EL之Bagging：kaggle比赛之利用泰坦尼克号数据集建立Bagging模型对每个人进行获救是否预测

EL之Bagging：kaggle比赛之利用泰坦尼克号数据集建立Bagging模型对每个人进行获救是否预测

 

 

目录

输出结果

设计思路

核心代码

---

 

 

 

输出结果

 

设计思路

 

核心代码

bagging_clf = BaggingRegressor(clf_LoR, n_estimators=10, max_samples=0.8, max_features=1.0, bootstrap=True, bootstrap_features=False, n_jobs=-1)
    bagging_clf.fit(X, y)



#BaggingRegressor
class BaggingRegressor Found at: sklearn.ensemble.bagging

class BaggingRegressor(BaseBagging, RegressorMixin):
    """A Bagging regressor.
    
    A Bagging regressor is an ensemble meta-estimator that fits base
    regressors each on random subsets of the original dataset and then
    aggregate their individual predictions (either by voting or by averaging)
    to form a final prediction. Such a meta-estimator can typically be used as
    a way to reduce the variance of a black-box estimator (e.g., a decision
    tree), by introducing randomization into its construction procedure and
    then making an ensemble out of it.
    
    This algorithm encompasses several works from the literature. When 
     random
    subsets of the dataset are drawn as random subsets of the samples, then
    this algorithm is known as Pasting [1]_. If samples are drawn with
    replacement, then the method is known as Bagging [2]_. When random 
     subsets
    of the dataset are drawn as random subsets of the features, then the 
     method
    is known as Random Subspaces [3]_. Finally, when base estimators are 
     built
    on subsets of both samples and features, then the method is known as
    Random Patches [4]_.
    
    Read more in the :ref:`User Guide `.
    
    Parameters
    ----------
    base_estimator : object or None, optional (default=None)
    The base estimator to fit on random subsets of the dataset.
    If None, then the base estimator is a decision tree.
    
    n_estimators : int, optional (default=10)
    The number of base estimators in the ensemble.
    
    max_samples : int or float, optional (default=1.0)
    The number of samples to draw from X to train each base estimator.
    - If int, then draw `max_samples` samples.
    - If float, then draw `max_samples * X.shape[0]` samples.
    
    max_features : int or float, optional (default=1.0)
    The number of features to draw from X to train each base estimator.
    - If int, then draw `max_features` features.
    - If float, then draw `max_features * X.shape[1]` features.
    
    bootstrap : boolean, optional (default=True)
    Whether samples are drawn with replacement.
    
    bootstrap_features : boolean, optional (default=False)
    Whether features are drawn with replacement.
    
    oob_score : bool
    Whether to use out-of-bag samples to estimate
    the generalization error.
    
    warm_start : bool, optional (default=False)
    When set to True, reuse the solution of the previous call to fit
    and add more estimators to the ensemble, otherwise, just fit
    a whole new ensemble.
    
    n_jobs : int, optional (default=1)
    The number of jobs to run in parallel for both `fit` and `predict`.
    If -1, then the number of jobs is set to the number of cores.
    
    random_state : int, RandomState instance or None, optional 
     (default=None)
    If int, random_state is the seed used by the random number generator;
    If RandomState instance, random_state is the random number 
     generator;
    If None, the random number generator is the RandomState instance 
     used
    by `np.random`.
    
    verbose : int, optional (default=0)
    Controls the verbosity of the building process.
    
    Attributes
    ----------
    estimators_ : list of estimators
    The collection of fitted sub-estimators.
    
    estimators_samples_ : list of arrays
    The subset of drawn samples (i.e., the in-bag samples) for each base
    estimator. Each subset is defined by a boolean mask.
    
    estimators_features_ : list of arrays
    The subset of drawn features for each base estimator.
    
    oob_score_ : float
    Score of the training dataset obtained using an out-of-bag estimate.
    
    oob_prediction_ : array of shape = [n_samples]
    Prediction computed with out-of-bag estimate on the training
    set. If n_estimators is small it might be possible that a data point
    was never left out during the bootstrap. In this case,
    `oob_prediction_` might contain NaN.
    
    References
    ----------
    
    .. [1] L. Breiman, "Pasting small votes for classification in large
    databases and on-line", Machine Learning, 36(1), 85-103, 1999.
    
    .. [2] L. Breiman, "Bagging predictors", Machine Learning, 24(2), 123-140,
    1996.
    
    .. [3] T. Ho, "The random subspace method for constructing decision
    forests", Pattern Analysis and Machine Intelligence, 20(8), 832-844,
    1998.
    
    .. [4] G. Louppe and P. Geurts, "Ensembles on Random Patches", Machine
    Learning and Knowledge Discovery in Databases, 346-361, 2012.
    """
    def __init__(self, 
        base_estimator=None, 
        n_estimators=10, 
        max_samples=1.0, 
        max_features=1.0, 
        bootstrap=True, 
        bootstrap_features=False, 
        oob_score=False, 
        warm_start=False, 
        n_jobs=1, 
        random_state=None, 
        verbose=0):
        super(BaggingRegressor, self).__init__(base_estimator, 
         n_estimators=n_estimators, max_samples=max_samples, 
         max_features=max_features, bootstrap=bootstrap, 
         bootstrap_features=bootstrap_features, oob_score=oob_score, 
         warm_start=warm_start, n_jobs=n_jobs, random_state=random_state, 
         verbose=verbose)
    
    def predict(self, X):
        """Predict regression target for X.

        The predicted regression target of an input sample is computed as 
         the
        mean predicted regression targets of the estimators in the ensemble.

        Parameters
        ----------
        X : {array-like, sparse matrix} of shape = [n_samples, n_features]
            The training input samples. Sparse matrices are accepted only if
            they are supported by the base estimator.

        Returns
        -------
        y : array of shape = [n_samples]
            The predicted values.
        """
        check_is_fitted(self, "estimators_features_")
    # Check data
        X = check_array(X, accept_sparse=['csr', 'csc'])
    # Parallel loop
        n_jobs, n_estimators, starts = _partition_estimators(self.n_estimators, 
         self.n_jobs)
        all_y_hat = Parallel(n_jobs=n_jobs, verbose=self.verbose)(
            delayed(_parallel_predict_regression)(
                self.estimators_[starts[i]:starts[i + 1]], 
                self.estimators_features_[starts[i]:starts[i + 1]], 
                X) for 
            i in range(n_jobs))
    # Reduce
        y_hat = sum(all_y_hat) / self.n_estimators
        return y_hat
    
    def _validate_estimator(self):
        """Check the estimator and set the base_estimator_ attribute."""
        super(BaggingRegressor, self)._validate_estimator
         (default=DecisionTreeRegressor())
    
    def _set_oob_score(self, X, y):
        n_samples = y.shape[0]
        predictions = np.zeros((n_samples, ))
        n_predictions = np.zeros((n_samples, ))
        for estimator, samples, features in zip(self.estimators_, 
            self.estimators_samples_, 
            self.estimators_features_):
        # Create mask for OOB samples
            mask = ~samples
            predictions[mask] += estimator.predict(mask:])[(X[:features])
            n_predictions[mask] += 1
        
        if (n_predictions == 0).any():
            warn("Some inputs do not have OOB scores. "
                "This probably means too few estimators were used "
                "to compute any reliable oob estimates.")
            n_predictions[n_predictions == 0] = 1
        predictions /= n_predictions
        self.oob_prediction_ = predictions
        self.oob_score_ = r2_score(y, predictions)