] for x in dataset]
    candidate_cuts = self._get_candidate_cuts(points)
    # (func_mode, cut, error_rate)
    candidate_cuts_result = []
    for cut in candidate_cuts:
        pos_neg_error_rate = self._get_cut_error_rate(cut, points, weights, labels, self.SignMode.POS_NEG)
        neg_pos_error_rate = self._get_cut_error_rate(cut, points, weights, labels, self.SignMode.NEG_POS)
        candidate_cuts_result.extend(
            [(self.SignMode.POS_NEG, cut, pos_neg_error_rate), (self.SignMode.NEG_POS, cut, neg_pos_error_rate)]
        )

    # sorted by error rate
    best_cut_result = sorted(candidate_cuts_result, key=lambda x: x[2])[0]
    sign_mode, best_cut, best_error_rate = best_cut_result
    return sign_mode, best_cut, best_error_rate