使用 GridSearchCV 的逻辑回归

Question

我正在尝试找出如何将线性回归与 GridSearchCV 一起使用，但我得到了一个严重的错误，我不知道这是不是 GridSearchCV 的估计器不正确的问题，或者这是我的“LogisticRegression” " 设置不正确。我让它适用于随机森林和 knn，但我坚持使用这个实现。

我使用一个小数据集，这就是我想使用 liblinear 的原因（即使它是默认情况下，如文档中所述）。

tuned_parameters = {'C': [0.1, 0.5, 1, 5, 10, 50, 100]}
clf = GridSearchCV(LogisticRegression(solver='liblinear'), tuned_parameters, cv=5, scoring="accuracy")
clf.fit(X_train, y_train)

和错误：

StratifiedShuffleSplit(n_splits=1, random_state=0, test_size=0.4,
            train_size=None)

Traceback (most recent call last):

  File "linearRegression.py", line 105, in <module>
    clf.fit(X_train, y_train)

  File "/usr/local/lib/python2.7/dist-packages/sklearn/model_selection/_search.py", line 945, in fit
    return self._fit(X, y, groups, ParameterGrid(self.param_grid))

  File "/usr/local/lib/python2.7/dist-packages/sklearn/model_selection/_search.py", line 564, in _fit
    for parameters in parameter_iterable

  File "/usr/local/lib/python2.7/dist-packages/sklearn/externals/joblib/parallel.py", line 758, in __call__
    while self.dispatch_one_batch(iterator):

  File "/usr/local/lib/python2.7/dist-packages/sklearn/externals/joblib/parallel.py", line 608, in dispatch_one_batch
    self._dispatch(tasks)

  File "/usr/local/lib/python2.7/dist-packages/sklearn/externals/joblib/parallel.py", line 571, in _dispatch
    job = self._backend.apply_async(batch, callback=cb)

  File "/usr/local/lib/python2.7/dist-packages/sklearn/externals/joblib/_parallel_backends.py", line 109, in apply_async

result = ImmediateResult(func)

  File "/usr/local/lib/python2.7/dist-packages/sklearn/externals/joblib/_parallel_backends.py", line 326, in __init__

self.results = batch()

  File "/usr/local/lib/python2.7/dist-packages/sklearn/externals/joblib/parallel.py", line 131, in __call__

return [func(*args, **kwargs) for func, args, kwargs in self.items]

  File "/usr/local/lib/python2.7/dist-packages/sklearn/model_selection/_validation.py", line 260, in _fit_and_score

test_score = _score(estimator, X_test, y_test, scorer)

  File "/usr/local/lib/python2.7/dist-packages/sklearn/model_selection/_validation.py", line 288, in _score

score = scorer(estimator, X_test, y_test)

  File "/usr/local/lib/python2.7/dist-packages/sklearn/metrics/scorer.py", line 91, in __call__

y_pred = estimator.predict(X)

  File "/usr/local/lib/python2.7/dist-packages/sklearn/linear_model/base.py", line 336, in predict

scores = self.decision_function(X)

  File "/usr/local/lib/python2.7/dist-packages/sklearn/linear_model/base.py", line 320, in decision_function

dense_output=True) + self.intercept_

  File "/usr/local/lib/python2.7/dist-packages/sklearn/utils/extmath.py", line 189, in safe_sparse_dot

return fast_dot(a, b)

TypeError: Cannot cast array data from dtype([('f0', 'f8'), ('f1','f8')]) to dtype('float64') according to the rule 'safe'

我阅读了文档： http://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html

和

http://scikit-learn.org/stable/modules/generated/sklearn.model_selection.GridSearchCV.html#sklearn.model_selection.GridSearchCV

感谢您的帮助。

编辑： X 和 Y 的形状：

X = np.array(Xlist,np.dtype('float,float')) #-> 两个浮点数作为特征 y = np.array(ylist,np.dtype('int')) #-> 标签 0 或 1

示例： X_train 是

[[(0.0, 0.0) (3.85, 0.0)] [(3.6, 0.0) (2.45, 0.0)] [(1.1, 0.0) (1.35, 0.0)] [(3.7, 0.0) (1.85, 0.0)]]

Y_train 是

[1 0 0 0 1 0 1 1]

Answer 1

好的，我的一个朋友解决了它：

我正在使用：

X = np.array(Xlist,np.dtype('float,float'))
y = np.array(ylist,np.dtype('int'))

即使使用这些分类器，它也不能很好地使用这个估计器：

SVC(kernel='rbf'), SVC(kernel='linear'), SVC(kernel='poly'), NeighborsClassifier(), DecisionTreeClassifier(), RandomForestClassifier()

所以我只是将这两行替换为：

X = np.asarray(Xlist)
y = np.asarray(ylist)

Answer 2

您输入的 X 数据集可能是元组列表：(A,B)，而不是数组列表：[A,B]？

我能够使用 scikit-learn==0.18.1 运行以下代码：

## Libraries
from sklearn.model_selection import train_test_split 
from sklearn.model_selection import GridSearchCV
from sklearn.linear_model import LogisticRegression

X = [[0.0, 0.0], [3.85, 0.0], [3.6, 0.0], [2.45, 0.0], [1.1, 0.0], [1.35, 0.0], [3.7, 0.0], [1.85, 0.0]]
y = [1, 0, 0, 0, 1, 0, 1, 1]

X_train, X_test, y_train, y_test = train_test_split(X, y, stratify=y, test_size=0.33, random_state=42)

tuned_parameters = {'C': [0.1, 0.5, 1, 5, 10, 50, 100]}
clf = GridSearchCV(LogisticRegression(solver='liblinear'), tuned_parameters, cv=3, scoring="accuracy")
clf.fit(X_train, y_train)

注意：我不得不减少 GridSearchCV 的 cv 属性，因为没有足够大的数据集来分成 5 个部分。