def encode_inputs(inputs, use_embedding=False):
encoded_features = []
for feature_name in inputs:
if feature_name in CATEGORICAL_FEATURE_NAMES:
vocabulary = CATEGORICAL_FEATURES_WITH_VOCABULARY[feature_name]
# Create a lookup to convert string values to an integer indices.
# Since we are not using a mask token nor expecting any out of vocabulary
# (oov) token, we set mask_token to None and num_oov_indices to 0.
index = StringLookup(vocabulary=vocabulary,
mask_token=None,
num_oov_indices=0)
# Convert the string input values into integer indices.
value_index = index(inputs[feature_name])
if use_embedding:
embedding_dims = int(math.sqrt(len(vocabulary)))
# Create an embedding layer with the specified dimensions.
embedding_ecoder = layers.Embedding(input_dim=len(vocabulary),
output_dim=embedding_dims)
# Convert the index values to embedding representations.
encoded_feature = embedding_ecoder(value_index)
else:
# Create a one-hot encoder.
onehot_encoder = CategoryEncoding(output_mode="binary")
onehot_encoder.adapt(index(vocabulary))
# Convert the index values to a one-hot representation.
encoded_feature = onehot_encoder(value_index)
else:
# Use the numerical features as-is.
encoded_feature = tf.expand_dims(inputs[feature_name], -1)
encoded_features.append(encoded_feature)
all_features = layers.concatenate(encoded_features)
return all_features
def encode_string_categorical_feature(feature, name, dataset):
# Create a StringLookup layer which will turn strings into integer indices
index = StringLookup()
# Prepare a Dataset that only yields our feature
feature_ds = dataset.map(lambda x, y: x[name])
feature_ds = feature_ds.map(lambda x: tf.expand_dims(x, -1))
# Learn the set of possible string values and assign them a fixed integer index
index.adapt(feature_ds)
# Turn the string input into integer indices
encoded_feature = index(feature)
# Create a CategoryEncoding for our integer indices
encoder = CategoryEncoding(output_mode="binary")
# Prepare a dataset of indices
feature_ds = feature_ds.map(index)
# Learn the space of possible indices
encoder.adapt(feature_ds)
# Apply one-hot encoding to our indices
encoded_feature = encoder(encoded_feature)
return encoded_feature
def encode_integer_categorical_feature(feature, name, dataset):
# Create a CategoryEncoding for the integer indices of the input feature passed as argument
encoder = CategoryEncoding(output_mode='binary')
# Prepare a Dataset containing only the feature
feature_dset = dataset.map(lambda x, y: x[name])
feature_dset = feature_dset.map(lambda x: tf.expand_dims(x, -1))
# Learn the space of possible indices and apply one-hot encoding to them
encoder.adapt(feature_dset)
encoded_feature = encoder(feature)
return encoded_feature
def encode_integer_categorical_feature(feature, name, dataset):
encoder = CategoryEncoding(output_mode="binary")
feature_ds = dataset.map(lambda x, y: x[name])
feature_ds = feature_ds.map(lambda x: tf.expand_dims(x, -1))
encoder.adapt(feature_ds)
encoded_feature = encoder(feature)
return encoded_feature
def encode_integer_categorical_feature(feature, name, dataset):
# Create a CategoryEncoding for our integer indices
encoder = CategoryEncoding(output_mode="binary")
# Prepare a Dataset that only yields our feature
feature_ds = dataset.map(lambda x, y: x[name])
feature_ds = feature_ds.map(lambda x: tf.expand_dims(x, -1))
# Learn the space of possible indices
encoder.adapt(feature_ds)
# Apply one-hot encoding to our indices
encoded_feature = encoder(feature)
return encoded_feature
def encode_string_categorical_feature(feature, name, dataset):
index = StringLookup()
feature_ds = dataset.map(lambda x, y: x[name])
feature_ds = feature_ds.map(lambda x: tf.expand_dims(x, -1))
index.adapt(feature_ds)
encoded_feature = index(feature)
encoder = CategoryEncoding(output_mode="binary")
feature_ds = feature_ds.map(index)
encoder.adapt(feature_ds)
encoded_feature = encoder(encoded_feature)
return encoded_feature
def encode(self, input_feature, name, dataset):
"""
"""
feature_ds = _extract_feature_column(dataset, name)
# apply String Indexer
index_encoder = StringIndexer()
index_encoder.adapt(feature_ds)
index_encoded_feature = index_encoder.encode(input_feature, name,
dataset)
feature_ds = feature_ds.map(index_encoder.encoder)
# apply categorical encoding
category_encoder = CategoryEncoding(output_mode="binary")
category_encoder.adapt(feature_ds)
encoded_feature = category_encoder(index_encoded_feature)
return encoded_feature
def _category_indicate(self, params: dict, weight_input: Layer = None):
"""
Replacing tf.feature_column.indicator_column with CategoryEncoding from
:param params:
:param weight_input:
:return:
"""
id_input = self._category_lookup(params)
if weight_input is None:
encoded_input = CategoryEncoding(max_tokens=params['num_buckets'], output_mode="count", sparse=True)(
id_input)
else:
encoded_input = CategoryEncoding(max_tokens=params['num_buckets'], output_mode="count", sparse=True)(
id_input, weight_input)
return encoded_input
def _encode_categorical_feature(
feature: KerasTensor,
name: str,
dataset: Optional[BatchDataset],
) -> KerasTensor:
"""One-hot encode categorical features.
Args:
- feature: The input layer of the feature.
- name: The feature's name (its column name in the original dataframe).
- dataset: The training data, if not specified, return a no-op layer.
Returns:
The one-hot encoded tensor of the input feature.
"""
# Return generic layer for the tuner initialization
if not dataset:
return KerasTensor(type_spec=TensorSpec(
shape=(None, 1), dtype=tf.float32, name=None))
# Create a StringLookup layer which will turn strings into integer indices
index = StringLookup()
# Prepare a Dataset that only yields our feature
feature_ds = dataset.map(lambda x, y: x[name])
feature_ds = feature_ds.map(lambda x: tf.expand_dims(x, -1))
# Learn the set of possible string values and assign them a fixed integer index
index.adapt(feature_ds)
# Turn the string input into integer indices
encoded_feature = index(feature)
# Create a CategoryEncoding for our integer indices
encoder = CategoryEncoding(output_mode="binary")
# Learn the space of possible indices
encoder.adapt(np.arange(index.vocab_size()))
# Apply one-hot encoding to our indices{split + 1} / {n_splits}
encoded_feature = encoder(encoded_feature)
return encoded_feature
def load_data():
data = pd.read_csv(
"https://storage.googleapis.com/tf-datasets/titanic/train.csv")
from sklearn.model_selection import train_test_split
labels = data.pop('survived')
label_names = ["Not survived", "Survived"]
features = {}
# Converting CSV file into Tensorflow object
for name, column in data.items():
dtype = column.dtype
if dtype == object:
dtype = string
else:
dtype = float32
features[name] = Input(shape=(1, ), name=name, dtype=dtype)
# Extracting and normalizing numeric features
numeric_features = {
name: feature
for name, feature in features.items() if feature.dtype == float32
}
x = Concatenate()(list(numeric_features.values()))
norm = Normalization()
norm.adapt(np.array(data[numeric_features.keys()]))
numeric_features = norm(x)
processed_features = [numeric_features]
# Extracting and normalizing non-numeric features
for name, feature in features.items():
if feature.dtype == float32:
continue
word = StringLookup(vocabulary=np.unique(data[name]))
one_hot = CategoryEncoding(max_tokens=word.vocab_size())
x = word(feature)
x = one_hot(x)
processed_features.append(x)
processed_features = Concatenate()(processed_features)
processed_features = Model(features, processed_features)
utils.plot_model(model=processed_features,
rankdir='LR',
dpi=72,
show_shapes=True)
feature_dict = {name: np.array(value) for name, value in data.items()}
train_features, test_features, train_labels, test_labels = train_test_split(
processed_features(feature_dict).numpy(), labels, test_size=0.2)
return train_features, train_labels, test_features, test_labels
def _category_onehot(self, params: dict):
if params['dtype'] in ('int', 'int32', 'int64'):
num_buckets = params['num_buckets']
key, input_layer = self._get_input_layer(params)
else:
input_layer = self._category_lookup(params)
num_buckets = len(params['vocabulary_list'])
name = params.get('name', params['key'] + '-onehot')
cate_encode = CategoryEncoding(
max_tokens=num_buckets, output_mode="binary", name=name)
output = cate_encode(input_layer)
return output
def __init__(self):
super().__init__(CategoryEncoding(output_mode="binary"))
