python - sklearn : Have an estimator that filters samples

Question

我正在尝试实现我自己的 Imputer。在某些情况下，我想过滤一些火车样本(我认为质量低)。

但是，由于transform方法只返回X而不返回y，而y本身就是一个numpy数组(据我所知我无法就地过滤)，而且 - 当我使用 GridSearchCV - y 我的 transform method receives is None，我似乎无法找到一种方法来做到这一点。

澄清一下:我非常清楚如何过滤数组。我找不到适合当前 API 的 y 向量样本过滤的方法。

我真的很想通过 BaseEstimator 实现来做到这一点，这样我就可以将它与 GridSearchCV 一起使用(它有几个参数)。我是否缺少实现样本过滤的不同方法(不是通过 BaseEstimator，而是通过 GridSearchCV 兼容)？有什么方法可以解决当前的 API 问题吗？

Answer 1

我找到了一个解决方案，它包含三个部分:

1. 有 if idx == id(self.X): 行。这将确保仅在训练集上过滤样本。
2. 覆盖 fit_transform 以确保转换方法得到 y 而不是 None
3. 重写Pipeline 以允许tranform 返回所述y。

下面是演示它的示例代码，我想它可能不会涵盖所有微小的细节，但我认为它解决了 API 的主要问题。

from sklearn.base import BaseEstimator
from mne.decoding.mixin import TransformerMixin
import numpy as np
from sklearn.pipeline import Pipeline
from sklearn.naive_bayes import GaussianNB
from sklearn import cross_validation
from sklearn.grid_search import GridSearchCV
from sklearn.externals import six

class SampleAndFeatureFilter(BaseEstimator, TransformerMixin):
    def __init__(self, perc = None):
        self.perc = perc

    def fit(self, X, y=None):
        self.X = X
        sum_per_feature = X.sum(0)
        sum_per_sample = X.sum(1)
        self.featurefilter = sum_per_feature >= np.percentile(sum_per_feature, self.perc)
        self.samplefilter  = sum_per_sample >= np.percentile(sum_per_sample, self.perc)
        return self

    def transform(self, X, y=None, copy=None):
        idx = id(X)
        X=X[:,self.featurefilter]
        if idx == id(self.X):
            X = X[self.samplefilter, :]
            if y is not None:
                y = y[self.samplefilter]
            return X, y
        return X

    def fit_transform(self, X, y=None, **fit_params):
        if y is None:
            return self.fit(X, **fit_params).transform(X)
        else:
            return self.fit(X, y, **fit_params).transform(X,y)

class PipelineWithSampleFiltering(Pipeline):
    def fit_transform(self, X, y=None, **fit_params):
        Xt, yt, fit_params = self._pre_transform(X, y, **fit_params)
        if hasattr(self.steps[-1][-1], 'fit_transform'):
            return self.steps[-1][-1].fit_transform(Xt, yt, **fit_params)
        else:
            return self.steps[-1][-1].fit(Xt, yt, **fit_params).transform(Xt)

    def fit(self, X, y=None, **fit_params):
        Xt, yt, fit_params = self._pre_transform(X, y, **fit_params)
        self.steps[-1][-1].fit(Xt, yt, **fit_params)
        return self

    def _pre_transform(self, X, y=None, **fit_params):
        fit_params_steps = dict((step, {}) for step, _ in self.steps)
        for pname, pval in six.iteritems(fit_params):
            step, param = pname.split('__', 1)
            fit_params_steps[step][param] = pval
        Xt = X
        yt = y
        for name, transform in self.steps[:-1]:
            if hasattr(transform, "fit_transform"):
                res = transform.fit_transform(Xt, yt, **fit_params_steps[name])
                if len(res) == 2:
                    Xt, yt = res
                else:
                    Xt = res
            else:
                Xt = transform.fit(Xt, y, **fit_params_steps[name]) \
                              .transform(Xt)
        return Xt, yt, fit_params_steps[self.steps[-1][0]]

if __name__ == '__main__':
    X = np.random.random((100,30))
    y = np.random.random_integers(0, 1, 100)
    pipe = PipelineWithSampleFiltering([('flt', SampleAndFeatureFilter()), ('cls', GaussianNB())])
    X_train, X_test, y_train, y_test = cross_validation.train_test_split(X, y, test_size = 0.3, random_state = 42)
    kfold = cross_validation.KFold(len(y_train), 10)
    clf = GridSearchCV(pipe, cv = kfold, param_grid = {'flt__perc':[10,20,30,40,50,60,70,80]}, n_jobs = 1)
    clf.fit(X_train, y_train)