fisher_iris_visualization.py 文件源码

def load_iris():
    try:
        # Load Iris dataset from the sklearn.datasets package
        from sklearn import datasets
        from sklearn import decomposition

        # Load Dataset
        iris = datasets.load_iris()
        X = iris.data
        y = iris.target
        labels = iris.target_names

        # Reduce components by Principal Component Analysis from sklearn
        X = decomposition.PCA(n_components=3).fit_transform(X)
    except ImportError:
        # Load Iris dataset manually
        path = os.path.join('data', 'iris', 'iris.data')
        iris_data = np.genfromtxt(path, dtype='str', delimiter=',')
        X = iris_data[:, :4].astype(dtype=float)
        y = np.ndarray((X.shape[0],), dtype=int)

        # Create target vector y and corresponding labels
        labels, idx = [], 0
        for i, label in enumerate(iris_data[:, 4]):
            label = label.split('-')[1]
            if label not in labels:
                labels.append(label); idx += 1
            y[i] = idx - 1

        # Reduce components by implemented Principal Component Analysis
        X = PCA(X, 3)[0]

    return X, y, labels