gcs_base_dir = "gs://celeb_a_dataset/"
celeb_a_builder = tfds.builder("celeb_a", data_dir=gcs_base_dir, version='2.0.0')

celeb_a_builder.download_and_prepare()

num_test_shards_dict = {'0.3.0': 4, '2.0.0': 2} # Used because we download the test dataset separately
version = str(celeb_a_builder.info.version)
print('Celeb_A dataset version: %s' % version)

# Train data returning either 2 or 3 elements (the third element being the group)
def celeb_a_train_data_wo_group(batch_size):
  celeb_a_train_data = celeb_a_builder.as_dataset(split='train').shuffle(1024).repeat().batch(batch_size).map(preprocess_input_dict)
  return celeb_a_train_data.map(get_image_and_label)
def celeb_a_train_data_w_group(batch_size):
  celeb_a_train_data = celeb_a_builder.as_dataset(split='train').shuffle(1024).repeat().batch(batch_size).map(preprocess_input_dict)
  return celeb_a_train_data.map(get_image_label_and_group)

# Test data for the overall evaluation
celeb_a_test_data = celeb_a_builder.as_dataset(split='test').batch(1).map(preprocess_input_dict).map(get_image_label_and_group)
# Copy test data locally to be able to read it into tfma
copy_test_files_to_local()

def create_model():
  # For this notebook, accuracy will be used to evaluate performance.
  METRICS = [
    tf.keras.metrics.BinaryAccuracy(name='accuracy')
  ]

  # The model consists of:
  # 1. An input layer that represents the 28x28x3 image flatten.
  # 2. A fully connected layer with 64 units activated by a ReLU function.
  # 3. A single-unit readout layer to output real-scores instead of probabilities.
  model = keras.Sequential([
      keras.layers.Flatten(input_shape=(IMAGE_SIZE, IMAGE_SIZE, 3), name='image'),
      keras.layers.Dense(64, activation='relu'),
      keras.layers.Dense(1, activation=None)
  ])

  # TFCO by default uses hinge loss — and that will also be used in the model.
  model.compile(
      optimizer=tf.keras.optimizers.Adam(0.001),
      loss='hinge',
      metrics=METRICS)
  return model

def set_seeds():
  np.random.seed(121212)
  tf.compat.v1.set_random_seed(212121)

def save_model(model, subdir):
  base_dir = tempfile.mkdtemp(prefix='saved_models')
  model_location = os.path.join(base_dir, subdir)
  model.save(model_location, save_format='tf')
  return model_location

def get_eval_results(model_location, eval_subdir):
  base_dir = tempfile.mkdtemp(prefix='saved_eval_results')
  tfma_eval_result_path = os.path.join(base_dir, eval_subdir)

  eval_config_pbtxt = """
        model_specs {
          label_key: "%s"
        }
        metrics_specs {
          metrics {
            class_name: "FairnessIndicators"
            config: '{ "thresholds": [0.22, 0.5, 0.75] }'
          }
          metrics {
            class_name: "ExampleCount"
          }
        }
        slicing_specs {}
        slicing_specs { feature_keys: "%s" }
        options {
          compute_confidence_intervals { value: False }
          disabled_outputs{values: "analysis"}
        }
      """ % (LABEL_KEY, GROUP_KEY)

  eval_config = text_format.Parse(eval_config_pbtxt, tfma.EvalConfig())

  eval_shared_model = tfma.default_eval_shared_model(
        eval_saved_model_path=model_location, tags=[tf.saved_model.SERVING])

  schema_pbtxt = """
        tensor_representation_group {
          key: ""
          value {
            tensor_representation {
              key: "%s"
              value {
                dense_tensor {
                  column_name: "%s"
                  shape {
                    dim { size: 28 }
                    dim { size: 28 }
                    dim { size: 3 }
                  }
                }
              }
            }
          }
        }
        feature {
          name: "%s"
          type: FLOAT
        }
        feature {
          name: "%s"
          type: FLOAT
        }
        feature {
          name: "%s"
          type: BYTES
        }
        """ % (IMAGE_KEY, IMAGE_KEY, IMAGE_KEY, LABEL_KEY, GROUP_KEY)
  schema = text_format.Parse(schema_pbtxt, schema_pb2.Schema())
  coder = tf_example_record.TFExampleBeamRecord(
      physical_format='inmem', schema=schema,
      raw_record_column_name=tfma.ARROW_INPUT_COLUMN)
  tensor_adapter_config = tensor_adapter.TensorAdapterConfig(
    arrow_schema=coder.ArrowSchema(),
    tensor_representations=coder.TensorRepresentations())
  # Run the fairness evaluation.
  with beam.Pipeline() as pipeline:
    _ = (
          tfds_as_pcollection(pipeline, 'celeb_a', 'test')
          | 'ExamplesToRecordBatch' >> coder.BeamSource()
          | 'ExtractEvaluateAndWriteResults' >>
          tfma.ExtractEvaluateAndWriteResults(
              eval_config=eval_config,
              eval_shared_model=eval_shared_model,
              output_path=tfma_eval_result_path,
              tensor_adapter_config=tensor_adapter_config)
    )
  return tfma.load_eval_result(output_path=tfma_eval_result_path)

BATCH_SIZE = 32

# Set seeds to get reproducible results
set_seeds()

model_unconstrained = create_model()
model_unconstrained.fit(celeb_a_train_data_wo_group(BATCH_SIZE), epochs=5, steps_per_epoch=1000)

print('Overall Results, Unconstrained')
celeb_a_test_data = celeb_a_builder.as_dataset(split='test').batch(1).map(preprocess_input_dict).map(get_image_label_and_group)
results = model_unconstrained.evaluate(celeb_a_test_data)

model_location = save_model(model_unconstrained, 'model_export_unconstrained')
eval_results_unconstrained = get_eval_results(model_location, 'eval_results_unconstrained')

tfma.addons.fairness.view.widget_view.render_fairness_indicator(eval_results_unconstrained)

# The batch size is needed to create the input, labels and group tensors.
# These tensors are initialized with all 0's. They will eventually be assigned
# the batch content to them. A large batch size is chosen so that there are
# enough number of "Young" and "Not Young" examples in each batch.
set_seeds()
model_constrained = create_model()
BATCH_SIZE = 32

# Create input tensor.
input_tensor = tf.Variable(
    np.zeros((BATCH_SIZE, IMAGE_SIZE, IMAGE_SIZE, 3), dtype="float32"),
    name="input")

# Create labels and group tensors (assuming both labels and groups are binary).
labels_tensor = tf.Variable(
    np.zeros(BATCH_SIZE, dtype="float32"), name="labels")
groups_tensor = tf.Variable(
    np.zeros(BATCH_SIZE, dtype="float32"), name="groups")

# Create a function that returns the applied 'model' to the input tensor
# and generates constrained predictions.
def predictions():
  return model_constrained(input_tensor)

# Create overall context and subsetted context.
# The subsetted context contains subset of examples where group attribute < 1
# (i.e. the subset of "Not Young" celebrity images).
# "groups_tensor < 1" is used instead of "groups_tensor == 0" as the former
# would be a comparison on the tensor value, while the latter would be a
# comparison on the Tensor object.
context = tfco.rate_context(predictions, labels=lambda:labels_tensor)
context_subset = context.subset(lambda:groups_tensor < 1)

# Setup list of constraints.
# In this notebook, the constraint will just be: FPR to less or equal to 5%.
constraints = [tfco.false_positive_rate(context_subset) <= 0.05]

# Setup rate minimization problem: minimize overall error rate s.t. constraints.
problem = tfco.RateMinimizationProblem(tfco.error_rate(context), constraints)

# Create constrained optimizer and obtain train_op.
# Separate optimizers are specified for the objective and constraints
optimizer = tfco.ProxyLagrangianOptimizerV2(
      optimizer=tf.keras.optimizers.legacy.Adam(learning_rate=0.001),
      constraint_optimizer=tf.keras.optimizers.legacy.Adam(learning_rate=0.001),
      num_constraints=problem.num_constraints)

# A list of all trainable variables is also needed to use TFCO.
var_list = (model_constrained.trainable_weights + list(problem.trainable_variables) +
            optimizer.trainable_variables())

# Obtain train set batches.

NUM_ITERATIONS = 100  # Number of training iterations.
SKIP_ITERATIONS = 10  # Print training stats once in this many iterations.

# Create temp directory for saving snapshots of models.
temp_directory = tempfile.mktemp()
os.mkdir(temp_directory)

# List of objective and constraints across iterations.
objective_list = []
violations_list = []

# Training iterations.
iteration_count = 0
for (image, label, group) in celeb_a_train_data_w_group(BATCH_SIZE):
  # Assign current batch to input, labels and groups tensors.
  input_tensor.assign(image)
  labels_tensor.assign(label)
  groups_tensor.assign(group)

  # Run gradient update.
  optimizer.minimize(problem, var_list=var_list)

  # Record objective and violations.
  objective = problem.objective()
  violations = problem.constraints()

  sys.stdout.write(
      "\r Iteration %d: Hinge Loss = %.3f, Max. Constraint Violation = %.3f"
      % (iteration_count + 1, objective, max(violations)))

  # Snapshot model once in SKIP_ITERATIONS iterations.
  if iteration_count % SKIP_ITERATIONS == 0:
    objective_list.append(objective)
    violations_list.append(violations)

    # Save snapshot of model weights.
    model_constrained.save_weights(
        temp_directory + "/celeb_a_constrained_" +
        str(iteration_count / SKIP_ITERATIONS) + ".h5")

  iteration_count += 1
  if iteration_count >= NUM_ITERATIONS:
    break

# Choose best model from recorded iterates and load that model.
best_index = tfco.find_best_candidate_index(
    np.array(objective_list), np.array(violations_list))

model_constrained.load_weights(
    temp_directory + "/celeb_a_constrained_" + str(best_index) + ".0.h5")

# Remove temp directory.
os.system("rm -r " + temp_directory)

model_location = save_model(model_constrained, 'model_export_constrained')
eval_result_constrained = get_eval_results(model_location, 'eval_results_constrained')

eval_results_dict = {
    'constrained': eval_result_constrained,
    'unconstrained': eval_results_unconstrained,
}
tfma.addons.fairness.view.widget_view.render_fairness_indicator(multi_eval_results=eval_results_dict)