deepctr.feature_column module

class deepctr.feature_column.DenseFeat(name, dimension=1, dtype='float32', transform_fn=None)

Bases: deepctr.feature_column.DenseFeat

Dense feature Args:

name: feature name. dimension: dimension of the feature, default = 1. dtype: dtype of the feature, default=”float32”. transform_fn: If not None , a function that can be used to transform values of the feature. the function takes the input Tensor as its argument, and returns the output Tensor. (e.g. lambda x: (x - 3.0) / 4.2).

class deepctr.feature_column.SparseFeat(name, vocabulary_size, embedding_dim=4, use_hash=False, vocabulary_path=None, dtype='int32', embeddings_initializer=None, embedding_name=None, group_name='default_group', trainable=True)

Bases: deepctr.feature_column.SparseFeat

class deepctr.feature_column.VarLenSparseFeat(sparsefeat, maxlen, combiner='mean', length_name=None, weight_name=None, weight_norm=True)

Bases: deepctr.feature_column.VarLenSparseFeat

property dtype

property embedding_dim

property embedding_name

property embeddings_initializer

property group_name

property name

property trainable

property use_hash

property vocabulary_path

property vocabulary_size

deepctr.feature_column.build_input_features(feature_columns, prefix='')

deepctr.feature_column.get_feature_names(feature_columns)

deepctr.feature_column.get_linear_logit(features, feature_columns, units=1, use_bias=False, seed=1024, prefix='linear', l2_reg=0, sparse_feat_refine_weight=None)

deepctr.feature_column.input_from_feature_columns(features, feature_columns, l2_reg, seed, prefix='', seq_mask_zero=True, support_dense=True, support_group=False)