spam.py 文件源码

def testDNN():

  # copied from quick start sample code https://www.tensorflow.org/get_started/tflearn

  # Load datasets.
  training_set = tf.contrib.learn.datasets.base.load_csv_with_header(
      filename='training.csv',
      target_dtype=np.int8,
      features_dtype=np.int8)
  test_set = tf.contrib.learn.datasets.base.load_csv_with_header(
      filename='testset.csv',
      target_dtype=np.int8,
      features_dtype=np.int8)

  feature_columns = [tf.contrib.layers.real_valued_column("", dtype=tf.int8, dimension=1000)]

  classifier = tf.contrib.learn.DNNClassifier(feature_columns=feature_columns,
                                              hidden_units=[10],
                                              n_classes=2,
                                              model_dir="/tmp/spammodel3")
  # Define the training inputs
  def get_train_inputs():
    x = tf.constant(training_set.data)
    y = tf.constant(training_set.target)

    return x, y

  # Fit model.
  classifier.fit(input_fn=get_train_inputs, steps=2000)

  # Define the test inputs
  def get_test_inputs():
    x = tf.constant(test_set.data)
    y = tf.constant(test_set.target)

    return x, y

  # Evaluate accuracy.
  score = classifier.evaluate(input_fn=get_test_inputs,
                                       steps=1)

  print("\nTest Accuracy: {0:f}\n".format(score["accuracy"]))

  for key in score:
    print(key, score[key])

  # Test Accuracy: 0.981333

  # accuracy/baseline_label_mean 0.0233333
  # loss 0.0698425
  # auc 0.892803
  # global_step 4000
  # accuracy/threshold_0.500000_mean 0.981333
  # recall/positive_threshold_0.500000_mean 0.257143
  # labels/prediction_mean 0.0196873
  # accuracy 0.981333
  # precision/positive_threshold_0.500000_mean 0.818182
  # labels/actual_label_mean 0.0233333