Python discriminant_analysis.LinearDiscriminantAnalysis类代码示例

def computing_cv_accuracy_LDA(in_path=None, cv_n_fold=10):
    def u65(mod_Y):
        return 1.6 / mod_Y - 0.6 / mod_Y ** 2

    def u80(mod_Y):
        return 2.2 / mod_Y - 1.2 / mod_Y ** 2

    from sklearn.discriminant_analysis import LinearDiscriminantAnalysis

    data = export_data_set('iris.data') if in_path is None else pd.read_csv(in_path)
    print("-----DATA SET TRAINING---", in_path)
    X = data.iloc[:, :-1].values
    y = np.array(data.iloc[:, -1].tolist())
    kf = KFold(n_splits=cv_n_fold, random_state=None, shuffle=True)
    lda = LinearDiscriminantAnalysis(solver="svd", store_covariance=True)
    mean_u65, mean_u80 = 0, 0
    for idx_train, idx_test in kf.split(y):
        print("---k-FOLD-new-executing--")
        X_cv_train, y_cv_train = X[idx_train], y[idx_train]
        X_cv_test, y_cv_test = X[idx_test], y[idx_test]
        lda.fit(X_cv_train, y_cv_train)
        n_test = len(idx_test)
        sum_u65, sum_u80 = 0, 0
        for i, test in enumerate(X_cv_test):
            evaluate = lda.predict([test])
            print("-----TESTING-----", i)
            if y_cv_test[i] in evaluate:
                sum_u65 += u65(len(evaluate))
                sum_u80 += u80(len(evaluate))
        mean_u65 += sum_u65 / n_test
        mean_u80 += sum_u80 / n_test
    print("--->", mean_u65 / cv_n_fold, mean_u80 / cv_n_fold)

def performLDA(data_to_fit, y, numComponent=None):
    data_to_fit_np_t = np.array(data_to_fit).T
    if numComponent is None:
        numComponent = len(data_to_fit_np_t)
    lda_model = LinearDiscriminantAnalysis(n_components=numComponent)
    lda_results = lda_model.fit_transform(data_to_fit_np_t, y)
    return lda_model, lda_results

def computing_performance_LDA(in_path=None, seeds=list([0])):
    def u65(mod_Y):
        return 1.6 / mod_Y - 0.6 / mod_Y ** 2

    def u80(mod_Y):
        return 2.2 / mod_Y - 1.2 / mod_Y ** 2

    data = export_data_set('iris.data') if in_path is None else pd.read_csv(in_path)
    print("-----DATA SET TRAINING---", in_path)
    X = data.iloc[:, :-1].values
    y = data.iloc[:, -1].tolist()
    lda = LinearDiscriminantAnalysis(solver="svd", store_covariance=True)
    mean_u65, mean_u80 = 0, 0
    n_times = len(seeds)
    for k in range(0, n_times):
        X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.4, random_state=seeds[k])
        sum_u65, sum_u80 = 0, 0
        lda.fit(X_train, y_train)
        n, _ = X_test.shape
        for i, test in enumerate(X_test):
            evaluate = lda.predict([test])
            print("-----TESTING-----", i)
            if y_test[i] in evaluate:
                sum_u65 += u65(len(evaluate))
                sum_u80 += u80(len(evaluate))
        print("--k-->", k, sum_u65 / n, sum_u80 / n)
        mean_u65 += sum_u65 / n
        mean_u80 += sum_u80 / n
    print("--->", mean_u65 / n_times, mean_u80 / n_times)

    def test(self):
        iris = datasets.load_iris()
        
        X = iris.data
        y = iris.target
        target_names = iris.target_names
        
        pca = PCA(n_components=3)
        X_r = pca.fit(X).transform(X)
        
        lda = LinearDiscriminantAnalysis(n_components=3)
        X_r2 = lda.fit(X, y).transform(X)
        
        # Percentage of variance explained for each components
        print('explained variance ratio (first two components): %s'
              % str(pca.explained_variance_ratio_))

        fig = plt.figure()
        ax = fig.add_subplot(111, projection='3d')
        for c, i, target_name in zip("rgb", [0, 1, 2], target_names):
            ax.scatter(X_r[y == i, 0], X_r[y == i, 1], zs=X[y == i, 2], c=c, label=target_name)
        plt.legend()
        plt.title('PCA of IRIS dataset')
            
        fig2 = plt.figure()
        ax = fig2.add_subplot(111, projection='3d')
        for c, i, target_name in zip("rgb", [0, 1, 2], target_names):
            ax.scatter(X_r2[y == i, 0], X_r2[y == i, 1], zs=X[y == i, 2], c=c, label=target_name)
        plt.legend()
        plt.title('LDA of IRIS dataset')
            
        plt.show()

class LinearDiscriminantAnalysiscls(object):
    """docstring for ClassName"""
    def __init__(self):
        self.lda_cls = LinearDiscriminantAnalysis()
        self.prediction = None
        self.train_x = None
        self.train_y = None

    def train_model(self, train_x, train_y):
        try:
            self.train_x = train_x
            self.train_y = train_y
            self.lda_cls.fit(train_x, train_y)
        except:
            print(traceback.format_exc())

    def predict(self, test_x):
        try:
            self.test_x = test_x
            self.prediction = self.lda_cls.predict(test_x)
            return self.prediction
        except:
            print(traceback.format_exc())

    def accuracy_score(self, test_y):
        try:
            # return r2_score(test_y, self.prediction)
            return self.lda_cls.score(self.test_x, test_y)
        except:
            print(traceback.format_exc())

def main():
    """Read Train/test log."""
    df = pd.read_csv("train.csv")

    # train/test split using stratified sampling
    labels = df['label']
    df = df.drop(['label'], 1)
    sss = StratifiedShuffleSplit(labels, 10, test_size=0.2, random_state=23)
    for train_index, test_index in sss:
        x_train, x_test = df.values[train_index], df.values[test_index]
        y_train, y_test = labels[train_index], labels[test_index]

    # classification algorithm
    classification(x_train, y_train, x_test, y_test)

    # Predict Test Set
    favorite_clf = LinearDiscriminantAnalysis()
    favorite_clf.fit(x_train, y_train)
    test = pd.read_csv('test.csv')
    test_predictions = favorite_clf.predict(test)
    print test_predictions

    # Format DataFrame
    submission = pd.DataFrame(test_predictions, columns=['Label'])
    submission.tail()
    submission.insert(0, 'ImageId', np.arange(len(test_predictions)) + 1)
    submission.reset_index()
    submission.tail()

    # Export Submission
    submission.to_csv('submission.csv', index=False)
    submission.tail()

def plot_lda(features, labels):
    """
    Input
        features: features to get LDA and plot
        labels: labels of features
    Description
        plots the LDA of features
    """
    lda = LinearDiscriminantAnalysis(n_components=2)
    new_features = lda.fit(chroma[0], chroma[1]).transform(chroma[0])

    colors = list("rgbykrgbyk")
    markers = list("xxxxxooooo")

    plt.figure(len(genres)) # for all together
    for i, genre in enumerate(genres):
        plt.figure(i) # for one particular genre
        plt.scatter(new_features[i*num_songs:(i+1)*num_songs, 0],
                    new_features[i*num_songs:(i+1)*num_songs, 1],
                    c=colors[i], marker=markers[i], label=genre)
        plt.title(genre)

        plt.figure(len(genres)) # for all together
        plt.scatter(new_features[i*num_songs:(i+1)*num_songs, 0],
                    new_features[i*num_songs:(i+1)*num_songs, 1],
                    c=colors[i], marker=markers[i], label=genre)
    plt.legend()
    plt.title('LDA')
    plt.show()

class LinearDiscriminantAnalysisPredictor(PredictorBase):
    '''
    Linear Discriminant Analysis
    '''

    def __init__(self, animal_type):
        self.animal_type = animal_type
        self.clf = LinearDiscriminantAnalysis()

    def fit(self, X_train, y_train):
        self.clf.fit(X_train, y_train)

    def predict(self, X_test):
        predictions = self.clf.predict_proba(X_test)
        predictions_df = self.bundle_predictions(predictions)

        return predictions_df

    def find_best_params(self):
        parameters = {'solver': ['svd', 'lsqr', 'eigen']}
        knn = LinearDiscriminantAnalysis()
        clf = grid_search.GridSearchCV(knn, parameters)
        train_data = get_data('../data/train.csv')
        train_data = select_features(train_data, self.animal_type)
        X = train_data.drop(['OutcomeType'], axis=1)
        y = train_data['OutcomeType']
        clf.fit(X, y)
        print clf.best_params_

def test_lda_orthogonality():
    # arrange four classes with their means in a kite-shaped pattern
    # the longer distance should be transformed to the first component, and
    # the shorter distance to the second component.
    means = np.array([[0, 0, -1], [0, 2, 0], [0, -2, 0], [0, 0, 5]])

    # We construct perfectly symmetric distributions, so the LDA can estimate
    # precise means.
    scatter = np.array([[0.1, 0, 0], [-0.1, 0, 0], [0, 0.1, 0], [0, -0.1, 0],
                        [0, 0, 0.1], [0, 0, -0.1]])

    X = (means[:, np.newaxis, :] + scatter[np.newaxis, :, :]).reshape((-1, 3))
    y = np.repeat(np.arange(means.shape[0]), scatter.shape[0])

    # Fit LDA and transform the means
    clf = LinearDiscriminantAnalysis(solver="svd").fit(X, y)
    means_transformed = clf.transform(means)

    d1 = means_transformed[3] - means_transformed[0]
    d2 = means_transformed[2] - means_transformed[1]
    d1 /= np.sqrt(np.sum(d1 ** 2))
    d2 /= np.sqrt(np.sum(d2 ** 2))

    # the transformed within-class covariance should be the identity matrix
    assert_almost_equal(np.cov(clf.transform(scatter).T), np.eye(2))

    # the means of classes 0 and 3 should lie on the first component
    assert_almost_equal(np.abs(np.dot(d1[:2], [1, 0])), 1.0)

    # the means of classes 1 and 2 should lie on the second component
    assert_almost_equal(np.abs(np.dot(d2[:2], [0, 1])), 1.0)

def test_lda_predict():
    # Test LDA classification.
    # This checks that LDA implements fit and predict and returns correct
    # values for simple toy data.
    for test_case in solver_shrinkage:
        solver, shrinkage = test_case
        clf = LinearDiscriminantAnalysis(solver=solver, shrinkage=shrinkage)
        y_pred = clf.fit(X, y).predict(X)
        assert_array_equal(y_pred, y, "solver %s" % solver)

        # Assert that it works with 1D data
        y_pred1 = clf.fit(X1, y).predict(X1)
        assert_array_equal(y_pred1, y, "solver %s" % solver)

        # Test probability estimates
        y_proba_pred1 = clf.predict_proba(X1)
        assert_array_equal((y_proba_pred1[:, 1] > 0.5) + 1, y, "solver %s" % solver)
        y_log_proba_pred1 = clf.predict_log_proba(X1)
        assert_array_almost_equal(np.exp(y_log_proba_pred1), y_proba_pred1, 8, "solver %s" % solver)

        # Primarily test for commit 2f34950 -- "reuse" of priors
        y_pred3 = clf.fit(X, y3).predict(X)
        # LDA shouldn't be able to separate those
        assert_true(np.any(y_pred3 != y3), "solver %s" % solver)

    # Test invalid shrinkages
    clf = LinearDiscriminantAnalysis(solver="lsqr", shrinkage=-0.2231)
    assert_raises(ValueError, clf.fit, X, y)
    clf = LinearDiscriminantAnalysis(solver="eigen", shrinkage="dummy")
    assert_raises(ValueError, clf.fit, X, y)
    clf = LinearDiscriminantAnalysis(solver="svd", shrinkage="auto")
    assert_raises(NotImplementedError, clf.fit, X, y)
    # Test unknown solver
    clf = LinearDiscriminantAnalysis(solver="dummy")
    assert_raises(ValueError, clf.fit, X, y)

    def tuneSpatialFilters(self):

        print colors.MAGENTA
        num_total_spatial_filters = self.all_spatial_filters.shape[0]

        best_mean = 0
        best_num = 0
        best_score = None

        for i in xrange(num_total_spatial_filters):

            num_filters_to_try = i+1
            print "trying with first",num_filters_to_try,"spatial filters"
            trial_X = self.extractFeatures(self.epochs, self.all_spatial_filters[:num_filters_to_try])
            lda = LinearDiscriminantAnalysis()
            lda = lda.fit(trial_X, self.y)
            cross_validation_folds = 10
            xval = cross_val_score(lda, trial_X, self.y, cv=cross_validation_folds)
            #print xval
            this_mean = xval.mean()
            print "mean",this_mean
            if this_mean > best_mean:
                best_mean = this_mean
                best_num = num_filters_to_try
                best_score = xval

        print "-----------------------------"
        print "best mean was", best_mean, "with", best_num, "filters used"
        print best_score

        print colors.ENDC

def feature_distribute_4_projection(channel_length=4, projection='pca'):
    ''' 六个动作的四个特征组合的2D映射分布，共34个通道  '''
    colors = ['b', 'g', 'r', 'c', 'm', 'y', 'k', 'w']
    markers = ['o', '+', 'v', '^', '*', 'x']
    sample_len = 100
    subjects = ['subject_'+str(i+1) for i in range(2)]          # 受试者
    # subjects = ['subject_1']
    for subject in subjects:
        title_pre = subject + '_feature_class_'

        channel_num = 34                                        # 通道
        # channel_num = 18
        # channel_num = 1
        for channel in range(channel_num):

            feature_list = ['MAV', 'ZC', 'SSC', 'WL']
            # feature_list = ['MAV']

            actions = [i + 1 for i in range(6)]                 # 动作
            # actions = [1, 2]
            fig = plt.figure(figsize=(8, 6))
            ax = fig.add_subplot()
            trains = np.array([])
            targets = np.array([], np.int)
            for action in actions:
                filename = title_pre + str(action)
                feature = np.load(
                    root_path + '/train1_250_100/' + filename + '.npy')
                train = feature[:sample_len, channel * channel_length : channel * channel_length+4]
                target = np.ones(train.shape[0], np.int) * action
                # print train.shape, target.shape, target[0, 0:5]
                trains = np.concatenate((trains, train), axis=None)
                targets = np.concatenate(
                    (targets, target), axis=None)

                # sys.exit(0)
            trains = trains.reshape((-1, 4))
            
            # print trains.shape, targets.shape
            if projection == 'pca':
                pca = PCA(n_components=2)
                X_r = pca.fit(trains).transform(trains)
            elif projection == 'lda':
                lda = LinearDiscriminantAnalysis(n_components=2)
                X_r = lda.fit(trains, targets).transform(trains)

            for action in actions:
                plt.scatter(X_r[targets == action, 0], X_r[targets == action, 1], 
                    c=colors[action], marker=markers[
                    action % 1], alpha=0.5, label=action)
            plt.legend()
            plt.title(subject + '-channel_' + str(channel) + '-' + projection + '-TD4')
            
            # plt.show()
            plt.savefig(
                'result/figure/distribute4_proj/' + subject + '-channel_'
                + str(channel) + '-' + projection + '-TD4',
                dpi=120)
            plt.close()

def plot_lda_only(filename, title, filename_fig):

    df = pd.read_csv(path+filename, names=['x1','x2','y'], header=None)
    fig = plt.figure()
    fig.suptitle(title, fontsize=20)
    columns_ls = []
    for column in df.columns:
        columns_ls.append(column)

    X = df[columns_ls[0:len(columns_ls)-1]].values
    Y = df[columns_ls[len(columns_ls)-1]].values

    clf_lda = LinearDiscriminantAnalysis()
    clf_lda.fit(X, Y)
    w = clf_lda.coef_[0]
    a = -w[0]/w[1]

    xx = np.linspace(-12, 34)
    yy = a*xx-clf_lda.intercept_[0]/w[1]
    plt.plot(xx,yy, color="blue", label ="LDA decision boundary")

    print "Weights W0 %.2f and W1%.2f"%(w[0], w[1])
    plt.text(0, 0, "Y=+1", fontsize=12)
    plt.text(10, -20, "Y=-1", fontsize=12)
    # plt.plot(xx, yy_down, 'k--')
    # plt.plot(xx, yy_up, 'k--')
    # plt.plot(xx,yy,color="black", label ="svm decision boundary")


    plt.xlabel('X1', fontsize=18)
    plt.ylabel('X2', fontsize=16)
    # fig.savefig(filename_fig)
    # model = LogisticRegression()
    # model.fit(X, Y)
    # w = model.coef_[0]
    # a = -w[0]/w[1]
    #
    # xx = np.linspace(-12, 34)
    # yy = a*xx-model.intercept_[0]/w[1]
    #
    # plt.plot(xx,yy, label ="logistic decision boundary")
    #
    # clf_lda = LinearDiscriminantAnalysis()
    # clf_lda.fit(X, Y)
    # w = clf_lda.coef_[0]
    # a = -w[0]/w[1]
    #
    # xx = np.linspace(-12, 34)
    # yy = a*xx-clf_lda.intercept_[0]/w[1]
    # plt.plot(xx,yy, color="blue", label ="LDA decision boundary")

    # plt.scatter(clf.support_vectors_[:, 0], clf.support_vectors_[:, 1],
    #         s=80, color='b')
    plt.scatter(X[:, 0], X[:, 1], c=Y)

    plt.axis('tight')
    plt.legend()

    plt.show()

def Train(enhancedGeneSet, classLabels):
    enhancedGeneSet = np.array(enhancedGeneSet);
    classLabels = np.array(classLabels);
    classifier = LinearDiscriminantAnalysis();
    classifier.fit(enhancedGeneSet, classLabels);
    #del enhancedGeneSet;
    #del classLabels;
    return classifier;

def lda(X, y, n):
	'''
		Returns optimal projection of the data
		LDA with n components
	'''
	selector = LinearDiscriminantAnalysis(n_components=n)
	selector.fit(X, y)
	return selector.transform(X), y