Python feature_column.real_valued_column函数代码示例

  def testMixedFeatures(self):
    """Tests SDCALogisticClassifier with a mix of features."""

    def input_fn():
      return {
          'example_id':
              constant_op.constant(['1', '2', '3']),
          'price':
              constant_op.constant([[0.6], [0.8], [0.3]]),
          'sq_footage':
              constant_op.constant([[900.0], [700.0], [600.0]]),
          'country':
              sparse_tensor.SparseTensor(
                  values=['IT', 'US', 'GB'],
                  indices=[[0, 0], [1, 3], [2, 1]],
                  dense_shape=[3, 5]),
          'weights':
              constant_op.constant([[3.0], [1.0], [1.0]])
      }, constant_op.constant([[1], [0], [1]])

    price = feature_column_lib.real_valued_column('price')
    sq_footage_bucket = feature_column_lib.bucketized_column(
        feature_column_lib.real_valued_column('sq_footage'),
        boundaries=[650.0, 800.0])
    country = feature_column_lib.sparse_column_with_hash_bucket(
        'country', hash_bucket_size=5)
    sq_footage_country = feature_column_lib.crossed_column(
        [sq_footage_bucket, country], hash_bucket_size=10)
    classifier = sdca_estimator.SDCALogisticClassifier(
        example_id_column='example_id',
        feature_columns=[price, sq_footage_bucket, country, sq_footage_country],
        weight_column_name='weights')
    classifier.fit(input_fn=input_fn, steps=50)
    metrics = classifier.evaluate(input_fn=input_fn, steps=1)
    self.assertGreater(metrics['accuracy'], 0.9)

  def testRealValuedColumnDensification(self):
    """Tests densification behavior of `RealValuedColumn`."""
    # No default value, dimension 1 float.
    real_valued_column = fc.real_valued_column(
        "sparse_real_valued1", dimension=None)
    sparse_tensor = sparse_tensor_lib.SparseTensor(
        values=[2.0, 5.0], indices=[[0, 0], [2, 0]], dense_shape=[3, 1])
    densified_output = real_valued_column._to_dnn_input_layer(sparse_tensor)

    # With default value, dimension 2 int.
    real_valued_column_with_default = fc.real_valued_column(
        "sparse_real_valued2",
        dimension=None,
        default_value=-1,
        dtype=dtypes.int32)
    sparse_tensor2 = sparse_tensor_lib.SparseTensor(
        values=[2, 5, 9, 0],
        indices=[[0, 0], [1, 1], [2, 0], [2, 1]],
        dense_shape=[3, 2])
    densified_output2 = real_valued_column_with_default._to_dnn_input_layer(
        sparse_tensor2)

    with self.test_session() as sess:
      densified_output_eval, densified_output_eval2 = sess.run(
          [densified_output, densified_output2])
      self.assertAllEqual(densified_output_eval, [[2.0], [0.0], [5.0]])
      self.assertAllEqual(densified_output_eval2, [[2, -1], [-1, 5], [9, 0]])

  def testRealValuedFeaturesWithBigL1Regularization(self):
    """Tests SVM classifier with real valued features and L2 regularization."""

    def input_fn():
      return {
          'example_id': constant_op.constant(['1', '2', '3']),
          'feature1': constant_op.constant([0.5, 1.0, 1.0]),
          'feature2': constant_op.constant([[1.0], [-1.0], [0.5]]),
      }, constant_op.constant([[1], [0], [1]])

    feature1 = feature_column.real_valued_column('feature1')
    feature2 = feature_column.real_valued_column('feature2')
    svm_classifier = svm.SVM(feature_columns=[feature1, feature2],
                             example_id_column='example_id',
                             l1_regularization=3.0,
                             l2_regularization=1.0)
    svm_classifier.fit(input_fn=input_fn, steps=30)
    metrics = svm_classifier.evaluate(input_fn=input_fn, steps=1)
    loss = metrics['loss']
    accuracy = metrics['accuracy']

    # When L1 regularization parameter is large, the loss due to regularization
    # outweights the unregularized loss. In this case, the classifier will favor
    # very small weights (in current case 0) resulting both big unregularized
    # loss and bad accuracy.
    self.assertAlmostEqual(loss, 1.0, places=3)
    self.assertAlmostEqual(accuracy, 1 / 3, places=3)

  def testRealValuedFeaturesWithL2Regularization(self):
    """Tests SVM classifier with real valued features and L2 regularization."""

    def input_fn():
      return {
          'example_id': constant_op.constant(['1', '2', '3']),
          'feature1': constant_op.constant([0.5, 1.0, 1.0]),
          'feature2': constant_op.constant([1.0, -1.0, 0.5]),
      }, constant_op.constant([1, 0, 1])

    feature1 = feature_column.real_valued_column('feature1')
    feature2 = feature_column.real_valued_column('feature2')
    svm_classifier = svm.SVM(feature_columns=[feature1, feature2],
                             example_id_column='example_id',
                             l1_regularization=0.0,
                             l2_regularization=1.0)
    svm_classifier.fit(input_fn=input_fn, steps=30)
    metrics = svm_classifier.evaluate(input_fn=input_fn, steps=1)
    loss = metrics['loss']
    accuracy = metrics['accuracy']
    # The points are in general separable. Also, if there was no regularization,
    # the margin inequalities would be satisfied too (for instance by w1=1.0,
    # w2=5.0). Due to regularization, smaller weights are chosen. This results
    # to a small but non-zero uneregularized loss. Still, all the predictions
    # will be correct resulting to perfect accuracy.
    self.assertLess(loss, 0.1)
    self.assertAlmostEqual(accuracy, 1.0, places=3)

  def testRealValuedFeaturesPerfectlySeparable(self):
    """Tests SVM classifier with real valued features."""

    def input_fn():
      return {
          'example_id': constant_op.constant(['1', '2', '3']),
          'feature1': constant_op.constant([[0.0], [1.0], [3.0]]),
          'feature2': constant_op.constant([[1.0], [-1.2], [1.0]]),
      }, constant_op.constant([[1], [0], [1]])

    feature1 = feature_column.real_valued_column('feature1')
    feature2 = feature_column.real_valued_column('feature2')
    svm_classifier = svm.SVM(feature_columns=[feature1, feature2],
                             example_id_column='example_id',
                             l1_regularization=0.0,
                             l2_regularization=0.0)
    svm_classifier.fit(input_fn=input_fn, steps=30)
    metrics = svm_classifier.evaluate(input_fn=input_fn, steps=1)
    loss = metrics['loss']
    accuracy = metrics['accuracy']
    # The points are not only separable but there exist weights (for instance
    # w1=0.0, w2=1.0) that satisfy the margin inequalities (y_i* w^T*x_i >=1).
    # The unregularized loss should therefore be 0.0.
    self.assertAlmostEqual(loss, 0.0, places=3)
    self.assertAlmostEqual(accuracy, 1.0, places=3)

  def testBucketizedFeatures(self):
    """Tests SDCALogisticClassifier with bucketized features."""

    def input_fn():
      return {
          'example_id': constant_op.constant(['1', '2', '3']),
          'price': constant_op.constant([600.0, 1000.0, 400.0]),
          'sq_footage': constant_op.constant([[1000.0], [600.0], [700.0]]),
          'weights': constant_op.constant([[1.0], [1.0], [1.0]])
      }, constant_op.constant([[1], [0], [1]])

    with self._single_threaded_test_session():
      price_bucket = feature_column_lib.bucketized_column(
          feature_column_lib.real_valued_column('price'),
          boundaries=[500.0, 700.0])
      sq_footage_bucket = feature_column_lib.bucketized_column(
          feature_column_lib.real_valued_column('sq_footage'),
          boundaries=[650.0])
      classifier = sdca_estimator.SDCALogisticClassifier(
          example_id_column='example_id',
          feature_columns=[price_bucket, sq_footage_bucket],
          weight_column_name='weights',
          l2_regularization=1.0)
      classifier.fit(input_fn=input_fn, steps=50)
      metrics = classifier.evaluate(input_fn=input_fn, steps=1)
      self.assertGreater(metrics['accuracy'], 0.9)

  def testPrepareInputsForRnnBatchSize2(self):

    num_unroll = 3

    expected = [
        np.array([[11., 31., 5., 7.], [21., 41., 6., 8.]]),
        np.array([[12., 32., 5., 7.], [22., 42., 6., 8.]]),
        np.array([[13., 33., 5., 7.], [23., 43., 6., 8.]])
    ]

    sequence_features = {
        'seq_feature0':
            constant_op.constant([[11., 12., 13.], [21., 22., 23.]]),
        'seq_feature1':
            constant_op.constant([[31., 32., 33.], [41., 42., 43.]])
    }

    sequence_feature_columns = [
        feature_column.real_valued_column(
            'seq_feature0', dimension=1),
        feature_column.real_valued_column(
            'seq_feature1', dimension=1),
    ]

    context_features = {
        'ctx_feature0': constant_op.constant([[5.], [6.]]),
        'ctx_feature1': constant_op.constant([[7.], [8.]])
    }

    self._test_prepare_inputs_for_rnn(sequence_features, context_features,
                                      sequence_feature_columns, num_unroll,
                                      expected)

  def testBiasAndOtherColumns(self):
    """SDCALinearRegressor has valid bias weight with other columns present."""

    def input_fn():
      """Testing the bias weight when there are other features present.

      1/2 of the instances in this input have feature 'a', the rest have
      feature 'b', and we expect the bias to be added to each instance as well.
      0.4 of all instances that have feature 'a' are positive, and 0.2 of all
      instances that have feature 'b' are positive. The labels in the dataset
      are ordered to appear shuffled since SDCA expects shuffled data, and
      converges faster with this pseudo-random ordering.
      If the bias was centered we would expect the weights to be:
      bias: 0.3
      a: 0.1
      b: -0.1
      Until b/29339026 is resolved, the bias gets regularized with the same
      global value for the other columns, and so the expected weights get
      shifted and are:
      bias: 0.2
      a: 0.2
      b: 0.0
      Returns:
        The test dataset.
      """
      num_examples = 200
      half = int(num_examples / 2)
      return {
          'example_id':
              constant_op.constant([str(x + 1) for x in range(num_examples)]),
          'a':
              constant_op.constant([[1]] * int(half) + [[0]] * int(half)),
          'b':
              constant_op.constant([[0]] * int(half) + [[1]] * int(half)),
      }, constant_op.constant(
          [[x]
           for x in [1, 0, 0, 1, 1, 0, 0, 0, 1, 0] * int(half / 10) +
           [0, 1, 0, 0, 0, 0, 0, 0, 1, 0] * int(half / 10)])

    with self._single_threaded_test_session():
      regressor = sdca_estimator.SDCALinearRegressor(
          example_id_column='example_id',
          feature_columns=[
              feature_column_lib.real_valued_column('a'),
              feature_column_lib.real_valued_column('b')
          ])

      regressor.fit(input_fn=input_fn, steps=200)

      variable_names = regressor.get_variable_names()
      self.assertIn('linear/bias_weight', variable_names)
      self.assertIn('linear/a/weight', variable_names)
      self.assertIn('linear/b/weight', variable_names)
      # TODO(b/29339026): Change the expected results to expect a centered bias.
      self.assertNear(
          regressor.get_variable_value('linear/bias_weight')[0], 0.2, err=0.05)
      self.assertNear(
          regressor.get_variable_value('linear/a/weight')[0], 0.2, err=0.05)
      self.assertNear(
          regressor.get_variable_value('linear/b/weight')[0], 0.0, err=0.05)

  def testRealValuedFeaturesWithMildL1Regularization(self):
    """Tests SVM classifier with real valued features and L2 regularization."""

    def input_fn():
      return {
          'example_id': constant_op.constant(['1', '2', '3']),
          'feature1': constant_op.constant([[0.5], [1.0], [1.0]]),
          'feature2': constant_op.constant([[1.0], [-1.0], [0.5]]),
      }, constant_op.constant([[1], [0], [1]])

    feature1 = feature_column.real_valued_column('feature1')
    feature2 = feature_column.real_valued_column('feature2')
    svm_classifier = svm.SVM(feature_columns=[feature1, feature2],
                             example_id_column='example_id',
                             l1_regularization=0.5,
                             l2_regularization=1.0)
    svm_classifier.fit(input_fn=input_fn, steps=30)
    metrics = svm_classifier.evaluate(input_fn=input_fn, steps=1)
    loss = metrics['loss']
    accuracy = metrics['accuracy']

    # Adding small L1 regularization favors even smaller weights. This results
    # to somewhat moderate unregularized loss (bigger than the one when there is
    # no L1 regularization. Still, since L1 is small, all the predictions will
    # be correct resulting to perfect accuracy.
    self.assertGreater(loss, 0.1)
    self.assertAlmostEqual(accuracy, 1.0, places=3)

  def testMakePlaceHolderTensorsForBaseFeatures(self):
    sparse_col = fc.sparse_column_with_hash_bucket(
        "sparse_column", hash_bucket_size=100)
    real_valued_col = fc.real_valued_column("real_valued_column", 5)
    vlen_real_valued_col = fc.real_valued_column(
        "vlen_real_valued_column", dimension=None)

    bucketized_col = fc.bucketized_column(
        fc.real_valued_column("real_valued_column_for_bucketization"), [0, 4])
    feature_columns = set(
        [sparse_col, real_valued_col, vlen_real_valued_col, bucketized_col])
    placeholders = (
        fc.make_place_holder_tensors_for_base_features(feature_columns))

    self.assertEqual(4, len(placeholders))
    self.assertTrue(
        isinstance(placeholders["sparse_column"],
                   sparse_tensor_lib.SparseTensor))
    self.assertTrue(
        isinstance(placeholders["vlen_real_valued_column"],
                   sparse_tensor_lib.SparseTensor))
    placeholder = placeholders["real_valued_column"]
    self.assertGreaterEqual(
        placeholder.name.find(u"Placeholder_real_valued_column"), 0)
    self.assertEqual(dtypes.float32, placeholder.dtype)
    self.assertEqual([None, 5], placeholder.get_shape().as_list())
    placeholder = placeholders["real_valued_column_for_bucketization"]
    self.assertGreaterEqual(
        placeholder.name.find(
            u"Placeholder_real_valued_column_for_bucketization"), 0)
    self.assertEqual(dtypes.float32, placeholder.dtype)
    self.assertEqual([None, 1], placeholder.get_shape().as_list())

  def testRealValuedColumnDtypes(self):
    rvc = fc.real_valued_column("rvc")
    self.assertDictEqual({
        "rvc": parsing_ops.FixedLenFeature([1], dtype=dtypes.float32)
    }, rvc.config)

    rvc = fc.real_valued_column("rvc", dtype=dtypes.int32)
    self.assertDictEqual({
        "rvc": parsing_ops.FixedLenFeature([1], dtype=dtypes.int32)
    }, rvc.config)

    with self.assertRaisesRegexp(ValueError,
                                 "dtype must be convertible to float"):
      fc.real_valued_column("rvc", dtype=dtypes.string)

  def testCreateSequenceFeatureSpec(self):
    sparse_col = fc.sparse_column_with_hash_bucket(
        "sparse_column", hash_bucket_size=100)
    embedding_col = fc.embedding_column(
        fc.sparse_column_with_hash_bucket(
            "sparse_column_for_embedding", hash_bucket_size=10),
        dimension=4)
    sparse_id_col = fc.sparse_column_with_keys("id_column",
                                               ["marlo", "omar", "stringer"])
    weighted_id_col = fc.weighted_sparse_column(sparse_id_col,
                                                "id_weights_column")
    real_valued_col1 = fc.real_valued_column("real_valued_column", dimension=2)
    real_valued_col2 = fc.real_valued_column(
        "real_valued_default_column", dimension=5, default_value=3.0)
    real_valued_col3 = fc._real_valued_var_len_column(
        "real_valued_var_len_column", default_value=3.0, is_sparse=True)
    real_valued_col4 = fc._real_valued_var_len_column(
        "real_valued_var_len_dense_column", default_value=4.0, is_sparse=False)

    feature_columns = set([
        sparse_col, embedding_col, weighted_id_col, real_valued_col1,
        real_valued_col2, real_valued_col3, real_valued_col4
    ])

    feature_spec = fc._create_sequence_feature_spec_for_parsing(feature_columns)

    expected_feature_spec = {
        "sparse_column":
            parsing_ops.VarLenFeature(dtypes.string),
        "sparse_column_for_embedding":
            parsing_ops.VarLenFeature(dtypes.string),
        "id_column":
            parsing_ops.VarLenFeature(dtypes.string),
        "id_weights_column":
            parsing_ops.VarLenFeature(dtypes.float32),
        "real_valued_column":
            parsing_ops.FixedLenSequenceFeature(
                shape=[2], dtype=dtypes.float32, allow_missing=False),
        "real_valued_default_column":
            parsing_ops.FixedLenSequenceFeature(
                shape=[5], dtype=dtypes.float32, allow_missing=True),
        "real_valued_var_len_column":
            parsing_ops.VarLenFeature(dtype=dtypes.float32),
        "real_valued_var_len_dense_column":
            parsing_ops.FixedLenSequenceFeature(
                shape=[], dtype=dtypes.float32, allow_missing=True,
                default_value=4.0),
    }

    self.assertDictEqual(expected_feature_spec, feature_spec)

  def testBiasAndOtherColumnsFabricatedCentered(self):
    """SDCALinearRegressor has valid bias weight when instances are centered."""

    def input_fn():
      """Testing the bias weight when there are other features present.

      1/2 of the instances in this input have feature 'a', the rest have
      feature 'b', and we expect the bias to be added to each instance as well.
      0.1 of all instances that have feature 'a' have a label of 1, and 0.1 of
      all instances that have feature 'b' have a label of -1.
      We can expect the weights to be:
      bias: 0.0
      a: 0.1
      b: -0.1
      Returns:
        The test dataset.
      """
      num_examples = 200
      half = int(num_examples / 2)
      return {
          'example_id':
              constant_op.constant([str(x + 1) for x in range(num_examples)]),
          'a':
              constant_op.constant([[1]] * int(half) + [[0]] * int(half)),
          'b':
              constant_op.constant([[0]] * int(half) + [[1]] * int(half)),
      }, constant_op.constant([[1 if x % 10 == 0 else 0] for x in range(half)] +
                              [[-1 if x % 10 == 0 else 0] for x in range(half)])

    with self._single_threaded_test_session():
      regressor = sdca_estimator.SDCALinearRegressor(
          example_id_column='example_id',
          feature_columns=[
              feature_column_lib.real_valued_column('a'),
              feature_column_lib.real_valued_column('b')
          ])

      regressor.fit(input_fn=input_fn, steps=100)

      variable_names = regressor.get_variable_names()
      self.assertIn('linear/bias_weight', variable_names)
      self.assertIn('linear/a/weight', variable_names)
      self.assertIn('linear/b/weight', variable_names)
      self.assertNear(
          regressor.get_variable_value('linear/bias_weight')[0], 0.0, err=0.05)
      self.assertNear(
          regressor.get_variable_value('linear/a/weight')[0], 0.1, err=0.05)
      self.assertNear(
          regressor.get_variable_value('linear/b/weight')[0], -0.1, err=0.05)

 def _getModelFnOpsForMode(self, mode):
   """Helper for testGetRnnModelFn{Train,Eval,Infer}()."""
   num_units = [4]
   seq_columns = [
       feature_column.real_valued_column(
           'inputs', dimension=1)
   ]
   features = {
       'inputs': constant_op.constant([1., 2., 3.]),
   }
   labels = constant_op.constant([1., 0., 1.])
   model_fn = ssre._get_rnn_model_fn(
       cell_type='basic_rnn',
       target_column=target_column_lib.multi_class_target(n_classes=2),
       optimizer='SGD',
       num_unroll=2,
       num_units=num_units,
       num_threads=1,
       queue_capacity=10,
       batch_size=1,
       # Only CLASSIFICATION yields eval metrics to test for.
       problem_type=constants.ProblemType.CLASSIFICATION,
       sequence_feature_columns=seq_columns,
       context_feature_columns=None,
       learning_rate=0.1)
   model_fn_ops = model_fn(features=features, labels=labels, mode=mode)
   return model_fn_ops

  def testMultiDimensionalRealValuedFeaturesWithL2Regularization(self):
    """Tests SVM with multi-dimensional real features and L2 regularization."""

    # This is identical to the one in testRealValuedFeaturesWithL2Regularization
    # where 2 tensors (dense features) of shape [3, 1] have been replaced by a
    # single tensor (dense feature) of shape [3, 2].
    def input_fn():
      return {
          'example_id':
              constant_op.constant(['1', '2', '3']),
          'multi_dim_feature':
              constant_op.constant([[0.5, 1.0], [1.0, -1.0], [1.0, 0.5]]),
      }, constant_op.constant([[1], [0], [1]])

    multi_dim_feature = feature_column.real_valued_column(
        'multi_dim_feature', dimension=2)
    svm_classifier = svm.SVM(feature_columns=[multi_dim_feature],
                             example_id_column='example_id',
                             l1_regularization=0.0,
                             l2_regularization=1.0)
    svm_classifier.fit(input_fn=input_fn, steps=30)
    metrics = svm_classifier.evaluate(input_fn=input_fn, steps=1)
    loss = metrics['loss']
    accuracy = metrics['accuracy']
    self.assertLess(loss, 0.1)
    self.assertAlmostEqual(accuracy, 1.0, places=3)