Python samples_generator.test_dataset_classif函数代码示例

def test_grid_search_error():
    """Test that grid search will capture errors on data with different
    length"""
    X_, y_ = test_dataset_classif(n_samples=200, n_features=100, seed=0)

    clf = LinearSVC()
    cv = GridSearchCV(clf, {'C':[0.1, 1.0]})
    assert_raises(ValueError, cv.fit, X_[:180], y_)

def test_weight():
    """
    Test class weights
    """

    X_, y_ = test_dataset_classif(n_samples=200, n_features=100, param=[5, 1], seed=0)
    X_ = scipy.sparse.csr_matrix(X_)
    for clf in (linear_model.sparse.LogisticRegression(), svm.sparse.LinearSVC(), svm.sparse.SVC()):
        clf.fit(X_[:180], y_[:180], class_weight={0: 5})
        y_pred = clf.predict(X_[180:])
        assert np.sum(y_pred == y_[180:]) >= 11

def test_f_classif_multi_class():
    """
    Test whether the F test yields meaningful results
    on a simple simulated classification problem
    """
    X, Y = test_dataset_classif(n_samples=50, n_features=20, k=5,
                                           seed=seed, param=[1, 1, 1])
    F, pv = f_classif(X, Y)
    assert(F>0).all()
    assert(pv>0).all()
    assert(pv<1).all()
    assert(pv[:5]<0.05).all()
    assert(pv[5:]>1.e-5).all()

def test_f_regression():
    """
    Test whether the F test yields meaningful results
    on a simple simulated regression problem
    """
    X, Y = test_dataset_classif(n_samples=50, n_features=20, k=5,
                                           seed=seed)
    F, pv = f_regression(X, Y)
    assert(F>0).all()
    assert(pv>0).all()
    assert(pv<1).all()
    assert(pv[:5]<0.05).all()
    assert(pv[5:]>1.e-4).all()

def test_weight():
    """
    Test class weights
    """
    clf = svm.SVC()
    # we give a small weights to class 1
    clf.fit(X, Y, {1: 0.1})
    # so all predicted values belong to class 2
    assert_array_almost_equal(clf.predict(X), [2] * 6)

    X_, y_ = test_dataset_classif(n_samples=200, n_features=100, param=[5, 1],
                                  seed=0)
    for clf in (linear_model.LogisticRegression(), svm.LinearSVC(), svm.SVC()):
        clf.fit(X_[: 180], y_[: 180], class_weight={0: 5})
        y_pred = clf.predict(X_[180:])
        assert np.sum(y_pred == y_[180:]) >= 11

def test_select_kbest_classif():
    """
    Test whether the relative univariate feature selection
    gets the correct items in a simple classification problem
    with the k best heuristic
    """
    X, Y = test_dataset_classif(n_samples=50, n_features=20, k=5,
                                           seed=seed)
    univariate_filter = SelectKBest(f_classif, k=5)
    X_r = univariate_filter.fit(X, Y).transform(X)
    X_r2 = GenericUnivariateSelect(f_classif, mode='k_best',
                    param=5).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)

def test_select_fwe_classif():
    """
    Test whether the relative univariate feature selection
    gets the correct items in a simple classification problem
    with the fpr heuristic
    """
    X, Y = test_dataset_classif(n_samples=50, n_features=20, k=5,
                                           seed=seed)
    univariate_filter = SelectFwe(f_classif, alpha=0.01)
    X_r = univariate_filter.fit(X, Y).transform(X)
    X_r2 = GenericUnivariateSelect(f_classif, mode='fwe',
                    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(np.sum(np.abs(support-gtruth))<2)

def test_grid_search_sparse_score_func():
    X_, y_ = test_dataset_classif(n_samples=200, n_features=100, seed=0)

    clf = LinearSVC()
    cv = GridSearchCV(clf, {'C': [0.1, 1.0]}, score_func=f1_score)
    cv.fit(X_[:180], y_[:180])
    y_pred = cv.predict(X_[180:])
    C = cv.best_estimator.C

    X_ = sp.csr_matrix(X_)
    clf = SparseLinearSVC()
    cv = GridSearchCV(clf, {'C': [0.1, 1.0]}, score_func=f1_score)
    cv.fit(X_[:180], y_[:180])
    y_pred2 = cv.predict(X_[180:])
    C2 = cv.best_estimator.C

    assert_array_equal(y_pred, y_pred2)
    assert_equal(C, C2)

def test_grid_search_sparse():
    """Test that grid search works with both dense and sparse matrices"""
    X_, y_ = test_dataset_classif(n_samples=200, n_features=100, seed=0)

    clf = LinearSVC()
    cv = GridSearchCV(clf, {'C':[0.1, 1.0]})
    cv.fit(X_[:180], y_[:180])
    y_pred = cv.predict(X_[180:])
    C = cv.best_estimator.C

    X_ = sp.csr_matrix(X_)
    clf = SparseLinearSVC()
    cv = GridSearchCV(clf, {'C':[0.1, 1.0]})
    cv.fit(X_[:180], y_[:180])
    y_pred2 = cv.predict(X_[180:])
    C2 = cv.best_estimator.C

    assert np.mean(y_pred == y_pred2) >= .9
    assert_equal(C, C2)

"""
==========================
Pipeline Anova SVM
==========================

Simple usages of pipeline:
- ANOVA SVM-C
"""

from scikits.learn import svm
from scikits.learn.datasets import samples_generator
from scikits.learn.feature_selection.univariate_selection import SelectKBest,f_regression
from scikits.learn.pipeline import Pipeline

# import some data to play with
X, y = samples_generator.test_dataset_classif(k=5)


# ANOVA SVM-C
# 1) anova filter, take 5 best ranked features 
anova_filter = SelectKBest(f_regression, k=5)
# 2) svm
clf = svm.SVC(kernel='linear')

anova_svm = Pipeline([anova_filter], clf)
anova_svm.fit(X, y)
anova_svm.predict(X)

Recursive feature elimination with automatic tuning of the
number of features selected with cross-validation
"""
print __doc__
import numpy as np

from scikits.learn.svm import SVC
from scikits.learn.cross_val import StratifiedKFold
from scikits.learn.feature_selection import RFECV
from scikits.learn.datasets import samples_generator
from scikits.learn.metrics import zero_one

################################################################################
# Loading a dataset

X, y = samples_generator.test_dataset_classif(n_features=500, k=5, seed=0)

################################################################################
# Create the RFE object and compute a cross-validated score

svc = SVC(kernel='linear')
rfecv = RFECV(estimator=svc, n_features=2, percentage=0.1, loss_func=zero_one)
rfecv.fit(X, y, cv=StratifiedKFold(y, 2))

print 'Optimal number of features : %d' % rfecv.support_.sum()

import pylab as pl
pl.figure()
pl.semilogx(rfecv.n_features_, rfecv.cv_scores_)
pl.xlabel('Number of features selected')
pl.ylabel('Cross validation score (nb of misclassifications)')