Python sklearn.cross_validation.cross_val_predict() Examples

def get_logistic_regression_coefs_l2(self, category,
                                         clf=RidgeClassifierCV()):
        ''' Computes l2-penalized logistic regression score.
        Parameters
        ----------
        category : str
            category name to score

        category : str
            category name to score
        Returns
        -------
            (coefficient array, accuracy, majority class baseline accuracy)
        '''
        try:
            from sklearn.cross_validation import cross_val_predict
        except:
            from sklearn.model_selection import cross_val_predict
        y = self._get_mask_from_category(category)
        X = TfidfTransformer().fit_transform(self._X)
        clf.fit(X, y)
        y_hat = cross_val_predict(clf, X, y)
        acc, baseline = self._get_accuracy_and_baseline_accuracy(y, y_hat)
        return clf.coef_[0], acc, baseline 

def get_logistic_regression_coefs_l1(self, category,
                                         clf=LassoCV(alphas=[0.1, 0.001],
                                                     max_iter=10000,
                                                     n_jobs=-1)):
        ''' Computes l1-penalized logistic regression score.
        Parameters
        ----------
        category : str
            category name to score

        Returns
        -------
            (coefficient array, accuracy, majority class baseline accuracy)
        '''
        try:
            from sklearn.cross_validation import cross_val_predict
        except:
            from sklearn.model_selection import cross_val_predict
        y = self._get_mask_from_category(category)
        y_continuous = self._get_continuous_version_boolean_y(y)
        # X = TfidfTransformer().fit_transform(self._X)
        X = self._X

        clf.fit(X, y_continuous)
        y_hat = (cross_val_predict(clf, X, y_continuous) > 0)
        acc, baseline = self._get_accuracy_and_baseline_accuracy(y, y_hat)
        clf.fit(X, y_continuous)
        return clf.coef_, acc, baseline 

def _generate_cross_val_predict_test(X, y, est, pd_est, must_match):
    def test(self):
        self.assertEqual(
            hasattr(est, 'predict'),
            hasattr(pd_est, 'predict'))
        if not hasattr(est, 'predict'):
            return
        pd_y_hat = pd_cross_val_predict(pd_est, X, y)
        self.assertTrue(isinstance(pd_y_hat, pd.Series))
        self.assertTrue(pd_y_hat.index.equals(X.index))
        if must_match:
            y_hat = cross_val_predict(est, X.as_matrix(), y.values)
            np.testing.assert_allclose(pd_y_hat, y_hat)
    return test 

def demo_getPerf(X,y,Classifier,Classifier_label):
    """
    Classifier_type: Sklearn model
        Type of classifier to use, and it's parameters
    Classifier_label: string
        Descriptive Name of the classifier. e.g "Forest"
    """
    results = {}

    scores = cross_val_predict(Classifier, X, y, cv=10, n_jobs=-1)
    results[label] = get_scores(scores,y,Classifier_label)

    res_df = pd.DataFrame(results)
    res_df.to_csv(outputFileName+"tsv", sep='\t') 

def test_cross_val_predict():
    boston = load_boston()
    X, y = boston.data, boston.target
    cv = cval.KFold(len(boston.target))

    est = Ridge()

    # Naive loop (should be same as cross_val_predict):
    preds2 = np.zeros_like(y)
    for train, test in cv:
        est.fit(X[train], y[train])
        preds2[test] = est.predict(X[test])

    preds = cval.cross_val_predict(est, X, y, cv=cv)
    assert_array_almost_equal(preds, preds2)

    preds = cval.cross_val_predict(est, X, y)
    assert_equal(len(preds), len(y))

    cv = cval.LeaveOneOut(len(y))
    preds = cval.cross_val_predict(est, X, y, cv=cv)
    assert_equal(len(preds), len(y))

    Xsp = X.copy()
    Xsp *= (Xsp > np.median(Xsp))
    Xsp = coo_matrix(Xsp)
    preds = cval.cross_val_predict(est, Xsp, y)
    assert_array_almost_equal(len(preds), len(y))

    preds = cval.cross_val_predict(KMeans(), X)
    assert_equal(len(preds), len(y))

    def bad_cv():
        for i in range(4):
            yield np.array([0, 1, 2, 3]), np.array([4, 5, 6, 7, 8])

    assert_raises(ValueError, cval.cross_val_predict, est, X, y, cv=bad_cv()) 

def test_cross_val_predict_input_types():
    clf = Ridge()
    # Smoke test
    predictions = cval.cross_val_predict(clf, X, y)
    assert_equal(predictions.shape, (10,))

    # test with multioutput y
    with ignore_warnings(category=ConvergenceWarning):
        predictions = cval.cross_val_predict(clf, X_sparse, X)
    assert_equal(predictions.shape, (10, 2))

    predictions = cval.cross_val_predict(clf, X_sparse, y)
    assert_array_equal(predictions.shape, (10,))

    # test with multioutput y
    with ignore_warnings(category=ConvergenceWarning):
        predictions = cval.cross_val_predict(clf, X_sparse, X)
    assert_array_equal(predictions.shape, (10, 2))

    # test with X and y as list
    list_check = lambda x: isinstance(x, list)
    clf = CheckingClassifier(check_X=list_check)
    predictions = cval.cross_val_predict(clf, X.tolist(), y.tolist())

    clf = CheckingClassifier(check_y=list_check)
    predictions = cval.cross_val_predict(clf, X, y.tolist())

    # test with 3d X and
    X_3d = X[:, :, np.newaxis]
    check_3d = lambda x: x.ndim == 3
    clf = CheckingClassifier(check_X=check_3d)
    predictions = cval.cross_val_predict(clf, X_3d, y)
    assert_array_equal(predictions.shape, (10,)) 

def test_cross_val_predict_pandas():
    # check cross_val_score doesn't destroy pandas dataframe
    types = [(MockDataFrame, MockDataFrame)]
    try:
        from pandas import Series, DataFrame
        types.append((Series, DataFrame))
    except ImportError:
        pass
    for TargetType, InputFeatureType in types:
        # X dataframe, y series
        X_df, y_ser = InputFeatureType(X), TargetType(y)
        check_df = lambda x: isinstance(x, InputFeatureType)
        check_series = lambda x: isinstance(x, TargetType)
        clf = CheckingClassifier(check_X=check_df, check_y=check_series)
        cval.cross_val_predict(clf, X_df, y_ser) 

def test_cross_val_predict_sparse_prediction():
    # check that cross_val_predict gives same result for sparse and dense input
    X, y = make_multilabel_classification(n_classes=2, n_labels=1,
                                          allow_unlabeled=False,
                                          return_indicator=True,
                                          random_state=1)
    X_sparse = csr_matrix(X)
    y_sparse = csr_matrix(y)
    classif = OneVsRestClassifier(SVC(kernel='linear'))
    preds = cval.cross_val_predict(classif, X, y, cv=10)
    preds_sparse = cval.cross_val_predict(classif, X_sparse, y_sparse, cv=10)
    preds_sparse = preds_sparse.toarray()
    assert_array_almost_equal(preds_sparse, preds)