Python sklearn.feature_selection 模块，f_regression() 实例源码

def select_kbest_reg(data_frame, target, k=5):
    """
    Selecting K-Best features regression
    :param data_frame: A pandas dataFrame with the training data
    :param target: target variable name in DataFrame
    :param k: desired number of features from the data
    :returns feature_scores: scores for each feature in the data as 
    pandas DataFrame
    """
    feat_selector = SelectKBest(f_regression, k=k)
    _ = feat_selector.fit(data_frame.drop(target, axis=1), data_frame[target])

    feat_scores = pd.DataFrame()
    feat_scores["F Score"] = feat_selector.scores_
    feat_scores["P Value"] = feat_selector.pvalues_
    feat_scores["Support"] = feat_selector.get_support()
    feat_scores["Attribute"] = data_frame.drop(target, axis=1).columns

    return feat_scores

def main():
    from sklearn import svm
    from sklearn.datasets import samples_generator
    from sklearn.feature_selection import SelectKBest
    from sklearn.feature_selection import f_regression
    from sklearn.preprocessing import MinMaxScaler

    X, y = samples_generator.make_classification(n_samples=1000, n_informative=5, n_redundant=4, random_state=_random_state)
    anova_filter = SelectKBest(f_regression, k=5)
    scaler = MinMaxScaler()
    clf = svm.SVC(kernel='linear')

    steps = [scaler, anova_filter, clf]
    cached_run(steps, X, y)

def ANOVA(X,y):
    '''Univariate linear regression tests
    Quick linear model for sequentially testing the effect of many regressors
    Using scikit learn's Feature selection toolbox
    Returns:
        F (array) = F-values for regressors
        pvalues (array) = p-values for F-scores'''

    (F,pvalues) = f_regression(X,y)
    return (F,pvalues)

def get_params_for_est(estimator, name):
    '''Choose initialization parameters for an estimator for auto-testing'''
    is_classifier = ClassifierMixin in estimator.__mro__
    is_cluster = ClusterMixin in estimator.__mro__
    is_ensemble = BaseEnsemble in estimator.__mro__
    uses_counts = any(c in name for c in USES_COUNTS)
    as_1d = name in REQUIRES_1D
    args, params, _ = get_args_kwargs_defaults(estimator.__init__)
    est_keys = set(('estimator', 'base_estimator', 'estimators'))
    est_keys = (set(params) | set(args)) & est_keys
    if is_classifier:
        score_func = feat.f_classif
    else:
        score_func = feat.f_regression
    for key in est_keys:
        if name == 'SelectFromModel':
            params[key] = sklearn.linear_model.LassoCV()
        elif is_classifier:
            params[key] = sklearn.tree.DecisionTreeClassifier()
        else:
            params[key] = sklearn.tree.DecisionTreeRegressor()
        if key == 'estimators':
            params[key] = [(str(_), clone(params[key])) for _ in range(10)]
    kw = dict(is_classifier=is_classifier, is_cluster=is_cluster,
              is_ensemble=is_ensemble, uses_counts=uses_counts)
    if 'score_func' in params:
        params['score_func'] = score_func
    X, y = make_X_y(**kw)
    return X, y, params, kw