Python feature_column.bucketized_column函数代码示例

  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 testBucketizedColumnRequiresRealValuedColumn(self):
   with self.assertRaisesRegexp(
       TypeError, "source_column must be an instance of _RealValuedColumn"):
     fc.bucketized_column("bbb", [0])
   with self.assertRaisesRegexp(
       TypeError, "source_column must be an instance of _RealValuedColumn"):
     fc.bucketized_column(
         fc.sparse_column_with_integerized_feature(
             column_name="bbb", bucket_size=10), [0])

  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 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 testCrossedColumnNameCreatesSortedNames(self):
    a = fc.sparse_column_with_hash_bucket("aaa", hash_bucket_size=100)
    b = fc.sparse_column_with_hash_bucket("bbb", hash_bucket_size=100)
    bucket = fc.bucketized_column(fc.real_valued_column("cost"), [0, 4])
    crossed = fc.crossed_column(set([b, bucket, a]), hash_bucket_size=10000)

    self.assertEqual("aaa_X_bbb_X_cost_bucketized", crossed.name,
                     "name should be generated by sorted column names")
    self.assertEqual("aaa", crossed.columns[0].name)
    self.assertEqual("bbb", crossed.columns[1].name)
    self.assertEqual("cost_bucketized", crossed.columns[2].name)

  def testBucketizedColumnDeepCopy(self):
    """Tests that we can do a deepcopy of a bucketized column.

    This test requires that the bucketized column also accept boundaries
    as tuples.
    """
    bucketized = fc.bucketized_column(
        fc.real_valued_column("a"), [1., 2., 2., 3., 3.])
    self.assertEqual(bucketized.name, "a_bucketized")
    self.assertTupleEqual(bucketized.boundaries, (1., 2., 3.))
    bucketized_copy = copy.deepcopy(bucketized)
    self.assertEqual(bucketized_copy.name, "a_bucketized")
    self.assertTupleEqual(bucketized_copy.boundaries, (1., 2., 3.))

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

    def input_fn():
      return {
          'example_id': constant_op.constant(['1', '2', '3']),
          'price': constant_op.constant([[600.0], [800.0], [400.0]]),
          'sq_footage': constant_op.constant([[1000.0], [800.0], [500.0]]),
          'weights': constant_op.constant([[1.0], [1.0], [1.0]])
      }, constant_op.constant([[1], [0], [1]])

    price_bucket = feature_column.bucketized_column(
        feature_column.real_valued_column('price'), boundaries=[500.0, 700.0])
    sq_footage_bucket = feature_column.bucketized_column(
        feature_column.real_valued_column('sq_footage'), boundaries=[650.0])

    svm_classifier = svm.SVM(feature_columns=[price_bucket, sq_footage_bucket],
                             example_id_column='example_id',
                             l1_regularization=0.1,
                             l2_regularization=1.0)
    svm_classifier.fit(input_fn=input_fn, steps=30)
    accuracy = svm_classifier.evaluate(input_fn=input_fn, steps=1)['accuracy']
    self.assertAlmostEqual(accuracy, 1.0, places=3)

  def benchmarkTensorData(self):

    def _input_fn():
      iris = test_data.prepare_iris_data_for_logistic_regression()
      features = {}
      for i in range(4):
        # The following shows how to provide the Tensor data for
        # RealValuedColumns.
        features.update({
            str(i):
                array_ops.reshape(
                    constant_op.constant(
                        iris.data[:, i], dtype=dtypes.float32), (-1, 1))
        })
      # The following shows how to provide the SparseTensor data for
      # a SparseColumn.
      features['dummy_sparse_column'] = sparse_tensor.SparseTensor(
          values=('en', 'fr', 'zh'),
          indices=((0, 0), (0, 1), (60, 0)),
          dense_shape=(len(iris.target), 2))
      labels = array_ops.reshape(
          constant_op.constant(
              iris.target, dtype=dtypes.int32), (-1, 1))
      return features, labels

    iris = test_data.prepare_iris_data_for_logistic_regression()
    cont_features = [
        feature_column.real_valued_column(str(i)) for i in range(4)
    ]
    linear_features = [
        feature_column.bucketized_column(
            cont_features[i],
            test_data.get_quantile_based_buckets(iris.data[:, i], 10))
        for i in range(4)
    ]
    linear_features.append(
        feature_column.sparse_column_with_hash_bucket(
            'dummy_sparse_column', hash_bucket_size=100))

    classifier = dnn_linear_combined.DNNLinearCombinedClassifier(
        model_dir=tempfile.mkdtemp(),
        linear_feature_columns=linear_features,
        dnn_feature_columns=cont_features,
        dnn_hidden_units=(3, 3))

    metrics = classifier.fit(input_fn=_input_fn, steps=_ITERS).evaluate(
        input_fn=_input_fn, steps=100)
    self._assertSingleClassMetrics(metrics)

  def benchmarkMultiClass(self):
    iris = base.load_iris()
    cont_feature = feature_column.real_valued_column('feature', dimension=4)
    bucketized_feature = feature_column.bucketized_column(
        cont_feature, test_data.get_quantile_based_buckets(iris.data, 10))

    classifier = dnn_linear_combined.DNNLinearCombinedClassifier(
        n_classes=3,
        linear_feature_columns=(bucketized_feature,),
        dnn_feature_columns=(cont_feature,),
        dnn_hidden_units=(3, 3))

    input_fn = test_data.iris_input_multiclass_fn
    metrics = classifier.fit(input_fn=input_fn, steps=_ITERS).evaluate(
        input_fn=input_fn, steps=100)
    self._assertCommonMetrics(metrics)

  def benchmarkMatrixData(self):
    iris = test_data.prepare_iris_data_for_logistic_regression()
    cont_feature = feature_column.real_valued_column('feature', dimension=4)
    bucketized_feature = feature_column.bucketized_column(
        cont_feature, test_data.get_quantile_based_buckets(iris.data, 10))

    classifier = dnn_linear_combined.DNNLinearCombinedClassifier(
        model_dir=tempfile.mkdtemp(),
        linear_feature_columns=(bucketized_feature,),
        dnn_feature_columns=(cont_feature,),
        dnn_hidden_units=(3, 3))

    input_fn = test_data.iris_input_logistic_fn
    metrics = classifier.fit(input_fn=input_fn, steps=_ITERS).evaluate(
        input_fn=input_fn, steps=100)
    self._assertSingleClassMetrics(metrics)

  def test_make_parsing_export_strategy(self):
    """Only tests that an ExportStrategy instance is created."""
    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)
    real_valued_col1 = fc.real_valued_column("real_valued_column1")
    bucketized_col1 = fc.bucketized_column(
        fc.real_valued_column("real_valued_column_for_bucketization1"), [0, 4])
    feature_columns = [sparse_col, embedding_col, real_valued_col1,
                       bucketized_col1]

    export_strategy = saved_model_export_utils.make_parsing_export_strategy(
        feature_columns=feature_columns)
    self.assertTrue(
        isinstance(export_strategy, export_strategy_lib.ExportStrategy))

  def testMixedFeaturesArbitraryWeightsPartitioned(self):
    """Tests SDCALinearRegressor works with a mix of features (partitioned)."""

    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], [5.0], [7.0]])
      }, constant_op.constant([[1.55], [-1.25], [-3.0]])

    with self._single_threaded_test_session():
      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)
      regressor = sdca_estimator.SDCALinearRegressor(
          example_id_column='example_id',
          feature_columns=[
              price, sq_footage_bucket, country, sq_footage_country
          ],
          l2_regularization=1.0,
          weight_column_name='weights',
          partitioner=partitioned_variables.fixed_size_partitioner(
              num_shards=2, axis=0))
      regressor.fit(input_fn=input_fn, steps=20)
      loss = regressor.evaluate(input_fn=input_fn, steps=1)['loss']
      self.assertLess(loss, 0.05)

  def testMixedFeatures(self):
    """Tests SVM classifier 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.real_valued_column('price')
    sq_footage_bucket = feature_column.bucketized_column(
        feature_column.real_valued_column('sq_footage'),
        boundaries=[650.0, 800.0])
    country = feature_column.sparse_column_with_hash_bucket(
        'country', hash_bucket_size=5)
    sq_footage_country = feature_column.crossed_column(
        [sq_footage_bucket, country], hash_bucket_size=10)
    svm_classifier = svm.SVM(
        feature_columns=[price, sq_footage_bucket, country, sq_footage_country],
        example_id_column='example_id',
        weight_column_name='weights',
        l1_regularization=0.1,
        l2_regularization=1.0)

    svm_classifier.fit(input_fn=input_fn, steps=30)
    accuracy = svm_classifier.evaluate(input_fn=input_fn, steps=1)['accuracy']
    self.assertAlmostEqual(accuracy, 1.0, places=3)

  def testCreateFeatureSpec(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_column1")
    real_valued_col2 = fc.real_valued_column("real_valued_column2", 5)
    real_valued_col3 = fc.real_valued_column(
        "real_valued_column3", dimension=None)
    bucketized_col1 = fc.bucketized_column(
        fc.real_valued_column("real_valued_column_for_bucketization1"), [0, 4])
    bucketized_col2 = fc.bucketized_column(
        fc.real_valued_column("real_valued_column_for_bucketization2", 4),
        [0, 4])
    a = fc.sparse_column_with_hash_bucket("cross_aaa", hash_bucket_size=100)
    b = fc.sparse_column_with_hash_bucket("cross_bbb", hash_bucket_size=100)
    cross_col = fc.crossed_column(set([a, b]), hash_bucket_size=10000)
    feature_columns = set([
        sparse_col, embedding_col, weighted_id_col, real_valued_col1,
        real_valued_col2, real_valued_col3, bucketized_col1, bucketized_col2,
        cross_col
    ])
    expected_config = {
        "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_column1":
            parsing_ops.FixedLenFeature(
                [1], dtype=dtypes.float32),
        "real_valued_column2":
            parsing_ops.FixedLenFeature(
                [5], dtype=dtypes.float32),
        "real_valued_column3":
            parsing_ops.VarLenFeature(dtype=dtypes.float32),
        "real_valued_column_for_bucketization1":
            parsing_ops.FixedLenFeature(
                [1], dtype=dtypes.float32),
        "real_valued_column_for_bucketization2":
            parsing_ops.FixedLenFeature(
                [4], dtype=dtypes.float32),
        "cross_aaa":
            parsing_ops.VarLenFeature(dtypes.string),
        "cross_bbb":
            parsing_ops.VarLenFeature(dtypes.string)
    }

    config = fc.create_feature_spec_for_parsing(feature_columns)
    self.assertDictEqual(expected_config, config)

    # Test that the same config is parsed out if we pass a dictionary.
    feature_columns_dict = {
        str(i): val
        for i, val in enumerate(feature_columns)
    }
    config = fc.create_feature_spec_for_parsing(feature_columns_dict)
    self.assertDictEqual(expected_config, config)

 def testBucketizedColumnWithSameBucketBoundaries(self):
   a_bucketized = fc.bucketized_column(
       fc.real_valued_column("a"), [1., 2., 2., 3., 3.])
   self.assertEqual(a_bucketized.name, "a_bucketized")
   self.assertTupleEqual(a_bucketized.boundaries, (1., 2., 3.))