Python cross_validation.cross_val_score方法代码示例

# 需要导入模块: from sklearn import cross_validation [as 别名]
# 或者: from sklearn.cross_validation import cross_val_score [as 别名]
def test_cross_val_score_multilabel():
    X = np.array([[-3, 4], [2, 4], [3, 3], [0, 2], [-3, 1],
                  [-2, 1], [0, 0], [-2, -1], [-1, -2], [1, -2]])
    y = np.array([[1, 1], [0, 1], [0, 1], [0, 1], [1, 1],
                  [0, 1], [1, 0], [1, 1], [1, 0], [0, 0]])
    clf = KNeighborsClassifier(n_neighbors=1)
    scoring_micro = make_scorer(precision_score, average='micro')
    scoring_macro = make_scorer(precision_score, average='macro')
    scoring_samples = make_scorer(precision_score, average='samples')
    score_micro = cval.cross_val_score(clf, X, y, scoring=scoring_micro, cv=5)
    score_macro = cval.cross_val_score(clf, X, y, scoring=scoring_macro, cv=5)
    score_samples = cval.cross_val_score(clf, X, y,
                                         scoring=scoring_samples, cv=5)
    assert_almost_equal(score_micro, [1, 1 / 2, 3 / 4, 1 / 2, 1 / 3])
    assert_almost_equal(score_macro, [1, 1 / 2, 3 / 4, 1 / 2, 1 / 4])
    assert_almost_equal(score_samples, [1, 1 / 2, 3 / 4, 1 / 2, 1 / 4]) 

# 需要导入模块: from sklearn import cross_validation [as 别名]
# 或者: from sklearn.cross_validation import cross_val_score [as 别名]
def classify(X, y, cl, name=''):
    """Classification using gene features"""

    from sklearn.metrics import classification_report, accuracy_score
    np.random.seed()
    ind = np.random.permutation(len(X))

    from sklearn.cross_validation import train_test_split
    Xtrain, Xtest, ytrain, ytest  = train_test_split(X, y, test_size=0.4)
    #print X
    cl.fit(Xtrain, ytrain)
    ypred = cl.predict(Xtest)

    print (classification_report(ytest, ypred))
    #print accuracy_score(ytest, ypred)
    from sklearn import cross_validation
    yl = pd.Categorical(y).labels
    sc = cross_validation.cross_val_score(cl, X, yl, scoring='roc_auc', cv=5)
    print("AUC: %0.2f (+/- %0.2f)" % (sc.mean(), sc.std() * 2))
    return cl 

# 需要导入模块: from sklearn import cross_validation [as 别名]
# 或者: from sklearn.cross_validation import cross_val_score [as 别名]
def run_model(model,dtrain,predictor_var,target,scoring_method='mean_squared_error'):
    cv_method = KFold(len(dtrain),5)
    cv_scores = cross_val_score(model,dtrain[predictor_var],dtrain[target],cv=cv_method,scoring=scoring_method)
    #print cv_scores, np.mean(cv_scores), np.sqrt((-1)*np.mean(cv_scores))
    
    dtrain_for_val = dtrain[dtrain['Year']<2000]
    dtest_for_val = dtrain[dtrain['Year']>1999]
    #cv_method = KFold(len(dtrain_for_val),5)
    #cv_scores_2 = cross_val_score(model,dtrain_for_val[predictor_var],dtrain_for_val[target],cv=cv_method,scoring=scoring_method)
    #print cv_scores_2, np.mean(cv_scores_2)
    
    dtrain_for_val_ini = dtrain_for_val[predictor_var]
    dtest_for_val_ini = dtest_for_val[predictor_var]
    model.fit(dtrain_for_val_ini,dtrain_for_val[target])
    pred_for_val = model.predict(dtest_for_val_ini)
        
    #print math.sqrt(mean_squared_error(dtest_for_val['Footfall'],pred_for_val)) 

# 需要导入模块: from sklearn import cross_validation [as 别名]
# 或者: from sklearn.cross_validation import cross_val_score [as 别名]
def test_cross_val_score_mask():
    # test that cross_val_score works with boolean masks
    svm = SVC(kernel="linear")
    iris = load_iris()
    X, y = iris.data, iris.target
    cv_indices = cval.KFold(len(y), 5)
    scores_indices = cval.cross_val_score(svm, X, y, cv=cv_indices)
    cv_indices = cval.KFold(len(y), 5)
    cv_masks = []
    for train, test in cv_indices:
        mask_train = np.zeros(len(y), dtype=np.bool)
        mask_test = np.zeros(len(y), dtype=np.bool)
        mask_train[train] = 1
        mask_test[test] = 1
        cv_masks.append((train, test))
    scores_masks = cval.cross_val_score(svm, X, y, cv=cv_masks)
    assert_array_equal(scores_indices, scores_masks) 

# 需要导入模块: from sklearn import cross_validation [as 别名]
# 或者: from sklearn.cross_validation import cross_val_score [as 别名]
def test_cross_val_score_precomputed():
    # test for svm with precomputed kernel
    svm = SVC(kernel="precomputed")
    iris = load_iris()
    X, y = iris.data, iris.target
    linear_kernel = np.dot(X, X.T)
    score_precomputed = cval.cross_val_score(svm, linear_kernel, y)
    svm = SVC(kernel="linear")
    score_linear = cval.cross_val_score(svm, X, y)
    assert_array_equal(score_precomputed, score_linear)

    # Error raised for non-square X
    svm = SVC(kernel="precomputed")
    assert_raises(ValueError, cval.cross_val_score, svm, X, y)

    # test error is raised when the precomputed kernel is not array-like
    # or sparse
    assert_raises(ValueError, cval.cross_val_score, svm,
                  linear_kernel.tolist(), y) 

# 需要导入模块: from sklearn import cross_validation [as 别名]
# 或者: from sklearn.cross_validation import cross_val_score [as 别名]
def test_cross_val_score_with_score_func_classification():
    iris = load_iris()
    clf = SVC(kernel='linear')

    # Default score (should be the accuracy score)
    scores = cval.cross_val_score(clf, iris.data, iris.target, cv=5)
    assert_array_almost_equal(scores, [0.97, 1., 0.97, 0.97, 1.], 2)

    # Correct classification score (aka. zero / one score) - should be the
    # same as the default estimator score
    zo_scores = cval.cross_val_score(clf, iris.data, iris.target,
                                     scoring="accuracy", cv=5)
    assert_array_almost_equal(zo_scores, [0.97, 1., 0.97, 0.97, 1.], 2)

    # F1 score (class are balanced so f1_score should be equal to zero/one
    # score
    f1_scores = cval.cross_val_score(clf, iris.data, iris.target,
                                     scoring="f1_weighted", cv=5)
    assert_array_almost_equal(f1_scores, [0.97, 1., 0.97, 0.97, 1.], 2) 

# 需要导入模块: from sklearn import cross_validation [as 别名]
# 或者: from sklearn.cross_validation import cross_val_score [as 别名]
def test_cross_val_score_with_score_func_regression():
    X, y = make_regression(n_samples=30, n_features=20, n_informative=5,
                           random_state=0)
    reg = Ridge()

    # Default score of the Ridge regression estimator
    scores = cval.cross_val_score(reg, X, y, cv=5)
    assert_array_almost_equal(scores, [0.94, 0.97, 0.97, 0.99, 0.92], 2)

    # R2 score (aka. determination coefficient) - should be the
    # same as the default estimator score
    r2_scores = cval.cross_val_score(reg, X, y, scoring="r2", cv=5)
    assert_array_almost_equal(r2_scores, [0.94, 0.97, 0.97, 0.99, 0.92], 2)

    # Mean squared error; this is a loss function, so "scores" are negative
    neg_mse_scores = cval.cross_val_score(reg, X, y, cv=5,
                                          scoring="neg_mean_squared_error")
    expected_neg_mse = np.array([-763.07, -553.16, -274.38, -273.26, -1681.99])
    assert_array_almost_equal(neg_mse_scores, expected_neg_mse, 2)

    # Explained variance
    scoring = make_scorer(explained_variance_score)
    ev_scores = cval.cross_val_score(reg, X, y, cv=5, scoring=scoring)
    assert_array_almost_equal(ev_scores, [0.94, 0.97, 0.97, 0.99, 0.92], 2) 

# 需要导入模块: from sklearn import cross_validation [as 别名]
# 或者: from sklearn.cross_validation import cross_val_score [as 别名]
def estimate_model(positive_data_matrix=None,
                   negative_data_matrix=None,
                   target=None,
                   estimator=None,
                   n_jobs=4):
    """estimate_model."""
    X, y = make_data_matrix(positive_data_matrix=positive_data_matrix,
                            negative_data_matrix=negative_data_matrix,
                            target=target)
    logger.info('Test set')
    logger.info(describe(X))
    logger.info('-' * 80)
    logger.info('Test Estimate')
    predictions = estimator.predict(X)
    margins = estimator.decision_function(X)
    logger.info(classification_report(y, predictions))
    apr = average_precision_score(y, margins)
    logger.info('APR: %.3f' % apr)
    roc = roc_auc_score(y, margins)
    logger.info('ROC: %.3f' % roc)

    logger.info('Cross-validated estimate')
    scoring_strings = ['accuracy', 'precision', 'recall', 'f1',
                       'average_precision', 'roc_auc']
    for scoring in scoring_strings:
        scores = cross_validation.cross_val_score(
            estimator, X, y, cv=5,
            scoring=scoring, n_jobs=n_jobs)
        logger.info('%20s: %.3f +- %.3f' % (scoring,
                                            np.mean(scores),
                                            np.std(scores)))

    return roc, apr 

# 需要导入模块: from sklearn import cross_validation [as 别名]
# 或者: from sklearn.cross_validation import cross_val_score [as 别名]
def evaluate_cross_validation(clf, X, y, K):
    # create a k-fold cross validation iterator
    cv = KFold(len(y), K, shuffle=True, random_state=0)
    # by default the score used is the one returned by score method of the estimator (accuracy)
    scores = cross_val_score(clf, X, y, cv=cv)
    print "Scores: ", (scores)
    print ("Mean score: {0:.3f} (+/-{1:.3f})".format(np.mean(scores), sem(scores)))


# Confusion Matrix and Results 

# 需要导入模块: from sklearn import cross_validation [as 别名]
# 或者: from sklearn.cross_validation import cross_val_score [as 别名]
def compute_score(clf, X, y,scoring='accuracy'):
    xval = cross_val_score(clf, X, y, cv = 5,scoring=scoring)
    return np.mean(xval) 

# 需要导入模块: from sklearn import cross_validation [as 别名]
# 或者: from sklearn.cross_validation import cross_val_score [as 别名]
def accuracy(features, labels):
    from sklearn.linear_model import LogisticRegression
    from sklearn.pipeline import Pipeline
    from sklearn.preprocessing import StandardScaler
    from sklearn import cross_validation
    # We use logistic regression because it is very fast.
    # Feel free to experiment with other classifiers
    clf = Pipeline([('preproc', StandardScaler()),
                ('classifier', LogisticRegression())])
    cv = cross_validation.LeaveOneOut(len(features))
    scores = cross_validation.cross_val_score(
        clf, features, labels, cv=cv)
    return scores.mean() 

# 需要导入模块: from sklearn import cross_validation [as 别名]
# 或者: from sklearn.cross_validation import cross_val_score [as 别名]
def stump(X, y):
    score = cross_val_score(LinearSVC(), X, y, cv = 5, n_jobs=5, scoring = 'average_precision')
    clf = LinearSVC()
    clf.fit(X, y)
    coef = clf.coef_[0,0]
    inter = clf.intercept_[0]
    return np.mean(score), np.sign(coef), inter / np.abs(coef) 

# 需要导入模块: from sklearn import cross_validation [as 别名]
# 或者: from sklearn.cross_validation import cross_val_score [as 别名]
def _f(x):
        # iris = load_iris()
        X, y = X, y = make_hastie_10_2(random_state=0)
        x = np.ravel(x)
        f = np.zeros(x.shape)
        for i in range(f.size):
            clf = RandomForestClassifier(n_estimators=1, min_samples_leaf=int(np.round(x[i])), random_state=0)
            # scores = cross_val_score(clf, iris.data, iris.target)
            scores = cross_val_score(clf, X, y, cv=5)
            f[i] = -scores.mean()
        return f.ravel() 

# 需要导入模块: from sklearn import cross_validation [as 别名]
# 或者: from sklearn.cross_validation import cross_val_score [as 别名]
def train(self):
        feats = self.get_features()
        scores = np.array(self.scores)

        # Compute error metrics for the estimator.
        self.cv_scores = cross_validation.cross_val_score(self.classifier, feats, scores)
        self.cv_score = self.cv_scores.mean()
        self.cv_dev = self.cv_scores.std()

        self.classifier.fit(feats, scores)
        self.fit_done = True 

# 需要导入模块: from sklearn import cross_validation [as 别名]
# 或者: from sklearn.cross_validation import cross_val_score [as 别名]
def run_croos_validation(self):
        features,labels,cv = self.getFeaturesLabel()
        scores = cross_validation.cross_val_score(self.clf, features, labels, cv=cv, scoring=mean_absolute_percentage_error_scoring, n_jobs = -1)
        print "cross validation scores: means, {}, std, {}, details,{}".format(np.absolute(scores.mean()), scores.std(), np.absolute(scores))
        return -np.absolute(scores.mean())