เมตริกและพล็อตการวิเคราะห์โมเดล Tensorflow

from google.protobuf import text_format

metrics_specs = text_format.Parse("""
  metrics_specs {
    metrics { class_name: "ExampleCount" }
    metrics { class_name: "MeanSquaredError" }
    metrics { class_name: "Accuracy" }
    metrics { class_name: "MeanLabel" }
    metrics { class_name: "MeanPrediction" }
    metrics { class_name: "Calibration" }
    metrics {
      class_name: "CalibrationPlot"
      config: '"min_value": 0, "max_value": 10'
    }
  }
""", tfma.EvalConfig()).metrics_specs

metrics = [
    tfma.metrics.ExampleCount(name='example_count'),
    tf.keras.metrics.MeanSquaredError(name='mse'),
    tf.keras.metrics.Accuracy(name='accuracy'),
    tfma.metrics.MeanLabel(name='mean_label'),
    tfma.metrics.MeanPrediction(name='mean_prediction'),
    tfma.metrics.Calibration(name='calibration'),
    tfma.metrics.CalibrationPlot(
        name='calibration', min_value=0, max_value=10)
]
metrics_specs = tfma.metrics.specs_from_metrics(metrics)

from google.protobuf import text_format

metrics_specs = text_format.Parse("""
  metrics_specs {
    metrics { class_name: "ExampleCount" }
    metrics { class_name: "BinaryCrossentropy" }
    metrics { class_name: "BinaryAccuracy" }
    metrics { class_name: "AUC" }
    metrics { class_name: "AUCPrecisionRecall" }
    metrics { class_name: "MeanLabel" }
    metrics { class_name: "MeanPrediction" }
    metrics { class_name: "Calibration" }
    metrics { class_name: "ConfusionMatrixPlot" }
    metrics { class_name: "CalibrationPlot" }
  }
""", tfma.EvalConfig()).metrics_specs

metrics = [
    tfma.metrics.ExampleCount(name='example_count'),
    tf.keras.metrics.BinaryCrossentropy(name='binary_crossentropy'),
    tf.keras.metrics.BinaryAccuracy(name='accuracy'),
    tf.keras.metrics.AUC(name='auc', num_thresholds=10000),
    tf.keras.metrics.AUC(
        name='auc_precision_recall', curve='PR', num_thresholds=10000),
    tf.keras.metrics.Precision(name='precision'),
    tf.keras.metrics.Recall(name='recall'),
    tfma.metrics.MeanLabel(name='mean_label'),
    tfma.metrics.MeanPrediction(name='mean_prediction'),
    tfma.metrics.Calibration(name='calibration'),
    tfma.metrics.ConfusionMatrixPlot(name='confusion_matrix_plot'),
    tfma.metrics.CalibrationPlot(name='calibration_plot')
]
metrics_specs = tfma.metrics.specs_from_metrics(metrics)

from google.protobuf import text_format

metrics_specs = text_format.Parse("""
  metrics_specs {
    metrics { class_name: "ExampleCount" }
    metrics { class_name: "SparseCategoricalCrossentropy" }
    metrics { class_name: "SparseCategoricalAccuracy" }
    metrics { class_name: "Precision" config: '"top_k": 1' }
    metrics { class_name: "Precision" config: '"top_k": 3' }
    metrics { class_name: "Recall" config: '"top_k": 1' }
    metrics { class_name: "Recall" config: '"top_k": 3' }
    metrics { class_name: "MultiClassConfusionMatrixPlot" }
  }
""", tfma.EvalConfig()).metrics_specs

metrics = [
    tfma.metrics.ExampleCount(name='example_count'),
    tf.keras.metrics.SparseCategoricalCrossentropy(
        name='sparse_categorical_crossentropy'),
    tf.keras.metrics.SparseCategoricalAccuracy(name='accuracy'),
    tf.keras.metrics.Precision(name='precision', top_k=1),
    tf.keras.metrics.Precision(name='precision', top_k=3),
    tf.keras.metrics.Recall(name='recall', top_k=1),
    tf.keras.metrics.Recall(name='recall', top_k=3),
    tfma.metrics.MultiClassConfusionMatrixPlot(
        name='multi_class_confusion_matrix_plot'),
]
metrics_specs = tfma.metrics.specs_from_metrics(metrics)

from google.protobuf import text_format

metrics_specs = text_format.Parse("""
  metrics_specs {
    binarize: { class_ids: { values: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9] } }
    // Metrics to binarize
    metrics { class_name: "AUC" }
    ...
  }
""", tfma.EvalConfig()).metrics_specs

metrics = [
    // Metrics to binarize
    tf.keras.metrics.AUC(name='auc', num_thresholds=10000),
    ...
]
metrics_specs = tfma.metrics.specs_from_metrics(
    metrics, binarize=tfma.BinarizationOptions(
        class_ids={'values': [0,1,2,3,4,5,6,7,8,9]}))

from google.protobuf import text_format

metrics_specs = text_format.Parse("""
  metrics_specs {
    aggregate: { micro_average: true }
    // Metrics to aggregate
    metrics { class_name: "AUC" }
    ...
  }
""", tfma.EvalConfig()).metrics_specs

metrics = [
    // Metrics to aggregate
    tf.keras.metrics.AUC(name='auc', num_thresholds=10000),
    ...
]
metrics_specs = tfma.metrics.specs_from_metrics(
    metrics, aggregate=tfma.AggregationOptions(micro_average=True))

from google.protobuf import text_format

metrics_specs = text_format.Parse("""
  metrics_specs {
    aggregate: {
      micro_average: true
      top_k_list: { values: [1, 3] }
    }
    // Metrics to aggregate
    metrics { class_name: "AUC" }
    ...
  }
""", tfma.EvalConfig()).metrics_specs

metrics = [
    // Metrics to aggregate
    tf.keras.metrics.AUC(name='auc', num_thresholds=10000),
    ...
]
metrics_specs = tfma.metrics.specs_from_metrics(
    metrics,
    aggregate=tfma.AggregationOptions(micro_average=True,
                                      top_k_list={'values': [1, 3]}))

from google.protobuf import text_format

metrics_specs = text_format.Parse("""
  metrics_specs {
    aggregate: {
      macro_average: true
      class_weights: { key: 0 value: 1.0 }
      class_weights: { key: 1 value: 1.0 }
      class_weights: { key: 2 value: 1.0 }
      class_weights: { key: 3 value: 1.0 }
      class_weights: { key: 4 value: 1.0 }
      class_weights: { key: 5 value: 1.0 }
      class_weights: { key: 6 value: 1.0 }
      class_weights: { key: 7 value: 1.0 }
      class_weights: { key: 8 value: 1.0 }
      class_weights: { key: 9 value: 1.0 }
    }
    // Metrics to aggregate
    metrics { class_name: "AUC" }
    ...
  }
""", tfma.EvalConfig()).metrics_specs

metrics = [
    // Metrics to aggregate
    tf.keras.metrics.AUC(name='auc', num_thresholds=10000),
    ...
]
metrics_specs = tfma.metrics.specs_from_metrics(
    metrics,
    aggregate=tfma.AggregationOptions(
        macro_average=True, class_weights={i: 1.0 for i in range(10)}))

from google.protobuf import text_format

metrics_specs = text_format.Parse("""
  metrics_specs {
    aggregate: {
      macro_average: true
      top_k_list: { values: [1, 3] }
    }
    // Metrics to aggregate
    metrics { class_name: "AUC" }
    ...
  }
""", tfma.EvalConfig()).metrics_specs

metrics = [
    // Metrics to aggregate
    tf.keras.metrics.AUC(name='auc', num_thresholds=10000),
    ...
]
metrics_specs = tfma.metrics.specs_from_metrics(
    metrics,
    aggregate=tfma.AggregationOptions(macro_average=True,
                                      top_k_list={'values': [1, 3]}))

from google.protobuf import text_format

metrics_specs = text_format.Parse("""
  metrics_specs {
    query_key: "doc_id"
    metrics {
      class_name: "NDCG"
      config: '"gain_key": "gain", "top_k_list": [1, 2]'
    }
    metrics { class_name: "MinLabelPosition" }
  }
""", tfma.EvalConfig()).metrics_specs

metrics = [
    tfma.metrics.NDCG(name='ndcg', gain_key='gain', top_k_list=[1, 2]),
    tfma.metrics.MinLabelPosition(name='min_label_position')
]
metrics_specs = tfma.metrics.specs_from_metrics(metrics, query_key='doc_id')

from google.protobuf import text_format

metrics_specs = text_format.Parse("""
  metrics_specs {
    # no model_names means all models
    ...
  }
""", tfma.EvalConfig()).metrics_specs

from google.protobuf import text_format

metrics_specs = text_format.Parse("""
  metrics_specs {
    model_names: ["my-model1"]
    ...
  }
""", tfma.EvalConfig()).metrics_specs

metrics = [
    ...
]
metrics_specs = tfma.metrics.specs_from_metrics(
    metrics, model_names=['my-model1'])

eval_config = text_format.Parse("""
  model_specs {
    # ... model_spec without names ...
  }
  metrics_spec {
    # ... metrics ...
  }
""", tfma.EvalConfig())

eval_shared_models = [
  tfma.default_eval_shared_model(
      model_name=tfma.CANDIDATE_KEY,
      eval_saved_model_path='/path/to/saved/candidate/model',
      eval_config=eval_config),
  tfma.default_eval_shared_model(
      model_name=tfma.BASELINE_KEY,
      eval_saved_model_path='/path/to/saved/baseline/model',
      eval_config=eval_config),
]

eval_result = tfma.run_model_analysis(
    eval_shared_models,
    eval_config=eval_config,
    # This assumes your data is a TFRecords file containing records in the
    # tf.train.Example format.
    data_location="/path/to/file/containing/tfrecords",
    output_path="/path/for/output")

from google.protobuf import text_format

metrics_specs = text_format.Parse("""
  metrics_specs {
    output_names: ["my-output"]
    ...
  }
""", tfma.EvalConfig()).metrics_specs

metrics = [
    ...
]
metrics_specs = tfma.metrics.specs_from_metrics(
    metrics, output_names=['my-output'])

from google.protobuf import text_format

metrics_specs = text_format.Parse("""
  metrics_specs {
    metrics {
      class_name: "ConfusionMatrixAtThresholds"
      config: '"thresholds": [0.3, 0.5, 0.8]'
    }
  }
""", tfma.MetricsSpec()).metrics_specs

metrics = [
   tfma.metrics.ConfusionMatrixAtThresholds(thresholds=[0.3, 0.5, 0.8]),
]
metrics_specs = tfma.metrics.specs_from_metrics(metrics)

from google.protobuf import text_format

metrics_specs = text_format.Parse("""
  metrics_specs {
    metrics { class_name: "MyMetric" module: "my.module"}
  }
""", tfma.EvalConfig()).metrics_specs

class MyMetric(tf.keras.metrics.Mean):

  def __init__(self, name='my_metric', dtype=None):
    super(MyMetric, self).__init__(name=name, dtype=dtype)

  def update_state(self, y_true, y_pred, sample_weight=None):
    return super(MyMetric, self).update_state(
        y_pred, sample_weight=sample_weight)

class ExampleCount(tfma.metrics.Metric):

  def __init__(self, name: Text = 'example_count'):
    super(ExampleCount, self).__init__(_example_count, name=name)


def _example_count(
    name: Text = 'example_count') -> tfma.metrics.MetricComputations:
  key = tfma.metrics.MetricKey(name=name)
  return [
      tfma.metrics.MetricComputation(
          keys=[key],
          preprocessors=[_ExampleCountPreprocessor()],
          combiner=_ExampleCountCombiner(key))
  ]


class ExampleCountTest(tfma.test.testutil.TensorflowModelAnalysisTest):

  def testExampleCount(self):
    metric = ExampleCount()
    computations = metric.computations(example_weighted=False)
    computation = computations[0]

    with beam.Pipeline() as pipeline:
      result = (
          pipeline
          | 'Create' >> beam.Create([...])  # Add inputs
          | 'PreProcess' >> beam.ParDo(computation.preprocessors[0])
          | 'Process' >> beam.Map(tfma.metrics.to_standard_metric_inputs)
          | 'AddSlice' >> beam.Map(lambda x: ((), x))
          | 'ComputeMetric' >> beam.CombinePerKey(computation.combiner)
      )

      def check_result(got):
        try:
          self.assertLen(got, 1)
          got_slice_key, got_metrics = got[0]
          self.assertEqual(got_slice_key, ())
          key = computation.keys[0]
          self.assertIn(key, got_metrics)
          self.assertAlmostEqual(got_metrics[key], expected_value, places=5)
        except AssertionError as err:
          raise util.BeamAssertException(err)

      util.assert_that(result, check_result, label='result')

class _ExampleCountPreprocessor(beam.DoFn):

  def process(self, extracts: tfma.Extracts) -> Iterable[int]:
    yield 1


class _ExampleCountPreprocessorTest(unittest.TestCase):

  def testExampleCountPreprocessor(self):
    ...  # Init the test case here
    with beam.Pipeline() as pipeline:
      updated_pcoll = (
          pipeline
          | 'Create' >> beam.Create([...])  # Add inputs
          | 'Preprocess'
          >> beam.ParDo(
              _ExampleCountPreprocessor()
          )
      )

      beam_testing_util.assert_that(
          updated_pcoll,
          lambda result: ...,  # Assert the test case
      )


class _ExampleCountCombiner(beam.CombineFn):

  def __init__(self, metric_key: tfma.metrics.MetricKey):
    self._metric_key = metric_key

  def create_accumulator(self) -> int:
    return 0

  def add_input(self, accumulator: int, state: int) -> int:
    return accumulator + state

  def merge_accumulators(self, accumulators: Iterable[int]) -> int:
    accumulators = iter(accumulators)
    result = next(accumulator)
    for accumulator in accumulators:
      result += accumulator
    return result

  def extract_output(self,
                     accumulator: int) -> Dict[tfma.metrics.MetricKey, int]:
    return {self._metric_key: accumulator}