python - 在 Scikit-Learn 中设置多个算法试验时遇到问题

Question

我正在尝试使用this sklearn 文档中的示例。我不太确定代码在做什么，尽管我假设我以错误的方式输入数据集，但我最近收到了此错误:

<ipython-input-26-3c3c0763766b> in <module>()
     49 for ds in datasets:
     50     # preprocess dataset, split into training and test part
---> 51     X, y = ds
     52     X = StandardScaler().fit_transform(X)
     53     X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=.4)

ValueError:太多值无法解压关于如何修改代码以处理我的数据集(这是来自 pandas 数据帧的多维 numpy 数组)并修复错误，有什么想法吗？

dataURL = "peridotites_clean_complete.csv"
pd_data = pd.read_csv(dataURL)
rock_names =  pd_data['ROCK NAME']
rock_compositions = pd_data.columns[1:]
rock_data = np.vstack([pd_data[x] for x in rock_compositions])

classifiers = [
    KNeighborsClassifier(3),
    SVC(kernel="linear", C=0.025),
    SVC(gamma=2, C=1),
    DecisionTreeClassifier(max_depth=5),
    RandomForestClassifier(max_depth=5, n_estimators=10, max_features=1),
    AdaBoostClassifier(),
    GaussianNB(),
    LDA(),
    QDA()]

X, y = make_classification(n_features=2, n_redundant=0, n_informative=2,
                           random_state=1, n_clusters_per_class=1)
rng = np.random.RandomState(2)
X += 2 * rng.uniform(size=X.shape)
linearly_separable = (X, y)

datasets = [rock_data]

figure = plt.figure(figsize=(27, 9))
i = 1
# iterate over datasets
for ds in datasets:
    # preprocess dataset, split into training and test part
    X, y = ds
    X = StandardScaler().fit_transform(X)
    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=.4)

    x_min, x_max = X[:, 0].min() - .5, X[:, 0].max() + .5
    y_min, y_max = X[:, 1].min() - .5, X[:, 1].max() + .5
    xx, yy = np.meshgrid(np.arange(x_min, x_max, h),
                         np.arange(y_min, y_max, h))

    # just plot the dataset first
    cm = plt.cm.RdBu
    cm_bright = ListedColormap(['#FF0000', '#0000FF'])
    ax = plt.subplot(len(datasets), len(classifiers) + 1, i)
    # Plot the training points
    ax.scatter(X_train[:, 0], X_train[:, 1], c=y_train, cmap=cm_bright)
    # and testing points
    ax.scatter(X_test[:, 0], X_test[:, 1], c=y_test, cmap=cm_bright, alpha=0.6)
    ax.set_xlim(xx.min(), xx.max())
    ax.set_ylim(yy.min(), yy.max())
    ax.set_xticks(())
    ax.set_yticks(())
    i += 1

    # iterate over classifiers
    for name, clf in zip(names, classifiers):
        ax = plt.subplot(len(datasets), len(classifiers) + 1, i)
        clf.fit(X_train, y_train)
        score = clf.score(X_test, y_test)

        # Plot the decision boundary. For that, we will assign a color to each
        # point in the mesh [x_min, m_max]x[y_min, y_max].
        if hasattr(clf, "decision_function"):
            Z = clf.decision_function(np.c_[xx.ravel(), yy.ravel()])
        else:
            Z = clf.predict_proba(np.c_[xx.ravel(), yy.ravel()])[:, 1]

        # Put the result into a color plot
        Z = Z.reshape(xx.shape)
        ax.contourf(xx, yy, Z, cmap=cm, alpha=.8)

        # Plot also the training points
        ax.scatter(X_train[:, 0], X_train[:, 1], c=y_train, cmap=cm_bright)
        # and testing points
        ax.scatter(X_test[:, 0], X_test[:, 1], c=y_test, cmap=cm_bright,
                   alpha=0.6)

        ax.set_xlim(xx.min(), xx.max())
        ax.set_ylim(yy.min(), yy.max())
        ax.set_xticks(())
        ax.set_yticks(())
        ax.set_title(name)
        ax.text(xx.max() - .3, yy.min() + .3, ('%.2f' % score).lstrip('0'),
                size=15, horizontalalignment='right')
        i += 1

figure.subplots_adjust(left=.02, right=.98)
plt.show()

Answer 1

问题是 ds 是一个包含两个以上值的列表，如下所示:

>>> ds=['rockatr1','rockatr2','rockatr','rocktype']
>>> X,y=ds
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
ValueError: too many values to unpack

您必须指定哪个部分是X，哪个部分是y，如下所示。通常在分类数据中，最后一列用作标签，这就是我在这里假设的。

>>> X,y=ds[:-1],ds[-1]
>>> X
['rockatr1', 'rockatr2', 'rockatr']
>>> y
'rocktype'