Python feature_column.sparse_column_with_hash_bucket函数代码示例

  def testCrossedFeatures(self):
    """Tests SDCALogisticClassifier with crossed features."""

    def input_fn():
      return {
          'example_id':
              constant_op.constant(['1', '2', '3']),
          'language':
              sparse_tensor.SparseTensor(
                  values=['english', 'italian', 'spanish'],
                  indices=[[0, 0], [1, 0], [2, 0]],
                  dense_shape=[3, 1]),
          'country':
              sparse_tensor.SparseTensor(
                  values=['US', 'IT', 'MX'],
                  indices=[[0, 0], [1, 0], [2, 0]],
                  dense_shape=[3, 1])
      }, constant_op.constant([[0], [0], [1]])

    language = feature_column_lib.sparse_column_with_hash_bucket(
        'language', hash_bucket_size=5)
    country = feature_column_lib.sparse_column_with_hash_bucket(
        'country', hash_bucket_size=5)
    country_language = feature_column_lib.crossed_column(
        [language, country], hash_bucket_size=10)
    classifier = sdca_estimator.SDCALogisticClassifier(
        example_id_column='example_id', feature_columns=[country_language])
    classifier.fit(input_fn=input_fn, steps=10)
    metrics = classifier.evaluate(input_fn=input_fn, steps=1)
    self.assertGreater(metrics['accuracy'], 0.9)

  def testSparseFeaturesWithDuplicates(self):
    """Tests SDCALogisticClassifier with duplicated sparse features."""

    def input_fn():
      return {
          'example_id':
              constant_op.constant(['1', '2']),
          'age':
              sparse_tensor.SparseTensor(
                  values=['20-29'] * 5 + ['31-40'] * 5,
                  indices=[[0, 0], [0, 0], [0, 0], [0, 0], [0, 0], [1, 0],
                           [1, 0], [1, 0], [1, 0], [1, 0]],
                  dense_shape=[2, 1]),
          'gender':
              sparse_tensor.SparseTensor(
                  values=['m'] * 5 + ['f'] * 5,
                  indices=[[0, 0], [0, 0], [0, 0], [0, 0], [0, 0], [1, 0],
                           [1, 0], [1, 0], [1, 0], [1, 0]],
                  dense_shape=[2, 1]),
      }, constant_op.constant([[1], [0]])

    with self._single_threaded_test_session():
      age = feature_column_lib.sparse_column_with_hash_bucket(
          'age', hash_bucket_size=10)
      gender = feature_column_lib.sparse_column_with_hash_bucket(
          'gender', hash_bucket_size=10)
      classifier = sdca_estimator.SDCALogisticClassifier(
          example_id_column='example_id', feature_columns=[age, gender])
      classifier.fit(input_fn=input_fn, steps=50)
      metrics = classifier.evaluate(input_fn=input_fn, steps=1)
      self.assertLess(metrics['loss'], 0.060)

  def testJointLinearModel(self):
    """Tests that loss goes down with training."""

    def input_fn():
      return {
          'age':
              sparse_tensor.SparseTensor(
                  values=['1'], indices=[[0, 0]], dense_shape=[1, 1]),
          'language':
              sparse_tensor.SparseTensor(
                  values=['english'], indices=[[0, 0]], dense_shape=[1, 1])
      }, constant_op.constant([[1]])

    language = feature_column.sparse_column_with_hash_bucket('language', 100)
    age = feature_column.sparse_column_with_hash_bucket('age', 2)

    head = head_lib._multi_class_head(n_classes=2)
    classifier = _joint_linear_estimator(head, feature_columns=[age, language])

    classifier.fit(input_fn=input_fn, steps=1000)
    loss1 = classifier.evaluate(input_fn=input_fn, steps=1)['loss']
    classifier.fit(input_fn=input_fn, steps=2000)
    loss2 = classifier.evaluate(input_fn=input_fn, steps=1)['loss']
    self.assertLess(loss2, loss1)
    self.assertLess(loss2, 0.01)

  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 testSparseColumnWithHashBucket(self):
    a = fc.sparse_column_with_hash_bucket("aaa", hash_bucket_size=100)
    self.assertEqual(a.name, "aaa")
    self.assertEqual(a.dtype, dtypes.string)

    a = fc.sparse_column_with_hash_bucket(
        "aaa", hash_bucket_size=100, dtype=dtypes.int64)
    self.assertEqual(a.name, "aaa")
    self.assertEqual(a.dtype, dtypes.int64)

    with self.assertRaisesRegexp(ValueError, "dtype must be string or integer"):
      a = fc.sparse_column_with_hash_bucket(
          "aaa", hash_bucket_size=100, dtype=dtypes.float32)

  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 testWeightedSparseFeatures(self):
    """Tests SDCALogisticClassifier with weighted sparse features."""

    def input_fn():
      return {
          'example_id':
              constant_op.constant(['1', '2', '3']),
          'price':
              sparse_tensor.SparseTensor(
                  values=[2., 3., 1.],
                  indices=[[0, 0], [1, 0], [2, 0]],
                  dense_shape=[3, 5]),
          'country':
              sparse_tensor.SparseTensor(
                  values=['IT', 'US', 'GB'],
                  indices=[[0, 0], [1, 0], [2, 0]],
                  dense_shape=[3, 5])
      }, constant_op.constant([[1], [0], [1]])

    country = feature_column_lib.sparse_column_with_hash_bucket(
        'country', hash_bucket_size=5)
    country_weighted_by_price = feature_column_lib.weighted_sparse_column(
        country, 'price')
    classifier = sdca_estimator.SDCALogisticClassifier(
        example_id_column='example_id',
        feature_columns=[country_weighted_by_price])
    classifier.fit(input_fn=input_fn, steps=50)
    metrics = classifier.evaluate(input_fn=input_fn, steps=1)
    self.assertGreater(metrics['accuracy'], 0.9)

  def testSparseFeatures(self):
    """Tests SDCALogisticClassifier with sparse features."""

    def input_fn():
      return {
          'example_id':
              constant_op.constant(['1', '2', '3']),
          'price':
              constant_op.constant([[0.4], [0.6], [0.3]]),
          'country':
              sparse_tensor.SparseTensor(
                  values=['IT', 'US', 'GB'],
                  indices=[[0, 0], [1, 3], [2, 1]],
                  dense_shape=[3, 5]),
          'weights':
              constant_op.constant([[1.0], [1.0], [1.0]])
      }, constant_op.constant([[1], [0], [1]])

    price = feature_column_lib.real_valued_column('price')
    country = feature_column_lib.sparse_column_with_hash_bucket(
        'country', hash_bucket_size=5)
    classifier = sdca_estimator.SDCALogisticClassifier(
        example_id_column='example_id',
        feature_columns=[price, 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 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 testExport(self):
    """Tests export model for servo."""

    def input_fn():
      return {
          'age':
              constant_op.constant([1]),
          'language':
              sparse_tensor.SparseTensor(
                  values=['english'], indices=[[0, 0]], dense_shape=[1, 1])
      }, constant_op.constant([[1]])

    language = feature_column.sparse_column_with_hash_bucket('language', 100)
    feature_columns = [
        feature_column.real_valued_column('age'),
        feature_column.embedding_column(
            language, dimension=1)
    ]

    classifier = debug.DebugClassifier(config=run_config.RunConfig(
        tf_random_seed=1))
    classifier.fit(input_fn=input_fn, steps=5)

    def default_input_fn(unused_estimator, examples):
      return feature_column_ops.parse_feature_columns_from_examples(
          examples, feature_columns)

    export_dir = tempfile.mkdtemp()
    classifier.export(export_dir, input_fn=default_input_fn)

 def testCrossedColumnNotSupportRealValuedColumn(self):
   b = fc.sparse_column_with_hash_bucket("bbb", hash_bucket_size=100)
   with self.assertRaisesRegexp(
       TypeError, "columns must be a set of _SparseColumn, _CrossedColumn, "
       "or _BucketizedColumn instances"):
     fc.crossed_column(
         set([b, fc.real_valued_column("real")]), hash_bucket_size=10000)

  def testSparseFeatures(self):
    """Tests SVM classifier with (hashed) sparse features."""

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

    price = feature_column.real_valued_column('price')
    country = feature_column.sparse_column_with_hash_bucket(
        'country', hash_bucket_size=5)
    svm_classifier = svm.SVM(feature_columns=[price, country],
                             example_id_column='example_id',
                             l1_regularization=0.0,
                             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 testEmbeddingColumn(self):
   a = fc.sparse_column_with_hash_bucket(
       "aaa", hash_bucket_size=100, combiner="sum")
   b = fc.embedding_column(a, dimension=4, combiner="mean")
   self.assertEqual(b.sparse_id_column.name, "aaa")
   self.assertEqual(b.dimension, 4)
   self.assertEqual(b.combiner, "mean")

  def testRegression_TensorData(self):
    """Tests regression using tensor data as input."""

    def _input_fn(num_epochs=None):
      features = {
          'age':
              input_lib.limit_epochs(
                  constant_op.constant([[.8], [.15], [0.]]),
                  num_epochs=num_epochs),
          'language':
              sparse_tensor.SparseTensor(
                  values=input_lib.limit_epochs(
                      ['en', 'fr', 'zh'], num_epochs=num_epochs),
                  indices=[[0, 0], [0, 1], [2, 0]],
                  dense_shape=[3, 2])
      }
      return features, constant_op.constant([1., 0., 0.2], dtype=dtypes.float32)

    language_column = feature_column.sparse_column_with_hash_bucket(
        'language', hash_bucket_size=20)
    feature_columns = [
        feature_column.embedding_column(
            language_column, dimension=1),
        feature_column.real_valued_column('age')
    ]

    regressor = dnn.DNNRegressor(
        feature_columns=feature_columns,
        hidden_units=[3, 3],
        config=run_config.RunConfig(tf_random_seed=1))

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

    scores = regressor.evaluate(input_fn=_input_fn, steps=1)
    self.assertIn('loss', scores)