tf.contrib.estimator.boosted_trees_classifier_train_in_memory

Обучает классификатор с усиленными деревьями с использованием набора данных в памяти.

tf.contrib.estimator.boosted_trees_classifier_train_in_memory(
    train_input_fn, feature_columns, model_dir=None,
    n_classes=canned_boosted_trees._HOLD_FOR_MULTI_CLASS_SUPPORT,
    weight_column=None, label_vocabulary=None, n_trees=100, max_depth=6,
    learning_rate=0.1, l1_regularization=0.0, l2_regularization=0.0,
    tree_complexity=0.0, min_node_weight=0.0, config=None, train_hooks=None,
    center_bias=False, pruning_mode='none', quantile_sketch_epsilon=0.01
)

Пример:

bucketized_feature_1 = bucketized_column(
  numeric_column('feature_1'), BUCKET_BOUNDARIES_1)
bucketized_feature_2 = bucketized_column(
  numeric_column('feature_2'), BUCKET_BOUNDARIES_2)

def train_input_fn():
  dataset = create-dataset-from-training-data
  # This is tf.data.Dataset of a tuple of feature dict and label.
  #   e.g. Dataset.zip((Dataset.from_tensors({'f1': f1_array, ...}),
  #                     Dataset.from_tensors(label_array)))
  # The returned Dataset shouldn't be batched.
  # If Dataset repeats, only the first repetition would be used for training.
  return dataset

classifier = boosted_trees_classifier_train_in_memory(
    train_input_fn,
    feature_columns=[bucketized_feature_1, bucketized_feature_2],
    n_trees=100,
    ... <some other params>
)

def input_fn_eval():
  ...
  return dataset

metrics = classifier.evaluate(input_fn=input_fn_eval, steps=10)