Question

试图弄清楚在使用Session训练时如何在随机森林Tensorflow中计算AUC。

尝试了许多类似此处提到的方法：

我认为我无法使用此处显示的代码来遵循上述模式：

# Splitting the dataset into the Training set and Test set

from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split(input_x, input_y, test_size = 0.25, random_state = 0)

data1 = data.iloc[:,:].values


# Parameters
num_steps = 50 # Total steps to train
num_classes = 2 
num_features = 14
num_trees = 10 
max_nodes = 1000 

# Input and Target placeholders 
X = tf.placeholder(tf.float32, shape=[None, num_features])
Y = tf.placeholder(tf.int64, shape=[None])


# Random Forest Parameters
hparams = tensor_forest.ForestHParams(num_classes=num_classes, num_features=num_features, num_trees=num_trees, max_nodes=max_nodes).fill()

# Build the Random Forest
forest_graph = tensor_forest.RandomForestGraphs(hparams)
train_op = forest_graph.training_graph(X, Y)
loss_op = forest_graph.training_loss(X, Y)
infer_op, _, _ = forest_graph.inference_graph(X)

### ACCURACY DEFINITION
correct_prediction = tf.equal(tf.argmax(infer_op, 1), tf.cast(Y, tf.int64))
accuracy_op = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))


### AUC DEFINITION
from sklearn.metrics import roc_auc_score
HELP HERE ? 


### SESSION DEFINITION
init_vars = tf.group(tf.global_variables_initializer(), resources.initialize_resources(resources.shared_resources()))

sess = tf.Session()

# Training here
for i in range(1, num_steps + 1):
    _, l = sess.run([train_op, loss_op], feed_dict={X: X_train, Y: y_train})
    sess.run(tf.local_variables_initializer())


    if i % 50 == 0 or i == 1:

        acc = sess.run(accuracy_op, feed_dict={X: X_train, Y: y_train})
        HELP HERE TO MAKE AUC AVAILABLE TOO?        

        print('Step %i, Loss: %f, Acc: %f' % (i, l, acc))


# EVALUATION
print("Test Accuracy:", sess.run(accuracy_op, feed_dict={X: X_test, Y: y_test}))

HELP HERE TO PRINT AUC?

有人可以帮助我了解如何在此处包括AUC Calc吗？

Answer 1

这就是您需要的：

predictions=pd.DataFrame(model.predict_proba(X_test),columns=model.classes_)
roc_score = roc_auc_score((real_test_class == 'True').astype(float), predictions['True'])

其中real_test_class是保存您的真实类的向量，而projections ['True']是预测数据框中的列，其中包含每个样本的概率是的

Tensorflow模型，随机森林AUC-如何使用会话进行计算？

1 个答案: