diff options
| author |  A. Unique TensorFlower <gardener@tensorflow.org> | 2016-11-04 14:11:59 -0800 |
|---|---|---|
| committer | TensorFlower Gardener <gardener@tensorflow.org> | 2016-11-04 15:24:22 -0700 |
| commit | 28f7720117a4b7f4346742eeb207197800c87345 (patch) | |
| tree | 772af694db801b3cc5f1147901c19869964585b2 | |
| parent | 9ac2ff7e2d71163b53dc0a3217eb4b71c920dde9 (diff) | |
Anonymize feature column names.
Change: 138240000
| -rw-r--r-- | tensorflow/contrib/layers/python/layers/feature_column.py | 33 |
1 files changed, 19 insertions, 14 deletions
diff --git a/tensorflow/contrib/layers/python/layers/feature_column.py b/tensorflow/contrib/layers/python/layers/feature_column.py index 314156a5e4..d9259dbaa1 100644 --- a/tensorflow/contrib/layers/python/layers/feature_column.py +++ b/tensorflow/contrib/layers/python/layers/feature_column.py @@ -32,22 +32,27 @@ Typical usage example: ```python # Define features and transformations - country = sparse_column_with_keys(column_name="native_country", - keys=["US", "BRA", ...]) - country_emb = embedding_column(sparse_id_column=country, dimension=3, - combiner="sum") - occupation = sparse_column_with_hash_bucket(column_name="occupation", - hash_bucket_size=1000) - occupation_emb = embedding_column(sparse_id_column=occupation, dimension=16, - combiner="sum") - occupation_x_country = crossed_column(columns=[occupation, country], - hash_bucket_size=10000) - age = real_valued_column("age") - age_buckets = bucketized_column( - source_column=age, + sparse_feature_a = sparse_column_with_keys( + column_name="sparse_feature_a", keys=["AB", "CD", ...]) + + embedding_feature_a = embedding_column( + sparse_id_column=sparse_feature_a, dimension=3, combiner="sum") + + sparse_feature_b = sparse_column_with_hash_bucket( + column_name="sparse_feature_b", hash_bucket_size=1000) + + embedding_feature_b = embedding_column( + sparse_id_column=sparse_feature_b, dimension=16, combiner="sum") + + crossed_feature_a_x_b = crossed_column( + columns=[sparse_feature_a, sparse_feature_b], hash_bucket_size=10000) + + real_feature = real_valued_column("real_feature") + real_feature_buckets = bucketized_column( + source_column=real_feature, boundaries=[18, 25, 30, 35, 40, 45, 50, 55, 60, 65]) - my_features = [occupation_emb, age_buckets, country_emb] + my_features = [embedding_feature_b, real_feature_buckets, embedding_feature_a] # Building model via layers columns_to_tensor = parse_feature_columns_from_examples( serialized=my_data, |