如何在 Python 中使用 Keras 的 scikit-learn 评估指标函数？

Question

Keras 提供了定义自定义评估指标的可能性——我对 F 指标的变体很感兴趣，例如F1、F2 等由 scikit learn 提供——但指示我们通过调用在这方面受到限制的 Keras 后端函数来执行此操作。

我的目标是将这些指标与 Keras 的早期停止方法结合使用。所以我应该找到一种方法将指标与 Keras 模型的学习过程相结合。（当然，在 learning/fitting 过程之外，我可以简单地用结果调用 Scikit-Learn）。

我有哪些选择？

更新

使用来自 Kaggle 的 titanic_all_numeric 数据集实施 Aaron 的解决方案后，我得到以下信息：

# Compile the model
model.compile(optimizer = 'adam', loss = 'categorical_crossentropy', metrics = ['accuracy', f1])

# Fit the model
hist = model.fit(predictors, target, validation_split = 0.3)

Train on 623 samples, validate on 268 samples
Epoch 1/1
623/623 [==============================] - 0s 642us/step - loss: 0.8037 - acc: 0.6132 - f1: 0.6132 - val_loss: 0.5815 - val_acc: 0.7537 - val_f1: 0.7537

# Compile the model
model.compile(optimizer = 'adam', loss = 'categorical_crossentropy', metrics = ['accuracy'])

# Fit the model
hist = model.fit(predictors, target, validation_split = 0.3)

Train on 623 samples, validate on 268 samples
Epoch 1/1
623/623 [==============================] - 0s 658us/step - loss: 0.8148 - acc: 0.6404 - val_loss: 0.7056 - val_acc: 0.7313

# Compile the model
model.compile(optimizer = 'adam', loss = 'categorical_crossentropy', metrics = [f1])

# Fit the model
hist = model.fit(predictors, target, validation_split = 0.3)

Train on 623 samples, validate on 268 samples
Epoch 1/1
623/623 [==============================] - 0s 690us/step - loss: 0.6554 - f1: 0.6709 - val_loss: 0.5107 - val_f1: 0.7612

我想知道这些结果是否合适。一次，准确率和f1分数是一样的。

Answer 1

您可以将您的预测和标签从您的 keras 模型传递到任何 scikit-learn 函数以进行评估。例如，如果您正在处理分类问题，您可以利用 scikit-learn 中的 classification_report，它提供诸如精度、召回率、f1 分数等指标，例如（示例代码直接取自他们的文档）：

from sklearn.metrics import classification_report
y_true = [0, 1, 2, 2, 2]
y_pred = [0, 0, 2, 2, 1]
target_names = ['class 0', 'class 1', 'class 2']
print(classification_report(y_true, y_pred, target_names=target_names))

          precision    recall  f1-score   support

 class 0       0.50      1.00      0.67         1
 class 1       0.00      0.00      0.00         1
 class 2       1.00      0.67      0.80         3

 micro avg     0.60      0.60      0.60         5
 macro avg     0.50      0.56      0.49         5
 weighted avg  0.70      0.60      0.61         5

更新：如果您想将指标纳入 keras 培训中，请使用：

from keras import backend as K

def f1(y_true, y_pred):
    def recall(y_true, y_pred):
        """Recall metric.

        Only computes a batch-wise average of recall.

        Computes the recall, a metric for multi-label classification of
        how many relevant items are selected.
        """
        true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))
        possible_positives = K.sum(K.round(K.clip(y_true, 0, 1)))
        recall = true_positives / (possible_positives + K.epsilon())
        return recall

    def precision(y_true, y_pred):
        """Precision metric.

        Only computes a batch-wise average of precision.

        Computes the precision, a metric for multi-label classification of
        how many selected items are relevant.
        """
        true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))
        predicted_positives = K.sum(K.round(K.clip(y_pred, 0, 1)))
        precision = true_positives / (predicted_positives + K.epsilon())
        return precision
    precision = precision(y_true, y_pred)
    recall = recall(y_true, y_pred)
    return 2*((precision*recall)/(precision+recall+K.epsilon()))


model.compile(loss='binary_crossentropy',
          optimizer= "adam",
          metrics=[f1])

如何在 Python 中使用 Keras 的 scikit-learn 评估指标函数？

How to employ the scikit-learn evaluation metrics functions with Keras in Python?

python-3.x

scikit-learn

keras

metrics

evaluation

更新