Python SelectFpr.get_support方法代码示例

# 需要导入模块: from sklearn.feature_selection import SelectFpr [as 别名]
# 或者: from sklearn.feature_selection.SelectFpr import get_support [as 别名]
def test_select_fpr_classif():
    """
    Test whether the relative univariate feature selection
    gets the correct items in a simple classification problem
    with the fpr heuristic
    """
    X, Y = make_classification(
        n_samples=200,
        n_features=20,
        n_informative=3,
        n_redundant=2,
        n_repeated=0,
        n_classes=8,
        n_clusters_per_class=1,
        flip_y=0.0,
        class_sep=10,
        shuffle=False,
        random_state=0,
    )

    univariate_filter = SelectFpr(f_classif, alpha=0.0001)
    X_r = univariate_filter.fit(X, Y).transform(X)
    X_r2 = GenericUnivariateSelect(f_classif, mode="fpr", param=0.0001).fit(X, Y).transform(X)
    assert_array_equal(X_r, X_r2)
    support = univariate_filter.get_support()
    gtruth = np.zeros(20)
    gtruth[:5] = 1
    assert_array_equal(support, gtruth)

# 需要导入模块: from sklearn.feature_selection import SelectFpr [as 别名]
# 或者: from sklearn.feature_selection.SelectFpr import get_support [as 别名]
def test_boundary_case_ch2():
    # Test boundary case, and always aim to select 1 feature.
    X = np.array([[10, 20], [20, 20], [20, 30]])
    y = np.array([[1], [0], [0]])
    scores, pvalues = chi2(X, y)
    assert_array_almost_equal(scores, np.array([4.0, 0.71428571]))
    assert_array_almost_equal(pvalues, np.array([0.04550026, 0.39802472]))

    filter_fdr = SelectFdr(chi2, alpha=0.1)
    filter_fdr.fit(X, y)
    support_fdr = filter_fdr.get_support()
    assert_array_equal(support_fdr, np.array([True, False]))

    filter_kbest = SelectKBest(chi2, k=1)
    filter_kbest.fit(X, y)
    support_kbest = filter_kbest.get_support()
    assert_array_equal(support_kbest, np.array([True, False]))

    filter_percentile = SelectPercentile(chi2, percentile=50)
    filter_percentile.fit(X, y)
    support_percentile = filter_percentile.get_support()
    assert_array_equal(support_percentile, np.array([True, False]))

    filter_fpr = SelectFpr(chi2, alpha=0.1)
    filter_fpr.fit(X, y)
    support_fpr = filter_fpr.get_support()
    assert_array_equal(support_fpr, np.array([True, False]))

    filter_fwe = SelectFwe(chi2, alpha=0.1)
    filter_fwe.fit(X, y)
    support_fwe = filter_fwe.get_support()
    assert_array_equal(support_fwe, np.array([True, False]))

# 需要导入模块: from sklearn.feature_selection import SelectFpr [as 别名]
# 或者: from sklearn.feature_selection.SelectFpr import get_support [as 别名]
def select_with_fpr(train, test):
  train_data = train.drop('ID', axis=1)
  test_data = test.drop('ID', axis=1)

  train_y = train_data['TARGET']
  train_X = train_data.drop('TARGET', 1)

  fpr = SelectFpr(alpha = 0.001)

  features = fpr.fit_transform(train_X, train_y)

  print('Fpr выбрал {} признаков.'.format(features.shape[1]))

  col_numbers = fpr.get_support()
  columns = np.delete(train_data.columns.values, train_data.shape[1] - 1, axis=0)
  features = []
  i = 0
  for i in range(len(columns)):
    if col_numbers[i] == True:
      features.append(columns[i])

  new_train = train[['ID'] + features + ['TARGET']]
  new_train.to_csv('train_after_fpr.csv')

  new_test = test[['ID'] + features]
  new_test.to_csv('test_after_fpr.csv')

# 需要导入模块: from sklearn.feature_selection import SelectFpr [as 别名]
# 或者: from sklearn.feature_selection.SelectFpr import get_support [as 别名]
def test_select_heuristics_regression():
    # Test whether the relative univariate feature selection
    # gets the correct items in a simple regression problem
    # with the fpr, fdr or fwe heuristics
    X, y = make_regression(n_samples=200, n_features=20, n_informative=5, shuffle=False, random_state=0, noise=10)

    univariate_filter = SelectFpr(f_regression, alpha=0.01)
    X_r = univariate_filter.fit(X, y).transform(X)
    gtruth = np.zeros(20)
    gtruth[:5] = 1
    for mode in ["fdr", "fpr", "fwe"]:
        X_r2 = GenericUnivariateSelect(f_regression, mode=mode, param=0.01).fit(X, y).transform(X)
        assert_array_equal(X_r, X_r2)
        support = univariate_filter.get_support()
        assert_array_equal(support[:5], np.ones((5,), dtype=np.bool))
        assert_less(np.sum(support[5:] == 1), 3)

# 需要导入模块: from sklearn.feature_selection import SelectFpr [as 别名]
# 或者: from sklearn.feature_selection.SelectFpr import get_support [as 别名]
def test_select_fpr_regression():
    """
    Test whether the relative univariate feature selection
    gets the correct items in a simple regression problem
    with the fpr heuristic
    """
    X, Y = make_regression(n_samples=200, n_features=20, n_informative=5, shuffle=False, random_state=0)

    univariate_filter = SelectFpr(f_regression, alpha=0.01)
    X_r = univariate_filter.fit(X, Y).transform(X)
    X_r2 = GenericUnivariateSelect(f_regression, mode="fpr", param=0.01).fit(X, Y).transform(X)
    assert_array_equal(X_r, X_r2)
    support = univariate_filter.get_support()
    gtruth = np.zeros(20)
    gtruth[:5] = 1
    assert (support[:5] == 1).all()
    assert np.sum(support[5:] == 1) < 3

# 需要导入模块: from sklearn.feature_selection import SelectFpr [as 别名]
# 或者: from sklearn.feature_selection.SelectFpr import get_support [as 别名]
# import data of all Count and Position features. Training and test sets altogether
dfCountfeatures = pd.read_csv('data/CountingAndPositionFeatures_TrainAndTestData.csv')
dfTrainRaw = pd.read_csv('data/train.csv')

# get only training data  
TrainQueryIDs = dfTrainRaw["id"]
relevance = dfTrainRaw["relevance"]
dfCountfeatures_TrainSet = dfCountfeatures[dfCountfeatures["id"].isin(TrainQueryIDs)]
#select these features which have non-zero variance
selector = VarianceThreshold()
selector.fit_transform(dfCountfeatures_TrainSet).shape # only one feature with zero variance - shape (74067L, 262L)

# select feature based on p-values from univariate regression with target feature (relevance)
selector2= SelectFpr(f_regression, alpha = 0.01)
selector2.fit(dfCountfeatures_TrainSet.drop("id", axis = 1), relevance)
selector2.get_support(indices=True).size # left 226 features out of 262 with p-value <=1%
# get titles of features which were selected
selectedCountfeatures = dfCountfeatures.columns[selector2.get_support(indices=True)]

# check correlation amongst features
corrReduced = dfCountfeatures_TrainSet[selectedCountfeatures].corr()
corrReduced.iloc[:,:] = np.tril(corrReduced.values, k=-1)
corrReduced =corrReduced.stack()
# get pairs of features which are highly correlated
corrReduced[corrReduced.abs()>0.8].size # 578 pairs correlated more than 80% out of 25.425
len(set(corrReduced[corrReduced.abs()>0.8].index.labels[0])) # 172 features to be removed due to high correlation with other features
# get feature titles which will be used in training the model after removing highly correlated features
indices = set(corrReduced[corrReduced.abs()>0.8].index.labels[0])
selectedCountfeatures2 = [i for j, i in enumerate(selectedCountfeatures.tolist()) if j not in indices]
selectedCountfeatures2.append("id")

# 需要导入模块: from sklearn.feature_selection import SelectFpr [as 别名]
# 或者: from sklearn.feature_selection.SelectFpr import get_support [as 别名]
X_fitted_4 = SelectPercentile(chi2, percentile=50).fit(X,y)
print "SelectPercentile -- chi2"
print X_fitted_4.scores_
print X_fitted_4.pvalues_
print X_fitted_4.get_support()
X_transformed_4 = X_fitted_4.transform(X)
print X_transformed_4.shape

#SelectFpr --- chi2
from sklearn.feature_selection import SelectFpr
from sklearn.feature_selection import chi2
X_fitted_5 = SelectFpr(chi2, alpha=2.50017968e-15).fit(X,y)
print "SelectFpr --- chi2"
print X_fitted_5.scores_
print X_fitted_5.pvalues_
print X_fitted_5.get_support()
X_transformed_5 = X_fitted_5.transform(X)
print X_transformed_5.shape

#SelectFpr --- f_classif
from sklearn.feature_selection import SelectFpr
from sklearn.feature_selection import f_classif
X_fitted_6 = SelectFpr(f_classif, alpha=1.66966919e-31 ).fit(X,y)
print "SelectFpr --- f_classif"
print X_fitted_6.scores_
print X_fitted_6.pvalues_
print X_fitted_6.get_support()
X_transformed_6 = X_fitted_6.transform(X)
print X_transformed_6.shape

# SelectFdr  和 SelectFwe 的用法和上面类似，只是选择特征时候的依据不同，真正决定得分不同的是